system

Abstract

The system according to this embodiment aims to provide visitors with an interactive exhibition experience by offering detailed information and explanations about the exhibits. [Solution] The system according to the embodiment comprises an explanation unit, a tour guide unit, a reproduction unit, a dialogue unit, and a learning support unit. The explanation unit recognizes exhibits and provides detailed information and explanations. The tour guide unit provides a virtual tour guide based on the information provided by the explanation unit. The reproduction unit reproduces historical scenes and exhibits based on the exhibits guided by the tour guide unit. The dialogue unit provides an interactive exhibit experience with visitors based on the scenes reproduced by the reproduction unit. The learning support unit provides educational programs and learning support programs based on the dialogues provided by the dialogue unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the provision of information about exhibits is limited, and it is difficult to provide an interactive experience that attracts the interest of visitors.

[0005] The system according to the embodiment aims to provide detailed information and explanations about exhibits and provide an interactive exhibition experience for visitors.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an explanation unit, a tour guide unit, a reproduction unit, a dialogue unit, and a learning support unit. The explanation unit recognizes exhibits and provides detailed information and explanations. The tour guide unit provides a virtual tour guide based on the information provided by the explanation unit. The reproduction unit reproduces historical scenes and exhibits based on the exhibits guided by the tour guide unit. The dialogue unit provides an interactive exhibit experience with visitors based on the scenes reproduced by the reproduction unit. The learning support unit provides educational programs and learning support programs based on the dialogues provided by the dialogue unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide detailed information and explanations about the exhibits and offer visitors an interactive exhibition experience. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The exhibition system according to an embodiment of the present invention is a system that aims to revitalize local areas by providing interactive and engaging exhibits and experiences in local history museums and art galleries using generative AI. The exhibition system uses generative AI to provide explanations and descriptions of exhibits and artifacts. When a visitor stands in front of an exhibit using a smartphone or tablet, the AI ​​automatically recognizes them and provides detailed information and interesting explanations. Next, the exhibition system uses generative AI to create a virtual tour guide, allowing visitors to freely explore the museum's exhibits using a smartphone or VR headset while the AI ​​provides guidance and explanations. Furthermore, the exhibition system uses generative AI to recreate and reconstruct historical scenes and exhibits, allowing visitors to realistically experience past landscapes and events through the AI. In addition, the exhibition system uses generative AI to provide an interactive exhibition experience with visitors, where the AI ​​interacts with visitors, answers questions, and conducts quizzes to deepen their understanding of the exhibits and themes. Finally, the exhibition system uses generative AI to provide educational programs and learning support programs, allowing visitors to deepen their knowledge of history and culture through interaction with the AI. As a result, visitors can enjoy the exhibits with a deeper understanding and interest, and rediscover the charm of their local area. This allows the exhibition system to provide visitors with an interactive and engaging exhibition experience, contributing to regional revitalization.

[0029] The exhibition system according to this embodiment comprises an explanation unit, a tour guide unit, a reproduction unit, an interaction unit, and a learning support unit. The explanation unit recognizes exhibits and provides detailed information and explanations. For example, the explanation unit uses generative AI to recognize exhibits and provide detailed information and explanations. For example, the explanation unit takes images of exhibits with a camera, and the generative AI analyzes the images to recognize the exhibits. The explanation unit can also use the generative AI to provide detailed information and explanations based on the exhibit recognition results. For example, the generative AI can provide information about the history and background of the exhibits. The tour guide unit uses generative AI to provide guidance and explanations while visitors explore exhibits using smartphones or VR headsets. For example, the tour guide unit uses generative AI to acquire the visitor's location information and provide guidance and explanations about the exhibits. The tour guide unit can also use generative AI to suggest the optimal route based on the visitor's interests. For example, the generative AI can refer to the visitor's past browsing history and prioritize guiding them to relevant exhibits. The reproduction unit uses generative AI to reproduce historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. The Recreation Unit uses, for example, generative AI to recreate historical scenes and exhibits using CG, AR, and VR technologies. The Recreation Unit can also adjust the selection and presentation of scenes based on the visitor's emotions and interests. For example, the generative AI might estimate the visitor's emotions and recreate visually stimulating scenes if they are excited. The Dialogue Unit uses generative AI to interact with visitors, answering questions and conducting quizzes to deepen their understanding of exhibits and themes. The Dialogue Unit uses, for example, generative AI to interact with visitors using voice dialogue or text chat. The Dialogue Unit can also adjust the tone and content of the dialogue based on the visitor's emotions and interests. For example, the generative AI might estimate the visitor's emotions and engage in a lively dialogue if they are excited. The Learning Support Unit uses generative AI to provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. The Learning Support Unit, for example, uses generative AI to provide educational programs such as quizzes, lectures, and practical exercises. Furthermore, the learning support department can use a generating AI to adjust the content and sequence of learning programs based on the visitor's emotions and interests.For example, the generative AI can estimate a visitor's emotions and, if excited, provide a detailed and specialized learning program. This allows the exhibition system, according to the embodiment, to provide visitors with an interactive and engaging exhibition experience, contributing to regional revitalization.

[0030] The explanatory section recognizes exhibits and provides detailed information and explanations. For example, it uses generative AI to recognize exhibits and provide detailed information and explanations. Specifically, it takes images of exhibits with a camera, and the generative AI analyzes these images to recognize the exhibits. The generative AI utilizes image recognition technology to extract features such as the shape, color, and texture of the exhibits, and identifies them by comparing them with a database. Furthermore, the generative AI provides detailed information and explanations based on the exhibit recognition results. For example, when the generative AI provides information about the history and background of an exhibit, it generates a detailed explanation including the exhibit's creation date, creator, the technology and materials used, and historical context. This allows visitors to gain a deeper understanding of the exhibits. The generative AI can also customize the content of the explanations according to the visitor's interests. For example, if a visitor is interested in a particular era or culture, it will prioritize providing relevant information. Additionally, the explanatory section can provide explanations in audio format using speech synthesis technology. This provides not only visual information but also auditory information, deepening the visitor's understanding. The explanatory section can update information on exhibits in real time, and if there are new research results or discoveries, it can immediately update the information to provide the latest information. As a result, the explanatory section can always provide high-quality explanations based on the latest information, satisfying visitors' desire for knowledge.

[0031] The tour guide department uses generative AI to provide guidance and explanations as visitors explore exhibits using smartphones or VR headsets. Specifically, the generative AI acquires the visitor's location information and provides guidance and explanations about the exhibits. The generative AI uses the GPS function and sensors of the visitor's smartphone or VR headset to accurately determine the visitor's current location. This allows it to identify which exhibit the visitor is in front of in real time and provide guidance and explanations about that exhibit. The generative AI can also suggest the optimal route based on the visitor's interests. For example, the generative AI can refer to the visitor's past browsing history and prioritize guiding them to relevant exhibits. This allows visitors to efficiently explore exhibits that match their interests. Furthermore, the tour guide department can adjust the speed of guidance and explanations to match the visitor's pace. For example, if a visitor is carefully observing an exhibit, the speed of guidance and explanations will be slowed down, and conversely, if the visitor is quickly moving from exhibit to exhibit, the speed will be increased. This allows visitors to enjoy the exhibits at their own pace. The tour guide department can also provide guidance and explanations in multiple languages. The AI ​​generates guidance and explanations in the appropriate language based on the visitor's language settings, allowing visitors to enjoy the exhibits without experiencing language barriers. This enables tour guides to provide personalized guidance and explanations to visitors, enriching the exhibition experience.

[0032] The recreation section uses generative AI to recreate historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. Specifically, the generative AI recreates historical scenes and exhibits using CG, AR, and VR technologies. Based on historical documents, literature, and photographs, the generative AI generates detailed models of historical scenes and exhibits. This allows visitors to experience what it's like to have traveled back in time. Furthermore, the recreation section can adjust the selection and presentation of scenes to be recreated based on the visitor's emotions and interests. For example, the generative AI can estimate the visitor's emotions and recreate visually stimulating scenes if they are excited, or quiet scenes if they are calm. This allows visitors to have an experience that matches their emotions and interests. In addition, the recreation section can incorporate interactive elements. For example, visitors can touch a specific object to display detailed information about that object, or perform a specific action to change the progression of historical events. This allows visitors to gain a deeper understanding not just by looking, but by actually experiencing and participating. Furthermore, the recreation unit can build a multi-user system that allows multiple visitors to experience the exhibits simultaneously. This enables families and friends to experience and share historical scenes together. In this way, the recreation unit can provide visitors with an immersive experience and stimulate their interest in the exhibits and history.

[0033] The dialogue unit uses generative AI to interact with visitors, answering questions and conducting quizzes to deepen their understanding of exhibits and themes. Specifically, the generative AI interacts with visitors using voice dialogue and text chat. The generative AI utilizes natural language processing technology to understand visitors' questions and statements and generate appropriate responses. For example, if a visitor asks about a specific exhibit, the generative AI provides detailed information about that exhibit. The dialogue unit can also adjust the tone and content of the dialogue based on the visitor's emotions and interests. For example, the generative AI can estimate the visitor's emotions and engage in a lively dialogue if they are excited, or a calmer dialogue if they are relaxed. This allows visitors to enjoy a dialogue that matches their emotions and interests. Furthermore, the dialogue unit can deepen visitors' understanding through quizzes and games. For example, the generative AI can ask quizzes about exhibits, and visitors can earn points by answering correctly. This allows visitors to deepen their knowledge of the exhibits while having fun. The dialogue unit can also collect visitor feedback and continuously improve the accuracy and effectiveness of the dialogue. For example, the system evaluates whether visitors are satisfied with the content of the dialogue and adjusts the dialogue algorithm based on the results. This allows the dialogue system to provide visitors with a high-quality dialogue experience and deepen their understanding of the exhibits and themes.

[0034] The Learning Support Department uses generative AI to provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. Specifically, the generative AI provides educational programs such as quizzes, lectures, and practical exercises. The generative AI selects and provides appropriate programs based on the visitor's learning progress and level of understanding. For example, if a visitor has basic knowledge of a particular topic, the generative AI will provide a detailed lecture on that topic; conversely, if the visitor lacks basic knowledge, it will provide a program that allows them to learn from the basics. The Learning Support Department can also have the generative AI adjust the content and order of learning programs based on the visitor's emotions and interests. For example, the generative AI can estimate the visitor's emotions and provide a detailed and specialized learning program if they are excited, or provide basic content if they are calm. This allows visitors to have a learning experience that matches their emotions and interests. Furthermore, the Learning Support Department can also incorporate interactive elements. For example, it can provide practical exercise programs where visitors learn by actually working with their hands, or group work where they can solve problems in cooperation with other visitors. This allows visitors to gain a deeper understanding not only by acquiring knowledge, but also by actually experiencing and applying it. Furthermore, the Learning Support Department can record visitors' learning history and provide programs based on that history during subsequent visits. This allows visitors to continue their learning and deepen their understanding of the exhibits and themes. In this way, the Learning Support Department can provide effective learning support to visitors and deepen their knowledge of history and culture.

[0035] The explanatory section can use generative AI to recognize exhibits and provide detailed information and explanations. For example, the explanatory section can use generative AI to analyze images of exhibits and recognize them. For example, the explanatory section can take pictures of exhibits with a camera, and the generative AI analyzes those images to recognize the exhibits. Furthermore, based on the recognition results of the exhibits, the generative AI can also provide detailed information and explanations. For example, the generative AI can provide information about the history and background of the exhibits. As a result, using generative AI improves the accuracy of exhibit recognition and the quality of explanations. Generative AI is implemented using technologies such as deep learning, natural language processing, and image recognition. Some or all of the above-mentioned processes in the explanatory section are performed using generative AI.

[0036] The tour guide department can use generative AI to provide guidance and explanations to visitors as they explore exhibits using smartphones or VR headsets. For example, the tour guide department can use generative AI to acquire the visitor's location information and provide guidance and explanations about the exhibits. For example, the tour guide department can use generative AI to provide detailed guidance about the exhibits based on the visitor's location information. The tour guide department can also use generative AI to suggest the optimal route based on the visitor's interests and preferences. For example, the tour guide department can use generative AI to refer to the visitor's past browsing history and prioritize guiding them to relevant exhibits. In this way, using generative AI allows visitors to have a more interactive and engaging tour experience. Some or all of the above processes in the tour guide department are performed using generative AI. Smartphones and VR headsets used include devices such as iOS, Android, Oculus Rift, and HTC Vive.

[0037] The recreation unit uses generative AI to recreate historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. For example, the recreation unit uses generative AI to recreate historical scenes and exhibits using CG, AR, and VR technologies. For instance, the recreation unit uses generative AI to recreate historical buildings and landscapes. Furthermore, the recreation unit can use AR technology to overlay historical scenes onto real-world landscapes. Additionally, the recreation unit can use VR technology to allow visitors to experience past events in a virtual space. This allows visitors to realistically experience past landscapes and events through the use of generative AI. Some or all of the above-described processes in the recreation unit are performed using generative AI. The recreation of historical scenes and exhibits is achieved, for example, through methods such as CG, AR, and VR technologies.

[0038] The interactive section uses generative AI to engage with visitors, answering questions and conducting quizzes to deepen their understanding of exhibits and themes. For example, the AI ​​can interact with visitors using voice dialogue or text chat. For instance, the AI ​​can use speech recognition technology to understand visitors' questions and provide appropriate answers. The AI ​​can also engage in real-time dialogue with visitors using text chat. Furthermore, the AI ​​can adjust the tone and content of the dialogue based on the visitor's emotions and interests. For example, the AI ​​can estimate the visitor's emotions and engage in a more lively tone if they are excited. This allows visitors to deepen their understanding of exhibits and themes through dialogue using the AI. Some or all of the above processes in the interactive section are performed using generative AI. Dialogue is implemented through methods such as voice dialogue, text chat, and gesture recognition.

[0039] The Learning Support Department uses generative AI to provide educational programs and learning support programs, enabling visitors to deepen their knowledge of history and culture. For example, the Learning Support Department uses generative AI to provide educational programs such as quizzes, lectures, and practical exercises. For instance, the Learning Support Department can use generative AI to present visitors with quizzes on history and culture and provide feedback on correct answers. The Learning Support Department can also use generative AI to provide visitors with knowledge on history and culture in a lecture format. Furthermore, the Learning Support Department can use generative AI to provide learning support to visitors in a practical exercise format. In this way, visitors can deepen their knowledge of history and culture by using generative AI. Some or all of the above processes in the Learning Support Department are performed using generative AI. Educational programs and learning support programs are implemented, for example, through methods such as quizzes, lectures, and practical exercises.

[0040] The explanatory section can prioritize providing relevant information by referencing the visitor's past browsing history when recognizing exhibits. For example, the explanatory section can prioritize displaying information related to exhibits the visitor has viewed in the past. It can also provide explanations of exhibits related to themes the visitor has previously shown interest in. Furthermore, the explanatory section can provide information related to events and workshops the visitor has previously participated in. In this way, by referring to past browsing history, it can provide information that is highly relevant to the visitor. Some or all of the above processing in the explanatory section is performed using generative AI. Past browsing history is obtained, for example, through methods such as browser history and app usage history.

[0041] The explanatory section can adjust the level of detail in its explanations based on the visitor's age and interests when recognizing exhibits. For example, it can provide simple and easy-to-understand explanations for children, and detailed and specialized explanations for adults. Furthermore, it can provide relevant in-depth information to visitors with specific interests. This allows for the provision of more appropriate information by tailoring explanations to the visitor's age and interests. Some or all of the above processing in the explanatory section is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0042] The explanatory section can provide region-related information based on the visitor's geographical location when recognizing exhibits. For example, if a visitor is from a specific region, the explanatory section can provide explanations of exhibits related to that region. The explanatory section can also explain the historical background related to the visitor's current location. Furthermore, the explanatory section can provide information on exhibits related to regions that the visitor is interested in. In this way, region-related information can be provided by providing information based on the visitor's geographical location. Some or all of the above processing in the explanatory section is performed using generative AI. Geographic location information is obtained by methods such as GPS and Wi-Fi location information.

[0043] The explanatory section can analyze visitors' social media activity when recognizing exhibits and provide relevant explanations. For example, it can provide explanations of relevant exhibits based on content shared by visitors on social media. It can also provide information related to accounts that visitors follow. Furthermore, it can provide explanations of exhibits related to events or groups that visitors have participated in. This allows for the provision of more relevant information by providing explanations based on visitors' social media activity. Some or all of the above processing in the explanatory section is performed using generative AI. Social media activity is obtained, for example, through methods such as post content, likes, and follower information.

[0044] The tour guide department can suggest the optimal route during a tour by referring to the visitor's past tour history. For example, the tour guide department can suggest a route related to exhibits the visitor has visited in the past. It can also suggest a route related to themes the visitor has shown interest in in the past. Furthermore, the tour guide department can suggest a route related to events or workshops the visitor has participated in in the past. In this way, by referring to past tour history, the optimal route can be suggested for the visitor. Some or all of the above processing in the tour guide department is performed using generative AI. Past tour history is obtained, for example, through methods such as visit history and tour participation history.

[0045] The tour guide department can highlight specific exhibits during tours based on the visitor's interests. For example, if a visitor shows interest in a particular theme, the tour guide department will highlight exhibits related to that theme. The tour guide department can also highlight works by specific artists or writers if the visitor shows interest. Furthermore, if a visitor shows interest in a particular era or region, the tour guide department can highlight related exhibits. This allows for the provision of more relevant information by highlighting exhibits that align with the visitor's interests. Some or all of the above processing in the tour guide department is performed using generative AI. Visitor interests are identified, for example, through survey results, user profiles, etc.

[0046] The tour guide department can prioritize showing visitors exhibits relevant to their region based on their geographical location. For example, if a visitor is from a specific region, the tour guide department will prioritize showing them exhibits related to that region. The tour guide department can also provide information about the historical context related to the visitor's current location. Furthermore, the tour guide department can prioritize showing visitors exhibits related to areas of interest to the visitor. In this way, by guiding visitors to exhibits based on their geographical location, the tour guide department can provide information relevant to their region. Some or all of the above processing in the tour guide department is performed using generative AI. Geographical location information is obtained by methods such as GPS and Wi-Fi location information.

[0047] The tour guide department can analyze visitors' social media activity during tours and guide them to relevant exhibits. For example, the tour guide department can guide visitors to exhibits related to what they have shared on social media. They can also guide visitors to exhibits related to accounts they follow. Furthermore, they can guide visitors to exhibits related to events or groups they have participated in. This allows for the provision of more relevant information by guiding visitors to exhibits based on their social media activity. Some or all of the above processing by the tour guide department is performed using generative AI. Social media activity is obtained, for example, through posts, likes, follower information, etc.

[0048] The replay unit can prioritize replaying relevant scenes by referring to the visitor's past browsing history. For example, the replay unit can replay scenes related to exhibits the visitor has viewed in the past. It can also replay scenes related to themes the visitor has shown interest in in the past. Furthermore, it can replay scenes related to events or workshops the visitor has participated in in the past. In this way, by referring to past browsing history, it can replay scenes that are highly relevant to the visitor. Some or all of the above processing in the replay unit is performed using generative AI. Past browsing history is obtained, for example, through methods such as browser history and app usage history.

[0049] The reproduction unit can adjust the level of detail of the reproduction according to the visitor's age and interests. For example, it can provide a simple and easy-to-understand reproduction for children, and a detailed and specialized reproduction for adults. Furthermore, it can provide in-depth reproductions relevant to visitors with specific interests. This allows for the provision of more appropriate information by offering reproductions tailored to the visitor's age and interests. Some or all of the above processing in the reproduction unit is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0050] The reenactment unit can recreate scenes related to a region based on the visitor's geographical location information during the reenactment process. For example, if a visitor is from a specific region, the reenactment unit will recreate scenes related to that region. The reenactment unit can also recreate historical background related to the visitor's current location. Furthermore, the reenactment unit can recreate scenes related to regions that the visitor is interested in. In this way, by recreating scenes based on the visitor's geographical location information, region-related information can be provided. Some or all of the above processing in the reenactment unit is performed using generative AI. Geographical location information is obtained by methods such as GPS and Wi-Fi location information.

[0051] The reconstruction unit can analyze a visitor's social media activity during the reconstruction process and recreate relevant scenes. For example, the reconstruction unit can recreate relevant scenes based on content shared by the visitor on social media. It can also recreate scenes related to accounts the visitor follows. Furthermore, the reconstruction unit can recreate scenes related to events or groups the visitor has participated in. This allows for the provision of more relevant information by recreating scenes based on the visitor's social media activity. Some or all of the above processing in the reconstruction unit is performed using generative AI. Social media activity is obtained, for example, through methods such as post content, likes, and follower information.

[0052] The dialogue unit can refer to the visitor's past dialogue history during a conversation to provide relevant questions and quizzes. For example, it can provide questions related to themes the visitor has shown interest in in the past. It can also provide relevant quizzes based on the visitor's past quiz results. Furthermore, it can provide relevant questions based on the content of past conversations the visitor has had. In this way, by referring to past dialogue history, it can provide questions and quizzes that are highly relevant to the visitor. Some or all of the above processing in the dialogue unit is performed using generative AI. Past dialogue history is obtained, for example, through methods such as chat logs and voice recordings.

[0053] The dialogue unit can adjust the level of detail in the conversation according to the visitor's age and interests. For example, it can provide simple and easy-to-understand conversations for children, and detailed and specialized conversations for adults. Furthermore, it can provide relevant in-depth conversations for visitors with specific interests. This allows for the provision of more appropriate information by offering conversations tailored to the visitor's age and interests. Some or all of the above processing in the dialogue unit is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0054] The dialogue unit can provide region-related questions and quizzes based on the visitor's geographical location during the conversation. For example, if the visitor is from a specific region, the dialogue unit will provide questions related to that region. The dialogue unit can also provide quizzes about the historical background related to the visitor's current location. Furthermore, the dialogue unit can provide questions related to regions that the visitor is interested in. In this way, by providing questions and quizzes based on the visitor's geographical location, region-related information can be provided. Some or all of the above processing in the dialogue unit is performed using generative AI. Geographical location information is obtained by methods such as GPS and Wi-Fi location information.

[0055] The dialogue unit can analyze the visitor's social media activity during the conversation and provide relevant questions and quizzes. For example, the dialogue unit can provide relevant questions based on what the visitor has shared on social media. It can also provide quizzes related to the accounts the visitor follows. Furthermore, the dialogue unit can provide questions related to events and groups the visitor has participated in. This allows for the provision of more relevant information by offering questions and quizzes based on the visitor's social media activity. Some or all of the above processing in the dialogue unit is performed using generative AI. Social media activity is obtained, for example, through methods such as posts, likes, and follower information.

[0056] The learning support unit can provide the most suitable program by referring to the visitor's past learning history during learning support. For example, the learning support unit can provide a program related to what the visitor has learned in the past. It can also provide a program related to themes the visitor has shown interest in in the past. Furthermore, the learning support unit can provide a program related to events or workshops the visitor has participated in in the past. In this way, by referring to past learning history, the learning support unit can provide the most suitable program for the visitor. Some or all of the above processing in the learning support unit is performed using generative AI. Past learning history is obtained, for example, through learning logs, test results, etc.

[0057] The Learning Support Department can adjust the level of detail in its programs according to the visitor's age and interests during learning support. For example, it can provide simple and easy-to-understand programs for children, and detailed and specialized programs for adults. Furthermore, it can provide relevant in-depth programs to visitors with specific interests. This allows for the provision of more appropriate information by offering programs tailored to the visitor's age and interests. Some or all of the above processing in the Learning Support Department is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0058] The Learning Support Department can provide region-related programs based on the visitor's geographical location information during learning support. For example, if a visitor is from a specific region, the Learning Support Department can provide a program related to that region. It can also provide programs related to the historical background of the visitor's current location. Furthermore, the Learning Support Department can provide programs related to regions of interest to the visitor. In this way, by providing programs based on the visitor's geographical location information, region-related information can be provided. Some or all of the above processing in the Learning Support Department is performed using generative AI. Geographical location information is obtained, for example, through methods such as GPS and Wi-Fi location information.

[0059] The Learning Support Department can analyze visitors' social media activity and provide relevant programs during learning support sessions. For example, it can provide programs based on content shared by visitors on social media. It can also provide programs related to accounts followed by visitors. Furthermore, it can provide programs related to events and groups that visitors have participated in. This allows for the provision of more relevant information by offering programs based on visitors' social media activity. Some or all of the above processing in the Learning Support Department is performed using generative AI. Social media activity is obtained, for example, through methods such as post content, likes, and follower information.

[0060] The learning support unit can provide programs based on the visitor's schedule by referring to their calendar information during learning support. For example, the learning support unit can refer to the schedule registered in the visitor's calendar and provide a relevant program. It can also provide programs related to specific events based on the visitor's calendar information. Furthermore, the learning support unit can provide the most suitable program based on the visitor's schedule. This allows for the provision of more relevant information by providing programs based on the visitor's calendar information. Some or all of the above processing in the learning support unit is performed using generative AI.

[0061] The learning support department can provide optimal learning programs based on the visitor's health condition during learning support sessions. For example, if a visitor is tired, the learning support department can provide a short, concise program. It can also provide a slightly longer program if the visitor is seeking healthy exercise. Furthermore, if a visitor is feeling unwell, the learning support department can provide a program that includes breaks. This allows for the provision of more appropriate information by offering programs based on the visitor's health condition. Some or all of the above processing in the learning support department is performed using generative AI. Health conditions are acquired through methods such as fitness trackers and medical records.

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

[0063] The exhibition system can prioritize displaying relevant exhibits by referencing a visitor's past browsing history. For example, it can prioritize displaying exhibits related to themes the visitor has previously shown interest in. It can also display exhibits related to events or workshops the visitor has previously attended. Furthermore, it can provide information related to exhibits the visitor has previously viewed. In this way, by referring to past browsing history, it can provide visitors with highly relevant information. Some or all of the above processing in the exhibition system is performed using generative AI. Past browsing history is obtained, for example, through methods such as browser history and app usage history.

[0064] The exhibition system can adjust the level of detail in the exhibit explanations according to the visitor's age and interests. For example, it can provide simple and easy-to-understand explanations for children, and detailed and specialized explanations for adults. Furthermore, it can provide relevant in-depth information to visitors with specific interests. This allows for more appropriate information to be provided by tailoring explanations to the visitor's age and interests. Some or all of the above processing in the exhibition system is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0065] The exhibition system can prioritize guiding visitors to exhibits relevant to their geographical location. For example, if a visitor is from a specific region, it will prioritize guiding them to exhibits related to that region. It can also provide historical context related to the visitor's current location. Furthermore, it can prioritize guiding visitors to exhibits related to regions of interest to them. In this way, by guiding visitors to exhibits based on their geographical location, the system can provide region-relevant information. Some or all of the above processing in the exhibition system is performed using generative AI. Geographic location information is obtained, for example, through methods such as GPS and Wi-Fi location information.

[0066] The exhibition system can analyze visitors' social media activity and guide them to relevant exhibits. For example, it can guide visitors to relevant exhibits based on what they have shared on social media. It can also guide visitors to exhibits related to accounts they follow. Furthermore, it can guide visitors to exhibits related to events and groups they have participated in. This allows for the provision of more relevant information by guiding visitors to exhibits based on their social media activity. Some or all of the above processing in the exhibition system is performed using generative AI. Social media activity is obtained, for example, through posts, likes, follower information, etc.

[0067] The exhibition system can refer to visitors' calendar information to provide guided tours of exhibits based on their schedules. For example, it can refer to appointments registered in a visitor's calendar and guide them to relevant exhibits. It can also guide visitors to exhibits related to specific events based on their calendar information. Furthermore, it can guide visitors to the most suitable exhibits based on their schedules, using their calendar information. This allows for the provision of more relevant information by guiding visitors to exhibits based on their calendar information. Some or all of the above processes in the exhibition system are performed using generative AI.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The explanatory section recognizes the exhibits and provides detailed information and explanations. For example, it uses a generative AI to take images of the exhibits with a camera, analyzes those images to recognize the exhibits, and then, based on the recognition results, provides detailed information and explanations about the history and background of the exhibits. Step 2: The tour guide department uses generative AI to provide guidance and explanations as visitors explore the exhibits using smartphones or VR headsets. For example, the generative AI can acquire the visitor's location information and provide guidance and explanations about the exhibits. It can also suggest the optimal route based on the visitor's interests and preferences. Step 3: The recreation section uses generative AI to recreate historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. For example, the generative AI can recreate historical scenes and exhibits using CG, AR, and VR technologies. It can also adjust the selection and presentation of scenes to be recreated based on the visitor's emotions and interests. Step 4: The dialogue section uses generative AI to interact with visitors, answering questions and conducting quizzes to deepen their understanding of the exhibits and themes. For example, the generative AI can interact with visitors using voice dialogue or text chat. It can also adjust the tone and content of the dialogue based on the visitor's emotions and interests. Step 5: The Learning Support Department uses generative AI to provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. For example, the generative AI provides educational programs such as quizzes, lectures, and practical exercises. It can also adjust the content and order of learning programs based on the visitor's emotions and interests.

[0070] (Example of form 2) The exhibition system according to an embodiment of the present invention is a system that aims to revitalize local areas by providing interactive and engaging exhibits and experiences in local history museums and art galleries using generative AI. The exhibition system uses generative AI to provide explanations and descriptions of exhibits and artifacts. When a visitor stands in front of an exhibit using a smartphone or tablet, the AI ​​automatically recognizes them and provides detailed information and interesting explanations. Next, the exhibition system uses generative AI to create a virtual tour guide, allowing visitors to freely explore the museum's exhibits using a smartphone or VR headset while the AI ​​provides guidance and explanations. Furthermore, the exhibition system uses generative AI to recreate and reconstruct historical scenes and exhibits, allowing visitors to realistically experience past landscapes and events through the AI. In addition, the exhibition system uses generative AI to provide an interactive exhibition experience with visitors, where the AI ​​interacts with visitors, answers questions, and conducts quizzes to deepen their understanding of the exhibits and themes. Finally, the exhibition system uses generative AI to provide educational programs and learning support programs, allowing visitors to deepen their knowledge of history and culture through interaction with the AI. As a result, visitors can enjoy the exhibits with a deeper understanding and interest, and rediscover the charm of their local area. This allows the exhibition system to provide visitors with an interactive and engaging exhibition experience, contributing to regional revitalization.

[0071] The exhibition system according to this embodiment comprises an explanation unit, a tour guide unit, a reproduction unit, an interaction unit, and a learning support unit. The explanation unit recognizes exhibits and provides detailed information and explanations. For example, the explanation unit uses generative AI to recognize exhibits and provide detailed information and explanations. For example, the explanation unit takes images of exhibits with a camera, and the generative AI analyzes the images to recognize the exhibits. The explanation unit can also use the generative AI to provide detailed information and explanations based on the exhibit recognition results. For example, the generative AI can provide information about the history and background of the exhibits. The tour guide unit uses generative AI to provide guidance and explanations while visitors explore exhibits using smartphones or VR headsets. For example, the tour guide unit uses generative AI to acquire the visitor's location information and provide guidance and explanations about the exhibits. The tour guide unit can also use generative AI to suggest the optimal route based on the visitor's interests. For example, the generative AI can refer to the visitor's past browsing history and prioritize guiding them to relevant exhibits. The reproduction unit uses generative AI to reproduce historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. The Recreation Unit uses, for example, generative AI to recreate historical scenes and exhibits using CG, AR, and VR technologies. The Recreation Unit can also adjust the selection and presentation of scenes based on the visitor's emotions and interests. For example, the generative AI might estimate the visitor's emotions and recreate visually stimulating scenes if they are excited. The Dialogue Unit uses generative AI to interact with visitors, answering questions and conducting quizzes to deepen their understanding of exhibits and themes. The Dialogue Unit uses, for example, generative AI to interact with visitors using voice dialogue or text chat. The Dialogue Unit can also adjust the tone and content of the dialogue based on the visitor's emotions and interests. For example, the generative AI might estimate the visitor's emotions and engage in a lively dialogue if they are excited. The Learning Support Unit uses generative AI to provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. The Learning Support Unit, for example, uses generative AI to provide educational programs such as quizzes, lectures, and practical exercises. Furthermore, the learning support department can use a generating AI to adjust the content and sequence of learning programs based on the visitor's emotions and interests.For example, the generative AI can estimate a visitor's emotions and, if excited, provide a detailed and specialized learning program. This allows the exhibition system, according to the embodiment, to provide visitors with an interactive and engaging exhibition experience, contributing to regional revitalization.

[0072] The explanatory section recognizes exhibits and provides detailed information and explanations. For example, it uses generative AI to recognize exhibits and provide detailed information and explanations. Specifically, it takes images of exhibits with a camera, and the generative AI analyzes these images to recognize the exhibits. The generative AI utilizes image recognition technology to extract features such as the shape, color, and texture of the exhibits, and identifies them by comparing them with a database. Furthermore, the generative AI provides detailed information and explanations based on the exhibit recognition results. For example, when the generative AI provides information about the history and background of an exhibit, it generates a detailed explanation including the exhibit's creation date, creator, the technology and materials used, and historical context. This allows visitors to gain a deeper understanding of the exhibits. The generative AI can also customize the content of the explanations according to the visitor's interests. For example, if a visitor is interested in a particular era or culture, it will prioritize providing relevant information. Additionally, the explanatory section can provide explanations in audio format using speech synthesis technology. This provides not only visual information but also auditory information, deepening the visitor's understanding. The explanatory section can update information on exhibits in real time, and if there are new research results or discoveries, it can immediately update the information to provide the latest information. As a result, the explanatory section can always provide high-quality explanations based on the latest information, satisfying visitors' desire for knowledge.

[0073] The tour guide department uses generative AI to provide guidance and explanations as visitors explore exhibits using smartphones or VR headsets. Specifically, the generative AI acquires the visitor's location information and provides guidance and explanations about the exhibits. The generative AI uses the GPS function and sensors of the visitor's smartphone or VR headset to accurately determine the visitor's current location. This allows it to identify which exhibit the visitor is in front of in real time and provide guidance and explanations about that exhibit. The generative AI can also suggest the optimal route based on the visitor's interests. For example, the generative AI can refer to the visitor's past browsing history and prioritize guiding them to relevant exhibits. This allows visitors to efficiently explore exhibits that match their interests. Furthermore, the tour guide department can adjust the speed of guidance and explanations to match the visitor's pace. For example, if a visitor is carefully observing an exhibit, the speed of guidance and explanations will be slowed down, and conversely, if the visitor is quickly moving from exhibit to exhibit, the speed will be increased. This allows visitors to enjoy the exhibits at their own pace. The tour guide department can also provide guidance and explanations in multiple languages. The AI ​​generates guidance and explanations in the appropriate language based on the visitor's language settings, allowing visitors to enjoy the exhibits without experiencing language barriers. This enables tour guides to provide personalized guidance and explanations to visitors, enriching the exhibition experience.

[0074] The recreation section uses generative AI to recreate historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. Specifically, the generative AI recreates historical scenes and exhibits using CG, AR, and VR technologies. Based on historical documents, literature, and photographs, the generative AI generates detailed models of historical scenes and exhibits. This allows visitors to experience what it's like to have traveled back in time. Furthermore, the recreation section can adjust the selection and presentation of scenes to be recreated based on the visitor's emotions and interests. For example, the generative AI can estimate the visitor's emotions and recreate visually stimulating scenes if they are excited, or quiet scenes if they are calm. This allows visitors to have an experience that matches their emotions and interests. In addition, the recreation section can incorporate interactive elements. For example, visitors can touch a specific object to display detailed information about that object, or perform a specific action to change the progression of historical events. This allows visitors to gain a deeper understanding not just by looking, but by actually experiencing and participating. Furthermore, the recreation unit can build a multi-user system that allows multiple visitors to experience the exhibits simultaneously. This enables families and friends to experience and share historical scenes together. In this way, the recreation unit can provide visitors with an immersive experience and stimulate their interest in the exhibits and history.

[0075] The dialogue unit uses generative AI to interact with visitors, answering questions and conducting quizzes to deepen their understanding of exhibits and themes. Specifically, the generative AI interacts with visitors using voice dialogue and text chat. The generative AI utilizes natural language processing technology to understand visitors' questions and statements and generate appropriate responses. For example, if a visitor asks about a specific exhibit, the generative AI provides detailed information about that exhibit. The dialogue unit can also adjust the tone and content of the dialogue based on the visitor's emotions and interests. For example, the generative AI can estimate the visitor's emotions and engage in a lively dialogue if they are excited, or a calmer dialogue if they are relaxed. This allows visitors to enjoy a dialogue that matches their emotions and interests. Furthermore, the dialogue unit can deepen visitors' understanding through quizzes and games. For example, the generative AI can ask quizzes about exhibits, and visitors can earn points by answering correctly. This allows visitors to deepen their knowledge of the exhibits while having fun. The dialogue unit can also collect visitor feedback and continuously improve the accuracy and effectiveness of the dialogue. For example, the system evaluates whether visitors are satisfied with the content of the dialogue and adjusts the dialogue algorithm based on the results. This allows the dialogue system to provide visitors with a high-quality dialogue experience and deepen their understanding of the exhibits and themes.

[0076] The Learning Support Department uses generative AI to provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. Specifically, the generative AI provides educational programs such as quizzes, lectures, and practical exercises. The generative AI selects and provides appropriate programs based on the visitor's learning progress and level of understanding. For example, if a visitor has basic knowledge of a particular topic, the generative AI will provide a detailed lecture on that topic; conversely, if the visitor lacks basic knowledge, it will provide a program that allows them to learn from the basics. The Learning Support Department can also have the generative AI adjust the content and order of learning programs based on the visitor's emotions and interests. For example, the generative AI can estimate the visitor's emotions and provide a detailed and specialized learning program if they are excited, or provide basic content if they are calm. This allows visitors to have a learning experience that matches their emotions and interests. Furthermore, the Learning Support Department can also incorporate interactive elements. For example, it can provide practical exercise programs where visitors learn by actually working with their hands, or group work where they can solve problems in cooperation with other visitors. This allows visitors to gain a deeper understanding not only by acquiring knowledge, but also by actually experiencing and applying it. Furthermore, the Learning Support Department can record visitors' learning history and provide programs based on that history during subsequent visits. This allows visitors to continue their learning and deepen their understanding of the exhibits and themes. In this way, the Learning Support Department can provide effective learning support to visitors and deepen their knowledge of history and culture.

[0077] The explanatory section can use generative AI to recognize exhibits and provide detailed information and explanations. For example, the explanatory section can use generative AI to analyze images of exhibits and recognize them. For example, the explanatory section can take pictures of exhibits with a camera, and the generative AI analyzes those images to recognize the exhibits. Furthermore, based on the recognition results of the exhibits, the generative AI can also provide detailed information and explanations. For example, the generative AI can provide information about the history and background of the exhibits. As a result, using generative AI improves the accuracy of exhibit recognition and the quality of explanations. Generative AI is implemented using technologies such as deep learning, natural language processing, and image recognition. Some or all of the above-mentioned processes in the explanatory section are performed using generative AI.

[0078] The tour guide department can use generative AI to provide guidance and explanations to visitors as they explore exhibits using smartphones or VR headsets. For example, the tour guide department can use generative AI to acquire the visitor's location information and provide guidance and explanations about the exhibits. For example, the tour guide department can use generative AI to provide detailed guidance about the exhibits based on the visitor's location information. The tour guide department can also use generative AI to suggest the optimal route based on the visitor's interests and preferences. For example, the tour guide department can use generative AI to refer to the visitor's past browsing history and prioritize guiding them to relevant exhibits. In this way, using generative AI allows visitors to have a more interactive and engaging tour experience. Some or all of the above processes in the tour guide department are performed using generative AI. Smartphones and VR headsets used include devices such as iOS, Android, Oculus Rift, and HTC Vive.

[0079] The recreation unit uses generative AI to recreate historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. For example, the recreation unit uses generative AI to recreate historical scenes and exhibits using CG, AR, and VR technologies. For instance, the recreation unit uses generative AI to recreate historical buildings and landscapes. Furthermore, the recreation unit can use AR technology to overlay historical scenes onto real-world landscapes. Additionally, the recreation unit can use VR technology to allow visitors to experience past events in a virtual space. This allows visitors to realistically experience past landscapes and events through the use of generative AI. Some or all of the above-described processes in the recreation unit are performed using generative AI. The recreation of historical scenes and exhibits is achieved, for example, through methods such as CG, AR, and VR technologies.

[0080] The interactive section uses generative AI to engage with visitors, answering questions and conducting quizzes to deepen their understanding of exhibits and themes. For example, the AI ​​can interact with visitors using voice dialogue or text chat. For instance, the AI ​​can use speech recognition technology to understand visitors' questions and provide appropriate answers. The AI ​​can also engage in real-time dialogue with visitors using text chat. Furthermore, the AI ​​can adjust the tone and content of the dialogue based on the visitor's emotions and interests. For example, the AI ​​can estimate the visitor's emotions and engage in a more lively tone if they are excited. This allows visitors to deepen their understanding of exhibits and themes through dialogue using the AI. Some or all of the above processes in the interactive section are performed using generative AI. Dialogue is implemented through methods such as voice dialogue, text chat, and gesture recognition.

[0081] The Learning Support Department uses generative AI to provide educational programs and learning support programs, enabling visitors to deepen their knowledge of history and culture. For example, the Learning Support Department uses generative AI to provide educational programs such as quizzes, lectures, and practical exercises. For instance, the Learning Support Department can use generative AI to present visitors with quizzes on history and culture and provide feedback on correct answers. The Learning Support Department can also use generative AI to provide visitors with knowledge on history and culture in a lecture format. Furthermore, the Learning Support Department can use generative AI to provide learning support to visitors in a practical exercise format. In this way, visitors can deepen their knowledge of history and culture by using generative AI. Some or all of the above processes in the Learning Support Department are performed using generative AI. Educational programs and learning support programs are implemented, for example, through methods such as quizzes, lectures, and practical exercises.

[0082] The commentary section can estimate the visitor's emotions and adjust the tone and content of the commentary based on the estimated emotions. For example, if the visitor is excited, the generative AI can provide a more detailed and expert commentary. If the visitor is tired, the generative AI can provide a concise and to-the-point commentary. Furthermore, if the visitor shows interest, the generative AI can provide additional relevant information or anecdotes. This allows for a more personalized experience by providing commentary that responds to the visitor'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. Some or all of the processing described above in the commentary section is performed using generative AI.

[0083] The explanatory section can prioritize providing relevant information by referencing the visitor's past browsing history when recognizing exhibits. For example, the explanatory section can prioritize displaying information related to exhibits the visitor has viewed in the past. It can also provide explanations of exhibits related to themes the visitor has previously shown interest in. Furthermore, the explanatory section can provide information related to events and workshops the visitor has previously participated in. In this way, by referring to past browsing history, it can provide information that is highly relevant to the visitor. Some or all of the above processing in the explanatory section is performed using generative AI. Past browsing history is obtained, for example, through methods such as browser history and app usage history.

[0084] The explanatory section can adjust the level of detail in its explanations based on the visitor's age and interests when recognizing exhibits. For example, it can provide simple and easy-to-understand explanations for children, and detailed and specialized explanations for adults. Furthermore, it can provide relevant in-depth information to visitors with specific interests. This allows for the provision of more appropriate information by tailoring explanations to the visitor's age and interests. Some or all of the above processing in the explanatory section is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0085] The commentary section can estimate the visitor's emotions and adjust the order of the commentary based on those emotions. For example, if the visitor is excited, the commentary section can start the commentary with exhibits that are of interest to them, using a generative AI. If the visitor is tired, the commentary section can also start the commentary with exhibits that are concise and to the point, using a generative AI. Furthermore, if the visitor is relaxed, the commentary section can provide commentary freely without adhering to any particular order. This allows for a more personalized experience by providing a commentary order that matches the visitor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the commentary section is performed using generative AI.

[0086] The explanatory section can provide region-related information based on the visitor's geographical location when recognizing exhibits. For example, if a visitor is from a specific region, the explanatory section can provide explanations of exhibits related to that region. The explanatory section can also explain the historical background related to the visitor's current location. Furthermore, the explanatory section can provide information on exhibits related to regions that the visitor is interested in. In this way, region-related information can be provided by providing information based on the visitor's geographical location. Some or all of the above processing in the explanatory section is performed using generative AI. Geographic location information is obtained by methods such as GPS and Wi-Fi location information.

[0087] The explanatory section can analyze visitors' social media activity when recognizing exhibits and provide relevant explanations. For example, it can provide explanations of relevant exhibits based on content shared by visitors on social media. It can also provide information related to accounts that visitors follow. Furthermore, it can provide explanations of exhibits related to events or groups that visitors have participated in. This allows for the provision of more relevant information by providing explanations based on visitors' social media activity. Some or all of the above processing in the explanatory section is performed using generative AI. Social media activity is obtained, for example, through methods such as post content, likes, and follower information.

[0088] The tour guide system can estimate visitors' emotions and adjust the pace and content of the tour guide based on those estimated emotions. For example, if a visitor is in a hurry, the generative AI can speed up the tour guide's pace. Conversely, if a visitor is relaxed, the generative AI can conduct the tour guide at a more leisurely pace. Furthermore, if a visitor shows interest, the generative AI can provide more detailed explanations. This allows for a more personalized experience by providing a tour guide tailored to the visitor'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. Some or all of the above-described processes in the tour guide system are performed using generative AI.

[0089] The tour guide department can suggest the optimal route during a tour by referring to the visitor's past tour history. For example, the tour guide department can suggest a route related to exhibits the visitor has visited in the past. It can also suggest a route related to themes the visitor has shown interest in in the past. Furthermore, the tour guide department can suggest a route related to events or workshops the visitor has participated in in the past. In this way, by referring to past tour history, the optimal route can be suggested for the visitor. Some or all of the above processing in the tour guide department is performed using generative AI. Past tour history is obtained, for example, through methods such as visit history and tour participation history.

[0090] The tour guide department can highlight specific exhibits during tours based on the visitor's interests. For example, if a visitor shows interest in a particular theme, the tour guide department will highlight exhibits related to that theme. The tour guide department can also highlight works by specific artists or writers if the visitor shows interest. Furthermore, if a visitor shows interest in a particular era or region, the tour guide department can highlight related exhibits. This allows for the provision of more relevant information by highlighting exhibits that align with the visitor's interests. Some or all of the above processing in the tour guide department is performed using generative AI. Visitor interests are identified, for example, through survey results, user profiles, etc.

[0091] The tour guide unit can estimate the visitor's emotions and adjust the order of the tour guide based on those emotions. For example, if the visitor is excited, the generative AI can start the tour with exhibits that are of interest to them. If the visitor is tired, the generative AI can start the tour with exhibits that are concise and to the point. Furthermore, if the visitor is relaxed, the generative AI can proceed with the tour freely without adhering to a specific order. This allows for a more personalized experience by providing a tour guide order that is tailored to the visitor'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. Some or all of the above processing in the tour guide unit is performed using generative AI.

[0092] The tour guide department can prioritize showing visitors exhibits relevant to their region based on their geographical location. For example, if a visitor is from a specific region, the tour guide department will prioritize showing them exhibits related to that region. The tour guide department can also provide information about the historical context related to the visitor's current location. Furthermore, the tour guide department can prioritize showing visitors exhibits related to areas of interest to the visitor. In this way, by guiding visitors to exhibits based on their geographical location, the tour guide department can provide information relevant to their region. Some or all of the above processing in the tour guide department is performed using generative AI. Geographical location information is obtained by methods such as GPS and Wi-Fi location information.

[0093] The tour guide department can analyze visitors' social media activity during tours and guide them to relevant exhibits. For example, the tour guide department can guide visitors to exhibits related to what they have shared on social media. They can also guide visitors to exhibits related to accounts they follow. Furthermore, they can guide visitors to exhibits related to events or groups they have participated in. This allows for the provision of more relevant information by guiding visitors to exhibits based on their social media activity. Some or all of the above processing by the tour guide department is performed using generative AI. Social media activity is obtained, for example, through posts, likes, follower information, etc.

[0094] The reenactment unit can estimate the visitor's emotions and adjust the selection and presentation of scenes to be reenacted based on the estimated emotions. For example, if the visitor is excited, the reenactment unit's generative AI can reenact a visually stimulating scene. If the visitor is relaxed, the reenactment unit's generative AI can also reenact a calm scene. Furthermore, if the visitor shows interest, the reenactment unit's generative AI can perform a more detailed reenactment. This allows for a more personalized experience by providing reenactments that respond to the visitor's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the reenactment unit is performed using generative AI.

[0095] The replay unit can prioritize replaying relevant scenes by referring to the visitor's past browsing history. For example, the replay unit can replay scenes related to exhibits the visitor has viewed in the past. It can also replay scenes related to themes the visitor has shown interest in in the past. Furthermore, it can replay scenes related to events or workshops the visitor has participated in in the past. In this way, by referring to past browsing history, it can replay scenes that are highly relevant to the visitor. Some or all of the above processing in the replay unit is performed using generative AI. Past browsing history is obtained, for example, through methods such as browser history and app usage history.

[0096] The reproduction unit can adjust the level of detail of the reproduction according to the visitor's age and interests. For example, it can provide a simple and easy-to-understand reproduction for children, and a detailed and specialized reproduction for adults. Furthermore, it can provide in-depth reproductions relevant to visitors with specific interests. This allows for the provision of more appropriate information by offering reproductions tailored to the visitor's age and interests. Some or all of the above processing in the reproduction unit is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0097] The replay unit can estimate the visitor's emotions and adjust the order of scenes to be recreated based on the estimated emotions. For example, if the visitor is excited, the replay unit can start recreating scenes that the generating AI finds interesting. If the visitor is tired, the replay unit can also start recreating scenes that are concise and to the point. Furthermore, if the visitor is relaxed, the replay unit can allow the generating AI to proceed with the recreation freely without being bound by order. This provides a more personalized experience by offering a recreation order that matches the visitor's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the replay unit is performed using a generating AI.

[0098] The reenactment unit can recreate scenes related to a region based on the visitor's geographical location information during the reenactment process. For example, if a visitor is from a specific region, the reenactment unit will recreate scenes related to that region. The reenactment unit can also recreate historical background related to the visitor's current location. Furthermore, the reenactment unit can recreate scenes related to regions that the visitor is interested in. In this way, by recreating scenes based on the visitor's geographical location information, region-related information can be provided. Some or all of the above processing in the reenactment unit is performed using generative AI. Geographical location information is obtained by methods such as GPS and Wi-Fi location information.

[0099] The reconstruction unit can analyze a visitor's social media activity during the reconstruction process and recreate relevant scenes. For example, the reconstruction unit can recreate relevant scenes based on content shared by the visitor on social media. It can also recreate scenes related to accounts the visitor follows. Furthermore, the reconstruction unit can recreate scenes related to events or groups the visitor has participated in. This allows for the provision of more relevant information by recreating scenes based on the visitor's social media activity. Some or all of the above processing in the reconstruction unit is performed using generative AI. Social media activity is obtained, for example, through methods such as post content, likes, and follower information.

[0100] The dialogue unit can estimate the visitor's emotions and adjust the tone and content of the dialogue based on the estimated emotions. For example, if the visitor is excited, the generative AI will engage in dialogue in a lively tone. Conversely, if the visitor is relaxed, the generative AI can engage in dialogue in a calm tone. Furthermore, if the visitor shows interest, the generative AI can provide more detailed information. This allows for a more personalized experience by providing dialogue that responds to the visitor's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit is performed using generative AI.

[0101] The dialogue unit can refer to the visitor's past dialogue history during a conversation to provide relevant questions and quizzes. For example, it can provide questions related to themes the visitor has shown interest in in the past. It can also provide relevant quizzes based on the visitor's past quiz results. Furthermore, it can provide relevant questions based on the content of past conversations the visitor has had. In this way, by referring to past dialogue history, it can provide questions and quizzes that are highly relevant to the visitor. Some or all of the above processing in the dialogue unit is performed using generative AI. Past dialogue history is obtained, for example, through methods such as chat logs and voice recordings.

[0102] The dialogue unit can adjust the level of detail in the conversation according to the visitor's age and interests. For example, it can provide simple and easy-to-understand conversations for children, and detailed and specialized conversations for adults. Furthermore, it can provide relevant in-depth conversations for visitors with specific interests. This allows for the provision of more appropriate information by offering conversations tailored to the visitor's age and interests. Some or all of the above processing in the dialogue unit is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0103] The dialogue unit can estimate the visitor's emotions and adjust the order of the conversation based on the estimated emotions. For example, if the visitor is excited, the dialogue unit can start the conversation with an engaging question using a generative AI. If the visitor is tired, the dialogue unit can also start the conversation with a concise and to-the-point question using a generative AI. Furthermore, if the visitor is relaxed, the dialogue unit can allow the generative AI to proceed with the conversation freely without adhering to a specific order. This provides a more personalized experience by offering a conversation order that is tailored to the visitor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit is performed using a generative AI.

[0104] The dialogue unit can provide region-related questions and quizzes based on the visitor's geographical location during the conversation. For example, if the visitor is from a specific region, the dialogue unit will provide questions related to that region. The dialogue unit can also provide quizzes about the historical background related to the visitor's current location. Furthermore, the dialogue unit can provide questions related to regions that the visitor is interested in. In this way, by providing questions and quizzes based on the visitor's geographical location, region-related information can be provided. Some or all of the above processing in the dialogue unit is performed using generative AI. Geographical location information is obtained by methods such as GPS and Wi-Fi location information.

[0105] The dialogue unit can analyze the visitor's social media activity during the conversation and provide relevant questions and quizzes. For example, the dialogue unit can provide relevant questions based on what the visitor has shared on social media. It can also provide quizzes related to the accounts the visitor follows. Furthermore, the dialogue unit can provide questions related to events and groups the visitor has participated in. This allows for the provision of more relevant information by offering questions and quizzes based on the visitor's social media activity. Some or all of the above processing in the dialogue unit is performed using generative AI. Social media activity is obtained, for example, through methods such as posts, likes, and follower information.

[0106] The learning support unit can estimate the visitor's emotions and adjust the content of the learning program based on those emotions. For example, if a visitor is excited, the learning support unit's generative AI can provide a detailed and specialized learning program. If a visitor is tired, the learning support unit's generative AI can also provide a concise and to-the-point learning program. Furthermore, if a visitor shows interest, the learning support unit's generative AI can provide additional relevant information or anecdotes. This allows for a more personalized experience by providing a learning program tailored to the visitor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the learning support unit is performed using generative AI.

[0107] The learning support unit can provide the most suitable program by referring to the visitor's past learning history during learning support. For example, the learning support unit can provide a program related to what the visitor has learned in the past. It can also provide a program related to themes the visitor has shown interest in in the past. Furthermore, the learning support unit can provide a program related to events or workshops the visitor has participated in in the past. In this way, by referring to past learning history, the learning support unit can provide the most suitable program for the visitor. Some or all of the above processing in the learning support unit is performed using generative AI. Past learning history is obtained, for example, through learning logs, test results, etc.

[0108] The Learning Support Department can adjust the level of detail in its programs according to the visitor's age and interests during learning support. For example, it can provide simple and easy-to-understand programs for children, and detailed and specialized programs for adults. Furthermore, it can provide relevant in-depth programs to visitors with specific interests. This allows for the provision of more appropriate information by offering programs tailored to the visitor's age and interests. Some or all of the above processing in the Learning Support Department is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0109] The learning support unit can estimate the visitor's emotions and adjust the order of the learning program based on the estimated emotions. For example, if the visitor is excited, the learning support unit can start the learning program with content that will interest them using the generative AI. If the visitor is tired, the learning support unit can also start the learning program with concise and to-the-point content using the generative AI. Furthermore, if the visitor is relaxed, the learning support unit can allow the generative AI to proceed freely with the learning program without adhering to a specific order. This provides a more personalized experience by offering a learning program order tailored to the visitor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning support unit is performed using generative AI.

[0110] The Learning Support Department can provide region-related programs based on the visitor's geographical location information during learning support. For example, if a visitor is from a specific region, the Learning Support Department can provide a program related to that region. It can also provide programs related to the historical background of the visitor's current location. Furthermore, the Learning Support Department can provide programs related to regions of interest to the visitor. In this way, by providing programs based on the visitor's geographical location information, region-related information can be provided. Some or all of the above processing in the Learning Support Department is performed using generative AI. Geographical location information is obtained, for example, through methods such as GPS and Wi-Fi location information.

[0111] The Learning Support Department can analyze visitors' social media activity and provide relevant programs during learning support sessions. For example, it can provide programs based on content shared by visitors on social media. It can also provide programs related to accounts followed by visitors. Furthermore, it can provide programs related to events and groups that visitors have participated in. This allows for the provision of more relevant information by offering programs based on visitors' social media activity. Some or all of the above processing in the Learning Support Department is performed using generative AI. Social media activity is obtained, for example, through methods such as post content, likes, and follower information.

[0112] The learning support unit can provide programs based on the visitor's schedule by referring to their calendar information during learning support. For example, the learning support unit can refer to the schedule registered in the visitor's calendar and provide a relevant program. It can also provide programs related to specific events based on the visitor's calendar information. Furthermore, the learning support unit can provide the most suitable program based on the visitor's schedule. This allows for the provision of more relevant information by providing programs based on the visitor's calendar information. Some or all of the above processing in the learning support unit is performed using generative AI.

[0113] The learning support department can provide optimal learning programs based on the visitor's health condition during learning support sessions. For example, if a visitor is tired, the learning support department can provide a short, concise program. It can also provide a slightly longer program if the visitor is seeking healthy exercise. Furthermore, if a visitor is feeling unwell, the learning support department can provide a program that includes breaks. This allows for the provision of more appropriate information by offering programs based on the visitor's health condition. Some or all of the above processing in the learning support department is performed using generative AI. Health conditions are acquired through methods such as fitness trackers and medical records.

[0114] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0115] The exhibition system can estimate visitors' emotions and adjust the lighting and sound effects of exhibits based on those emotions. For example, if a visitor is excited, the lighting can be brightened and the music changed to something more lively. If a visitor is relaxed, the lighting can be softened and the music changed to something calmer. Furthermore, if a visitor is surprised, special effects such as spotlighting specific exhibits can be implemented. This provides a more personalized experience by offering an environment that responds to the visitor'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. Some or all of the above processing in the exhibition system is performed using generative AI.

[0116] The exhibition system can estimate visitors' emotions and adjust the interactive elements of the exhibits based on those emotions. For example, if a visitor is excited, the generative AI can provide more interactive elements. If a visitor is relaxed, the generative AI can provide simple and intuitive interactive elements. Furthermore, if a visitor is surprised, the generative AI can provide an interactive experience that includes surprise elements. This allows for a more personalized experience by providing interactive elements that respond to the visitor'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. Some or all of the above processing in the exhibition system is performed using generative AI.

[0117] The exhibition system can estimate visitors' emotions and adjust the content of the exhibit's explanations based on those emotions. For example, if a visitor is excited, the generative AI can provide a detailed and expert explanation. If a visitor is relaxed, the generative AI can provide a concise and to-the-point explanation. Furthermore, if a visitor is surprised, the generative AI can provide an explanation that includes relevant episodes and anecdotes. This allows for a more personalized experience by providing explanations that match the visitor'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. Some or all of the above processing in the exhibition system is performed using generative AI.

[0118] The exhibition system can estimate visitors' emotions and dynamically change the arrangement of exhibits based on those emotions. For example, if a visitor is excited, the generative AI can place exhibits closer to encourage closer observation. If a visitor is relaxed, the generative AI can also place exhibits more widely to encourage a more relaxed viewing experience. Furthermore, if a visitor is surprised, the generative AI can place specific exhibits in a more prominent position. This provides a more personalized experience by offering exhibit arrangements that respond to the visitor'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. Some or all of the above processing in the exhibition system is performed using generative AI.

[0119] The exhibition system can estimate visitors' emotions and provide interactive quizzes and games based on those emotions. For example, if a visitor is excited, the generative AI can provide a difficult quiz or a challenging game. If a visitor is relaxed, the generative AI can provide an easy and relaxing quiz or game. Furthermore, if a visitor is surprised, the generative AI can provide a quiz or game that includes a surprise element. This allows for a more personalized experience by providing interactive quizzes and games that respond to the visitor'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. Some or all of the above processing in the exhibition system is performed using generative AI.

[0120] The exhibition system can prioritize displaying relevant exhibits by referencing a visitor's past browsing history. For example, it can prioritize displaying exhibits related to themes the visitor has previously shown interest in. It can also display exhibits related to events or workshops the visitor has previously attended. Furthermore, it can provide information related to exhibits the visitor has previously viewed. In this way, by referring to past browsing history, it can provide visitors with highly relevant information. Some or all of the above processing in the exhibition system is performed using generative AI. Past browsing history is obtained, for example, through methods such as browser history and app usage history.

[0121] The exhibition system can adjust the level of detail in the exhibit explanations according to the visitor's age and interests. For example, it can provide simple and easy-to-understand explanations for children, and detailed and specialized explanations for adults. Furthermore, it can provide relevant in-depth information to visitors with specific interests. This allows for more appropriate information to be provided by tailoring explanations to the visitor's age and interests. Some or all of the above processing in the exhibition system is performed using generative AI. The visitor's age and interests are identified, for example, through survey results, user profiles, etc.

[0122] The exhibition system can prioritize guiding visitors to exhibits relevant to their geographical location. For example, if a visitor is from a specific region, it will prioritize guiding them to exhibits related to that region. It can also provide historical context related to the visitor's current location. Furthermore, it can prioritize guiding visitors to exhibits related to regions of interest to them. In this way, by guiding visitors to exhibits based on their geographical location, the system can provide region-relevant information. Some or all of the above processing in the exhibition system is performed using generative AI. Geographic location information is obtained, for example, through methods such as GPS and Wi-Fi location information.

[0123] The exhibition system can analyze visitors' social media activity and guide them to relevant exhibits. For example, it can guide visitors to relevant exhibits based on what they have shared on social media. It can also guide visitors to exhibits related to accounts they follow. Furthermore, it can guide visitors to exhibits related to events and groups they have participated in. This allows for the provision of more relevant information by guiding visitors to exhibits based on their social media activity. Some or all of the above processing in the exhibition system is performed using generative AI. Social media activity is obtained, for example, through posts, likes, follower information, etc.

[0124] The exhibition system can refer to visitors' calendar information to provide guided tours of exhibits based on their schedules. For example, it can refer to appointments registered in a visitor's calendar and guide them to relevant exhibits. It can also guide visitors to exhibits related to specific events based on their calendar information. Furthermore, it can guide visitors to the most suitable exhibits based on their schedules, using their calendar information. This allows for the provision of more relevant information by guiding visitors to exhibits based on their calendar information. Some or all of the above processes in the exhibition system are performed using generative AI.

[0125] The following briefly describes the processing flow for example form 2.

[0126] Step 1: The explanatory section recognizes the exhibits and provides detailed information and explanations. For example, it uses a generative AI to take images of the exhibits with a camera, analyzes those images to recognize the exhibits, and then, based on the recognition results, provides detailed information and explanations about the history and background of the exhibits. Step 2: The tour guide department uses generative AI to provide guidance and explanations as visitors explore the exhibits using smartphones or VR headsets. For example, the generative AI can acquire the visitor's location information and provide guidance and explanations about the exhibits. It can also suggest the optimal route based on the visitor's interests and preferences. Step 3: The recreation section uses generative AI to recreate historical scenes and exhibits, enabling visitors to realistically experience past landscapes and events. For example, the generative AI can recreate historical scenes and exhibits using CG, AR, and VR technologies. It can also adjust the selection and presentation of scenes to be recreated based on the visitor's emotions and interests. Step 4: The dialogue section uses generative AI to interact with visitors, answering questions and conducting quizzes to deepen their understanding of the exhibits and themes. For example, the generative AI can interact with visitors using voice dialogue or text chat. It can also adjust the tone and content of the dialogue based on the visitor's emotions and interests. Step 5: The Learning Support Department uses generative AI to provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. For example, the generative AI provides educational programs such as quizzes, lectures, and practical exercises. It can also adjust the content and order of learning programs based on the visitor's emotions and interests.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] Each of the multiple elements described above, including the explanation unit, tour guide unit, reproduction unit, dialogue unit, and learning support unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the explanation unit photographs exhibits using the camera 42 of the smart device 14 and analyzes them by the specific processing unit 290 of the data processing unit 12. The tour guide unit acquires location information from the smart device 14 and provides guidance and explanations by the specific processing unit 290 of the data processing unit 12. The reproduction unit displays CG, AR, and VR technologies using the display 40A of the smart device 14 and reproduces them by the specific processing unit 290 of the data processing unit 12. The dialogue unit interacts with visitors using the microphone 38B and speaker 40B of the smart device 14 and answers questions by the specific processing unit 290 of the data processing unit 12. The learning support unit displays educational programs using the display 40A of the smart device 14 and provides them by the specific processing unit 290 of the data processing unit 12. 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.

[0131] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements described above, including the explanation unit, tour guide unit, reproduction unit, dialogue unit, and learning support unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the explanation unit uses the camera 42 of the smart glasses 214 to photograph exhibits, which are then analyzed by the specific processing unit 290 of the data processing unit 12. The tour guide unit acquires location information from the smart glasses 214, and the specific processing unit 290 of the data processing unit 12 provides guidance and explanations. The reproduction unit uses the display of the smart glasses 214 to display CG, AR, and VR technologies, which are then reproduced by the specific processing unit 290 of the data processing unit 12. The dialogue unit interacts with visitors using the microphone 238 and speaker 240 of the smart glasses 214, and answers questions using the specific processing unit 290 of the data processing unit 12. The learning support unit displays educational programs using the display of the smart glasses 214, which are then provided by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0147] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements described above, including the explanation unit, tour guide unit, reproduction unit, dialogue unit, and learning support unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the explanation unit photographs exhibits using the camera 42 of the headset terminal 314 and analyzes them by the specific processing unit 290 of the data processing unit 12. The tour guide unit acquires location information from the headset terminal 314 and provides guidance and explanations by the specific processing unit 290 of the data processing unit 12. The reproduction unit displays CG, AR, and VR technologies using the display 343 of the headset terminal 314 and reproduces them by the specific processing unit 290 of the data processing unit 12. The dialogue unit interacts with visitors using the microphone 238 and speaker 240 of the headset terminal 314 and answers questions by the specific processing unit 290 of the data processing unit 12. The learning support unit displays educational programs using the display 343 of the headset terminal 314 and provides them by the specific processing unit 290 of the data processing unit 12. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0163] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] Each of the multiple elements described above, including the explanation unit, tour guide unit, reproduction unit, dialogue unit, and learning support unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the explanation unit uses the camera 42 of the robot 414 to photograph exhibits, which are then analyzed by the specific processing unit 290 of the data processing unit 12. The tour guide unit acquires the location information of the robot 414, and the specific processing unit 290 of the data processing unit 12 provides guidance and explanations. The reproduction unit uses the display of the robot 414 to display CG, AR, and VR technologies, which are then reproduced by the specific processing unit 290 of the data processing unit 12. The dialogue unit interacts with visitors using the microphone 238 and speaker 240 of the robot 414, and answers questions using the specific processing unit 290 of the data processing unit 12. The learning support unit displays educational programs using the display of the robot 414, which are then provided by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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."

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] (Note 1) The explanatory section recognizes the exhibits and provides detailed information and explanations, The tour guide section provides a virtual tour guide based on the information provided by the aforementioned explanatory section, Based on the exhibits introduced by the aforementioned tour guide section, the recreation section recreates historical scenes and exhibits, An interactive exhibit unit provides visitors with an interactive exhibit experience based on the scene recreated by the aforementioned reproduction unit, The system includes a learning support unit that provides educational programs and learning support programs based on the dialogue provided by the aforementioned dialogue unit. A system characterized by the following features. (Note 2) The aforementioned explanatory section is, Using generative AI, the exhibits are recognized, and detailed information and explanations are provided. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned tour guide department, Using generative AI, visitors can explore exhibits using smartphones or VR headsets while receiving guidance and explanations. The system described in Appendix 1, characterized by the features described herein. (Note 4) The reproduction unit is, Using generative AI, historical scenes and exhibits are recreated, enabling visitors to realistically experience past landscapes and events. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned dialogue unit, Using generative AI, visitors can interact with the exhibits and themes, deepening their understanding by answering questions and conducting quizzes. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned Learning Support Department, Using generative AI, we provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned explanatory section is, The system estimates the visitor's emotions and adjusts the tone and content of the explanation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned explanatory section is, When recognizing exhibits, the system prioritizes providing relevant information by referencing the visitor's past browsing history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned explanatory section is, When identifying exhibits, the level of detail in the explanations is adjusted according to the visitor's age and interests. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned explanatory section is, The system estimates the visitor's emotions and adjusts the order of explanations based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned explanatory section is, When recognizing exhibits, provide region-relevant information based on the visitor's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned explanatory section is, When visitors identify exhibits, the system analyzes their social media activity and provides relevant explanations. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned tour guide department, The system estimates the visitor's emotions and adjusts the pace and content of the tour guide based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned tour guide department, When guiding a tour, we refer to the visitor's past tour history to suggest the most suitable route. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned tour guide department, During the tour, highlight specific exhibits based on the visitors' interests. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned tour guide department, The system estimates the emotions of visitors and adjusts the order of tour guides based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned tour guide department, During tours, the system prioritizes showing visitors exhibits relevant to their local area based on their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned tour guide department, During tours, we analyze visitors' social media activity and guide them to relevant exhibits. The system described in Appendix 1, characterized by the features described herein. (Note 19) The reproduction unit is, The system estimates the visitor's emotions and adjusts the selection and presentation of scenes to be recreated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The reproduction unit is, During the recreation process, the system prioritizes recreating relevant scenes by referencing the visitor's past browsing history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The reproduction unit is, During the recreation process, the level of detail is adjusted according to the visitor's age and interests. The system described in Appendix 1, characterized by the features described herein. (Note 22) The reproduction unit is, The system estimates the visitor's emotions and adjusts the order of scenes to be recreated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The reproduction unit is, During the recreation process, scenes relevant to the region are recreated based on the visitor's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The reproduction unit is, During the recreation process, the social media activity of visitors is analyzed, and relevant scenes are recreated. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned dialogue unit, It estimates the visitor's emotions and adjusts the tone and content of the conversation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned dialogue unit, During the interaction, the system refers to the visitor's past conversation history to provide relevant questions and quizzes. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned dialogue unit, During the conversation, adjust the level of detail based on the visitor's age and interests. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned dialogue unit, It estimates the visitor's emotions and adjusts the order of conversations based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned dialogue unit, During the interaction, the system provides region-related questions and quizzes based on the visitor's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned dialogue unit, During the interaction, the system analyzes the visitor's social media activity and provides relevant questions and quizzes. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned Learning Support Department, The system estimates the visitor's emotions and adjusts the learning program content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned Learning Support Department, When providing learning support, we refer to the visitor's past learning history to provide the most suitable program. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned Learning Support Department, When providing learning support, the level of detail in the program is adjusted according to the visitor's age and interests. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned Learning Support Department, It estimates the visitor's emotions and adjusts the learning program sequence based on the estimated visitor emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned Learning Support Department, When providing learning support, we offer programs relevant to the region based on the visitor's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned Learning Support Department, When providing learning support, we analyze visitors' social media activity and offer relevant programs. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned Learning Support Department, When providing learning support, we refer to the visitor's calendar information to provide a program based on their schedule. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned Learning Support Department, When providing learning support, we offer an optimal learning program based on the visitor's health condition. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0199] 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. The explanatory section recognizes the exhibits and provides detailed information and explanations, The tour guide section provides a virtual tour guide based on the information provided by the aforementioned explanatory section, Based on the exhibits introduced by the aforementioned tour guide section, the recreation section recreates historical scenes and exhibits, An interactive exhibit unit provides visitors with an interactive exhibit experience based on the scene recreated by the aforementioned reproduction unit, The system includes a learning support unit that provides educational programs and learning support programs based on the dialogue provided by the aforementioned dialogue unit. A system characterized by the following features.

2. The aforementioned explanatory section is, It uses generative AI to recognize exhibits and provide detailed information and explanations. The system according to feature 1.

3. The aforementioned tour guide department, Using generative AI, visitors can explore exhibits using smartphones or VR headsets while receiving guidance and explanations. The system according to feature 1.

4. The reproduction unit is, Using generative AI, historical scenes and exhibits are recreated, enabling visitors to realistically experience past landscapes and events. The system according to feature 1.

5. The aforementioned dialogue unit, Using generative AI, visitors can interact with the exhibits and themes, answering questions and conducting quizzes to deepen their understanding of the exhibits and themes. The system according to feature 1.

6. The aforementioned Learning Support Department, Using generative AI, we provide educational and learning support programs, enabling visitors to deepen their knowledge of history and culture. The system according to feature 1.

7. The aforementioned explanatory section is, The system estimates the visitor's emotions and adjusts the tone and content of the explanation based on those estimated emotions. The system according to feature 1.

8. The aforementioned explanatory section is, When recognizing exhibits, the system prioritizes providing relevant information by referencing the visitor's past browsing history. The system according to feature 1.

9. The aforementioned explanatory section is, When identifying exhibits, the level of detail in the explanations is adjusted according to the visitor's age and interests. The system according to feature 1.

10. The aforementioned explanatory section is, The system estimates the visitor's emotions and adjusts the order of explanations based on those emotions. The system according to feature 1.

Images