system

Abstract

The system according to this embodiment aims to predict congestion levels in tourist destinations and propose the most suitable itinerary for travelers. [Solution] The system according to the embodiment comprises a prediction unit, a proposal unit, and a setting unit. The prediction unit predicts the congestion level of tourist destinations. The proposal unit proposes an optimal itinerary for travelers based on the congestion level predicted by the prediction unit. The setting unit dynamically sets the price based on the itinerary proposed by the proposal 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 conventional technology, predicting the congestion situation of a tourist destination and proposing an optimal itinerary for travelers has not been sufficiently carried out, and there is room for improvement.

[0005] The system according to an embodiment aims to predict the congestion situation of a tourist destination and propose an optimal itinerary for travelers.

Means for Solving the Problems

[0006] The system according to an embodiment includes a prediction unit, a proposal unit, and a setting unit. The prediction unit predicts the congestion situation of a tourist destination. The proposal unit proposes an optimal itinerary for travelers based on the congestion situation predicted by the prediction unit. The setting unit dynamically sets a price based on the itinerary proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to this embodiment can predict the congestion level of tourist destinations and suggest the optimal itinerary for travelers. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 AI-powered tourism distribution system according to an embodiment of the present invention is a system that solves the problem of overtourism by utilizing generative AI. This AI-powered tourism distribution system has key functions including real-time congestion prediction, personalized itinerary suggestions, dynamic pricing, virtual tour experiences, and support for regional economic revitalization. For example, the real-time congestion prediction function uses AI to analyze past data, weather information, event information, etc., to predict the congestion level of tourist destinations. Next, the personalized itinerary suggestion function uses AI to analyze travelers' preferences and past travel history to suggest the optimal itinerary. The dynamic pricing function uses AI to dynamically set prices based on the congestion level and demand of tourist destinations. The virtual tour experience function uses AI to generate images and videos to provide travelers with virtual tours. Finally, the regional economic revitalization support function uses AI to analyze tourist trends and guide them to local small businesses. In this way, the AI-powered tourism distribution system can solve the problem of overtourism by utilizing generative AI, provide travelers with fulfilling travel experiences, and revitalize the regional economy.

[0029] The AI-powered tourism distribution system according to this embodiment comprises a prediction unit, a suggestion unit, and a setting unit. The prediction unit predicts the congestion level of a tourist destination. The prediction unit predicts the congestion level of a tourist destination by analyzing, for example, past data, weather information, and event information. The prediction unit can use AI to analyze past data and predict the congestion level of a tourist destination. For example, the prediction unit predicts the congestion level of a tourist destination based on past visitor data. The prediction unit can also predict the congestion level of a tourist destination based on weather information. Furthermore, the prediction unit can also predict the congestion level of a tourist destination based on event information. The suggestion unit proposes the optimal itinerary for travelers based on the congestion level predicted by the prediction unit. The suggestion unit proposes the optimal itinerary by analyzing, for example, the traveler's preferences and past travel history. The suggestion unit can use AI to analyze the traveler's preferences and propose the optimal itinerary. For example, the suggestion unit proposes the optimal itinerary based on the traveler's past travel history. Furthermore, the suggestion unit can propose the optimal itinerary based on the traveler's preferences. Furthermore, the suggestion unit can propose the optimal itinerary based on the traveler's current situation. The setting unit dynamically sets prices based on the itinerary proposed by the suggestion unit. The setting unit dynamically sets prices based, for example, on the congestion level and demand at tourist destinations. The setting unit can use AI to analyze the congestion level at tourist destinations and dynamically set prices. For example, the setting unit dynamically sets prices based on the congestion level at tourist destinations. The setting unit can also dynamically set prices based on the demand at tourist destinations. Furthermore, the setting unit can also dynamically set prices based on the supply level at tourist destinations. As a result, the AI ​​tourism distribution system according to this embodiment can solve the problem of overtourism by predicting the congestion level at tourist destinations, proposing the optimal itinerary, and dynamically setting prices.

[0030] The prediction unit predicts the level of congestion at tourist destinations. For example, it analyzes historical data, weather information, and event information to predict congestion levels. Specifically, it predicts congestion levels based on past visitor data. For instance, it collects visitor data from the past several years and analyzes seasonal fluctuations and increases / decreases in visitor numbers during specific events. This allows for understanding congestion trends during specific periods or events. It can also predict congestion levels based on weather information. For example, since visitor numbers tend to increase on sunny days and decrease on bad weather days, it predicts congestion levels based on weather forecasts. Furthermore, it can predict congestion levels based on event information. For example, it collects event information such as local festivals and concerts and predicts congestion levels considering their impact. The prediction unit analyzes this data using AI to predict congestion levels at tourist destinations with high accuracy. The AI ​​uses machine learning algorithms to learn patterns from past data and predict future congestion levels. For example, it uses regression analysis and time series analysis to build visitor prediction models. This allows the prediction unit to forecast congestion levels at tourist destinations in real time and provide travelers with appropriate information. Furthermore, the prediction unit can continuously update its prediction results and make predictions based on the latest information. For example, whenever new event information or weather information becomes available, the prediction model is updated to improve accuracy. As a result, the prediction unit can accurately predict congestion levels at tourist destinations and provide travelers with useful information.

[0031] The suggestion unit proposes the optimal itinerary for travelers based on the congestion levels predicted by the prediction unit. Specifically, it analyzes travelers' preferences and past travel history to propose the best itinerary. For example, it collects data on tourist destinations and activities travelers have previously visited to understand their preferences. This allows it to suggest tourist destinations and activities that travelers are likely to be interested in. It can also propose the optimal itinerary based on the traveler's current situation. For example, it considers information such as the traveler's current location, length of stay, and budget to propose the optimal sightseeing route and schedule. The suggestion unit uses AI to analyze this data and propose a personalized itinerary for travelers. The AI ​​uses collaborative filtering and content-based recommendation algorithms to recommend tourist destinations and activities that match the traveler's preferences. For example, it uses collaborative filtering to recommend tourist destinations visited by other travelers with similar preferences. It also uses content-based recommendation algorithms to suggest new tourist destinations with similar characteristics to those previously visited by travelers. Furthermore, the suggestion unit can consider real-time updated congestion levels to suggest the optimal timing for travelers to visit. For example, if a particular tourist destination is crowded, the system suggests visiting other destinations first and adjusts the schedule so that the destinations are visited after the crowds have subsided. This allows the system to provide travelers with a comfortable and efficient itinerary while distributing the congestion across tourist destinations.

[0032] The pricing unit dynamically sets prices based on the itinerary proposed by the suggestion unit. Specifically, it dynamically sets prices based on the congestion and demand at tourist destinations. For example, if a tourist destination is crowded, it raises prices to suppress demand and alleviate congestion. Conversely, if a tourist destination is not crowded, it lowers prices to stimulate demand and promote the use of the tourist destination. The pricing unit can use AI to analyze the congestion status of tourist destinations and dynamically set prices. The AI ​​uses a demand forecasting algorithm to predict the demand at tourist destinations and set the optimal price. For example, it uses a demand forecasting algorithm to predict fluctuations in demand during specific periods or events and adjusts prices accordingly. The pricing unit can also dynamically set prices based on the supply situation at tourist destinations. For example, it sets prices considering the capacity of tourist destinations and the services provided. This allows the pricing unit to flexibly adjust prices according to the congestion and demand at tourist destinations, optimizing the use of tourist destinations. Furthermore, the pricing unit can analyze the history of pricing and evaluate the effectiveness of pricing. For example, it can compare past pricing with the results to analyze the effectiveness of pricing. This allows the settings unit to improve the accuracy of pricing and provide data to optimize the use of tourist destinations. As a result, the settings unit can predict congestion levels at tourist destinations, propose optimal itineraries, and dynamically set prices, thereby solving the problem of overtourism.

[0033] The generation unit generates virtual tours. For example, the generation unit uses AI to generate images and videos of tourist destinations and provide virtual tours to travelers. The generation unit can also use AI to generate 3D models of tourist destinations and provide virtual tours to travelers. For example, the generation unit generates 3D models based on image data of tourist destinations. Furthermore, the generation unit can generate virtual tours based on video data of tourist destinations. In addition, the generation unit can generate virtual tours based on real-time data of tourist destinations. This allows for the provision of new experiences to travelers through virtual tours.

[0034] The guidance unit analyzes tourist movements and aims to guide them to local small businesses. For example, the guidance unit can use AI to analyze tourist movements and guide them to local small businesses. The guidance unit can use AI to analyze tourist movement patterns and guide them to local small businesses. For example, the guidance unit can guide tourists to local small businesses based on their movement data. Furthermore, the guidance unit can guide tourists to local small businesses based on their length of stay. In addition, the guidance unit can guide tourists to local small businesses based on their spending behavior. This helps to support the revitalization of the local economy by guiding tourists to local small businesses.

[0035] The prediction unit can predict the congestion level of tourist destinations by analyzing historical data, weather information, and event information. For example, the prediction unit can predict the congestion level of tourist destinations based on past visitor data. The prediction unit can use AI to analyze past visitor data and predict the congestion level of tourist destinations. For example, the prediction unit can predict the congestion level of tourist destinations based on past visitor data. The prediction unit can also predict the congestion level of tourist destinations based on weather information. Furthermore, the prediction unit can also predict the congestion level of tourist destinations based on event information. As a result, the accuracy of congestion predictions is improved by analyzing historical data, weather information, and event information.

[0036] The suggestion function can analyze travelers' preferences and past travel history to propose the optimal itinerary. For example, the suggestion function can analyze travelers' preferences and propose the optimal itinerary. The suggestion function can use AI to analyze travelers' preferences and propose the optimal itinerary. For example, the suggestion function can propose the optimal itinerary based on travelers' past travel history. Furthermore, the suggestion function can propose the optimal itinerary based on travelers' preferences. In addition, the suggestion function can propose the optimal itinerary based on travelers' current circumstances. This allows for the proposal of individually optimized itineraries by analyzing travelers' preferences and past travel history.

[0037] The pricing unit can dynamically set prices based on the congestion and demand at tourist destinations. For example, the pricing unit can dynamically set prices based on the congestion at tourist destinations. The pricing unit can use AI to analyze the congestion at tourist destinations and dynamically set prices. For example, the pricing unit can dynamically set prices based on the congestion at tourist destinations. The pricing unit can also dynamically set prices based on the demand at tourist destinations. Furthermore, the pricing unit can also dynamically set prices based on the supply situation at tourist destinations. This allows for a balance between supply and demand by setting prices based on the congestion and demand at tourist destinations.

[0038] The prediction unit can analyze real-time social media posts and predict congestion levels. For example, the prediction unit can analyze real-time tweets and predict congestion levels at tourist destinations. The prediction unit uses AI to analyze real-time social media posts and predict congestion levels. For example, the prediction unit can analyze Instagram posts to grasp the popularity of tourist destinations in real time. The prediction unit can also analyze SNS information and predict congestion levels at tourist destinations. This allows for the latest congestion information to be grasped by analyzing real-time social media posts.

[0039] The prediction unit can improve prediction accuracy by considering the traffic conditions around tourist destinations. For example, the prediction unit can analyze surrounding traffic congestion information and predict the congestion level of tourist destinations. The prediction unit can use AI to analyze surrounding traffic congestion information and predict the congestion level of tourist destinations. For example, the prediction unit can predict the congestion level of tourist destinations by considering the operating status of public transportation. The prediction unit can also analyze the availability of parking spaces in the surrounding area and predict the congestion level of tourist destinations. In this way, the accuracy of congestion prediction is improved by considering the surrounding traffic conditions.

[0040] The prediction unit can make predictions while considering the geographical characteristics of tourist destinations. For example, the prediction unit can predict congestion by considering the topography of the tourist destination. The prediction unit can use AI to make predictions while considering the geographical characteristics of tourist destinations. For example, the prediction unit can predict congestion by considering the access methods to the tourist destination. In addition, the prediction unit can also predict congestion by considering the size of the tourist destination. This makes it possible to make more accurate congestion predictions by considering the geographical characteristics of tourist destinations.

[0041] The prediction unit can improve its prediction accuracy by referring to the past event history of tourist destinations. For example, the prediction unit can improve its prediction accuracy by referring to the congestion levels during past events. The prediction unit can use AI to improve its prediction accuracy by referring to the past event history of tourist destinations. For example, the prediction unit makes congestion predictions by considering the types of past events. The prediction unit can also make congestion predictions by referring to the number of participants in past events. In this way, the accuracy of congestion predictions is improved by referring to past event history.

[0042] The suggestion function can analyze a traveler's past travel history as well as their current health condition to propose the optimal itinerary. For example, the suggestion function can propose the optimal itinerary based on places the traveler has visited in the past. The suggestion function can use AI to analyze a traveler's past travel history and current health condition to propose the optimal itinerary. For example, the suggestion function can propose a manageable itinerary considering the traveler's current health condition. Furthermore, the suggestion function can comprehensively analyze a traveler's past travel history and health condition to propose the optimal itinerary. This allows for the proposal of a manageable itinerary that takes the traveler's health condition into consideration.

[0043] The suggestion function can apply different suggestion algorithms based on the traveler's interests. For example, if the traveler is interested in history, the suggestion function will suggest an itinerary that includes historical tourist attractions. The suggestion function can use AI to apply different suggestion algorithms based on the traveler's interests. For example, if the traveler is interested in nature, the suggestion function will suggest an itinerary that allows them to enjoy natural scenery. Also, if the traveler is interested in food, the suggestion function can suggest an itinerary that allows them to enjoy delicious local cuisine. In this way, by applying suggestion algorithms based on the traveler's interests, more personalized itinerary suggestions become possible.

[0044] The suggestion function can propose the optimal itinerary by considering the traveler's geographical location. For example, it can suggest the best tourist destinations based on the traveler's current location. The suggestion function can use AI to propose the optimal itinerary by considering the traveler's geographical location. For example, it can propose the optimal itinerary by considering the traveler's mode of transportation. It can also propose an efficient itinerary by considering the traveler's length of stay. In this way, considering the traveler's geographical location makes it possible to propose a more efficient itinerary.

[0045] The suggestion function can analyze travelers' social media activity and propose relevant itineraries. For example, it can analyze travelers' tweets and suggest tourist destinations of interest. The suggestion function can use AI to analyze travelers' social media activity and propose relevant itineraries. For example, it can analyze travelers' Instagram posts and suggest relevant tourist destinations. Furthermore, the suggestion function can analyze travelers' social media information and propose the optimal itinerary. This allows for more relevant itinerary suggestions by analyzing travelers' social media activity.

[0046] The setting unit can set the optimal price by referring to past price fluctuation data for tourist destinations. For example, the setting unit can set the optimal price based on past price fluctuation data. The setting unit can also use AI to analyze past price fluctuation data for tourist destinations and set the optimal price. For example, the setting unit can set the price by considering past demand data. In addition, the setting unit can set the price by referring to past price data of competitors. This makes it possible to set more appropriate prices by referring to past price fluctuation data.

[0047] The pricing unit can set prices considering seasonal demand fluctuations in tourist destinations. For example, the pricing unit can set prices based on seasonal demand data. The pricing unit can also use AI to analyze seasonal demand fluctuations in tourist destinations and set prices accordingly. For example, the pricing unit can set prices considering the trends of tourists in each season. Furthermore, the pricing unit can also set prices by referring to the pricing data of competitors in each season. This allows for more appropriate pricing by considering seasonal demand fluctuations.

[0048] The pricing unit can set prices considering the geographical characteristics of tourist destinations. For example, the pricing unit can set prices considering the accessibility of tourist destinations. The pricing unit can use AI to set prices considering the geographical characteristics of tourist destinations. For example, the pricing unit can set prices considering the popularity of tourist destinations. The pricing unit can also set prices considering the availability of surrounding facilities for tourist destinations. This makes it possible to set more appropriate prices by considering the geographical characteristics of tourist destinations.

[0049] The pricing unit can set prices by referring to relevant market data for tourist destinations. For example, the pricing unit can set prices by referring to the pricing data of competitors. The pricing unit can also set prices by using AI to refer to relevant market data for tourist destinations. For example, the pricing unit can set prices based on relevant market demand data. The pricing unit can also set prices by considering relevant market supply data. This allows for more appropriate pricing by referring to relevant market data.

[0050] The generation unit can generate the optimal virtual tour by referencing past video data of tourist destinations during the virtual tour generation process. For example, the generation unit generates the optimal virtual tour based on past video data. The generation unit can use AI to generate the optimal tour by referencing past video data of tourist destinations. For example, the generation unit generates a virtual tour by considering past tourist evaluation data. The generation unit can also generate a virtual tour by referencing past event footage. This allows for the generation of more appropriate virtual tours by referencing past video data.

[0051] The generation unit can generate virtual tours while considering the geographical characteristics of the tourist destination. For example, the generation unit can generate virtual tours while considering the topography of the tourist destination. The generation unit can use AI to generate tours while considering the geographical characteristics of the tourist destination. For example, the generation unit can generate virtual tours while considering how to access the tourist destination. The generation unit can also generate virtual tours while considering the size of the tourist destination. This allows for the generation of more appropriate virtual tours by considering the geographical characteristics of the tourist destination.

[0052] The guidance unit can analyze tourists' past spending behavior during guidance and select the optimal guidance method. For example, the guidance unit can select the optimal guidance method based on past spending behavior. The guidance unit can use AI to analyze tourists' past spending behavior and select the optimal guidance method. For example, the guidance unit can select a guidance method by considering past spending patterns. The guidance unit can also select the optimal guidance method by referring to past spending history. In this way, by analyzing past spending behavior, a more appropriate guidance method can be selected.

[0053] The guidance unit can select the optimal guidance method by considering the tourist's geographical location information during guidance. For example, the guidance unit can select the optimal guidance method based on the tourist's current location. The guidance unit can also use AI to select the optimal guidance method by considering the tourist's geographical location information. For example, the guidance unit can select the optimal guidance method by considering the tourist's mode of transportation. Furthermore, the guidance unit can also select an efficient guidance method by considering the tourist's length of stay. This makes it possible to provide more appropriate guidance by considering the tourist's geographical location information.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The AI-powered tourism distribution system can also be equipped with a "feedback collection unit." This unit collects real-time feedback from travelers and uses it to improve the overall accuracy of the system. For example, the feedback collection unit provides questionnaires that allow travelers to evaluate their satisfaction with the tourist destinations they visit. It can also collect comments from travelers regarding the level of crowding and the quality of service they experience. Furthermore, the feedback collection unit can collect travelers' opinions on suggested itineraries and incorporate them into future suggestions. In this way, the accuracy and usability of the system can be improved by utilizing traveler feedback.

[0056] The AI-powered tourism distribution system can also be equipped with a "health monitoring unit." This unit monitors travelers' health status in real time and provides appropriate advice. For example, it can monitor travelers' heart rate and steps and suggest breaks to avoid excessive fatigue. It can also manage travelers' hydration and meal timing to support healthy travel. Furthermore, if a traveler has a specific health problem, the health monitoring unit can suggest tourist destinations and activities that address that problem. This allows for a safe and comfortable travel experience that takes travelers' health into consideration.

[0057] The AI-powered tourism distribution system can also include an "entertainment service." This service provides travelers with entertainment content related to the tourist destination. For example, it could offer documentary videos about the history and culture of the destination. It could also offer quizzes and games related to the destination to engage travelers. Furthermore, it could stream live performances and music by local artists in the destination. This allows travelers to deepen their knowledge of the destination while having an enjoyable time.

[0058] The AI-powered tourism distribution system can also be equipped with an "emergency response unit." This unit provides functions to quickly respond when travelers face emergencies. For example, if a traveler gets lost, the emergency response unit can locate their current location and guide them to the nearest safe place. It can also guide travelers to the nearest medical facility if they complain of feeling unwell. Furthermore, the emergency response unit can assist travelers in contacting the police if they become victims of crime. This allows travelers to enjoy their trip with peace of mind.

[0059] The AI-powered distributed tourism system can also be equipped with an "environmental monitoring unit." This unit monitors the environmental conditions of tourist destinations in real time and provides travelers with appropriate information. For example, it monitors the air quality, temperature, and humidity of tourist destinations to support travelers in having a comfortable trip. It can also monitor the state of protection of the natural environment of tourist destinations and raise awareness among travelers about the importance of environmental protection. Furthermore, it can monitor the amount of waste and water quality of tourist destinations and promote environmental protection activities. This allows travelers to enjoy environmentally conscious tourism.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The prediction unit predicts the congestion level of tourist destinations. The prediction unit analyzes past data, weather information, and event information to predict the congestion level of tourist destinations. Using AI, it is possible to analyze past data and predict the congestion level of tourist destinations. For example, predictions can be made based on past visitor data, weather information, and event information. Step 2: The suggestion unit proposes the optimal itinerary for travelers based on the congestion predicted by the prediction unit. The suggestion unit analyzes the traveler's preferences and past travel history to propose the optimal itinerary. Using AI, it is possible to analyze the traveler's preferences and propose the optimal itinerary. For example, it can make suggestions based on the traveler's past travel history and current situation. Step 3: The setting unit dynamically sets the price based on the itinerary proposed by the suggestion unit. The setting unit dynamically sets the price based on the congestion and demand at the tourist destination. Using AI, it is possible to analyze the congestion at the tourist destination and dynamically set the price. For example, the price can be set based on the congestion, demand, and supply situation at the tourist destination.

[0062] (Example of form 2) The AI-powered tourism distribution system according to an embodiment of the present invention is a system that solves the problem of overtourism by utilizing generative AI. This AI-powered tourism distribution system has key functions including real-time congestion prediction, personalized itinerary suggestions, dynamic pricing, virtual tour experiences, and support for regional economic revitalization. For example, the real-time congestion prediction function uses AI to analyze past data, weather information, event information, etc., to predict the congestion level of tourist destinations. Next, the personalized itinerary suggestion function uses AI to analyze travelers' preferences and past travel history to suggest the optimal itinerary. The dynamic pricing function uses AI to dynamically set prices based on the congestion level and demand of tourist destinations. The virtual tour experience function uses AI to generate images and videos to provide travelers with virtual tours. Finally, the regional economic revitalization support function uses AI to analyze tourist trends and guide them to local small businesses. In this way, the AI-powered tourism distribution system can solve the problem of overtourism by utilizing generative AI, provide travelers with fulfilling travel experiences, and revitalize the regional economy.

[0063] The AI-powered tourism distribution system according to this embodiment comprises a prediction unit, a suggestion unit, and a setting unit. The prediction unit predicts the congestion level of a tourist destination. The prediction unit predicts the congestion level of a tourist destination by analyzing, for example, past data, weather information, and event information. The prediction unit can use AI to analyze past data and predict the congestion level of a tourist destination. For example, the prediction unit predicts the congestion level of a tourist destination based on past visitor data. The prediction unit can also predict the congestion level of a tourist destination based on weather information. Furthermore, the prediction unit can also predict the congestion level of a tourist destination based on event information. The suggestion unit proposes the optimal itinerary for travelers based on the congestion level predicted by the prediction unit. The suggestion unit proposes the optimal itinerary by analyzing, for example, the traveler's preferences and past travel history. The suggestion unit can use AI to analyze the traveler's preferences and propose the optimal itinerary. For example, the suggestion unit proposes the optimal itinerary based on the traveler's past travel history. Furthermore, the suggestion unit can propose the optimal itinerary based on the traveler's preferences. Furthermore, the suggestion unit can propose the optimal itinerary based on the traveler's current situation. The setting unit dynamically sets prices based on the itinerary proposed by the suggestion unit. The setting unit dynamically sets prices based, for example, on the congestion level and demand at tourist destinations. The setting unit can use AI to analyze the congestion level at tourist destinations and dynamically set prices. For example, the setting unit dynamically sets prices based on the congestion level at tourist destinations. The setting unit can also dynamically set prices based on the demand at tourist destinations. Furthermore, the setting unit can also dynamically set prices based on the supply level at tourist destinations. As a result, the AI ​​tourism distribution system according to this embodiment can solve the problem of overtourism by predicting the congestion level at tourist destinations, proposing the optimal itinerary, and dynamically setting prices.

[0064] The prediction unit predicts the level of congestion at tourist destinations. For example, it analyzes historical data, weather information, and event information to predict congestion levels. Specifically, it predicts congestion levels based on past visitor data. For instance, it collects visitor data from the past several years and analyzes seasonal fluctuations and increases / decreases in visitor numbers during specific events. This allows for understanding congestion trends during specific periods or events. It can also predict congestion levels based on weather information. For example, since visitor numbers tend to increase on sunny days and decrease on bad weather days, it predicts congestion levels based on weather forecasts. Furthermore, it can predict congestion levels based on event information. For example, it collects event information such as local festivals and concerts and predicts congestion levels considering their impact. The prediction unit analyzes this data using AI to predict congestion levels at tourist destinations with high accuracy. The AI ​​uses machine learning algorithms to learn patterns from past data and predict future congestion levels. For example, it uses regression analysis and time series analysis to build visitor prediction models. This allows the prediction unit to forecast congestion levels at tourist destinations in real time and provide travelers with appropriate information. Furthermore, the prediction unit can continuously update its prediction results and make predictions based on the latest information. For example, whenever new event information or weather information becomes available, the prediction model is updated to improve accuracy. As a result, the prediction unit can accurately predict congestion levels at tourist destinations and provide travelers with useful information.

[0065] The suggestion unit proposes the optimal itinerary for travelers based on the congestion levels predicted by the prediction unit. Specifically, it analyzes travelers' preferences and past travel history to propose the best itinerary. For example, it collects data on tourist destinations and activities travelers have previously visited to understand their preferences. This allows it to suggest tourist destinations and activities that travelers are likely to be interested in. It can also propose the optimal itinerary based on the traveler's current situation. For example, it considers information such as the traveler's current location, length of stay, and budget to propose the optimal sightseeing route and schedule. The suggestion unit uses AI to analyze this data and propose a personalized itinerary for travelers. The AI ​​uses collaborative filtering and content-based recommendation algorithms to recommend tourist destinations and activities that match the traveler's preferences. For example, it uses collaborative filtering to recommend tourist destinations visited by other travelers with similar preferences. It also uses content-based recommendation algorithms to suggest new tourist destinations with similar characteristics to those previously visited by travelers. Furthermore, the suggestion unit can consider real-time updated congestion levels to suggest the optimal timing for travelers to visit. For example, if a particular tourist destination is crowded, the system suggests visiting other destinations first and adjusts the schedule so that the destinations are visited after the crowds have subsided. This allows the system to provide travelers with a comfortable and efficient itinerary while distributing the congestion across tourist destinations.

[0066] The pricing unit dynamically sets prices based on the itinerary proposed by the suggestion unit. Specifically, it dynamically sets prices based on the congestion and demand at tourist destinations. For example, if a tourist destination is crowded, it raises prices to suppress demand and alleviate congestion. Conversely, if a tourist destination is not crowded, it lowers prices to stimulate demand and promote the use of the tourist destination. The pricing unit can use AI to analyze the congestion status of tourist destinations and dynamically set prices. The AI ​​uses a demand forecasting algorithm to predict the demand at tourist destinations and set the optimal price. For example, it uses a demand forecasting algorithm to predict fluctuations in demand during specific periods or events and adjusts prices accordingly. The pricing unit can also dynamically set prices based on the supply situation at tourist destinations. For example, it sets prices considering the capacity of tourist destinations and the services provided. This allows the pricing unit to flexibly adjust prices according to the congestion and demand at tourist destinations, optimizing the use of tourist destinations. Furthermore, the pricing unit can analyze the history of pricing and evaluate the effectiveness of pricing. For example, it can compare past pricing with the results to analyze the effectiveness of pricing. This allows the settings unit to improve the accuracy of pricing and provide data to optimize the use of tourist destinations. As a result, the settings unit can predict congestion levels at tourist destinations, propose optimal itineraries, and dynamically set prices, thereby solving the problem of overtourism.

[0067] The generation unit generates virtual tours. For example, the generation unit uses AI to generate images and videos of tourist destinations and provide virtual tours to travelers. The generation unit can also use AI to generate 3D models of tourist destinations and provide virtual tours to travelers. For example, the generation unit generates 3D models based on image data of tourist destinations. Furthermore, the generation unit can generate virtual tours based on video data of tourist destinations. In addition, the generation unit can generate virtual tours based on real-time data of tourist destinations. This allows for the provision of new experiences to travelers through virtual tours.

[0068] The guidance unit analyzes tourist movements and aims to guide them to local small businesses. For example, the guidance unit can use AI to analyze tourist movements and guide them to local small businesses. The guidance unit can use AI to analyze tourist movement patterns and guide them to local small businesses. For example, the guidance unit can guide tourists to local small businesses based on their movement data. Furthermore, the guidance unit can guide tourists to local small businesses based on their length of stay. In addition, the guidance unit can guide tourists to local small businesses based on their spending behavior. This helps to support the revitalization of the local economy by guiding tourists to local small businesses.

[0069] The prediction unit can predict the congestion level of tourist destinations by analyzing historical data, weather information, and event information. For example, the prediction unit can predict the congestion level of tourist destinations based on past visitor data. The prediction unit can use AI to analyze past visitor data and predict the congestion level of tourist destinations. For example, the prediction unit can predict the congestion level of tourist destinations based on past visitor data. The prediction unit can also predict the congestion level of tourist destinations based on weather information. Furthermore, the prediction unit can also predict the congestion level of tourist destinations based on event information. As a result, the accuracy of congestion predictions is improved by analyzing historical data, weather information, and event information.

[0070] The suggestion function can analyze travelers' preferences and past travel history to propose the optimal itinerary. For example, the suggestion function can analyze travelers' preferences and propose the optimal itinerary. The suggestion function can use AI to analyze travelers' preferences and propose the optimal itinerary. For example, the suggestion function can propose the optimal itinerary based on travelers' past travel history. Furthermore, the suggestion function can propose the optimal itinerary based on travelers' preferences. In addition, the suggestion function can propose the optimal itinerary based on travelers' current circumstances. This allows for the proposal of individually optimized itineraries by analyzing travelers' preferences and past travel history.

[0071] The pricing unit can dynamically set prices based on the congestion and demand at tourist destinations. For example, the pricing unit can dynamically set prices based on the congestion at tourist destinations. The pricing unit can use AI to analyze the congestion at tourist destinations and dynamically set prices. For example, the pricing unit can dynamically set prices based on the congestion at tourist destinations. The pricing unit can also dynamically set prices based on the demand at tourist destinations. Furthermore, the pricing unit can also dynamically set prices based on the supply situation at tourist destinations. This allows for a balance between supply and demand by setting prices based on the congestion and demand at tourist destinations.

[0072] The prediction unit can estimate tourists' emotions and adjust the accuracy of congestion predictions based on those emotions. For example, if tourists are feeling stressed, the prediction unit can increase the accuracy of congestion predictions and suggest routes that avoid crowds. The prediction unit can use AI to estimate tourists' emotions and adjust the accuracy of congestion predictions. For example, if tourists are relaxed, the prediction unit can loosen the accuracy of congestion predictions and suggest routes that allow them to enjoy the attractions of the tourist destination to the fullest. Also, if tourists are in a hurry, the prediction unit can increase the accuracy of congestion predictions and suggest the shortest route. In this way, adjusting the accuracy of congestion predictions based on tourists' emotions makes it possible to make more appropriate congestion predictions. 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.

[0073] The prediction unit can analyze real-time social media posts and predict congestion levels. For example, the prediction unit can analyze real-time tweets and predict congestion levels at tourist destinations. The prediction unit uses AI to analyze real-time social media posts and predict congestion levels. For example, the prediction unit can analyze Instagram posts to grasp the popularity of tourist destinations in real time. The prediction unit can also analyze SNS information and predict congestion levels at tourist destinations. This allows for the latest congestion information to be grasped by analyzing real-time social media posts.

[0074] The prediction unit can improve prediction accuracy by considering the traffic conditions around tourist destinations. For example, the prediction unit can analyze surrounding traffic congestion information and predict the congestion level of tourist destinations. The prediction unit can use AI to analyze surrounding traffic congestion information and predict the congestion level of tourist destinations. For example, the prediction unit can predict the congestion level of tourist destinations by considering the operating status of public transportation. The prediction unit can also analyze the availability of parking spaces in the surrounding area and predict the congestion level of tourist destinations. In this way, the accuracy of congestion prediction is improved by considering the surrounding traffic conditions.

[0075] The prediction unit can estimate tourists' emotions and adjust the order in which congestion prediction results are displayed based on the estimated emotions. For example, if a tourist is feeling stressed, the prediction unit will prioritize displaying less crowded tourist destinations. The prediction unit can use AI to estimate tourists' emotions and adjust the order in which congestion prediction results are displayed. For example, if a tourist is relaxed, the prediction unit will prioritize displaying places where they can enjoy the attractions to the fullest. Also, if a tourist is in a hurry, the prediction unit can prioritize displaying the shortest route. This allows for the provision of more appropriate information by adjusting the display order based on the tourist's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0076] The prediction unit can make predictions while considering the geographical characteristics of tourist destinations. For example, the prediction unit can predict congestion by considering the topography of the tourist destination. The prediction unit can use AI to make predictions while considering the geographical characteristics of tourist destinations. For example, the prediction unit can predict congestion by considering the access methods to the tourist destination. In addition, the prediction unit can also predict congestion by considering the size of the tourist destination. This makes it possible to make more accurate congestion predictions by considering the geographical characteristics of tourist destinations.

[0077] The prediction unit can improve its prediction accuracy by referring to the past event history of tourist destinations. For example, the prediction unit can improve its prediction accuracy by referring to the congestion levels during past events. The prediction unit can use AI to improve its prediction accuracy by referring to the past event history of tourist destinations. For example, the prediction unit makes congestion predictions by considering the types of past events. The prediction unit can also make congestion predictions by referring to the number of participants in past events. In this way, the accuracy of congestion predictions is improved by referring to past event history.

[0078] The suggestion unit can estimate the tourist's emotions and adjust the itinerary suggestion method based on the estimated emotions. For example, if the tourist is relaxed, the suggestion unit will suggest an itinerary that proceeds at a leisurely pace. The suggestion unit can use AI to estimate the tourist's emotions and adjust the itinerary suggestion method. For example, if the tourist is in a hurry, the suggestion unit will suggest an itinerary that emphasizes the shortest route. Also, if the tourist is excited, the suggestion unit can suggest an itinerary with visually stimulating effects. By adjusting the itinerary suggestion method based on the tourist's emotions, more appropriate itinerary suggestions become possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0079] The suggestion function can analyze a traveler's past travel history as well as their current health condition to propose the optimal itinerary. For example, the suggestion function can propose the optimal itinerary based on places the traveler has visited in the past. The suggestion function can use AI to analyze a traveler's past travel history and current health condition to propose the optimal itinerary. For example, the suggestion function can propose a manageable itinerary considering the traveler's current health condition. Furthermore, the suggestion function can comprehensively analyze a traveler's past travel history and health condition to propose the optimal itinerary. This allows for the proposal of a manageable itinerary that takes the traveler's health condition into consideration.

[0080] The suggestion function can apply different suggestion algorithms based on the traveler's interests. For example, if the traveler is interested in history, the suggestion function will suggest an itinerary that includes historical tourist attractions. The suggestion function can use AI to apply different suggestion algorithms based on the traveler's interests. For example, if the traveler is interested in nature, the suggestion function will suggest an itinerary that allows them to enjoy natural scenery. Also, if the traveler is interested in food, the suggestion function can suggest an itinerary that allows them to enjoy delicious local cuisine. In this way, by applying suggestion algorithms based on the traveler's interests, more personalized itinerary suggestions become possible.

[0081] The suggestion system can estimate the emotions of tourists and prioritize itineraries based on those emotions. For example, if a tourist is feeling stressed, the suggestion system will prioritize suggesting relaxing tourist destinations. The suggestion system can use AI to estimate the emotions of tourists and prioritize itineraries. For example, if a tourist is relaxed, the suggestion system will prioritize suggesting places where they can enjoy the attractions to the fullest. The suggestion system can also prioritize suggesting the shortest route if a tourist is in a hurry. This allows for more appropriate itinerary suggestions by prioritizing itineraries based on the emotions of tourists. 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.

[0082] The suggestion function can propose the optimal itinerary by considering the traveler's geographical location. For example, it can suggest the best tourist destinations based on the traveler's current location. The suggestion function can use AI to propose the optimal itinerary by considering the traveler's geographical location. For example, it can propose the optimal itinerary by considering the traveler's mode of transportation. It can also propose an efficient itinerary by considering the traveler's length of stay. In this way, considering the traveler's geographical location makes it possible to propose a more efficient itinerary.

[0083] The suggestion function can analyze travelers' social media activity and propose relevant itineraries. For example, it can analyze travelers' tweets and suggest tourist destinations of interest. The suggestion function can use AI to analyze travelers' social media activity and propose relevant itineraries. For example, it can analyze travelers' Instagram posts and suggest relevant tourist destinations. Furthermore, the suggestion function can analyze travelers' social media information and propose the optimal itinerary. This allows for more relevant itinerary suggestions by analyzing travelers' social media activity.

[0084] The pricing unit can estimate the emotions of tourists and adjust the pricing method based on the estimated emotions. For example, if a tourist is relaxed, the pricing unit will set a normal price. The pricing unit can use AI to estimate the emotions of tourists and adjust the pricing method. For example, if a tourist is stressed, the pricing unit will set a discounted price. The pricing unit can also set a premium price if a tourist is in a hurry. This allows for more appropriate pricing by adjusting the pricing method based on the emotions of tourists. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The setting unit can set the optimal price by referring to past price fluctuation data for tourist destinations. For example, the setting unit can set the optimal price based on past price fluctuation data. The setting unit can also use AI to analyze past price fluctuation data for tourist destinations and set the optimal price. For example, the setting unit can set the price by considering past demand data. In addition, the setting unit can set the price by referring to past price data of competitors. This makes it possible to set more appropriate prices by referring to past price fluctuation data.

[0086] The pricing unit can set prices considering seasonal demand fluctuations in tourist destinations. For example, the pricing unit can set prices based on seasonal demand data. The pricing unit can also use AI to analyze seasonal demand fluctuations in tourist destinations and set prices accordingly. For example, the pricing unit can set prices considering the trends of tourists in each season. Furthermore, the pricing unit can also set prices by referring to the pricing data of competitors in each season. This allows for more appropriate pricing by considering seasonal demand fluctuations.

[0087] The pricing unit can estimate the emotions of tourists and determine pricing priorities based on those estimated emotions. For example, if a tourist is relaxed, the pricing unit will prioritize normal pricing. The pricing unit can use AI to estimate the emotions of tourists and determine pricing priorities. For example, if a tourist is stressed, the pricing unit will prioritize discounted prices. The pricing unit can also prioritize premium prices if a tourist is in a hurry. This allows for more appropriate pricing by determining pricing priorities based on the emotions of tourists. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0088] The pricing unit can set prices considering the geographical characteristics of tourist destinations. For example, the pricing unit can set prices considering the accessibility of tourist destinations. The pricing unit can use AI to set prices considering the geographical characteristics of tourist destinations. For example, the pricing unit can set prices considering the popularity of tourist destinations. The pricing unit can also set prices considering the availability of surrounding facilities for tourist destinations. This makes it possible to set more appropriate prices by considering the geographical characteristics of tourist destinations.

[0089] The pricing unit can set prices by referring to relevant market data for tourist destinations. For example, the pricing unit can set prices by referring to the pricing data of competitors. The pricing unit can also set prices by using AI to refer to relevant market data for tourist destinations. For example, the pricing unit can set prices based on relevant market demand data. The pricing unit can also set prices by considering relevant market supply data. This allows for more appropriate pricing by referring to relevant market data.

[0090] The generation unit can estimate the emotions of tourists and adjust the content of the virtual tour based on the estimated emotions. For example, if a tourist is relaxed, the generation unit will provide a virtual tour that proceeds at a leisurely pace. The generation unit can use AI to estimate the emotions of tourists and adjust the content of the virtual tour. For example, if a tourist is excited, the generation unit will provide a virtual tour with visually stimulating effects. Also, if a tourist is stressed, the generation unit can provide a virtual tour with relaxing content. In this way, by adjusting the content of the virtual tour based on the emotions of tourists, a more appropriate virtual tour can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0091] The generation unit can generate the optimal virtual tour by referencing past video data of tourist destinations during the virtual tour generation process. For example, the generation unit generates the optimal virtual tour based on past video data. The generation unit can use AI to generate the optimal tour by referencing past video data of tourist destinations. For example, the generation unit generates a virtual tour by considering past tourist evaluation data. The generation unit can also generate a virtual tour by referencing past event footage. This allows for the generation of more appropriate virtual tours by referencing past video data.

[0092] The generation unit can estimate the emotions of tourists and adjust the display method of the virtual tour based on the estimated emotions. For example, if a tourist is relaxed, the generation unit will provide a display method that proceeds at a relaxed pace. The generation unit can use AI to estimate the emotions of tourists and adjust the display method of the virtual tour. For example, if a tourist is excited, the generation unit will provide a display method that adds visually stimulating effects. The generation unit can also provide a relaxing display method if a tourist is stressed. In this way, a more appropriate virtual tour can be provided by adjusting the display method based on the emotions of tourists. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0093] The generation unit can generate virtual tours while considering the geographical characteristics of the tourist destination. For example, the generation unit can generate virtual tours while considering the topography of the tourist destination. The generation unit can use AI to generate tours while considering the geographical characteristics of the tourist destination. For example, the generation unit can generate virtual tours while considering how to access the tourist destination. The generation unit can also generate virtual tours while considering the size of the tourist destination. This allows for the generation of more appropriate virtual tours by considering the geographical characteristics of the tourist destination.

[0094] The guidance unit can estimate the emotions of tourists and adjust the guidance method based on the estimated emotions. For example, if a tourist is relaxed, the guidance unit will provide a guidance method that proceeds at a relaxed pace. The guidance unit can use AI to estimate the emotions of tourists and adjust the guidance method. For example, if a tourist is excited, the guidance unit will provide a guidance method that adds visually stimulating effects. Also, if a tourist is stressed, the guidance unit can provide a guidance method that helps them relax. This allows for more appropriate guidance by adjusting the guidance method based on the emotions of tourists. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The guidance unit can analyze tourists' past spending behavior during guidance and select the optimal guidance method. For example, the guidance unit can select the optimal guidance method based on past spending behavior. The guidance unit can use AI to analyze tourists' past spending behavior and select the optimal guidance method. For example, the guidance unit can select a guidance method by considering past spending patterns. The guidance unit can also select the optimal guidance method by referring to past spending history. In this way, by analyzing past spending behavior, a more appropriate guidance method can be selected.

[0096] The guidance unit can estimate the emotions of tourists and determine guidance priorities based on the estimated emotions. For example, if a tourist is relaxed, the guidance unit will prioritize normal guidance. The guidance unit can use AI to estimate the emotions of tourists and determine guidance priorities. For example, if a tourist is stressed, the guidance unit will prioritize relaxing guidance. The guidance unit can also prioritize quick guidance if a tourist is in a hurry. This allows for more appropriate guidance by determining guidance priorities based on the emotions of tourists. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The guidance unit can select the optimal guidance method by considering the tourist's geographical location information during guidance. For example, the guidance unit can select the optimal guidance method based on the tourist's current location. The guidance unit can also use AI to select the optimal guidance method by considering the tourist's geographical location information. For example, the guidance unit can select the optimal guidance method by considering the tourist's mode of transportation. Furthermore, the guidance unit can also select an efficient guidance method by considering the tourist's length of stay. This makes it possible to provide more appropriate guidance by considering the tourist's geographical location information.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The AI-powered tourism distribution system can also be equipped with a "feedback collection unit." This unit collects real-time feedback from travelers and uses it to improve the overall accuracy of the system. For example, the feedback collection unit provides questionnaires that allow travelers to evaluate their satisfaction with the tourist destinations they visit. It can also collect comments from travelers regarding the level of crowding and the quality of service they experience. Furthermore, the feedback collection unit can collect travelers' opinions on suggested itineraries and incorporate them into future suggestions. In this way, the accuracy and usability of the system can be improved by utilizing traveler feedback.

[0100] The AI-powered tourism distribution system can also be equipped with a "health monitoring unit." This unit monitors travelers' health status in real time and provides appropriate advice. For example, it can monitor travelers' heart rate and steps and suggest breaks to avoid excessive fatigue. It can also manage travelers' hydration and meal timing to support healthy travel. Furthermore, if a traveler has a specific health problem, the health monitoring unit can suggest tourist destinations and activities that address that problem. This allows for a safe and comfortable travel experience that takes travelers' health into consideration.

[0101] The AI-powered tourism distribution system can also include an "entertainment service." This service provides travelers with entertainment content related to the tourist destination. For example, it could offer documentary videos about the history and culture of the destination. It could also offer quizzes and games related to the destination to engage travelers. Furthermore, it could stream live performances and music by local artists in the destination. This allows travelers to deepen their knowledge of the destination while having an enjoyable time.

[0102] The AI-powered tourism distribution system can also be equipped with an "emergency response unit." This unit provides functions to quickly respond when travelers face emergencies. For example, if a traveler gets lost, the emergency response unit can locate their current location and guide them to the nearest safe place. It can also guide travelers to the nearest medical facility if they complain of feeling unwell. Furthermore, the emergency response unit can assist travelers in contacting the police if they become victims of crime. This allows travelers to enjoy their trip with peace of mind.

[0103] The AI-powered distributed tourism system can also be equipped with an "environmental monitoring unit." This unit monitors the environmental conditions of tourist destinations in real time and provides travelers with appropriate information. For example, it monitors the air quality, temperature, and humidity of tourist destinations to support travelers in having a comfortable trip. It can also monitor the state of protection of the natural environment of tourist destinations and raise awareness among travelers about the importance of environmental protection. Furthermore, it can monitor the amount of waste and water quality of tourist destinations and promote environmental protection activities. This allows travelers to enjoy environmentally conscious tourism.

[0104] The AI-powered distributed tourism system can also be equipped with an "emotion estimation unit." This unit estimates the traveler's emotions in real time and provides appropriate services based on those emotions. For example, if the traveler is feeling stressed, the emotion estimation unit can suggest relaxing tourist destinations and activities. It can also suggest visually stimulating tourist destinations and activities if the traveler is excited. Furthermore, if the traveler is tired, the emotion estimation unit can suggest rest spots and places to refresh. This allows the system to provide the optimal tourism experience based on the traveler's emotions.

[0105] The AI-powered distributed tourism system can also be equipped with an "emotional feedback unit." This unit collects feedback on the emotions experienced by travelers and uses it to improve the system. For example, the emotional feedback unit provides a questionnaire for travelers to evaluate the emotions they felt at the tourist destinations they visited. It can also collect emotional reactions to the activities travelers experienced. Furthermore, the emotional feedback unit can collect travelers' emotional opinions on the suggested itineraries and incorporate them into future suggestions. In this way, the accuracy and usability of the system can be improved by utilizing travelers' emotional feedback.

[0106] The AI-powered distributed tourism system can also be equipped with an "emotional analysis unit." This unit analyzes travelers' emotional data and evaluates tourist destinations and activities. For example, it analyzes the emotional data travelers felt at tourist destinations they visited and evaluates the appeal of those destinations. It can also analyze emotional data travelers experienced in activities and evaluate the popularity of those activities. Furthermore, based on travelers' emotional data, the emotional analysis unit can suggest areas for improvement in tourist destinations and activities. In this way, it becomes possible to evaluate and improve tourist destinations and activities by utilizing travelers' emotional data.

[0107] The AI-powered distributed tourism system can also be equipped with an "emotion prediction unit." This unit predicts future emotions based on the traveler's past emotional data and provides appropriate services. For example, it can predict emotions at a next tourist destination based on emotional data from previous tourist destinations the traveler has visited. It can also predict emotions during a future activity based on emotional data from past activities the traveler has experienced. Furthermore, it can propose an itinerary based on the traveler's past emotional data and future emotions. In this way, by utilizing the traveler's past emotional data, it is possible to predict future emotions and provide optimal services.

[0108] The AI-powered distributed tourism system can also be equipped with an "emotion adjustment unit." This unit adjusts the traveler's emotions in real time to provide a comfortable travel experience. For example, if the traveler is feeling stressed, the unit can provide relaxing music or videos. It can also suggest relaxing activities if the traveler is feeling excited. Furthermore, if the traveler is feeling tired, the unit can suggest resting spots where they can refresh themselves. In this way, by adjusting the traveler's emotions in real time, a comfortable travel experience can be provided.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The prediction unit predicts the congestion level of tourist destinations. The prediction unit analyzes past data, weather information, and event information to predict the congestion level of tourist destinations. Using AI, it is possible to analyze past data and predict the congestion level of tourist destinations. For example, predictions can be made based on past visitor data, weather information, and event information. Step 2: The suggestion unit proposes the optimal itinerary for travelers based on the congestion predicted by the prediction unit. The suggestion unit analyzes the traveler's preferences and past travel history to propose the optimal itinerary. Using AI, it is possible to analyze the traveler's preferences and propose the optimal itinerary. For example, it can make suggestions based on the traveler's past travel history and current situation. Step 3: The setting unit dynamically sets the price based on the itinerary proposed by the suggestion unit. The setting unit dynamically sets the price based on the congestion and demand at the tourist destination. Using AI, it is possible to analyze the congestion at the tourist destination and dynamically set the price. For example, the price can be set based on the congestion, demand, and supply situation at the tourist destination.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements described above, including the prediction unit, proposal unit, setting unit, generation unit, and guidance unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the prediction unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The proposal unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The setting unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The guidance unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] Each of the multiple elements described above, including the prediction unit, proposal unit, setting unit, generation unit, and guidance unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the prediction unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The proposal unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The setting unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The guidance unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] 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.

[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 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.

[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 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.

[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 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.

[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 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.

[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 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.

[0146] Each of the multiple elements described above, including the prediction unit, proposal unit, setting unit, generation unit, and guidance unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the prediction unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The proposal unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The setting unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The guidance unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] 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.

[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 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.

[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 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).

[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] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] Each of the multiple elements described above, including the prediction unit, proposal unit, setting unit, generation unit, and guidance unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the prediction unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The setting unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The guidance unit is implemented by the control unit 46A of the robot 414 or 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 examples described above, and various modifications are possible.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] (Note 1) A prediction unit that predicts the congestion level of tourist destinations, Based on the congestion situation predicted by the prediction unit, the proposal unit suggests the optimal itinerary for travelers. The system includes a setting unit that dynamically sets the price based on the itinerary proposed by the proposal unit. A system characterized by the following features. (Note 2) It includes a generation unit that generates virtual tours. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a guidance unit that analyzes tourist trends and directs them to local small businesses. The system described in Appendix 1, characterized by the features described herein. (Note 4) The prediction unit, By analyzing past data, weather information, and event information, we predict congestion levels at tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, We analyze travelers' preferences and past travel history to suggest the optimal itinerary. The system described in Appendix 1, characterized by the features described herein. (Note 6) The setting unit is, Prices are dynamically set based on the level of congestion and demand at tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 7) The prediction unit, The system estimates the sentiments of tourists and adjusts the accuracy of congestion predictions based on these estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 8) The prediction unit, Analyze real-time social media posts to predict congestion levels. The system described in Appendix 1, characterized by the features described herein. (Note 9) The prediction unit, Improve prediction accuracy by considering traffic conditions around tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 10) The prediction unit, The system estimates the sentiment of tourists and adjusts the order in which it displays congestion prediction results based on the estimated sentiment of tourists. The system described in Appendix 1, characterized by the features described herein. (Note 11) The prediction unit, Predictions are made considering the geographical characteristics of tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 12) The prediction unit, Improve prediction accuracy by referencing past event history of tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned proposal section is, We estimate the sentiments of tourists and adjust the itinerary suggestions based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned proposal section is, In addition to the traveler's past travel history, we analyze their current health condition to suggest the optimal itinerary. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned proposal section is, Apply different suggestion algorithms based on the traveler's interests. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, The system estimates the sentiments of tourists and prioritizes the itinerary based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, We propose the optimal itinerary, taking into account the traveler's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, Analyze travelers' social media activity and suggest relevant itineraries. The system described in Appendix 1, characterized by the features described herein. (Note 19) The setting unit is, We estimate the sentiments of tourists and adjust pricing methods based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 20) The setting unit is, The optimal price is set by referring to historical price fluctuation data for tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 21) The setting unit is, Prices are set taking into account seasonal fluctuations in demand for tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 22) The setting unit is, Estimate the sentiments of tourists and determine pricing priorities based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 23) The setting unit is, Prices are set considering the geographical characteristics of the tourist destination. The system described in Appendix 1, characterized by the features described herein. (Note 24) The setting unit is, Pricing is set by referring to relevant market data for tourist destinations. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is The system estimates the emotions of tourists and adjusts the content of the virtual tour based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The generating unit is When generating virtual tours, the system references historical video data of tourist destinations to create the optimal tour. The system described in Appendix 2, characterized by the features described herein. (Note 27) The generating unit is It estimates the emotions of tourists and adjusts how the virtual tour is displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The generating unit is When generating virtual tours, the geographical characteristics of tourist destinations are taken into consideration. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned induction unit is The system estimates the emotions of tourists and adjusts the guidance methods based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 30) The aforementioned induction unit is During the guidance process, the optimal guidance method is selected by analyzing the past spending behavior of tourists. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned induction unit is The system estimates the emotions of tourists and determines guidance priorities based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned induction unit is When guiding tourists, the optimal guidance method is selected considering their geographical location. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A prediction unit that predicts the congestion level of tourist destinations, Based on the congestion situation predicted by the prediction unit, the proposal unit suggests the optimal itinerary for travelers. The system includes a setting unit that dynamically sets the price based on the itinerary proposed by the proposal unit. A system characterized by the following features.

2. It includes a generation unit that generates virtual tours. The system according to feature 1.

3. It includes a guidance unit that analyzes tourist trends and directs them to local small businesses. The system according to feature 1.

4. The prediction unit, By analyzing past data, weather information, and event information, we predict congestion levels at tourist destinations. The system according to feature 1.

5. The aforementioned proposal section is, We analyze travelers' preferences and past travel history to suggest the optimal itinerary. The system according to feature 1.

6. The setting unit is, Prices are dynamically set based on the level of congestion and demand at tourist destinations. The system according to feature 1.

7. The prediction unit, The system estimates the sentiments of tourists and adjusts the accuracy of congestion predictions based on these estimated sentiments. The system according to feature 1.

8. The prediction unit, Analyze real-time social media posts to predict congestion levels. The system according to feature 1.

9. The prediction unit, Improve prediction accuracy by considering traffic conditions around tourist destinations. The system according to feature 1.

10. The prediction unit, The system estimates the sentiment of tourists and adjusts the order in which it displays congestion prediction results based on the estimated sentiment of tourists. The system according to feature 1.

Images