system

Abstract

The system according to this embodiment aims to effectively plan and develop travel plans in a way that is tailored to the user's needs. [Solution] The system according to the embodiment comprises a hearing unit, a selection unit, a provision unit, and a re-formulation unit. The hearing unit hears information from the user. The selection unit selects a plan based on the information heard by the hearing unit. The provision unit provides the plan selected by the selection unit. The re-formulation unit re-formulates the plan based on the plan provided by the provision unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, information collection is complicated when making a travel plan, and there is a risk of plan fatigue and dissatisfaction due to insufficient information.

[0005] The system according to the embodiment aims to effectively plan and formulate a travel plan in a user-friendly manner.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a hearing unit, a selection unit, a provision unit, and a re-formulation unit. The hearing unit hears information from the user. The selection unit selects a plan based on the information heard by the hearing unit. The provision unit provides the plan selected by the selection unit. The re-formulation unit re-formulates the plan based on the plan provided by the provision unit. [Effects of the Invention]

[0007] The system according to this embodiment can effectively plan and develop travel plans in a way that is tailored to the user. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The travel planning support system according to an embodiment of the present invention is a system that utilizes an AI personal agent to reduce the effort required for information gathering and planning when planning a trip. When a user plans a trip, the travel planning support system has the AI ​​agent periodically ask questions to gather information such as budget, desired destinations, and current mood. Next, the AI ​​agent selects a personalized plan for the traveler based on the information gathered. This plan includes accommodations that fit the budget in the desired region, methods of transportation (including variations such as choosing an express train instead of a bullet train), and places to stop along the way. The AI ​​agent also supports English and other languages, and can guide users to local festivals and scenic spots in Japan, thereby increasing the average travel value for Japan as a tourism-oriented country. For example, when a user plans a trip, the AI ​​agent periodically asks questions. At this time, the user answers with information such as budget, desired destinations, and current mood. For example, the user might input information such as, "My budget is under 50,000 yen, and I want to go to a hot spring resort," or "I want to relax." This information is input into the AI ​​agent. Next, the AI ​​agent analyzes the input information and selects a personalized plan for the traveler. The AI ​​agent suggests accommodations, transportation options, and places to visit along the way that fit the user's budget. For example, based on information such as "I want to go to a hot spring resort with a budget of 50,000 yen or less," it will suggest hot spring inns that fit the budget, transportation options using express trains, and sightseeing spots to visit along the way. Furthermore, the AI ​​agent supports English and other languages, and can guide users to local festivals and scenic spots within Japan. This allows the agent to cater to foreign tourists and increase the average spending per visit as Japan becomes a tourism-oriented country. For example, it can provide foreign tourists with information on domestic festivals and scenic spots in English and propose travel plans. This reduces the effort required for information gathering and planning when planning a trip. In addition, because the AI ​​agent proposes personalized plans, travelers can enjoy a trip that suits their preferences and budget. Moreover, the AI ​​agent can revise its plans as many times as needed, so by using it repeatedly, users can receive suggestions for plans that match their preferences and offer unexpected ideas.This allows the travel planning support system to efficiently assist users with their travel planning and provide personalized travel plans.

[0029] The travel planning support system according to this embodiment comprises a hearing unit, a selection unit, a provision unit, and a revision unit. The hearing unit hears information from the user. For example, when the user is planning a trip, the hearing unit asks questions about their budget, places they want to go, their current mood, etc. For example, the hearing unit can ask questions such as, "What is your budget?", "Where do you want to go?", and "How are you feeling right now?". The hearing unit records the user's answers and sends them to the selection unit. The selection unit selects a plan based on the information gathered by the hearing unit. For example, the selection unit suggests accommodations, transportation methods, and places to visit along the way that fit the user's budget. For example, based on information such as, "I want to go to a hot spring resort with a budget of 50,000 yen or less," the selection unit can suggest hot spring inns that can be stayed at within the budget, transportation methods using express trains, and sightseeing spots to visit along the way. The selection unit may include AI processing and can use AI to analyze the user's information and select the optimal plan. The provision unit provides the plan selected by the selection unit. The provisioning unit, for example, presents a selected plan to the user and provides detailed information. For example, the provisioning unit can provide the user with information on the selected inn, how to access it, and sightseeing spots to visit along the way. The provisioning unit may include AI processing and can use AI to provide the user with the most suitable information. The re-planning unit re-plans based on the plan provided by the provisioning unit. For example, the re-planning unit re-plans if the user is not satisfied with the plan provided. For example, the re-planning unit can receive user feedback and re-select a plan. The re-planning unit may include AI processing and can use AI to analyze user feedback and re-plan the most suitable option. As a result, the travel planning support system according to this embodiment can provide personalized travel plans by interviewing users, selecting, providing, and re-planning them.

[0030] The interviewing department gathers information from users. For example, when a user is planning a trip, the interviewing department asks questions about their budget, places they want to visit, and their current mood. Specifically, when a user is planning a trip, the interviewing department asks questions about their budget, places they want to visit, and their current mood. For example, it can ask questions such as, "What is your budget?", "Where do you want to go?", and "How are you feeling right now?". These questions are important for accurately understanding the user's needs and desires. The interviewing department records the user's responses and sends them to the selection department. The user's responses are recorded in text format and stored in a database. The interviewing department can utilize speech recognition and natural language processing technologies to record user responses quickly and accurately. For example, if a user responds by voice, speech recognition technology is used to convert it to text and store it in the database. In addition, natural language processing technology can be used to analyze the user's responses and extract important information. This allows the interviewing department to accurately understand the user's needs and desires and send them to the selection department. Furthermore, the interviewing department can ask additional questions based on the user's responses. For example, if a user answers "I want to go to a hot spring resort," the interviewing department can ask additional questions such as "Which region's hot spring resort would you like to visit?" This allows the interviewing department to gain a more detailed understanding of the user's needs and preferences and then transmit that information to the selection department.

[0031] The selection department selects a plan based on information gathered by the interview department. For example, the selection department suggests accommodations, transportation methods, and places to visit along the way that fit the user's budget. Specifically, the selection department selects the optimal travel plan based on information such as the user's budget, desired destinations, and current mood. For example, based on information such as "I want to go to a hot spring resort with a budget of 50,000 yen or less," it can suggest hot spring inns that fit within the budget, transportation methods using express trains, and sightseeing spots to visit along the way. The selection department can incorporate AI processing, using AI to analyze user information and select the optimal plan. The AI ​​selects the plan best suited to the user's needs and desires based on past data and statistical information. For example, the AI ​​can refer to plans selected under similar conditions in the past to select the plan best suited to the user's needs and desires. Furthermore, the AI ​​can analyze user responses and extract important information. This allows the selection department to quickly and accurately select the plan best suited to the user's needs and desires. In addition, the selection department can propose multiple plans according to the user's needs and desires. For example, it can suggest multiple hot spring inns that fit within the budget, multiple access options, and multiple tourist spots. This allows the selection department to respond flexibly to the user's needs and preferences.

[0032] The service provider provides the plans selected by the selection provider. For example, the service provider presents the selected plans to the user and provides detailed information. Specifically, the service provider can provide the user with information about the selected inn, how to access it, and information about sightseeing spots to visit along the way. For example, the service provider can provide detailed information such as the address, contact information, price, facilities, and services of the selected inn. Regarding access, it provides information such as how to access it from the nearest station or bus stop, the travel time, and the price. Furthermore, regarding sightseeing spots to visit along the way, it provides information such as the name of the sightseeing spot, address, opening hours, price, and highlights. The service provider can include AI processing and use AI to provide the user with the most suitable information. The AI ​​selects and provides the most suitable information according to the user's needs and preferences. For example, the AI ​​selects and provides the most suitable information based on information such as the user's budget, desired destinations, and current mood. The AI ​​can also analyze the user's responses and extract important information. This allows the service provider to quickly and accurately provide information that is best suited to the user's needs and preferences. Furthermore, the service provider can provide multiple pieces of information according to the user's needs and preferences. For example, it can provide information on multiple inns, access methods, and tourist attractions. This allows the service provider to respond flexibly to the user's needs and preferences.

[0033] The Redesign Department redesigns plans based on those provided by the Service Provider. For example, if a user is dissatisfied with the provided plan, the Redesign Department will redesign it. Specifically, the Redesign Department can receive user feedback and re-select a plan. For instance, if a user provides feedback such as "I can't find a hot spring inn that fits my budget," the Redesign Department will suggest other hot spring inns that fit the budget. Similarly, if a user provides feedback such as "Access is inconvenient," the Redesign Department will suggest alternative access methods. The Redesign Department can incorporate AI processing, using AI to analyze user feedback and redesign the optimal plan. AI can analyze user feedback and extract important information. This allows the Redesign Department to quickly and accurately redesign a plan that best suits the user's needs and preferences. Furthermore, the Redesign Department can propose multiple plans based on the user's needs and preferences. For example, it can propose plans for multiple hot spring inns, access methods, and tourist spots. This allows the Redesign Department to respond flexibly to user needs and preferences. The Redesign Department can continuously improve plans based on user feedback. For example, based on user feedback, the plan's content and presentation methods can be reviewed and improved. This allows the planning department to increase user satisfaction.

[0034] The selection unit includes a hotel recommendation unit that proposes hotels that fit the budget. For example, the selection unit proposes hotels that can be booked within the user's budget based on the user's budget. For example, based on information such as "I want to go to a hot spring resort with a budget of 50,000 yen or less," the selection unit can propose hot spring hotels that can be booked within that budget. The selection unit can include AI processing and use AI to analyze the user's budget information and propose the most suitable hotels. For example, the selection unit can take the user's budget information as input and have the AI ​​generate a list of hotels that can be booked within that budget. This allows the system to propose hotels that fit the budget and provide the user with a travel plan that suits their budget.

[0035] The selection unit includes an access suggestion unit that proposes access methods. The selection unit proposes the optimal access method based, for example, on the user's mode of transportation. For example, based on information such as "I want to use a limited express train instead of a bullet train," the selection unit can propose an access method using a limited express train. The selection unit can include AI processing and use AI to analyze the user's mode of transportation information and propose the optimal access method. For example, the selection unit can take the user's mode of transportation information as input and have a generation AI generate the optimal access method. This allows the system to provide travel plans that match the user's mode of transportation by proposing access methods.

[0036] The selection unit includes a detour suggestion unit that proposes places to stop along the way. For example, the selection unit suggests places to stop along the way based on the user's interests. For example, based on information such as "I want to stop by a tourist spot on the way to a hot spring resort," the selection unit can suggest tourist spots to stop at along the way. The selection unit can include AI processing and use AI to analyze the user's interest information and suggest the most suitable detour locations. For example, the selection unit can take the user's interest information as input and have the generation AI generate the most suitable detour locations. This allows the system to provide a travel plan that matches the user's interests by suggesting places to stop along the way.

[0037] The service provider includes a sightseeing guide unit that provides information on festivals and scenic spots in rural areas of Japan. For example, the service provider can provide users with information on festivals and scenic spots in rural areas of Japan. For example, based on information such as "I want to see a festival on the way to a hot spring resort," the service provider can provide information on festivals to visit along the way. The service provider can include AI processing and use AI to analyze the user's interest information and guide them to the most suitable sightseeing spots. For example, the service provider can take the user's interest information as input and have the AI ​​generate the most suitable sightseeing spots. This allows the service provider to effectively guide users to tourist attractions by providing information on sightseeing spots.

[0038] The service provider includes a foreigner support unit that provides information to foreign tourists in English. For example, the service provider can provide information about domestic festivals and scenery to foreign tourists in English. For example, based on the information "provide information about hot spring resorts to foreign tourists in English," the service provider can provide information about hot spring resorts in English. The service provider can include AI processing and use AI to analyze information about foreign tourists and provide the most suitable information. For example, the service provider can take information about foreign tourists as input and have the AI ​​generate the most suitable information. This allows the service provider to cater to foreign tourists by providing information in English.

[0039] The interview function analyzes the user's past travel history and selects the most appropriate questions. For example, the interview function asks relevant questions based on places the user has visited in the past. For instance, it might ask, "What hot spring resorts have you visited in the past?" The interview function also analyzes the user's preferences from their past travel history and asks questions based on those preferences. For example, it might ask, "What was your favorite place you've visited in the past?" The interview function also asks relevant questions based on the modes of transportation and accommodations the user has used in the past. For example, it might ask, "What modes of transportation have you used in the past?" or "What accommodations have you stayed at in the past?" The interview function can also incorporate AI processing, using AI to analyze the user's past travel history and select the most appropriate questions. For example, the interview function can use the user's past travel history as input to generate the most appropriate questions using AI. This allows for the selection of optimal questions by analyzing the user's past travel history.

[0040] The interview function customizes questions based on the user's current living situation and areas of interest. For example, the interview function can ask questions related to topics the user has recently been interested in. For instance, it might ask, "What topics have you been interested in lately?" The interview function also asks appropriate questions based on the user's current living situation (e.g., workload, family structure). For example, it might ask, "How busy is your current job?" or "What is your family structure like?" The interview function also asks relevant questions based on the user's hobbies and areas of interest. For example, it might ask, "What are your hobbies?" or "What topics are you interested in?" The interview function can include AI processing, using AI to analyze the user's current living situation and areas of interest and customize the most appropriate questions. For example, the interview function can take the user's current living situation and areas of interest as input and have the AI ​​generate the most appropriate questions. This allows for more appropriate questions to be asked by customizing them based on the user's current living situation and areas of interest.

[0041] The interview function prioritizes questions that are highly relevant, taking into account the user's geographical location. For example, it prioritizes questions about tourist attractions near the user's current location, such as, "What are some tourist attractions near my current location?" It also prioritizes questions about regions the user plans to visit, such as, "What information do you have about the region you plan to visit?" Furthermore, it prioritizes questions about places easily accessible from the user's current location, such as, "What places are easily accessible from my current location?" The interview function can incorporate AI processing, using AI to analyze the user's geographical location and select the most appropriate questions. For example, the interview function can use the user's geographical location as input to generate optimal questions using AI. This allows the system to prioritize questions that are highly relevant, taking into account the user's geographical location.

[0042] The interviewing unit analyzes the user's social media activity and asks relevant questions. For example, the interviewing unit might ask questions about travel destinations the user has shared on social media. For example, it might ask, "Where did you travel to that destination that you shared on social media?" The interviewing unit also asks questions about events the user has shown interest in on social media. For example, it might ask, "What events have you shown interest in on social media?" The interviewing unit also analyzes the content of the user's social media posts and asks relevant questions. For example, it can ask relevant questions based on the content of the user's social media posts. The interviewing unit can include AI processing and use AI to analyze the user's social media activity and select the most appropriate questions. For example, the interviewing unit can use the user's social media activity as input and have the AI ​​generate the most appropriate questions. This makes it possible to ask relevant questions by analyzing the user's social media activity.

[0043] The selection unit optimizes the selection algorithm by referring to past selection results. For example, the selection unit prioritizes selecting plans that match the user's preferences based on past selection results. For instance, the selection unit can optimize a selection algorithm that prioritizes selecting plans preferred by the user from among those previously selected. The selection unit also analyzes past selection results and improves the selection algorithm. For example, the selection unit can optimize a selection algorithm that adjusts the parameters of the selection algorithm based on past selection results. Furthermore, the selection unit predicts user preferences based on past selection results and selects plans. For example, the selection unit can optimize a selection algorithm that predicts user preferences based on past selection results and selects plans. The selection unit can include AI processing and use AI to analyze past selection results and optimize the selection algorithm. For example, the selection unit can take past selection results as input and have a generation AI generate an optimal selection algorithm. This allows the selection algorithm to be optimized by referring to past selection results.

[0044] The selection unit customizes plans based on the user's current lifestyle and areas of interest. For example, the selection unit can customize plans according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize a plan that allows for relaxation based on the user's current work workload. The selection unit also customizes plans based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize a plan that includes relevant tourist destinations based on the user's hobbies. Furthermore, the selection unit customizes plans according to the user's current health and physical condition. For example, it can customize a plan that is manageable based on the user's current health. The selection unit can include AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal plan. For example, the selection unit can take the user's current lifestyle and areas of interest as input and have the AI ​​generate the optimal plan. This allows for the provision of more appropriate plans by customizing plans based on the user's current lifestyle and areas of interest.

[0045] The selection unit prioritizes selecting highly relevant plans, taking into account the user's geographical location. For example, the selection unit might prioritize plans that include tourist destinations near the user's current location. For instance, it could select plans that prioritize including tourist destinations near the user's current location. The selection unit might also prioritize plans related to areas the user plans to visit. For example, it could select plans that prioritize areas the user plans to visit. Furthermore, the selection unit might prioritize plans that include locations easily accessible from the user's current location. For instance, it could select plans that prioritize including locations easily accessible from the user's current location. The selection unit can incorporate AI processing, using AI to analyze the user's geographical location and select the optimal plan. For example, the selection unit could take the user's geographical location as input and have an AI generate the optimal plan. This allows for the selection of highly relevant plans, taking into account the user's geographical location.

[0046] The selection unit analyzes the user's social media activity and selects relevant plans. For example, the selection unit can select plans related to travel destinations shared by the user on social media. For instance, the selection unit can select a plan such as "Select travel destinations shared on social media." The selection unit can also select plans related to events the user has shown interest in on social media. For example, the selection unit can select a plan such as "Select plans related to events the user has shown interest in on social media." Furthermore, the selection unit analyzes the content of the user's social media posts and selects relevant plans. For example, the selection unit can select a plan such as "Select relevant plans based on the content of social media posts." The selection unit can include AI processing, using AI to analyze the user's social media activity and select the optimal plan. For example, the selection unit can take the user's social media activity as input and have the AI ​​generate the optimal plan. This allows the system to provide relevant plans by analyzing the user's social media activity.

[0047] The service delivery unit optimizes its delivery algorithm by referring to past delivery results. For example, the service delivery unit prioritizes selecting delivery methods that match user preferences based on past delivery results. For instance, the service delivery unit can optimize its delivery algorithm to "prioritize selecting delivery methods preferred by users from among plans previously delivered." The service delivery unit also analyzes past delivery results and improves its delivery algorithm. For example, the service delivery unit can optimize its delivery algorithm by "adjusting the parameters of the delivery algorithm based on past delivery results." Furthermore, the service delivery unit predicts user preferences based on past delivery results and provides plans accordingly. For example, the service delivery unit can optimize its delivery algorithm by "predicting user preferences based on past delivery results and providing plans accordingly." The service delivery unit can include AI processing and use AI to analyze past delivery results and optimize its delivery algorithm. For example, the service delivery unit can use past delivery results as input to generate an optimal delivery algorithm using a generation AI. This allows the service delivery algorithm to be optimized by referring to past delivery results.

[0048] The service provider customizes plans based on the user's current lifestyle and areas of interest. For example, the service provider can customize plans according to the user's current lifestyle (work workload, family structure, etc.). For instance, the service provider can customize a plan that allows for relaxation based on the user's current work workload. The service provider can also customize plans based on the user's areas of interest (hobbies, topics of interest, etc.). For example, the service provider can customize a plan that includes relevant tourist destinations based on the user's hobbies. Furthermore, the service provider can customize plans according to the user's current health and physical condition. For example, the service provider can customize a plan that is manageable based on the user's current health. The service provider can incorporate AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal plan. For example, the service provider can use the user's current lifestyle and areas of interest as input to generate an optimal plan using AI. This allows for the provision of more appropriate plans by customizing them based on the user's current lifestyle and areas of interest.

[0049] The service provider prioritizes providing highly relevant plans, taking into account the user's geographical location. For example, the service provider might prioritize plans that include tourist destinations near the user's current location. For instance, it could provide a plan that prioritizes plans that include tourist destinations near the user's current location. The service provider might also prioritize plans related to areas the user plans to visit. For example, it could provide a plan that prioritizes plans related to areas the user plans to visit. Furthermore, the service provider might prioritize plans that include locations easily accessible from the user's current location. For example, it could provide a plan that prioritizes plans that include locations easily accessible from the user's current location. The service provider can incorporate AI processing, using AI to analyze the user's geographical location and provide the optimal plan. For example, the service provider could use the user's geographical location as input to generate an optimal plan using AI. This allows the service provider to prioritize providing highly relevant plans, taking into account the user's geographical location.

[0050] The service provider analyzes users' social media activity and provides relevant plans. For example, the service provider can provide plans related to travel destinations shared by users on social media. For instance, the service provider can provide plans such as "Providing travel destinations shared on social media." The service provider can also provide plans related to events that users have shown interest in on social media. For example, the service provider can provide plans such as "Providing plans related to events that users have shown interest in on social media." Furthermore, the service provider analyzes the content of users' social media posts and provides relevant plans. For example, the service provider can provide plans such as "Providing relevant plans based on the content of social media posts." The service provider can include AI processing, using AI to analyze users' social media activity and provide optimal plans. For example, the service provider can use users' social media activity as input to generate optimal plans using AI. This allows the service provider to provide relevant plans by analyzing users' social media activity.

[0051] The redesign unit optimizes the redesign algorithm by referring to past redesign results. For example, the redesign unit prioritizes redesigning plans that match user preferences based on past redesign results. For instance, the redesign unit can optimize a redesign algorithm that prioritizes redesigning plans preferred by users from among previously redesigned plans. The redesign unit also analyzes past redesign results and improves the redesign algorithm. For example, the redesign unit can optimize a redesign algorithm that adjusts the parameters of the redesign algorithm based on past redesign results. Furthermore, the redesign unit predicts user preferences based on past redesign results and redesigns plans. For example, the redesign unit can optimize a redesign algorithm that predicts user preferences based on past redesign results and redesigns plans. The redesign unit can include AI processing and use AI to analyze past redesign results and optimize the redesign algorithm. For example, the redesign unit can take past redesign results as input and have a generation AI generate an optimal redesign algorithm. This allows the redesign algorithm to be optimized by referring to past redesign results.

[0052] The replanning unit customizes the replanning based on the user's current lifestyle and areas of interest. For example, the replanning unit can replan a plan according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can replan a plan that allows for relaxation based on the user's current work workload. The replanning unit can also replan a plan based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can replan a plan that includes relevant tourist destinations based on the user's hobbies. Furthermore, the replanning unit can replan a plan according to the user's current health and physical condition. For example, it can replan a plan that is manageable based on the user's current health. The replanning unit can include AI processing, using AI to analyze the user's current lifestyle and areas of interest and replan the optimal plan. For example, the replanning unit can use the user's current lifestyle and areas of interest as input to generate an optimal plan using AI. This allows for the creation of a more appropriate plan by customizing the revised plan based on the user's current living situation and areas of interest.

[0053] The redesign unit prioritizes highly relevant redesigns, taking into account the user's geographical location. For example, it might prioritize redesigning plans that include tourist destinations near the user's current location. For instance, it could redesign a plan that prioritizes plans that include tourist destinations near the user's current location. It could also prioritize redesigning plans related to areas the user plans to visit. For example, it could redesign a plan that prioritizes plans related to areas the user plans to visit. Furthermore, it could prioritize redesigning plans that include locations easily accessible from the user's current location. For example, it could redesign a plan that prioritizes plans that include locations easily accessible from the user's current location. The redesign unit can incorporate AI processing, using AI to analyze the user's geographical location and redesign the optimal plan. For example, it could use the user's geographical location as input to generate an optimal plan using AI. This allows the unit to prioritize highly relevant redesigns, taking into account the user's geographical location.

[0054] The replanning unit analyzes the user's social media activity and replans accordingly. For example, the replanning unit can replan travel destinations shared by the user on social media. For instance, the replanning unit can replan a plan such as "Replan travel destinations shared on social media." The replanning unit can also replan events that the user has shown interest in on social media. For example, the replanning unit can replan an event that the user has shown interest in on social media. Furthermore, the replanning unit analyzes the content of the user's social media posts and replans accordingly. For example, the replanning unit can replan a plan such as "Replan relevant plans based on the content of social media posts." The replanning unit can include AI processing, using AI to analyze the user's social media activity and replan the optimal plan. For example, the replanning unit can take the user's social media activity as input and have the AI ​​generate the optimal plan. This makes it possible to replan accordingly by analyzing the user's social media activity.

[0055] The Inn Proposal Department optimizes its proposal algorithm by referring to past proposal results. For example, the Inn Proposal Department prioritizes proposing inns that match the user's preferences based on past proposal results. For instance, the Inn Proposal Department can optimize its proposal algorithm to "prioritize proposing inns that the user liked from among those previously proposed." The Inn Proposal Department also analyzes past proposal results and improves its proposal algorithm. For example, the Inn Proposal Department can optimize its proposal algorithm by "adjusting the parameters of the proposal algorithm based on past proposal results." Furthermore, the Inn Proposal Department predicts the user's preferences based on past proposal results and proposes inns. For example, the Inn Proposal Department can optimize its proposal algorithm to "predict the user's preferences based on past proposal results and propose inns." The Inn Proposal Department can include AI processing and use AI to analyze past proposal results and optimize its proposal algorithm. For example, the Inn Proposal Department can use past proposal results as input to generate an optimal proposal algorithm using a generation AI. This allows the proposal algorithm to be optimized by referring to past proposal results.

[0056] The Inn Recommendation Department customizes inns based on the user's current lifestyle and areas of interest. For example, it can customize inns according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize an inn to "create a relaxing inn based on the user's current work workload." The Inn Recommendation Department also customizes inns based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize an inn to "provide activities related to the user's hobbies." Furthermore, the Inn Recommendation Department customizes inns according to the user's current health and physical condition. For example, it can customize an inn to "provide services that are not strenuous based on the user's current health." The Inn Recommendation Department can incorporate AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal inn. For example, the Inn Recommendation Department can use the user's current lifestyle and areas of interest as input to generate the optimal inn using AI. This allows for more appropriate inn recommendations by customizing inns based on the user's current lifestyle and areas of interest.

[0057] The hotel recommendation system prioritizes suggesting hotels that are highly relevant to the user's geographical location. For example, it can prioritize suggesting hotels close to the user's current location. It can also prioritize suggesting hotels in areas the user plans to visit. Furthermore, it can prioritize suggesting hotels easily accessible from the user's current location. The hotel recommendation system can incorporate AI processing, using AI to analyze the user's geographical location and suggest the most suitable hotel. For example, it can use the user's geographical location as input to generate the optimal hotel using AI. This allows the system to prioritize suggesting hotels that are highly relevant to the user's geographical location.

[0058] The Inn Recommendation Department analyzes users' social media activity and suggests relevant inns. For example, it can suggest inns related to travel destinations shared by users on social media. For instance, it can make suggestions such as, "Suggest inns related to travel destinations shared on social media." It can also suggest inns related to events users have shown interest in on social media. For example, it can make suggestions such as, "Suggest inns related to events users have shown interest in on social media." Furthermore, it can analyze the content of users' social media posts and suggest relevant inns. For example, it can make suggestions such as, "Suggest relevant inns based on the content of social media posts." The Inn Recommendation Department can incorporate AI processing, using AI to analyze users' social media activity and suggest the most suitable inn. For example, it can use users' social media activity as input to generate the optimal inn using AI. This allows it to suggest relevant inns by analyzing users' social media activity.

[0059] The access suggestion unit optimizes the suggestion algorithm by referring to past suggestion results. For example, the access suggestion unit prioritizes suggesting access methods that match the user's preferences based on past suggestion results. For instance, the access suggestion unit can optimize a suggestion algorithm that prioritizes suggesting access methods preferred by the user from among previously suggested access methods. The access suggestion unit also analyzes past suggestion results and improves the suggestion algorithm. For example, the access suggestion unit can optimize a suggestion algorithm that adjusts the parameters of the suggestion algorithm based on past suggestion results. Furthermore, the access suggestion unit predicts user preferences based on past suggestion results and suggests access methods. For example, the access suggestion unit can optimize a suggestion algorithm that predicts user preferences based on past suggestion results and suggests access methods. The access suggestion unit can include AI processing and use AI to analyze past suggestion results and optimize the suggestion algorithm. For example, the access suggestion unit can take past suggestion results as input and have a generation AI generate the optimal suggestion algorithm. This allows the suggestion algorithm to be optimized by referring to past suggestion results.

[0060] The access suggestion unit customizes access methods based on the user's current lifestyle and areas of interest. For example, it can customize access methods according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize an access method that allows for relaxation based on the user's current work workload. The access suggestion unit also customizes access methods based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize an access method that follows a scenic route related to the user's hobbies. Furthermore, the access suggestion unit customizes access methods according to the user's current health and physical condition. For example, it can customize an access method that is not strenuous based on the user's current health. The access suggestion unit can include AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal access method. For example, the access suggestion unit can take the user's current lifestyle and areas of interest as input and have the AI ​​generate the optimal access method. This allows us to suggest more appropriate access methods by customizing access methods based on the user's current lifestyle and areas of interest.

[0061] The access suggestion unit prioritizes suggesting the most relevant access methods, taking into account the user's geographical location. For example, it might suggest access methods close to the user's current location. It can also suggest access methods related to areas the user plans to visit. Furthermore, it might suggest access methods easily accessible from the user's current location. The access suggestion unit can incorporate AI processing, using AI to analyze the user's geographical location and suggest the optimal access method. For example, it can use the user's geographical location as input to generate the optimal access method using AI. This allows it to prioritize suggesting the most relevant access methods, taking the user's geographical location into account.

[0062] The Access Suggestion Unit analyzes the user's social media activity and proposes relevant access methods. For example, the Access Suggestion Unit can propose access methods related to travel destinations shared by the user on social media. For example, the Access Suggestion Unit can make a proposal such as, "Suggest access methods related to travel destinations shared on social media." The Access Suggestion Unit can also propose access methods related to events the user has shown interest in on social media. For example, the Access Suggestion Unit can make a proposal such as, "Suggest access methods related to events the user has shown interest in on social media." Furthermore, the Access Suggestion Unit analyzes the content of the user's social media posts and proposes relevant access methods. For example, the Access Suggestion Unit can make a proposal such as, "Suggest relevant access methods based on the content of social media posts." The Access Suggestion Unit can include AI processing and use AI to analyze the user's social media activity and propose the optimal access method. For example, the Access Suggestion Unit can take the user's social media activity as input and have a generation AI generate the optimal access method. This allows it to propose relevant access methods by analyzing the user's social media activity.

[0063] The detour suggestion unit optimizes its suggestion algorithm by referring to past suggestion results. For example, the detour suggestion unit prioritizes suggesting detours that match the user's preferences based on past suggestion results. For instance, the detour suggestion unit can optimize its suggestion algorithm to "prioritize suggesting detours that the user preferred from among previously suggested detours." The detour suggestion unit also analyzes past suggestion results and improves its suggestion algorithm. For example, the detour suggestion unit can optimize its suggestion algorithm to "adjust the parameters of the suggestion algorithm based on past suggestion results." Furthermore, the detour suggestion unit predicts the user's preferences based on past suggestion results and suggests detours. For example, the detour suggestion unit can optimize its suggestion algorithm to "predict the user's preferences based on past suggestion results and suggest detours." The detour suggestion unit can include AI processing and use AI to analyze past suggestion results and optimize its suggestion algorithm. For example, the detour suggestion unit can take past suggestion results as input and have a generation AI generate the optimal suggestion algorithm. This allows the suggestion algorithm to be optimized by referring to past suggestion results.

[0064] The detour suggestion function customizes detour locations based on the user's current lifestyle and areas of interest. For example, it can customize detour locations according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize detour locations to include relaxing cafes and parks based on the user's current work workload. It can also customize detour locations based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize detour locations to include sports facilities and amusement parks offering relevant activities based on the user's hobbies. Furthermore, it can customize detour locations according to the user's current health and physical condition. For example, it can customize detour locations to include restaurants and tourist spots offering services that are not strenuous based on the user's current health. The detour suggestion function can include AI processing, which can be used to analyze the user's current lifestyle and areas of interest and customize the optimal detour locations. For example, the detour suggestion function can take the user's current lifestyle and areas of interest as input and have the AI ​​generate optimal detour locations. This allows for the suggestion of more appropriate detour locations by customizing them based on the user's current lifestyle and areas of interest.

[0065] The detour suggestion unit prioritizes suggesting highly relevant detours, taking into account the user's geographical location. For example, it might prioritize suggesting detours close to the user's current location. It can also prioritize suggesting detours related to the area the user plans to visit. Furthermore, it prioritizes suggesting detours easily accessible from the user's current location. The detour suggestion unit can incorporate AI processing, using AI to analyze the user's geographical location and suggest optimal detours. For example, it can use the user's geographical location as input to generate optimal detours using an AI. This allows the system to prioritize suggesting highly relevant detours, taking into account the user's geographical location.

[0066] The detour suggestion unit analyzes the user's social media activity and suggests relevant detours. For example, the detour suggestion unit can suggest detours related to travel destinations shared by the user on social media. For example, the detour suggestion unit can make a suggestion such as, "Suggest detours related to travel destinations shared on social media." The detour suggestion unit can also suggest detours related to events the user has shown interest in on social media. For example, the detour suggestion unit can make a suggestion such as, "Suggest detours related to events the user has shown interest in on social media." Furthermore, the detour suggestion unit analyzes the content of the user's social media posts and suggests relevant detours. For example, the detour suggestion unit can make a suggestion such as, "Suggest relevant detours based on the content of social media posts." The detour suggestion unit can include AI processing and use AI to analyze the user's social media activity and suggest the optimal detours. For example, the detour suggestion unit can take the user's social media activity as input and have the generation AI generate the optimal detours. This allows it to suggest relevant detours by analyzing the user's social media activity.

[0067] The sightseeing guide unit optimizes its guidance algorithm by referring to past guidance results. For example, the sightseeing guide unit prioritizes guiding users to sightseeing spots that match their preferences based on past guidance results. For instance, the sightseeing guide unit can optimize its guidance algorithm to prioritize guiding users to sightseeing spots that they liked from those they were previously guided to. The sightseeing guide unit also analyzes past guidance results and improves its guidance algorithm. For example, the sightseeing guide unit can optimize its guidance algorithm by adjusting the parameters of the guidance algorithm based on past guidance results. Furthermore, the sightseeing guide unit predicts user preferences based on past guidance results and guides users to sightseeing spots accordingly. For example, the sightseeing guide unit can optimize its guidance algorithm by predicting user preferences based on past guidance results and guiding users to sightseeing spots accordingly. The sightseeing guide unit can include AI processing and use AI to analyze past guidance results and optimize its guidance algorithm. For example, the sightseeing guide unit can use past guidance results as input to generate an optimal guidance algorithm using a generation AI. This allows the guidance algorithm to be optimized by referring to past guidance results.

[0068] The sightseeing guide customizes sightseeing spots based on the user's current lifestyle and areas of interest. For example, it can customize sightseeing spots according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize sightseeing spots to include relaxing parks and hot springs based on the user's current work workload. The sightseeing guide also customizes sightseeing spots based on the user's areas of interest (hobbies, themes of interest, etc.). For example, it can customize sightseeing spots to include sports facilities and amusement parks offering relevant activities based on the user's hobbies. Furthermore, the sightseeing guide customizes sightseeing spots according to the user's current health and physical condition. For example, it can customize sightseeing spots to include restaurants and tourist attractions that offer services that are not strenuous based on the user's current health. The sightseeing guide can include AI processing, which can be used to analyze the user's current lifestyle and areas of interest and customize the most suitable sightseeing spots. For example, the sightseeing guide function can use the user's current lifestyle and areas of interest as input to generate optimal sightseeing spots using an AI. This allows for more appropriate sightseeing recommendations by customizing the destinations based on the user's current lifestyle and areas of interest.

[0069] The sightseeing guide section prioritizes guiding users to highly relevant sights, taking into account the user's geographical location. For example, it can prioritize guiding users to sights close to the user's current location. It can also prioritize guiding users to sights related to the region the user plans to visit. For example, it can prioritize guiding users to sights related to the region the user plans to visit. Furthermore, it can prioritize guiding users to sights easily accessible from the user's current location. For example, it can prioritize guiding users to sights easily accessible from the user's current location. The sightseeing guide section can incorporate AI processing, using AI to analyze the user's geographical location and guide users to the most suitable sights. For example, it can use the user's geographical location as input to generate the most suitable sights using an AI. This allows the system to prioritize guiding users to highly relevant sights, taking into account the user's geographical location.

[0070] The sightseeing spot guide analyzes the user's social media activity and guides them to relevant sightseeing spots. For example, the sightseeing spot guide can guide users to sightseeing spots related to travel destinations they have shared on social media. For example, the sightseeing spot guide can provide guidance such as, "We will guide you to sightseeing spots related to travel destinations you have shared on social media." The sightseeing spot guide can also guide users to sightseeing spots related to events they have shown interest in on social media. For example, the sightseeing spot guide can provide guidance such as, "We will guide you to sightseeing spots related to events you have shown interest in on social media." Furthermore, the sightseeing spot guide can analyze the content of the user's social media posts and guide them to relevant sightseeing spots. For example, the sightseeing spot guide can provide guidance such as, "We will guide you to relevant sightseeing spots based on the content of your social media posts." The sightseeing spot guide can include AI processing and use AI to analyze the user's social media activity and guide them to the most suitable sightseeing spots. For example, the sightseeing spot guide can take the user's social media activity as input and have the AI ​​generate the most suitable sightseeing spots. This allows the system to guide users to relevant sightseeing spots by analyzing the user's social media activity.

[0071] The foreign language support unit optimizes its response algorithm by referring to past response results. For example, the foreign language support unit prioritizes providing information that matches the user's preferences based on past response results. For instance, the foreign language support unit can optimize its response algorithm to "prioritize providing information that the user preferred from the information provided in the past." The foreign language support unit also analyzes past response results and improves its response algorithm. For example, the foreign language support unit can optimize its response algorithm to "adjust the parameters of the response algorithm based on past response results." Furthermore, the foreign language support unit predicts user preferences based on past response results and provides information accordingly. For example, the foreign language support unit can optimize its response algorithm to "predict user preferences based on past response results and provide information accordingly." The foreign language support unit can include AI processing and use AI to analyze past response results and optimize the response algorithm. For example, the foreign language support unit can use past response results as input to have a generation AI generate the optimal response algorithm. This allows the response algorithm to be optimized by referring to past response results.

[0072] The foreign language support unit customizes information based on the user's current living situation and areas of interest. For example, it can customize information according to the user's current living situation (work workload, family structure, etc.). For instance, it can customize information to provide relaxation based on the user's current work workload. The foreign language support unit also customizes information based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize information to provide information on relevant activities based on the user's hobbies. Furthermore, the foreign language support unit customizes information according to the user's current health and physical condition. For example, it can customize information to provide services that are suitable for the user based on their current health condition. The foreign language support unit can include AI processing, using AI to analyze the user's current living situation and areas of interest and customize the most appropriate information. For example, the foreign language support unit can take the user's current living situation and areas of interest as input and have the AI ​​generate the most appropriate information. This allows for the provision of more appropriate information by customizing information based on the user's current living situation and areas of interest.

[0073] The foreign user support unit prioritizes providing highly relevant information, taking into account the user's geographical location. For example, it prioritizes providing information close to the user's current location. For instance, it can provide information such as "prioritizing information on tourist spots near the user's current location." It also prioritizes providing information about areas the user plans to visit. For example, it can provide information such as "prioritizing information on tourist spots in areas the user plans to visit." Furthermore, it prioritizes providing information easily accessible from the user's current location. For instance, it can provide information such as "prioritizing information on tourist spots easily accessible from the user's current location." The foreign user support unit can incorporate AI processing, using AI to analyze the user's geographical location and provide optimal information. For example, it can use the user's geographical location as input to generate optimal information using AI. This allows it to prioritize providing highly relevant information, taking into account the user's geographical location.

[0074] The foreign user support department analyzes users' social media activity and provides relevant information. For example, it can provide information about travel destinations shared by users on social media. For example, it can provide information such as "providing information about travel destinations shared on social media." The foreign user support department can also provide information about events that users have shown interest in on social media. For example, it can provide information such as "providing information about events that users have shown interest in on social media." The foreign user support department also analyzes the content of users' social media posts and provides relevant information. For example, it can provide information such as "providing relevant information based on the content of social media posts." The foreign user support department can include AI processing and use AI to analyze users' social media activity and provide optimal information. For example, the foreign user support department can take users' social media activity as input and have the AI ​​generate optimal information. This allows it to provide relevant information by analyzing users' social media activity.

[0075] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0076] The service provider can optimize its service provision algorithm by referring to past service provision results. For example, it can prioritize selecting service provision methods that match user preferences based on past service provision results. Specifically, the service provider can prioritize selecting service provision methods preferred by users from among the plans provided in the past. Furthermore, the service provider can analyze past service provision results and improve its service provision algorithm. For example, the service provider can adjust the parameters of the service provision algorithm based on past service provision results. In addition, the service provider can predict user preferences based on past service provision results and provide plans accordingly. For example, the service provider can predict user preferences based on past service provision results and provide plans accordingly. This allows the service provider to optimize its service provision algorithm by referring to past service provision results.

[0077] The interviewing team can analyze a user's past travel history and select the most appropriate questions. For example, it can ask relevant questions based on places the user has visited in the past. Specifically, the interviewing team can ask questions such as, "What hot spring resorts have you visited in the past?" The interviewing team can also analyze the user's preferences from their past travel history and ask questions based on those preferences. For example, the interviewing team can ask questions such as, "What was your favorite place you've visited in the past?" Furthermore, the interviewing team can ask relevant questions based on the modes of transportation and accommodations the user has used in the past. For example, the interviewing team can ask questions such as, "What modes of transportation have you used in the past?" and "What accommodations have you stayed at in the past?" In this way, by analyzing the user's past travel history, the team can select the most appropriate questions.

[0078] The selection unit can optimize its selection algorithm by referring to past selection results. For example, it can prioritize selecting plans that match the user's preferences based on past selection results. Specifically, the selection unit can prioritize selecting plans that users preferred from among those previously selected. Furthermore, the selection unit can analyze past selection results and improve its selection algorithm. For example, it can adjust the parameters of the selection algorithm based on past selection results. In addition, the selection unit can predict user preferences and select plans based on past selection results. For example, it can predict user preferences and select plans based on past selection results. In this way, the selection algorithm can be optimized by referring to past selection results.

[0079] The service provider can customize plans based on the user's current lifestyle and areas of interest. For example, they can customize plans according to the user's current lifestyle (work workload, family structure, etc.). Specifically, they can customize a relaxing plan based on the user's current work workload. They can also customize plans based on the user's areas of interest (hobbies, topics of interest, etc.). For example, they can customize a plan to include relevant tourist destinations based on the user's hobbies. Furthermore, they can customize plans according to the user's current health and physical condition. For example, they can customize a plan that is not strenuous based on the user's current health condition. By customizing plans based on the user's current lifestyle and areas of interest, they can provide more appropriate plans.

[0080] The redesign unit can prioritize highly relevant redesigns by taking the user's geographical location into consideration. For example, it can prioritize redesigning plans that include tourist destinations close to the user's current location. Specifically, the redesign unit can prioritize redesigning plans that include tourist destinations close to the user's current location. Furthermore, the redesign unit can prioritize redesigning plans that relate to areas the user plans to visit. For example, the redesign unit can prioritize redesigning plans that relate to areas the user plans to visit. In addition, the redesign unit can prioritize redesigning plans that include places easily accessible from the user's current location. For example, the redesign unit can prioritize redesigning plans that include places easily accessible from the user's current location. This allows the unit to prioritize highly relevant redesigns by taking the user's geographical location into consideration.

[0081] The following briefly describes the processing flow for example form 1.

[0082] Step 1: The interviewing department gathers information from users. For example, when a user is planning a trip, they will be asked about their budget, places they want to visit, and their current mood. Specifically, they will ask questions such as, "What is your budget?", "Where do you want to go?", and "How are you feeling right now?", record the user's answers, and send them to the selection department. Step 2: The selection unit selects a plan based on the information gathered by the interviewing unit. For example, it proposes a hotel that fits the user's budget, access methods, and places to stop along the way. The selection unit can include AI processing, using AI to analyze the user's information and select the optimal plan. Step 3: The delivery unit provides the plan selected by the selection unit. For example, it presents the selected plan to the user and provides detailed information. The delivery unit may include AI processing and use AI to provide the user with the most suitable information. Step 4: The redesign department redesigns the plan based on the plan provided by the delivery department. For example, if the user is not satisfied with the plan provided, the department redesigns the plan. The redesign department may include AI processing, using AI to analyze user feedback and redesign the optimal plan.

[0083] (Example of form 2) The travel planning support system according to an embodiment of the present invention is a system that utilizes an AI personal agent to reduce the effort required for information gathering and planning when planning a trip. When a user plans a trip, the travel planning support system has the AI ​​agent periodically ask questions to gather information such as budget, desired destinations, and current mood. Next, the AI ​​agent selects a personalized plan for the traveler based on the information gathered. This plan includes accommodations that fit the budget in the desired region, methods of transportation (including variations such as choosing an express train instead of a bullet train), and places to stop along the way. The AI ​​agent also supports English and other languages, and can guide users to local festivals and scenic spots in Japan, thereby increasing the average travel value for Japan as a tourism-oriented country. For example, when a user plans a trip, the AI ​​agent periodically asks questions. At this time, the user answers with information such as budget, desired destinations, and current mood. For example, the user might input information such as, "My budget is under 50,000 yen, and I want to go to a hot spring resort," or "I want to relax." This information is input into the AI ​​agent. Next, the AI ​​agent analyzes the input information and selects a personalized plan for the traveler. The AI ​​agent suggests accommodations, transportation options, and places to visit along the way that fit the user's budget. For example, based on information such as "I want to go to a hot spring resort with a budget of 50,000 yen or less," it will suggest hot spring inns that fit the budget, transportation options using express trains, and sightseeing spots to visit along the way. Furthermore, the AI ​​agent supports English and other languages, and can guide users to local festivals and scenic spots within Japan. This allows the agent to cater to foreign tourists and increase the average spending per visit as Japan becomes a tourism-oriented country. For example, it can provide foreign tourists with information on domestic festivals and scenic spots in English and propose travel plans. This reduces the effort required for information gathering and planning when planning a trip. In addition, because the AI ​​agent proposes personalized plans, travelers can enjoy a trip that suits their preferences and budget. Moreover, the AI ​​agent can revise its plans as many times as needed, so by using it repeatedly, users can receive suggestions for plans that match their preferences and offer unexpected ideas.This allows the travel planning support system to efficiently assist users with their travel planning and provide personalized travel plans.

[0084] The travel planning support system according to this embodiment comprises a hearing unit, a selection unit, a provision unit, and a revision unit. The hearing unit hears information from the user. For example, when the user is planning a trip, the hearing unit asks questions about their budget, places they want to go, their current mood, etc. For example, the hearing unit can ask questions such as, "What is your budget?", "Where do you want to go?", and "How are you feeling right now?". The hearing unit records the user's answers and sends them to the selection unit. The selection unit selects a plan based on the information gathered by the hearing unit. For example, the selection unit suggests accommodations, transportation methods, and places to visit along the way that fit the user's budget. For example, based on information such as, "I want to go to a hot spring resort with a budget of 50,000 yen or less," the selection unit can suggest hot spring inns that can be stayed at within the budget, transportation methods using express trains, and sightseeing spots to visit along the way. The selection unit may include AI processing and can use AI to analyze the user's information and select the optimal plan. The provision unit provides the plan selected by the selection unit. The provisioning unit, for example, presents a selected plan to the user and provides detailed information. For example, the provisioning unit can provide the user with information on the selected inn, how to access it, and sightseeing spots to visit along the way. The provisioning unit may include AI processing and can use AI to provide the user with the most suitable information. The re-planning unit re-plans based on the plan provided by the provisioning unit. For example, the re-planning unit re-plans if the user is not satisfied with the plan provided. For example, the re-planning unit can receive user feedback and re-select a plan. The re-planning unit may include AI processing and can use AI to analyze user feedback and re-plan the most suitable option. As a result, the travel planning support system according to this embodiment can provide personalized travel plans by interviewing users, selecting, providing, and re-planning them.

[0085] The interviewing department gathers information from users. For example, when a user is planning a trip, the interviewing department asks questions about their budget, places they want to visit, and their current mood. Specifically, when a user is planning a trip, the interviewing department asks questions about their budget, places they want to visit, and their current mood. For example, it can ask questions such as, "What is your budget?", "Where do you want to go?", and "How are you feeling right now?". These questions are important for accurately understanding the user's needs and desires. The interviewing department records the user's responses and sends them to the selection department. The user's responses are recorded in text format and stored in a database. The interviewing department can utilize speech recognition and natural language processing technologies to record user responses quickly and accurately. For example, if a user responds by voice, speech recognition technology is used to convert it to text and store it in the database. In addition, natural language processing technology can be used to analyze the user's responses and extract important information. This allows the interviewing department to accurately understand the user's needs and desires and send them to the selection department. Furthermore, the interviewing department can ask additional questions based on the user's responses. For example, if a user answers "I want to go to a hot spring resort," the interviewing department can ask additional questions such as "Which region's hot spring resort would you like to visit?" This allows the interviewing department to gain a more detailed understanding of the user's needs and preferences and then transmit that information to the selection department.

[0086] The selection department selects a plan based on information gathered by the interview department. For example, the selection department suggests accommodations, transportation methods, and places to visit along the way that fit the user's budget. Specifically, the selection department selects the optimal travel plan based on information such as the user's budget, desired destinations, and current mood. For example, based on information such as "I want to go to a hot spring resort with a budget of 50,000 yen or less," it can suggest hot spring inns that fit within the budget, transportation methods using express trains, and sightseeing spots to visit along the way. The selection department can incorporate AI processing, using AI to analyze user information and select the optimal plan. The AI ​​selects the plan best suited to the user's needs and desires based on past data and statistical information. For example, the AI ​​can refer to plans selected under similar conditions in the past to select the plan best suited to the user's needs and desires. Furthermore, the AI ​​can analyze user responses and extract important information. This allows the selection department to quickly and accurately select the plan best suited to the user's needs and desires. In addition, the selection department can propose multiple plans according to the user's needs and desires. For example, it can suggest multiple hot spring inns that fit within the budget, multiple access options, and multiple tourist spots. This allows the selection department to respond flexibly to the user's needs and preferences.

[0087] The service provider provides the plans selected by the selection provider. For example, the service provider presents the selected plans to the user and provides detailed information. Specifically, the service provider can provide the user with information about the selected inn, how to access it, and information about sightseeing spots to visit along the way. For example, the service provider can provide detailed information such as the address, contact information, price, facilities, and services of the selected inn. Regarding access, it provides information such as how to access it from the nearest station or bus stop, the travel time, and the price. Furthermore, regarding sightseeing spots to visit along the way, it provides information such as the name of the sightseeing spot, address, opening hours, price, and highlights. The service provider can include AI processing and use AI to provide the user with the most suitable information. The AI ​​selects and provides the most suitable information according to the user's needs and preferences. For example, the AI ​​selects and provides the most suitable information based on information such as the user's budget, desired destinations, and current mood. The AI ​​can also analyze the user's responses and extract important information. This allows the service provider to quickly and accurately provide information that is best suited to the user's needs and preferences. Furthermore, the service provider can provide multiple pieces of information according to the user's needs and preferences. For example, it can provide information on multiple inns, access methods, and tourist attractions. This allows the service provider to respond flexibly to the user's needs and preferences.

[0088] The Redesign Department redesigns plans based on those provided by the Service Provider. For example, if a user is dissatisfied with the provided plan, the Redesign Department will redesign it. Specifically, the Redesign Department can receive user feedback and re-select a plan. For instance, if a user provides feedback such as "I can't find a hot spring inn that fits my budget," the Redesign Department will suggest other hot spring inns that fit the budget. Similarly, if a user provides feedback such as "Access is inconvenient," the Redesign Department will suggest alternative access methods. The Redesign Department can incorporate AI processing, using AI to analyze user feedback and redesign the optimal plan. AI can analyze user feedback and extract important information. This allows the Redesign Department to quickly and accurately redesign a plan that best suits the user's needs and preferences. Furthermore, the Redesign Department can propose multiple plans based on the user's needs and preferences. For example, it can propose plans for multiple hot spring inns, access methods, and tourist spots. This allows the Redesign Department to respond flexibly to user needs and preferences. The Redesign Department can continuously improve plans based on user feedback. For example, based on user feedback, the plan's content and presentation methods can be reviewed and improved. This allows the planning department to increase user satisfaction.

[0089] The selection unit includes a hotel recommendation unit that proposes hotels that fit the budget. For example, the selection unit proposes hotels that can be booked within the user's budget based on the user's budget. For example, based on information such as "I want to go to a hot spring resort with a budget of 50,000 yen or less," the selection unit can propose hot spring hotels that can be booked within that budget. The selection unit can include AI processing and use AI to analyze the user's budget information and propose the most suitable hotels. For example, the selection unit can take the user's budget information as input and have the AI ​​generate a list of hotels that can be booked within that budget. This allows the system to propose hotels that fit the budget and provide the user with a travel plan that suits their budget.

[0090] The selection unit includes an access suggestion unit that proposes access methods. The selection unit proposes the optimal access method based, for example, on the user's mode of transportation. For example, based on information such as "I want to use a limited express train instead of a bullet train," the selection unit can propose an access method using a limited express train. The selection unit can include AI processing and use AI to analyze the user's mode of transportation information and propose the optimal access method. For example, the selection unit can take the user's mode of transportation information as input and have a generation AI generate the optimal access method. This allows the system to provide travel plans that match the user's mode of transportation by proposing access methods.

[0091] The selection unit includes a detour suggestion unit that proposes places to stop along the way. For example, the selection unit suggests places to stop along the way based on the user's interests. For example, based on information such as "I want to stop by a tourist spot on the way to a hot spring resort," the selection unit can suggest tourist spots to stop at along the way. The selection unit can include AI processing and use AI to analyze the user's interest information and suggest the most suitable detour locations. For example, the selection unit can take the user's interest information as input and have the generation AI generate the most suitable detour locations. This allows the system to provide a travel plan that matches the user's interests by suggesting places to stop along the way.

[0092] The service provider includes a sightseeing guide unit that provides information on festivals and scenic spots in rural areas of Japan. For example, the service provider can provide users with information on festivals and scenic spots in rural areas of Japan. For example, based on information such as "I want to see a festival on the way to a hot spring resort," the service provider can provide information on festivals to visit along the way. The service provider can include AI processing and use AI to analyze the user's interest information and guide them to the most suitable sightseeing spots. For example, the service provider can take the user's interest information as input and have the AI ​​generate the most suitable sightseeing spots. This allows the service provider to effectively guide users to tourist attractions by providing information on sightseeing spots.

[0093] The service provider includes a foreigner support unit that provides information to foreign tourists in English. For example, the service provider can provide information about domestic festivals and scenery to foreign tourists in English. For example, based on the information "provide information about hot spring resorts to foreign tourists in English," the service provider can provide information about hot spring resorts in English. The service provider can include AI processing and use AI to analyze information about foreign tourists and provide the most suitable information. For example, the service provider can take information about foreign tourists as input and have the AI ​​generate the most suitable information. This allows the service provider to cater to foreign tourists by providing information in English.

[0094] The interviewer estimates the user's emotions and adjusts the content and timing of questions based on the estimated emotions. For example, if the user is stressed, the interviewer reduces the frequency of questions and asks concise questions. For example, the interviewer might ask a simple question like, "What is your budget?" If the user is relaxed, the interviewer will ask more detailed questions to delve deeper into the user's preferences. For example, the interviewer might ask detailed questions like, "Where would you like to go?" or "How are you feeling right now?" If the user is in a hurry, the interviewer will prioritize important questions to quickly gather information. For example, the interviewer might prioritize important questions like, "What is your budget?" or "Where would you like to go?" 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. This allows for more appropriate questions to be asked by adjusting the content and timing of questions based on the user's emotions.

[0095] The interview function analyzes the user's past travel history and selects the most appropriate questions. For example, the interview function asks relevant questions based on places the user has visited in the past. For instance, it might ask, "What hot spring resorts have you visited in the past?" The interview function also analyzes the user's preferences from their past travel history and asks questions based on those preferences. For example, it might ask, "What was your favorite place you've visited in the past?" The interview function also asks relevant questions based on the modes of transportation and accommodations the user has used in the past. For example, it might ask, "What modes of transportation have you used in the past?" or "What accommodations have you stayed at in the past?" The interview function can also incorporate AI processing, using AI to analyze the user's past travel history and select the most appropriate questions. For example, the interview function can use the user's past travel history as input to generate the most appropriate questions using AI. This allows for the selection of optimal questions by analyzing the user's past travel history.

[0096] The interview function customizes questions based on the user's current living situation and areas of interest. For example, the interview function can ask questions related to topics the user has recently been interested in. For instance, it might ask, "What topics have you been interested in lately?" The interview function also asks appropriate questions based on the user's current living situation (e.g., workload, family structure). For example, it might ask, "How busy is your current job?" or "What is your family structure like?" The interview function also asks relevant questions based on the user's hobbies and areas of interest. For example, it might ask, "What are your hobbies?" or "What topics are you interested in?" The interview function can include AI processing, using AI to analyze the user's current living situation and areas of interest and customize the most appropriate questions. For example, the interview function can take the user's current living situation and areas of interest as input and have the AI ​​generate the most appropriate questions. This allows for more appropriate questions to be asked by customizing them based on the user's current living situation and areas of interest.

[0097] The interviewer estimates the user's emotions and prioritizes questions based on those emotions. For example, if the user is stressed, the interviewer will prioritize important questions such as, "What is your budget?" If the user is relaxed, the interviewer will prioritize detailed questions such as, "Where do you want to go?" or "How are you feeling right now?" If the user is in a hurry, the interviewer will prioritize questions that can be answered quickly, such as, "What is your budget?" or "Where do you want to go?" 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. This allows for more appropriate questions to be asked by prioritizing questions based on the user's emotions.

[0098] The interview function prioritizes questions that are highly relevant, taking into account the user's geographical location. For example, it prioritizes questions about tourist attractions near the user's current location, such as, "What are some tourist attractions near my current location?" It also prioritizes questions about regions the user plans to visit, such as, "What information do you have about the region you plan to visit?" Furthermore, it prioritizes questions about places easily accessible from the user's current location, such as, "What places are easily accessible from my current location?" The interview function can incorporate AI processing, using AI to analyze the user's geographical location and select the most appropriate questions. For example, the interview function can use the user's geographical location as input to generate optimal questions using AI. This allows the system to prioritize questions that are highly relevant, taking into account the user's geographical location.

[0099] The interviewing unit analyzes the user's social media activity and asks relevant questions. For example, the interviewing unit might ask questions about travel destinations the user has shared on social media. For example, it might ask, "Where did you travel to that destination that you shared on social media?" The interviewing unit also asks questions about events the user has shown interest in on social media. For example, it might ask, "What events have you shown interest in on social media?" The interviewing unit also analyzes the content of the user's social media posts and asks relevant questions. For example, it can ask relevant questions based on the content of the user's social media posts. The interviewing unit can include AI processing and use AI to analyze the user's social media activity and select the most appropriate questions. For example, the interviewing unit can use the user's social media activity as input and have the AI ​​generate the most appropriate questions. This makes it possible to ask relevant questions by analyzing the user's social media activity.

[0100] The selection unit estimates the user's emotions and adjusts the plan selection criteria based on the estimated emotions. For example, if the user wants to relax, the selection unit will prioritize relaxing plans. For instance, the selection unit could adjust the criteria to "select a plan for a relaxing hot spring resort." If the user wants to be active, the selection unit will prioritize active plans. For example, the selection unit could adjust the criteria to "select a plan for an active tourist destination." If the user wants to spend time with family, the selection unit will prioritize family-friendly plans. For example, the selection unit could adjust the criteria to "select a plan for a ryokan (Japanese inn) that provides family-friendly services." 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. This allows for the selection of more appropriate plans by adjusting the plan selection criteria based on the user's emotions.

[0101] The selection unit optimizes the selection algorithm by referring to past selection results. For example, the selection unit prioritizes selecting plans that match the user's preferences based on past selection results. For instance, the selection unit can optimize a selection algorithm that prioritizes selecting plans preferred by the user from among those previously selected. The selection unit also analyzes past selection results and improves the selection algorithm. For example, the selection unit can optimize a selection algorithm that adjusts the parameters of the selection algorithm based on past selection results. Furthermore, the selection unit predicts user preferences based on past selection results and selects plans. For example, the selection unit can optimize a selection algorithm that predicts user preferences based on past selection results and selects plans. The selection unit can include AI processing and use AI to analyze past selection results and optimize the selection algorithm. For example, the selection unit can take past selection results as input and have a generation AI generate an optimal selection algorithm. This allows the selection algorithm to be optimized by referring to past selection results.

[0102] The selection unit customizes plans based on the user's current lifestyle and areas of interest. For example, the selection unit can customize plans according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize a plan that allows for relaxation based on the user's current work workload. The selection unit also customizes plans based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize a plan that includes relevant tourist destinations based on the user's hobbies. Furthermore, the selection unit customizes plans according to the user's current health and physical condition. For example, it can customize a plan that is manageable based on the user's current health. The selection unit can include AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal plan. For example, the selection unit can take the user's current lifestyle and areas of interest as input and have the AI ​​generate the optimal plan. This allows for the provision of more appropriate plans by customizing plans based on the user's current lifestyle and areas of interest.

[0103] The selection unit estimates the user's emotions and determines the priority of plans based on the estimated emotions. For example, if the user wants to relax, the selection unit will prioritize relaxing plans. For instance, the selection unit might prioritize plans such as "plans for relaxing hot spring resorts." Similarly, if the user wants to be active, the selection unit will prioritize active plans. For example, the selection unit might prioritize plans for active tourist destinations. Furthermore, if the user wants to spend time with family, the selection unit will prioritize family-friendly plans. For example, the selection unit might prioritize plans for inns offering family-friendly services. 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. This allows for the provision of more appropriate plans by prioritizing plans based on the user's emotions.

[0104] The selection unit prioritizes selecting highly relevant plans, taking into account the user's geographical location. For example, the selection unit might prioritize plans that include tourist destinations near the user's current location. For instance, it could select plans that prioritize including tourist destinations near the user's current location. The selection unit might also prioritize plans related to areas the user plans to visit. For example, it could select plans that prioritize areas the user plans to visit. Furthermore, the selection unit might prioritize plans that include locations easily accessible from the user's current location. For instance, it could select plans that prioritize including locations easily accessible from the user's current location. The selection unit can incorporate AI processing, using AI to analyze the user's geographical location and select the optimal plan. For example, the selection unit could take the user's geographical location as input and have an AI generate the optimal plan. This allows for the selection of highly relevant plans, taking into account the user's geographical location.

[0105] The selection unit analyzes the user's social media activity and selects relevant plans. For example, the selection unit can select plans related to travel destinations shared by the user on social media. For instance, the selection unit can select a plan such as "Select travel destinations shared on social media." The selection unit can also select plans related to events the user has shown interest in on social media. For example, the selection unit can select a plan such as "Select plans related to events the user has shown interest in on social media." Furthermore, the selection unit analyzes the content of the user's social media posts and selects relevant plans. For example, the selection unit can select a plan such as "Select relevant plans based on the content of social media posts." The selection unit can include AI processing, using AI to analyze the user's social media activity and select the optimal plan. For example, the selection unit can take the user's social media activity as input and have the AI ​​generate the optimal plan. This allows the system to provide relevant plans by analyzing the user's social media activity.

[0106] The service provider estimates the user's emotions and adjusts the way the plan is delivered based on those emotions. For example, if the user is relaxed, the service provider will deliver the plan at a leisurely pace. For instance, the service provider might adjust the delivery method to "deliver a relaxing hot spring resort plan at a leisurely pace." If the user is in a hurry, the service provider will deliver the plan quickly. For instance, the service provider might adjust the delivery method to "deliver a plan quickly to users in a hurry." If the user is excited, the service provider will deliver the plan in a visually stimulating way. For instance, the service provider might adjust the delivery method to "deliver a plan in a visually stimulating way to users who are excited." 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. This allows for the delivery of more appropriate plans by adjusting the delivery method based on the user's emotions.

[0107] The service delivery unit optimizes its delivery algorithm by referring to past delivery results. For example, the service delivery unit prioritizes selecting delivery methods that match user preferences based on past delivery results. For instance, the service delivery unit can optimize its delivery algorithm to "prioritize selecting delivery methods preferred by users from among plans previously delivered." The service delivery unit also analyzes past delivery results and improves its delivery algorithm. For example, the service delivery unit can optimize its delivery algorithm by "adjusting the parameters of the delivery algorithm based on past delivery results." Furthermore, the service delivery unit predicts user preferences based on past delivery results and provides plans accordingly. For example, the service delivery unit can optimize its delivery algorithm by "predicting user preferences based on past delivery results and providing plans accordingly." The service delivery unit can include AI processing and use AI to analyze past delivery results and optimize its delivery algorithm. For example, the service delivery unit can use past delivery results as input to generate an optimal delivery algorithm using a generation AI. This allows the service delivery algorithm to be optimized by referring to past delivery results.

[0108] The service provider customizes plans based on the user's current lifestyle and areas of interest. For example, the service provider can customize plans according to the user's current lifestyle (work workload, family structure, etc.). For instance, the service provider can customize a plan that allows for relaxation based on the user's current work workload. The service provider can also customize plans based on the user's areas of interest (hobbies, topics of interest, etc.). For example, the service provider can customize a plan that includes relevant tourist destinations based on the user's hobbies. Furthermore, the service provider can customize plans according to the user's current health and physical condition. For example, the service provider can customize a plan that is manageable based on the user's current health. The service provider can incorporate AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal plan. For example, the service provider can use the user's current lifestyle and areas of interest as input to generate an optimal plan using AI. This allows for the provision of more appropriate plans by customizing them based on the user's current lifestyle and areas of interest.

[0109] The service provider estimates the user's emotions and determines the order in which plans are offered based on the estimated emotions. For example, if the user is relaxed, the service provider will prioritize offering relaxing plans. For instance, the service provider might prioritize offering plans for relaxing hot spring resorts. If the user wants to be active, the service provider will prioritize offering active plans. For example, the service provider might prioritize offering plans for active tourist destinations. If the user wants to spend time with family, the service provider will prioritize offering family-friendly plans. For example, the service provider might prioritize offering plans for inns that offer family-friendly services. 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. This allows for the provision of more appropriate plans by determining the order in which plans are offered based on the user's emotions.

[0110] The service provider prioritizes providing highly relevant plans, taking into account the user's geographical location. For example, the service provider might prioritize plans that include tourist destinations near the user's current location. For instance, it could provide a plan that prioritizes plans that include tourist destinations near the user's current location. The service provider might also prioritize plans related to areas the user plans to visit. For example, it could provide a plan that prioritizes plans related to areas the user plans to visit. Furthermore, the service provider might prioritize plans that include locations easily accessible from the user's current location. For example, it could provide a plan that prioritizes plans that include locations easily accessible from the user's current location. The service provider can incorporate AI processing, using AI to analyze the user's geographical location and provide the optimal plan. For example, the service provider could use the user's geographical location as input to generate an optimal plan using AI. This allows the service provider to prioritize providing highly relevant plans, taking into account the user's geographical location.

[0111] The service provider analyzes users' social media activity and provides relevant plans. For example, the service provider can provide plans related to travel destinations shared by users on social media. For instance, the service provider can provide plans such as "Providing travel destinations shared on social media." The service provider can also provide plans related to events that users have shown interest in on social media. For example, the service provider can provide plans such as "Providing plans related to events that users have shown interest in on social media." Furthermore, the service provider analyzes the content of users' social media posts and provides relevant plans. For example, the service provider can provide plans such as "Providing relevant plans based on the content of social media posts." The service provider can include AI processing, using AI to analyze users' social media activity and provide optimal plans. For example, the service provider can use users' social media activity as input to generate optimal plans using AI. This allows the service provider to provide relevant plans by analyzing users' social media activity.

[0112] The redesign unit estimates the user's emotions and adjusts the redesign criteria based on the estimated emotions. For example, if the user wants to relax, the redesign unit will prioritize redesigning plans that promote relaxation. For instance, the redesign unit could adjust the criteria to prioritize redesigning plans for relaxing hot spring resorts. If the user wants to be active, the redesign unit will prioritize redesigning plans that promote active activities. For example, the redesign unit could adjust the criteria to prioritize redesigning plans for active tourist destinations. If the user wants to spend time with family, the redesign unit will prioritize redesigning plans that are suitable for families. For example, the redesign unit could adjust the criteria to prioritize redesigning plans for inns that offer family-friendly services. 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. This allows for the development of more appropriate plans by adjusting the redesign criteria based on user sentiment.

[0113] The redesign unit optimizes the redesign algorithm by referring to past redesign results. For example, the redesign unit prioritizes redesigning plans that match user preferences based on past redesign results. For instance, the redesign unit can optimize a redesign algorithm that prioritizes redesigning plans preferred by users from among previously redesigned plans. The redesign unit also analyzes past redesign results and improves the redesign algorithm. For example, the redesign unit can optimize a redesign algorithm that adjusts the parameters of the redesign algorithm based on past redesign results. Furthermore, the redesign unit predicts user preferences based on past redesign results and redesigns plans. For example, the redesign unit can optimize a redesign algorithm that predicts user preferences based on past redesign results and redesigns plans. The redesign unit can include AI processing and use AI to analyze past redesign results and optimize the redesign algorithm. For example, the redesign unit can take past redesign results as input and have a generation AI generate an optimal redesign algorithm. This allows the redesign algorithm to be optimized by referring to past redesign results.

[0114] The replanning unit customizes the replanning based on the user's current lifestyle and areas of interest. For example, the replanning unit can replan a plan according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can replan a plan that allows for relaxation based on the user's current work workload. The replanning unit can also replan a plan based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can replan a plan that includes relevant tourist destinations based on the user's hobbies. Furthermore, the replanning unit can replan a plan according to the user's current health and physical condition. For example, it can replan a plan that is manageable based on the user's current health. The replanning unit can include AI processing, using AI to analyze the user's current lifestyle and areas of interest and replan the optimal plan. For example, the replanning unit can use the user's current lifestyle and areas of interest as input to generate an optimal plan using AI. This allows for the creation of a more appropriate plan by customizing the revised plan based on the user's current living situation and areas of interest.

[0115] The redesign unit estimates the user's emotions and determines the redesign priority based on the estimated emotions. For example, if the user wants to relax, the redesign unit will prioritize redesigning plans that promote relaxation. For instance, the redesign unit might prioritize redesigning plans for relaxing hot spring resorts. If the user wants to be active, the redesign unit will prioritize redesigning plans that promote active activities. For example, the redesign unit might prioritize redesigning plans for active tourist destinations. If the user wants to spend time with family, the redesign unit will prioritize redesigning plans that are suitable for families. For example, the redesign unit might prioritize redesigning plans for inns that offer family-friendly services. 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. This allows for the development of more appropriate plans by prioritizing revisions based on user sentiment.

[0116] The redesign unit prioritizes highly relevant redesigns, taking into account the user's geographical location. For example, it might prioritize redesigning plans that include tourist destinations near the user's current location. For instance, it could redesign a plan that prioritizes plans that include tourist destinations near the user's current location. It could also prioritize redesigning plans related to areas the user plans to visit. For example, it could redesign a plan that prioritizes plans related to areas the user plans to visit. Furthermore, it could prioritize redesigning plans that include locations easily accessible from the user's current location. For example, it could redesign a plan that prioritizes plans that include locations easily accessible from the user's current location. The redesign unit can incorporate AI processing, using AI to analyze the user's geographical location and redesign the optimal plan. For example, it could use the user's geographical location as input to generate an optimal plan using AI. This allows the unit to prioritize highly relevant redesigns, taking into account the user's geographical location.

[0117] The replanning unit analyzes the user's social media activity and replans accordingly. For example, the replanning unit can replan travel destinations shared by the user on social media. For instance, the replanning unit can replan a plan such as "Replan travel destinations shared on social media." The replanning unit can also replan events that the user has shown interest in on social media. For example, the replanning unit can replan an event that the user has shown interest in on social media. Furthermore, the replanning unit analyzes the content of the user's social media posts and replans accordingly. For example, the replanning unit can replan a plan such as "Replan relevant plans based on the content of social media posts." The replanning unit can include AI processing, using AI to analyze the user's social media activity and replan the optimal plan. For example, the replanning unit can take the user's social media activity as input and have the AI ​​generate the optimal plan. This makes it possible to replan accordingly by analyzing the user's social media activity.

[0118] The hotel recommendation department estimates the user's emotions and adjusts its hotel recommendation method based on the estimated emotions. For example, if the user wants to relax, the hotel recommendation department will prioritize recommending hotels that offer relaxation. For example, the hotel recommendation department can adjust its recommendation method to "prioritize recommending relaxing hot spring hotels." Also, if the user wants to be active, the hotel recommendation department will prioritize recommending hotels that offer active activities. For example, the hotel recommendation department can adjust its recommendation method to "prioritize recommending hotels that offer active activities." Furthermore, if the user wants to spend time with family, the hotel recommendation department will prioritize recommending hotels that provide family-friendly services. For example, the hotel recommendation department can adjust its recommendation method to "prioritize recommending hotels that provide family-friendly services." Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more appropriate hotel recommendations by adjusting the hotel recommendation method based on the user's emotions.

[0119] The Inn Proposal Department optimizes its proposal algorithm by referring to past proposal results. For example, the Inn Proposal Department prioritizes proposing inns that match the user's preferences based on past proposal results. For instance, the Inn Proposal Department can optimize its proposal algorithm to "prioritize proposing inns that the user liked from among those previously proposed." The Inn Proposal Department also analyzes past proposal results and improves its proposal algorithm. For example, the Inn Proposal Department can optimize its proposal algorithm by "adjusting the parameters of the proposal algorithm based on past proposal results." Furthermore, the Inn Proposal Department predicts the user's preferences based on past proposal results and proposes inns. For example, the Inn Proposal Department can optimize its proposal algorithm to "predict the user's preferences based on past proposal results and propose inns." The Inn Proposal Department can include AI processing and use AI to analyze past proposal results and optimize its proposal algorithm. For example, the Inn Proposal Department can use past proposal results as input to generate an optimal proposal algorithm using a generation AI. This allows the proposal algorithm to be optimized by referring to past proposal results.

[0120] The Inn Recommendation Department customizes inns based on the user's current lifestyle and areas of interest. For example, it can customize inns according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize an inn to "create a relaxing inn based on the user's current work workload." The Inn Recommendation Department also customizes inns based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize an inn to "provide activities related to the user's hobbies." Furthermore, the Inn Recommendation Department customizes inns according to the user's current health and physical condition. For example, it can customize an inn to "provide services that are not strenuous based on the user's current health." The Inn Recommendation Department can incorporate AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal inn. For example, the Inn Recommendation Department can use the user's current lifestyle and areas of interest as input to generate the optimal inn using AI. This allows for more appropriate inn recommendations by customizing inns based on the user's current lifestyle and areas of interest.

[0121] The hotel recommendation department estimates the user's emotions and prioritizes hotels based on those emotions. For example, if the user wants to relax, the hotel recommendation department will prioritize hotels that offer relaxation. For instance, the hotel recommendation department could prioritize hotels with relaxing hot springs. If the user wants to be active, the hotel recommendation department will prioritize hotels that offer active activities. For instance, the hotel recommendation department could prioritize hotels that offer active activities. If the user wants to spend time with family, the hotel recommendation department will prioritize hotels that provide family-friendly services. For instance, the hotel recommendation department could prioritize hotels that provide family-friendly services. 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. This allows for the recommendation of more appropriate hotels by prioritizing them based on the user's emotions.

[0122] The hotel recommendation system prioritizes suggesting hotels that are highly relevant to the user's geographical location. For example, it can prioritize suggesting hotels close to the user's current location. It can also prioritize suggesting hotels in areas the user plans to visit. Furthermore, it can prioritize suggesting hotels easily accessible from the user's current location. The hotel recommendation system can incorporate AI processing, using AI to analyze the user's geographical location and suggest the most suitable hotel. For example, it can use the user's geographical location as input to generate the optimal hotel using AI. This allows the system to prioritize suggesting hotels that are highly relevant to the user's geographical location.

[0123] The Inn Recommendation Department analyzes users' social media activity and suggests relevant inns. For example, it can suggest inns related to travel destinations shared by users on social media. For instance, it can make suggestions such as, "Suggest inns related to travel destinations shared on social media." It can also suggest inns related to events users have shown interest in on social media. For example, it can make suggestions such as, "Suggest inns related to events users have shown interest in on social media." Furthermore, it can analyze the content of users' social media posts and suggest relevant inns. For example, it can make suggestions such as, "Suggest relevant inns based on the content of social media posts." The Inn Recommendation Department can incorporate AI processing, using AI to analyze users' social media activity and suggest the most suitable inn. For example, it can use users' social media activity as input to generate the optimal inn using AI. This allows it to suggest relevant inns by analyzing users' social media activity.

[0124] The access suggestion unit estimates the user's emotions and adjusts the suggested access methods based on those emotions. For example, if the user wants to relax, the access suggestion unit will prioritize suggesting relaxing access methods. For instance, it might suggest "prioritizing relaxing express trains." If the user is in a hurry, the access suggestion unit will prioritize suggesting fast access methods. For example, it might suggest "prioritizing fast Shinkansen (bullet train) for users in a hurry." If the user wants to enjoy the scenery, the access suggestion unit will prioritize suggesting scenic access methods. For example, it might suggest "prioritizing express trains that take scenic routes." 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. This allows for the suggestion of more appropriate access methods by adjusting the suggested access methods based on the user's emotions.

[0125] The access suggestion unit optimizes the suggestion algorithm by referring to past suggestion results. For example, the access suggestion unit prioritizes suggesting access methods that match the user's preferences based on past suggestion results. For instance, the access suggestion unit can optimize a suggestion algorithm that prioritizes suggesting access methods preferred by the user from among previously suggested access methods. The access suggestion unit also analyzes past suggestion results and improves the suggestion algorithm. For example, the access suggestion unit can optimize a suggestion algorithm that adjusts the parameters of the suggestion algorithm based on past suggestion results. Furthermore, the access suggestion unit predicts user preferences based on past suggestion results and suggests access methods. For example, the access suggestion unit can optimize a suggestion algorithm that predicts user preferences based on past suggestion results and suggests access methods. The access suggestion unit can include AI processing and use AI to analyze past suggestion results and optimize the suggestion algorithm. For example, the access suggestion unit can take past suggestion results as input and have a generation AI generate the optimal suggestion algorithm. This allows the suggestion algorithm to be optimized by referring to past suggestion results.

[0126] The access suggestion unit customizes access methods based on the user's current lifestyle and areas of interest. For example, it can customize access methods according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize an access method that allows for relaxation based on the user's current work workload. The access suggestion unit also customizes access methods based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize an access method that follows a scenic route related to the user's hobbies. Furthermore, the access suggestion unit customizes access methods according to the user's current health and physical condition. For example, it can customize an access method that is not strenuous based on the user's current health. The access suggestion unit can include AI processing, using AI to analyze the user's current lifestyle and areas of interest and customize the optimal access method. For example, the access suggestion unit can take the user's current lifestyle and areas of interest as input and have the AI ​​generate the optimal access method. This allows us to suggest more appropriate access methods by customizing access methods based on the user's current lifestyle and areas of interest.

[0127] The access suggestion unit estimates the user's emotions and prioritizes access methods based on those emotions. For example, if the user wants to relax, the access suggestion unit will prioritize suggesting relaxing access methods. For instance, it might prioritize suggesting a relaxing express train. If the user is in a hurry, the access suggestion unit will prioritize suggesting a fast access method. For example, it might prioritize suggesting a fast Shinkansen (bullet train) for users in a hurry. If the user wants to enjoy the scenery, the access suggestion unit will prioritize suggesting scenic access methods. For example, it might prioritize suggesting an express train that takes a scenic route. 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. This allows for the suggestion of more appropriate access methods by prioritizing access methods based on the user's emotions.

[0128] The access suggestion unit prioritizes suggesting the most relevant access methods, taking into account the user's geographical location. For example, it might suggest access methods close to the user's current location. It can also suggest access methods related to areas the user plans to visit. Furthermore, it might suggest access methods easily accessible from the user's current location. The access suggestion unit can incorporate AI processing, using AI to analyze the user's geographical location and suggest the optimal access method. For example, it can use the user's geographical location as input to generate the optimal access method using AI. This allows it to prioritize suggesting the most relevant access methods, taking the user's geographical location into account.

[0129] The Access Suggestion Unit analyzes the user's social media activity and proposes relevant access methods. For example, the Access Suggestion Unit can propose access methods related to travel destinations shared by the user on social media. For example, the Access Suggestion Unit can make a proposal such as, "Suggest access methods related to travel destinations shared on social media." The Access Suggestion Unit can also propose access methods related to events the user has shown interest in on social media. For example, the Access Suggestion Unit can make a proposal such as, "Suggest access methods related to events the user has shown interest in on social media." Furthermore, the Access Suggestion Unit analyzes the content of the user's social media posts and proposes relevant access methods. For example, the Access Suggestion Unit can make a proposal such as, "Suggest relevant access methods based on the content of social media posts." The Access Suggestion Unit can include AI processing and use AI to analyze the user's social media activity and propose the optimal access method. For example, the Access Suggestion Unit can take the user's social media activity as input and have a generation AI generate the optimal access method. This allows it to propose relevant access methods by analyzing the user's social media activity.

[0130] The detour suggestion unit estimates the user's emotions and adjusts the suggested detour locations based on the estimated emotions. For example, if the user wants to relax, the detour suggestion unit will prioritize suggesting relaxing detour locations. For example, the detour suggestion unit may suggest "relaxing cafes and parks as a priority." If the user wants to be active, the detour suggestion unit will prioritize suggesting detour locations that offer active activities. For example, the detour suggestion unit may suggest "sports facilities and amusement parks that offer active activities as a priority." If the user wants to spend time with family, the detour suggestion unit will prioritize suggesting family-friendly detour locations. For example, the detour suggestion unit may suggest "restaurants and tourist spots that offer family-friendly services as a priority." 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. This allows for more appropriate suggestions of detours by adjusting them based on the user's emotions.

[0131] The detour suggestion unit optimizes its suggestion algorithm by referring to past suggestion results. For example, the detour suggestion unit prioritizes suggesting detours that match the user's preferences based on past suggestion results. For instance, the detour suggestion unit can optimize its suggestion algorithm to "prioritize suggesting detours that the user preferred from among previously suggested detours." The detour suggestion unit also analyzes past suggestion results and improves its suggestion algorithm. For example, the detour suggestion unit can optimize its suggestion algorithm to "adjust the parameters of the suggestion algorithm based on past suggestion results." Furthermore, the detour suggestion unit predicts the user's preferences based on past suggestion results and suggests detours. For example, the detour suggestion unit can optimize its suggestion algorithm to "predict the user's preferences based on past suggestion results and suggest detours." The detour suggestion unit can include AI processing and use AI to analyze past suggestion results and optimize its suggestion algorithm. For example, the detour suggestion unit can take past suggestion results as input and have a generation AI generate the optimal suggestion algorithm. This allows the suggestion algorithm to be optimized by referring to past suggestion results.

[0132] The detour suggestion function customizes detour locations based on the user's current lifestyle and areas of interest. For example, it can customize detour locations according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize detour locations to include relaxing cafes and parks based on the user's current work workload. It can also customize detour locations based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize detour locations to include sports facilities and amusement parks offering relevant activities based on the user's hobbies. Furthermore, it can customize detour locations according to the user's current health and physical condition. For example, it can customize detour locations to include restaurants and tourist spots offering services that are not strenuous based on the user's current health. The detour suggestion function can include AI processing, which can be used to analyze the user's current lifestyle and areas of interest and customize the optimal detour locations. For example, the detour suggestion function can take the user's current lifestyle and areas of interest as input and have the AI ​​generate optimal detour locations. This allows for the suggestion of more appropriate detour locations by customizing them based on the user's current lifestyle and areas of interest.

[0133] The detour suggestion unit estimates the user's emotions and determines the priority of detour locations based on the estimated emotions. For example, if the user wants to relax, the detour suggestion unit will prioritize suggesting relaxing detour locations. For example, the detour suggestion unit may prioritize suggesting relaxing cafes and parks. Also, if the user wants to be active, the detour suggestion unit will prioritize suggesting detour locations that offer active activities. For example, the detour suggestion unit may prioritize suggesting sports facilities and amusement parks that offer active activities. Furthermore, if the user wants to spend time with family, the detour suggestion unit will prioritize suggesting family-friendly detour locations. For example, the detour suggestion unit may prioritize suggesting restaurants and tourist spots that offer family-friendly services. 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) and multimodal generation AI. This allows us to prioritize detours based on the user's emotions, thereby suggesting more appropriate detours.

[0134] The detour suggestion unit prioritizes suggesting highly relevant detours, taking into account the user's geographical location. For example, it might prioritize suggesting detours close to the user's current location. It can also prioritize suggesting detours related to the area the user plans to visit. Furthermore, it prioritizes suggesting detours easily accessible from the user's current location. The detour suggestion unit can incorporate AI processing, using AI to analyze the user's geographical location and suggest optimal detours. For example, it can use the user's geographical location as input to generate optimal detours using an AI. This allows the system to prioritize suggesting highly relevant detours, taking into account the user's geographical location.

[0135] The detour suggestion unit analyzes the user's social media activity and suggests relevant detours. For example, the detour suggestion unit can suggest detours related to travel destinations shared by the user on social media. For example, the detour suggestion unit can make a suggestion such as, "Suggest detours related to travel destinations shared on social media." The detour suggestion unit can also suggest detours related to events the user has shown interest in on social media. For example, the detour suggestion unit can make a suggestion such as, "Suggest detours related to events the user has shown interest in on social media." Furthermore, the detour suggestion unit analyzes the content of the user's social media posts and suggests relevant detours. For example, the detour suggestion unit can make a suggestion such as, "Suggest relevant detours based on the content of social media posts." The detour suggestion unit can include AI processing and use AI to analyze the user's social media activity and suggest the optimal detours. For example, the detour suggestion unit can take the user's social media activity as input and have the generation AI generate the optimal detours. This allows it to suggest relevant detours by analyzing the user's social media activity.

[0136] The sightseeing guide system estimates the user's emotions and adjusts the way it guides users to attractions based on those emotions. For example, if the user wants to relax, the system will prioritize guiding them to relaxing attractions. For instance, it might prioritize guiding them to relaxing parks and hot spring resorts. If the user wants to be active, the system will prioritize guiding them to attractions that offer active activities. For example, it might prioritize guiding them to sports facilities and amusement parks that offer active activities. If the user wants to spend time with their family, the system will prioritize guiding them to family-friendly attractions. For example, it might prioritize guiding them to restaurants and tourist spots that offer family-friendly services. 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) and multimodal generation AI. This allows for more appropriate sightseeing recommendations by adjusting the way attractions are presented based on the user's emotions.

[0137] The sightseeing guide unit optimizes its guidance algorithm by referring to past guidance results. For example, the sightseeing guide unit prioritizes guiding users to sightseeing spots that match their preferences based on past guidance results. For instance, the sightseeing guide unit can optimize its guidance algorithm to prioritize guiding users to sightseeing spots that they liked from those they were previously guided to. The sightseeing guide unit also analyzes past guidance results and improves its guidance algorithm. For example, the sightseeing guide unit can optimize its guidance algorithm by adjusting the parameters of the guidance algorithm based on past guidance results. Furthermore, the sightseeing guide unit predicts user preferences based on past guidance results and guides users to sightseeing spots accordingly. For example, the sightseeing guide unit can optimize its guidance algorithm by predicting user preferences based on past guidance results and guiding users to sightseeing spots accordingly. The sightseeing guide unit can include AI processing and use AI to analyze past guidance results and optimize its guidance algorithm. For example, the sightseeing guide unit can use past guidance results as input to generate an optimal guidance algorithm using a generation AI. This allows the guidance algorithm to be optimized by referring to past guidance results.

[0138] The sightseeing guide customizes sightseeing spots based on the user's current lifestyle and areas of interest. For example, it can customize sightseeing spots according to the user's current lifestyle (work workload, family structure, etc.). For instance, it can customize sightseeing spots to include relaxing parks and hot springs based on the user's current work workload. The sightseeing guide also customizes sightseeing spots based on the user's areas of interest (hobbies, themes of interest, etc.). For example, it can customize sightseeing spots to include sports facilities and amusement parks offering relevant activities based on the user's hobbies. Furthermore, the sightseeing guide customizes sightseeing spots according to the user's current health and physical condition. For example, it can customize sightseeing spots to include restaurants and tourist attractions that offer services that are not strenuous based on the user's current health. The sightseeing guide can include AI processing, which can be used to analyze the user's current lifestyle and areas of interest and customize the most suitable sightseeing spots. For example, the sightseeing guide function can use the user's current lifestyle and areas of interest as input to generate optimal sightseeing spots using an AI. This allows for more appropriate sightseeing recommendations by customizing the destinations based on the user's current lifestyle and areas of interest.

[0139] The sightseeing guide system estimates the user's emotions and prioritizes sightseeing spots based on those emotions. For example, if the user wants to relax, the system will prioritize recommending relaxing sightseeing spots. For instance, it might prioritize recommending relaxing parks and hot spring resorts. If the user wants to be active, the system will prioritize recommending sightseeing spots that offer active activities. For example, it might prioritize recommending sports facilities and amusement parks that offer active activities. If the user wants to spend time with family, the system will prioritize recommending family-friendly sightseeing spots. For example, it might prioritize recommending restaurants and tourist spots that offer family-friendly services. 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) and multimodal generation AI. This allows for prioritizing attractions based on the user's emotions, enabling the guide to more appropriate places.

[0140] The sightseeing guide section prioritizes guiding users to highly relevant sights, taking into account the user's geographical location. For example, it can prioritize guiding users to sights close to the user's current location. It can also prioritize guiding users to sights related to the region the user plans to visit. For example, it can prioritize guiding users to sights related to the region the user plans to visit. Furthermore, it can prioritize guiding users to sights easily accessible from the user's current location. For example, it can prioritize guiding users to sights easily accessible from the user's current location. The sightseeing guide section can incorporate AI processing, using AI to analyze the user's geographical location and guide users to the most suitable sights. For example, it can use the user's geographical location as input to generate the most suitable sights using an AI. This allows the system to prioritize guiding users to highly relevant sights, taking into account the user's geographical location.

[0141] The sightseeing spot guide analyzes the user's social media activity and guides them to relevant sightseeing spots. For example, the sightseeing spot guide can guide users to sightseeing spots related to travel destinations they have shared on social media. For example, the sightseeing spot guide can provide guidance such as, "We will guide you to sightseeing spots related to travel destinations you have shared on social media." The sightseeing spot guide can also guide users to sightseeing spots related to events they have shown interest in on social media. For example, the sightseeing spot guide can provide guidance such as, "We will guide you to sightseeing spots related to events you have shown interest in on social media." Furthermore, the sightseeing spot guide can analyze the content of the user's social media posts and guide them to relevant sightseeing spots. For example, the sightseeing spot guide can provide guidance such as, "We will guide you to relevant sightseeing spots based on the content of your social media posts." The sightseeing spot guide can include AI processing and use AI to analyze the user's social media activity and guide them to the most suitable sightseeing spots. For example, the sightseeing spot guide can take the user's social media activity as input and have the AI ​​generate the most suitable sightseeing spots. This allows the system to guide users to relevant sightseeing spots by analyzing the user's social media activity.

[0142] The foreign language support department estimates the user's emotions and adjusts the way information is provided to foreigners based on the estimated emotions. For example, if the user wants to relax, the foreign language support department will prioritize providing information that promotes relaxation. For instance, the foreign language support department might prioritize providing information about relaxing hot spring resorts. If the user wants to be active, the foreign language support department will prioritize providing information about active activities. For example, the foreign language support department might prioritize providing information about active activities. If the user wants to spend time with family, the foreign language support department will prioritize providing information for families. For example, the foreign language support department might prioritize providing information about restaurants and tourist spots that offer family-friendly services. 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. This allows for the provision of more appropriate information by adjusting the way information is provided to foreigners based on the user's emotions.

[0143] The foreign language support unit optimizes its response algorithm by referring to past response results. For example, the foreign language support unit prioritizes providing information that matches the user's preferences based on past response results. For instance, the foreign language support unit can optimize its response algorithm to "prioritize providing information that the user preferred from the information provided in the past." The foreign language support unit also analyzes past response results and improves its response algorithm. For example, the foreign language support unit can optimize its response algorithm to "adjust the parameters of the response algorithm based on past response results." Furthermore, the foreign language support unit predicts user preferences based on past response results and provides information accordingly. For example, the foreign language support unit can optimize its response algorithm to "predict user preferences based on past response results and provide information accordingly." The foreign language support unit can include AI processing and use AI to analyze past response results and optimize the response algorithm. For example, the foreign language support unit can use past response results as input to have a generation AI generate the optimal response algorithm. This allows the response algorithm to be optimized by referring to past response results.

[0144] The foreign language support unit customizes information based on the user's current living situation and areas of interest. For example, it can customize information according to the user's current living situation (work workload, family structure, etc.). For instance, it can customize information to provide relaxation based on the user's current work workload. The foreign language support unit also customizes information based on the user's areas of interest (hobbies, topics of interest, etc.). For example, it can customize information to provide information on relevant activities based on the user's hobbies. Furthermore, the foreign language support unit customizes information according to the user's current health and physical condition. For example, it can customize information to provide services that are suitable for the user based on their current health condition. The foreign language support unit can include AI processing, using AI to analyze the user's current living situation and areas of interest and customize the most appropriate information. For example, the foreign language support unit can take the user's current living situation and areas of interest as input and have the AI ​​generate the most appropriate information. This allows for the provision of more appropriate information by customizing information based on the user's current living situation and areas of interest.

[0145] The foreign language support department estimates the user's emotions and determines the priority of information provision based on the estimated emotions. For example, if the user wants to relax, the foreign language support department will prioritize providing information that promotes relaxation. For example, the foreign language support department may prioritize providing information on relaxing hot spring resorts. Also, if the user wants to be active, the foreign language support department will prioritize providing information on active activities. For example, the foreign language support department may prioritize providing information on active activities. Furthermore, if the user wants to spend time with family, the foreign language support department will prioritize providing information for families. For example, the foreign language support department may prioritize providing information on restaurants and tourist spots that offer family-friendly services. 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. This allows for the provision of more appropriate information by prioritizing information provision based on the user's emotions.

[0146] The foreign user support unit prioritizes providing highly relevant information, taking into account the user's geographical location. For example, it prioritizes providing information close to the user's current location. For instance, it can provide information such as "prioritizing information on tourist spots near the user's current location." It also prioritizes providing information about areas the user plans to visit. For example, it can provide information such as "prioritizing information on tourist spots in areas the user plans to visit." Furthermore, it prioritizes providing information easily accessible from the user's current location. For instance, it can provide information such as "prioritizing information on tourist spots easily accessible from the user's current location." The foreign user support unit can incorporate AI processing, using AI to analyze the user's geographical location and provide optimal information. For example, it can use the user's geographical location as input to generate optimal information using AI. This allows it to prioritize providing highly relevant information, taking into account the user's geographical location.

[0147] The foreign user support department analyzes users' social media activity and provides relevant information. For example, it can provide information about travel destinations shared by users on social media. For example, it can provide information such as "providing information about travel destinations shared on social media." The foreign user support department can also provide information about events that users have shown interest in on social media. For example, it can provide information such as "providing information about events that users have shown interest in on social media." The foreign user support department also analyzes the content of users' social media posts and provides relevant information. For example, it can provide information such as "providing relevant information based on the content of social media posts." The foreign user support department can include AI processing and use AI to analyze users' social media activity and provide optimal information. For example, the foreign user support department can take users' social media activity as input and have the AI ​​generate optimal information. This allows it to provide relevant information by analyzing users' social media activity.

[0148] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0149] The selection unit can estimate the user's emotions and adjust the plan selection criteria based on those emotions. For example, if the user wants to relax, the selection unit can prioritize selecting plans that promote relaxation. Specifically, the selection unit can select plans for relaxing hot spring resorts. Also, if the user wants to be active, the selection unit can prioritize selecting active plans. For example, the selection unit can select plans for active tourist destinations. Furthermore, if the user wants to spend time with family, the selection unit can prioritize selecting family-friendly plans. For example, the selection unit can select plans for inns that offer family-friendly services. In this way, by adjusting the plan selection criteria based on the user's emotions, a more appropriate plan can be selected.

[0150] The service provider can estimate the user's emotions and adjust the way the plan is delivered based on those emotions. For example, if the user is relaxed, the service provider can deliver the plan at a leisurely pace. Specifically, the service provider can deliver a relaxing hot spring resort plan at a relaxed pace. Also, if the user is in a hurry, the service provider can deliver the plan quickly. For example, the service provider can deliver a plan quickly to a user who is in a hurry. Furthermore, if the user is excited, the service provider can deliver the plan in a visually stimulating way. For example, the service provider can deliver a plan in a visually stimulating way to an excited user. In this way, by adjusting the way the plan is delivered based on the user's emotions, a more appropriate plan can be delivered.

[0151] The redesign unit can estimate the user's emotions and adjust the redesign criteria based on those emotions. For example, if the user wants to relax, the redesign unit can prioritize redesigning plans that promote relaxation. Specifically, the redesign unit can prioritize redesigning plans for relaxing hot spring resorts. Also, if the user wants to be active, the redesign unit can prioritize redesigning plans for active activities. For example, the redesign unit can prioritize redesigning plans for active tourist destinations. Furthermore, if the user wants to spend time with family, the redesign unit can prioritize redesigning plans for families. For example, the redesign unit can prioritize redesigning plans for inns that offer family-friendly services. In this way, by adjusting the redesign criteria based on the user's emotions, a more appropriate plan can be redesigned.

[0152] The interview function can estimate the user's emotions and adjust the content and timing of questions based on those estimations. For example, if the user is stressed, the frequency of questions can be reduced and questions can be kept concise. Specifically, the interview function can ask simple questions such as, "What is your budget?" Conversely, if the user is relaxed, detailed questions can be asked to delve deeper into their preferences. For example, the interview function can ask detailed questions such as, "Where would you like to go?" or "How are you feeling right now?" Furthermore, if the user is in a hurry, important questions can be prioritized to quickly gather information. For example, the interview function can prioritize important questions such as, "What is your budget?" or "Where would you like to go?" By adjusting the content and timing of questions based on the user's emotions, more appropriate questions can be asked.

[0153] The selection unit can estimate the user's emotions and determine the priority of plans based on those emotions. For example, if the user wants to relax, it can prioritize plans that promote relaxation. Specifically, the selection unit can prioritize plans for relaxing hot spring resorts. Also, if the user wants to be active, it can prioritize active plans. For example, the selection unit can prioritize plans for active tourist destinations. Furthermore, if the user wants to spend time with family, it can prioritize plans suitable for families. For example, the selection unit can prioritize plans for inns that offer family-friendly services. In this way, by prioritizing plans based on the user's emotions, it is possible to provide more appropriate plans.

[0154] The service provider can optimize its service provision algorithm by referring to past service provision results. For example, it can prioritize selecting service provision methods that match user preferences based on past service provision results. Specifically, the service provider can prioritize selecting service provision methods preferred by users from among the plans provided in the past. Furthermore, the service provider can analyze past service provision results and improve its service provision algorithm. For example, the service provider can adjust the parameters of the service provision algorithm based on past service provision results. In addition, the service provider can predict user preferences based on past service provision results and provide plans accordingly. For example, the service provider can predict user preferences based on past service provision results and provide plans accordingly. This allows the service provider to optimize its service provision algorithm by referring to past service provision results.

[0155] The interviewing team can analyze a user's past travel history and select the most appropriate questions. For example, it can ask relevant questions based on places the user has visited in the past. Specifically, the interviewing team can ask questions such as, "What hot spring resorts have you visited in the past?" The interviewing team can also analyze the user's preferences from their past travel history and ask questions based on those preferences. For example, the interviewing team can ask questions such as, "What was your favorite place you've visited in the past?" Furthermore, the interviewing team can ask relevant questions based on the modes of transportation and accommodations the user has used in the past. For example, the interviewing team can ask questions such as, "What modes of transportation have you used in the past?" and "What accommodations have you stayed at in the past?" In this way, by analyzing the user's past travel history, the team can select the most appropriate questions.

[0156] The selection unit can optimize its selection algorithm by referring to past selection results. For example, it can prioritize selecting plans that match the user's preferences based on past selection results. Specifically, the selection unit can prioritize selecting plans that users preferred from among those previously selected. Furthermore, the selection unit can analyze past selection results and improve its selection algorithm. For example, it can adjust the parameters of the selection algorithm based on past selection results. In addition, the selection unit can predict user preferences and select plans based on past selection results. For example, it can predict user preferences and select plans based on past selection results. In this way, the selection algorithm can be optimized by referring to past selection results.

[0157] The service provider can customize plans based on the user's current lifestyle and areas of interest. For example, they can customize plans according to the user's current lifestyle (work workload, family structure, etc.). Specifically, they can customize a relaxing plan based on the user's current work workload. They can also customize plans based on the user's areas of interest (hobbies, topics of interest, etc.). For example, they can customize a plan to include relevant tourist destinations based on the user's hobbies. Furthermore, they can customize plans according to the user's current health and physical condition. For example, they can customize a plan that is not strenuous based on the user's current health condition. By customizing plans based on the user's current lifestyle and areas of interest, they can provide more appropriate plans.

[0158] The redesign unit can prioritize highly relevant redesigns by taking the user's geographical location into consideration. For example, it can prioritize redesigning plans that include tourist destinations close to the user's current location. Specifically, the redesign unit can prioritize redesigning plans that include tourist destinations close to the user's current location. Furthermore, the redesign unit can prioritize redesigning plans that relate to areas the user plans to visit. For example, the redesign unit can prioritize redesigning plans that relate to areas the user plans to visit. In addition, the redesign unit can prioritize redesigning plans that include places easily accessible from the user's current location. For example, the redesign unit can prioritize redesigning plans that include places easily accessible from the user's current location. This allows the unit to prioritize highly relevant redesigns by taking the user's geographical location into consideration.

[0159] The following briefly describes the processing flow for example form 2.

[0160] Step 1: The interviewing department gathers information from users. For example, when a user is planning a trip, they will be asked about their budget, places they want to visit, and their current mood. Specifically, they will ask questions such as, "What is your budget?", "Where do you want to go?", and "How are you feeling right now?", record the user's answers, and send them to the selection department. Step 2: The selection unit selects a plan based on the information gathered by the interviewing unit. For example, it proposes a hotel that fits the user's budget, access methods, and places to stop along the way. The selection unit can include AI processing, using AI to analyze the user's information and select the optimal plan. Step 3: The delivery unit provides the plan selected by the selection unit. For example, it presents the selected plan to the user and provides detailed information. The delivery unit may include AI processing and use AI to provide the user with the most suitable information. Step 4: The redesign department redesigns the plan based on the plan provided by the delivery department. For example, if the user is not satisfied with the plan provided, the department redesigns the plan. The redesign department may include AI processing, using AI to analyze user feedback and redesign the optimal plan.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the hearing unit, selection unit, provision unit, and revision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the hearing unit is implemented by the control unit 46A of the smart device 14 and hears information from the user. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects a plan based on the information heard. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the selected plan to the user. The revision unit is implemented by the specific processing unit 290 of the data processing unit 12 and re-formulates the plan based on the provided plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0165] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] Each of the multiple elements described above, including the hearing unit, selection unit, provision unit, and revision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the hearing unit is implemented by the control unit 46A of the smart glasses 214 and hears information from the user. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects a plan based on the information heard. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the selected plan to the user. The revision unit is implemented by the specific processing unit 290 of the data processing unit 12 and re-formulates the plan based on the provided plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0181] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.).

[0193] 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.

[0194] 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.

[0195] 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.

[0196] Each of the multiple elements described above, including the hearing unit, selection unit, provision unit, and revision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the hearing unit is implemented by the control unit 46A of the headset terminal 314 and hears information from the user. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects a plan based on the information heard. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the selected plan to the user. The revision unit is implemented by the specific processing unit 290 of the data processing unit 12 and re-formulates the plan based on the provided plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0197] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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).

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] Each of the multiple elements described above, including the hearing unit, selection unit, provision unit, and revision unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the hearing unit is implemented by the control unit 46A of the robot 414 and hears information from the user. The selection unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and selects a plan based on the information heard. The provision unit is implemented by, for example, the control unit 46A of the robot 414 and provides the selected plan to the user. The revision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and re-formulates the plan based on the provided plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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."

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] (Note 1) The interviewing department gathers information from users, A selection unit selects a plan based on the information gathered by the aforementioned hearing unit, A provisioning unit that provides the plan selected by the aforementioned selection unit, The system comprises a re-formulation unit that re-forms the plan based on the plan provided by the aforementioned provision unit. A system characterized by the following features. (Note 2) The aforementioned selection unit is We have a hotel proposal department that suggests hotels that fit your budget. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned selection unit is It includes an access suggestion unit that proposes access methods. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned selection unit is It includes a section that suggests places to stop along the way. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, It has a sightseeing guide department that provides information on festivals and scenic spots in various regions of Japan. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, It has a department that provides information in English to foreign tourists. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned hearing section is, The system estimates the user's emotions and adjusts the content and timing of questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned hearing section is, Analyze the user's past travel history to select the most appropriate questions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned hearing section is, Customize questions based on the user's current life situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned hearing section is, The system estimates the user's emotions and prioritizes questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned hearing section is, We prioritize asking relevant questions by taking the user's geographical location into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned hearing section is, Analyze users' social media activity and ask relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned selection unit is We estimate user sentiment and adjust the plan selection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned selection unit is Optimize the selection algorithm by referring to past selection results. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned selection unit is Customize the plan based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned selection unit is It estimates user sentiment and determines plan priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned selection unit is The system prioritizes selecting the most relevant plans by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned selection unit is Analyze users' social media activity and select relevant plans. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, It estimates the user's emotions and adjusts how the plan is delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, Optimize the delivery algorithm by referring to past delivery results. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, Customize the plan based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates the user's emotions and determines the order in which plans are offered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, We prioritize providing the most relevant plans by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, We analyze users' social media activity and provide relevant plans. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned revision department, We estimate user sentiment and adjust the redefinition criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned revision department, Optimize the redesign algorithm by referring to past redesign results. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned revision department, Customize the formulation based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned revision department, We estimate user sentiment and determine redesign priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned revision department, Prioritize highly relevant revisions, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned revision department, Analyze users' social media activity and make relevant revisions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned hotel proposal department, The system estimates the user's emotions and adjusts the way inns are suggested based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned hotel proposal department, Refer to past proposal results to optimize the proposed algorithm. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned hotel proposal department, Customize the inn based on the user's current lifestyle and areas of interest. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned hotel proposal department, Estimate the user's emotions and determine the priority of hotels based on the estimated user emotions The system according to Appendix 2, characterized by the above (Appendix 35) The hotel recommendation department Prioritizes the recommendation of highly relevant hotels considering the user's geographical location information The system according to Appendix 2, characterized by the above (Appendix 36) The hotel recommendation department Analyzes the user's social media activities and recommends relevant hotels The system according to Appendix 2, characterized by the above (Appendix 37) The access recommendation department Estimates the user's emotions and adjusts the recommendation of access methods based on the estimated user emotions The system according to Appendix 3, characterized by the above (Appendix 38) The access recommendation department Optimizes the recommendation algorithm by referring to past recommendation results The system according to Appendix 3, characterized by the above (Appendix 39) The access recommendation department Customizes the access method based on the user's current life situation and areas of interest<​​​​​​​​​​​​​​​​​​​​​​Analyze users' social media activity and suggest relevant access methods. The system described in Appendix 3, characterized by the features described herein. (Note 43) The aforementioned detour suggestion section is, It estimates the user's emotions and adjusts suggested detours based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned detour suggestion section is, Refer to past proposal results to optimize the proposed algorithm. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned detour suggestion section is, Customize detours based on the user's current lifestyle and areas of interest. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned detour suggestion section is, The system estimates the user's emotions and prioritizes detours based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 47) The aforementioned detour suggestion section is, The system prioritizes suggesting highly relevant detours, taking into account the user's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 48) The aforementioned detour suggestion section is, Analyze users' social media activity and suggest relevant places to visit. The system described in Appendix 4, characterized by the features described herein. (Note 49) The aforementioned sightseeing information section, The system estimates the user's emotions and adjusts the way it guides users to attractions based on those emotions. The system described in Appendix 5, characterized by the features described herein. (Note 50) The aforementioned sightseeing information section, Optimize the guidance algorithm by referring to past guidance results The system according to appendix 5, characterized in that (Appendix 51) The scenic spot guidance unit Customizes scenic spots based on the user's current living situation and areas of interest The system according to appendix 5, characterized in that (Appendix 52) The scenic spot guidance unit Estimates the user's emotions and determines the priority of scenic spots based on the estimated user emotions The system according to appendix 5, characterized in that (Appendix 53) The scenic spot guidance unit Considers the user's geographical location information and preferentially guides highly relevant scenic spots The system according to appendix 5, characterized in that (Appendix 54) The scenic spot guidance unit Analyzes the user's social media activities and guides relevant scenic spots The system according to appendix 5, characterized in that (Appendix 55) The foreigner service unit Estimates the user's emotions and adjusts the information provision method for foreigners based on the estimated user emotions The system according to appendix 6, characterized in that (Appendix 56) The foreigner service unit Refers to past response results and optimizes the response algorithm The system according to appendix 6, characterized in that (Appendix 57) The foreigner service unit Customizes information based on the user's current living situation and areas of interest The system according to appendix 6, characterized in that (Appendix 58) The foreigner service unit The system estimates the user's emotions and prioritizes information provision based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 59) The aforementioned department for handling foreigners, We prioritize providing highly relevant information by taking into account the user's geographical location. The system described in Appendix 6, characterized by the features described herein. (Note 60) The aforementioned department for handling foreigners, Analyze users' social media activity and provide relevant information. The system described in Appendix 6, characterized by the features described herein. [Explanation of symbols]

[0233] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The interviewing department gathers information from users, A selection unit selects a plan based on the information gathered by the aforementioned hearing unit, A provisioning unit that provides the plan selected by the aforementioned selection unit, The system comprises a re-formulation unit that re-forms the plan based on the plan provided by the aforementioned provision unit. A system characterized by the following features.

2. The aforementioned selection unit is We have a hotel proposal department that suggests hotels that fit your budget. The system according to feature 1.

3. The aforementioned selection unit is It includes an access suggestion unit that proposes access methods. The system according to feature 1.

4. The aforementioned selection unit is It includes a section that suggests places to stop along the way. The system according to feature 1.

5. The aforementioned supply unit is, It has a sightseeing guide department that provides information on festivals and scenic spots in various regions of Japan. The system according to feature 1.

6. The aforementioned supply unit is, It has a department that provides information in English to foreign tourists. The system according to feature 1.

7. The aforementioned hearing section is, The system estimates the user's emotions and adjusts the content and timing of questions based on those estimated emotions. The system according to feature 1.

8. The aforementioned hearing section is, Analyze the user's past travel history to select the most appropriate questions. The system according to feature 1.

9. The aforementioned hearing section is, Customize questions based on the user's current life situation and areas of interest. The system according to feature 1.

10. The aforementioned hearing section is, The system estimates the user's emotions and prioritizes questions based on those estimated emotions. The system according to feature 1.

Images