System

Abstract

An object of a system according to an embodiment is to automatically generate a travel plan and provide foreign language information.SOLUTION: A system according to an embodiment includes a condition analysis unit, a plan generation unit, a re-proposal unit, and a translation unit. The condition analysis unit analyzes the conditions of the destination, the staying time, the departure time, and the home return time input by the user. The plan generation unit generates an optimal travel plan based on the condition analyzed by the condition analysis unit. The re-proposal unit re-proposes a new plan when the proposed stay time is exceeded or when the schedule is changed. The translation part analyzes the information of the Japanese site, translates it into a foreign language and provides it to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem that planning a trip is time-consuming, and obtaining information in foreign languages ​​is particularly difficult.

[0005] The system according to the embodiment aims to automatically generate travel plans and provide foreign language information. [Means for solving the problem]

[0006] The system according to the embodiment includes a condition analysis unit, a plan generation unit, a re-proposal unit, and a translation unit. The condition analysis unit analyzes the conditions of destination, stay time, departure time, and return time input by the user. The plan generation unit generates an optimal travel plan based on the conditions analyzed by the condition analysis unit. The re-proposal unit re-proposes a new plan if the proposed stay time is exceeded or if plans are changed. The translation unit analyzes information from Japanese language websites, translates it into a foreign language, and provides it to the user. [Effects of the Invention]

[0007] An embodiment of the system can automatically generate travel plans and provide foreign language information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) In the travel plan proposal system according to an embodiment of the present invention, a generation AI proposes an optimal travel plan based on conditions input by a user, and re-proposes the plan if the user exceeds the planned time or if the plan changes. This makes it easier for users to plan trips and outings, allowing them to enjoy their trips efficiently and enjoyably.

[0029] A travel plan proposal system according to an embodiment includes a condition analysis unit, a plan generation unit, a re-proposal unit, and a translation unit. The condition analysis unit analyzes conditions input by a user, such as destination, stay time, departure time, and return time. For example, the condition analysis unit analyzes the destination and stay time input by the user to generate basic data for a travel plan. The condition analysis unit analyzes conditions for generating an optimal travel plan based on the user's input data. The plan generation unit generates an optimal travel plan based on the conditions analyzed by the condition analysis unit. For example, the plan generation unit uses a generation AI to create a schedule including tourist spots, places to eat, and means of transportation. The plan generation unit can also generate a customized plan taking into account the user's preferences and past travel history. The re-proposal unit re-proposes a new plan if the proposed stay time is exceeded or the plans are changed. For example, the re-proposal unit creates a new schedule and proposes it to the user if the stay time at a tourist spot is longer than planned. The re-proposal unit can also acquire the user's location information in real time and respond immediately to an exceeded stay time or a change in plans. The translation unit analyzes information from Japanese websites, translates it into a foreign language, and provides it to users. For example, the translation unit collects data from Japanese tourist information websites and translates it into English or other languages ​​to suggest the best tourist spots for visitors to Japan. The translation unit can also improve translation accuracy by taking cultural backgrounds and nuances into account. As a result, the travel plan suggestion system according to the embodiment simplifies trip and outing planning, allowing users to enjoy their trips efficiently and enjoyably. For example, users can create an optimal schedule based on their destinations and stay time, and the system automatically re-proposes the plan if the plans change. Furthermore, the system can provide a more fulfilling travel experience for visitors to Japan by suggesting places that are only featured on Japanese websites.

[0030] The condition analysis unit can reflect the user's mood or physical condition based on data obtained from the wearable device. The condition analysis unit uses data such as heart rate, body temperature, and stress level obtained from the wearable device to allow the generation AI to suggest tourist spots and activities that are optimal for the user's physical condition. For example, if the user appears tired, it will prioritize places where they can relax. The condition analysis unit also analyzes data from the wearable device in real time to generate a plan based on the user's mood and physical condition. For example, if the user's heart rate is high, it will suggest taking a break in a quiet place. The condition analysis unit also uses data from the wearable device to suggest places to eat and means of transportation that suit the user's physical condition. For example, if the user's body temperature is high, it will suggest eating in a cool place. This makes it possible to provide an optimal travel plan based on the user's real-time mood and physical condition.

[0031] The plan generation unit can generate a customized plan based on the user's past reviews or ratings. For example, the plan generation unit analyzes reviews and ratings of places and activities the user has visited in the past and customizes a new plan based on the reviews and ratings. For example, the plan generation unit may propose a plan to revisit highly rated places. The plan generation unit may also propose similar places and activities based on the user's past reviews and ratings. For example, the plan generation unit may propose a new experience similar to an activity that the user has enjoyed in the past. The plan generation unit may also analyze the user's past reviews and ratings and customize the plan to avoid negative ratings. For example, the plan generation unit may exclude places that the user has been dissatisfied with in the past. This allows the provision of a more personalized travel plan based on the user's past reviews and ratings.

[0032] The plan generation unit can include optimal tourist spots depending on the season or weather. For example, the generation AI of the plan generation unit suggests optimal tourist spots based on seasonal and weather data. For example, it suggests cherry blossom spots in spring and beaches in summer. The plan generation unit also analyzes weather forecasts in real time and suggests indoor tourist spots when it rains. For example, it suggests art museums and shopping malls. The plan generation unit also takes seasonal events and festivals into consideration and the generation AI suggests optimal sightseeing plans. For example, it suggests autumn leaf viewing in autumn and illuminations in winter. This makes it possible to provide optimal tourist spots depending on the season and weather.

[0033] The plan generation unit can generate a plan for a group trip taking into account the preferences of the user's friends or family. For example, the plan generation unit analyzes the preferences of the user's friends and family and generates a plan that everyone in the group can enjoy based on that. For example, it suggests places to eat and activities that everyone likes. The plan generation unit also suggests tourist spots and activities that will satisfy everyone based on the group members' past travel history and ratings. For example, it suggests a plan to revisit places that everyone has given high ratings. The plan generation unit also generates a balanced plan taking into account the preferences and interests of the group members. For example, it suggests a plan that combines active activities with relaxing spots. This makes it possible to provide a group trip plan that takes into account the preferences of the user's friends and family.

[0034] The condition analysis unit can suggest optimal conditions based on past travel data for the conditions entered by the user. For example, for the destination and length of stay entered by the user, the generation AI analyzes past travel data and suggests optimal conditions. For example, it suggests destinations and lengths of stay that have been highly rated by past travelers. The condition analysis unit also suggests the optimal departure and return times for the user's conditions based on past travel data. For example, it suggests the optimal time of day to avoid crowds based on past data. The condition analysis unit also suggests optimal tourist spots and places to eat based on past travel data for the conditions entered by the user. For example, it suggests spots that have been highly rated by past travelers. This allows the generation AI to suggest optimal conditions based on past travel data for the conditions entered by the user.

[0035] The condition analysis unit can suggest the optimal time slot for the conditions entered by the user, taking into account real-time traffic information or congestion. In the condition analysis unit, for example, the generation AI analyzes real-time traffic information and suggests the optimal departure time or return time for the conditions entered by the user. For example, it suggests a time slot to avoid traffic congestion. In addition, the condition analysis unit suggests tourist spots and places to eat that are optimal for the user's conditions, taking into account real-time congestion. For example, it suggests a time slot to avoid congestion. In addition, the condition analysis unit suggests the optimal means of transportation for the user's conditions, based on real-time traffic information and congestion. For example, it suggests public transportation or taxis to avoid congestion. This makes it possible to suggest the optimal time slot, taking into account real-time traffic information and congestion.

[0036] The condition analysis unit can suggest recommended conditions based on the reviews or ratings of past travelers for the conditions entered by the user. In the condition analysis unit, for example, the generation AI analyzes the reviews and ratings of past travelers and suggests recommended destinations and lengths of stay for the conditions entered by the user. For example, it suggests highly rated destinations and lengths of stay. In addition, in the condition analysis unit, the generation AI suggests recommended departure times and return times for the conditions entered by the user based on the reviews and ratings of past travelers. For example, it suggests time periods to avoid crowds. In addition, the condition analysis unit suggests tourist spots and places to eat that are best suited to the user's conditions based on the reviews and ratings of past travelers. For example, it suggests highly rated spots and places to eat. This makes it possible to suggest recommended conditions based on the reviews and ratings of past travelers.

[0037] The condition analysis unit can propose optimal conditions for different seasons or events based on the conditions entered by the user. In the condition analysis unit, for example, the generation AI analyzes different seasons and event data to propose optimal destinations and lengths of stay for the conditions entered by the user. For example, proposals are made that take seasonal events and festivals into consideration. In addition, the condition analysis unit proposes optimal departure times and return times for different seasons and events based on the conditions entered by the user. For example, proposals are made that match the times when events are held. In addition, the condition analysis unit proposes tourist spots and places to eat that are optimal for the user's conditions based on different seasons and event data. For example, it proposes recommended spots and events for each season. This makes it possible to propose optimal conditions for different seasons and events.

[0038] The plan generation unit can reflect the user's past visit history or preferences. In the plan generation unit, for example, the generation AI analyzes the user's past visit history and suggests new tourist spots and places to eat based on that. For example, it suggests spots similar to places visited in the past. The plan generation unit also analyzes the user's preferences and suggests customized tourist spots and places to eat based on that. For example, it suggests restaurants that serve the user's favorite dishes. In addition, the plan generation unit uses the generation AI to suggest new tourist spots and places to eat based on the user's past visit history and preferences. For example, it suggests spots similar to places that the user has given high ratings in the past. This makes it possible to provide a more personalized travel plan based on the user's past visit history and preferences.

[0039] The plan generation unit can include options that take into account the user's physical strength or travel comfort. For example, the generation AI of the plan generation unit considers the user's physical strength and travel comfort and suggests the optimal means of transportation based on that. For example, it suggests a comfortable bus or taxi for long-distance travel. The plan generation unit also analyzes the user's physical strength and customizes the means of transportation based on that. For example, if the user's physical strength is low, it suggests shortening the walking distance. The generation AI of the plan generation unit also considers the user's travel comfort and suggests a comfortable means of transportation. For example, it suggests an air-conditioned vehicle or a train with reserved seats. This makes it possible to provide options that take into account the user's physical strength and travel comfort.

[0040] The plan generation unit can reflect recommendations from local people. For example, the generation AI in the plan generation unit analyzes reviews and ratings from local people and suggests tourist spots and places to eat based on that. For example, it suggests places that local people have given high ratings. The plan generation unit also collects information recommended by local people and suggests tourist spots and places to eat based on that. For example, it suggests hidden spots that locals often visit. The generation AI in the plan generation unit also reflects the opinions of local people and suggests tourist spots and places to eat. For example, it suggests restaurants and cafes recommended by local people. This makes it possible to provide travel plans that reflect the recommendations of local people.

[0041] The plan generation unit can include eco-friendly means of transportation. For example, the generation AI of the plan generation unit suggests eco-friendly means of transportation. For example, it may preferentially suggest electric bikes, bicycles, or public transportation. The plan generation unit also includes eco-friendly options in the user's means of transportation. For example, it may suggest means of transportation that reduce carbon footprints. The plan generation unit also suggests eco-friendly means of transportation and provides an environmentally friendly travel plan. For example, it may suggest electric cars or sharing services. This makes it possible to provide a travel plan that includes eco-friendly means of transportation.

[0042] The re-suggestion unit acquires the user's location information in real time and can immediately respond to an excess stay time or a change in plans. In the re-suggestion unit, for example, the generation AI acquires the user's location information in real time and can immediately respond to an excess stay time or a change in plans. For example, it proposes a new schedule if the stay time at a tourist spot becomes longer. In addition, the re-suggestion unit has the generation AI propose optimal means of transportation and routes in real time based on the user's location information. For example, it proposes new means of transportation to accommodate changes in plans. In addition, the re-suggestion unit has the generation AI analyze the user's location information and propose new tourist spots and places to eat to accommodate an excess stay time or a change in plans. For example, it proposes new spots to accommodate changes in plans. In this way, the user's location information can be acquired in real time and can immediately respond to an excess stay time or a change in plans.

[0043] The re-suggestion unit can analyze the user's current situation and make optimal re-suggestions by utilizing past data. In the re-suggestion unit, for example, the generation AI analyzes the user's current situation and makes optimal re-suggestions based on past data. For example, it proposes a new plan based on past travel history and ratings. In addition, the re-suggestion unit re-suggests optimal tourist spots and places to eat by utilizing past data based on the user's current situation. For example, it proposes a plan to revisit places that have been highly rated in the past. In addition, the re-suggestion unit can analyze the user's current situation and re-suggest optimal means of transportation and routes based on past data. For example, it proposes the optimal means of transportation from past data. In this way, the generation AI can analyze the user's current situation and make optimal re-suggestions by utilizing past data.

[0044] The re-suggestion unit can utilize real-time feedback from other travelers. In the re-suggestion unit, for example, the generation AI analyzes the real-time feedback from other travelers and proposes a new plan to accommodate changes in the user's plans. For example, it proposes new tourist spots based on the ratings of other travelers. Furthermore, the re-suggestion unit proposes optimal means of transportation and routes to accommodate changes in the user's plans based on the real-time feedback from other travelers. For example, it proposes new means of transportation based on the feedback of other travelers. Furthermore, the re-suggestion unit proposes new places to eat and activities to accommodate changes in the user's plans based on the real-time feedback of other travelers. For example, it proposes new places to eat based on the ratings of other travelers. In this way, optimal re-suggestions can be made by utilizing the real-time feedback of other travelers.

[0045] The re-proposal unit can propose a different means of transportation or route to accommodate a change in the user's plans. For example, the re-proposal unit causes the generation AI to propose a different means of transportation or route to accommodate a change in the user's plans. For example, it proposes a new public transportation or taxi to accommodate the change in plans. Furthermore, the re-proposal unit causes the generation AI to propose an optimal means of transportation or route based on the change in the user's plans. For example, it proposes a new means of transportation to accommodate the change in plans. Furthermore, the re-proposal unit causes the generation AI to propose a different means of transportation or route to accommodate a change in the user's plans. For example, it proposes a new means of transportation or route to accommodate the change in plans. This allows a different means of transportation or route to be proposed to accommodate a change in the user's plans.

[0046] The translation department analyzes information from Japanese websites and can suggest the best tourist spots for tourists visiting Japan. For example, the generation AI in the translation department analyzes tourist information from Japanese websites and suggests the best tourist spots for tourists visiting Japan. For example, it collects data from Japanese tourist information websites and translates it into English for suggestions. The translation department also analyzes information from Japanese websites and suggests recommended tourist spots for tourists visiting Japan. For example, it suggests the best spots based on Japanese reviews and ratings. The translation department also analyzes information from Japanese websites and can suggest the best tourist spots for tourists visiting Japan using the generation AI. For example, it translates tourist information from Japanese into English or other languages ​​for suggestions. This allows the information from Japanese websites to be analyzed and the best tourist spots to be suggested for tourists visiting Japan.

[0047] The translation unit can improve translation accuracy by taking cultural background or nuances into account when translating information on a Japanese website. For example, when the generation AI translates information on a Japanese website, the translation unit improves translation accuracy by taking cultural background and nuances into account. For example, it accurately translates information about Japanese culture and customs. Furthermore, when the generation AI translates information on a Japanese website, the translation unit improves translation accuracy by taking cultural background and nuances into account. For example, it accurately translates information about traditional Japanese events and festivals. Furthermore, when the generation AI translates information on a Japanese website, the translation unit improves translation accuracy by taking cultural background and nuances into account. For example, it accurately translates information about Japanese food culture and tourist spots. This allows translation accuracy to be improved by taking cultural background and nuances into account when translating information on a Japanese website.

[0048] The translation department can analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan. For example, the generation AI analyzes information from Japanese websites and provides guides in different languages ​​for tourists visiting Japan. For example, Japanese tourist information is translated into English, French, Chinese, etc. The translation department can also analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan. For example, guides are provided in multiple languages ​​based on Japanese reviews and ratings. The translation department can also analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan. For example, Japanese tourist information is translated into multiple languages. This allows the generation AI to analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan.

[0049] The translation department can analyze information from Japanese websites and suggest recommended routes or plans for tourists visiting Japan. In the translation department, for example, a generation AI analyzes information from Japanese websites and suggests recommended routes and plans for tourists visiting Japan. For example, it suggests the best route based on tourist information in Japanese. In addition, the translation department can analyze information from Japanese websites and a generation AI suggests recommended routes and plans for tourists visiting Japan. For example, it suggests the best plan based on reviews and ratings in Japanese. In addition, the translation department can analyze information from Japanese websites and suggest recommended routes and plans for tourists visiting Japan. For example, it suggests the best route or plan based on tourist information in Japanese. In this way, it can analyze information from Japanese websites and suggest recommended routes and plans for tourists visiting Japan.

[0050] The plan generation unit can include options for maximizing the comfort or efficiency of the user's travel when providing detailed means of transportation and transfer information. For example, when the generation AI provides detailed means of transportation and transfer information, the plan generation unit includes options for maximizing the comfort or efficiency of the user's travel. For example, it suggests vehicles with comfortable seats or air conditioning. The plan generation unit also takes into account the user's travel comfort and provides the optimal means of transportation and transfer information. For example, it suggests comfortable buses or taxis for long-distance travel. The plan generation unit also provides means of transportation and transfer information that include options for maximizing the efficiency of the user's travel. For example, it suggests the shortest route or a route with the fewest transfers. This makes it possible to provide options for maximizing the comfort and efficiency of the user's travel.

[0051] The plan generation unit can reflect the user's past travel history or preferences when creating a detailed schedule. For example, the generation AI in the plan generation unit analyzes the user's past travel history and creates a detailed schedule based on it. For example, it reflects means of transportation and routes used in the past. The plan generation unit also analyzes the user's preferences and creates a customized schedule based on them. For example, it suggests means of transportation and routes that the user prefers. The plan generation unit also creates a detailed schedule based on the user's past travel history and preferences. For example, it reflects means of transportation and routes that have been highly rated in the past. This makes it possible to provide a detailed schedule based on the user's past travel history and preferences.

[0052] The plan generation unit can propose an optimal route that combines different means of transportation when providing detailed information on means of transportation or transfer information. For example, when the generation AI provides detailed information on means of transportation or transfer information, the plan generation unit proposes an optimal route that combines different means of transportation. For example, it proposes a route that combines trains and buses. Furthermore, the plan generation unit proposes an optimal route that combines different means of transportation to maximize the efficiency of the user's travel. For example, it proposes a route that combines taxis and trains. Furthermore, the plan generation unit proposes an optimal route that combines different means of transportation to maximize the comfort and efficiency of the user's travel. For example, it proposes a route that combines bicycles and trains. This makes it possible to provide an optimal route that combines different means of transportation.

[0053] When creating a detailed schedule, the plan generation unit can generate a schedule for a group trip by taking into account the travel history or preferences of the user's friends or family. For example, the generation AI of the plan generation unit analyzes the travel history and preferences of the user's friends and family and generates a schedule for a group trip based on that. For example, it proposes means of transportation and routes that will satisfy everyone. The plan generation unit also considers the preferences of the user's friends and family and creates a customized schedule for the group trip by the generation AI. For example, it proposes tourist spots and activities that everyone can enjoy. The plan generation unit also generates a schedule for a group trip by taking into account the travel history and preferences of the user's friends and family. For example, it reflects means of transportation and routes that everyone has given a high rating. This makes it possible to provide a schedule for a group trip that takes into account the travel history and preferences of the user's friends and family.

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

[0055] The plan generation unit can generate a customized travel plan by taking into account the user's past travel history and preferences. For example, it can analyze reviews and ratings of places and activities the user has visited in the past and customize a new plan based on them. It can also suggest plans to revisit highly rated places. It can also suggest similar places and activities based on the user's past reviews and ratings. It can suggest new experiences similar to activities that the user has enjoyed in the past. It can also analyze the user's past reviews and ratings and customize the plan to avoid negative ratings. By excluding places that the user has previously dissatisfied with, it can provide a more personalized travel plan.

[0056] The condition analysis unit can suggest optimal conditions based on past travel data for the conditions entered by the user. For example, the generation AI analyzes past travel data and suggests optimal conditions for the destination and length of stay entered by the user. It can suggest destinations and lengths of stay that have been highly rated by past travelers. The generation AI can also suggest departure and return times that are optimal for the user's conditions based on past travel data. It can also suggest optimal times to avoid crowds based on past data. Furthermore, the generation AI can suggest optimal tourist spots and places to eat for the conditions entered by the user based on past travel data. By suggesting spots that have been highly rated by past travelers, it can suggest optimal conditions for the conditions entered by the user based on past travel data.

[0057] The plan generation unit can include optimal tourist spots depending on the season or weather. For example, the generation AI can suggest optimal tourist spots based on season and weather data. It can suggest cherry blossom viewing spots in spring and beaches in summer. It can also analyze weather forecasts in real time and suggest indoor tourist spots when it rains. It can suggest museums and shopping malls. Furthermore, the generation AI can suggest optimal sightseeing plans taking into account seasonal events and festivals. By suggesting autumn leaf viewing in autumn and illuminations in winter, it can provide optimal tourist spots depending on the season and weather.

[0058] The plan generation unit can generate a plan for a group trip taking into account the preferences of the user's friends or family. For example, it can analyze the preferences of the user's friends and family and generate a plan that everyone in the group can enjoy based on that. It can suggest restaurants and activities that everyone likes. It can also suggest tourist spots and activities that everyone will enjoy based on the group members' past travel history and ratings. It can suggest a plan to revisit places that everyone has given high ratings to. It can also generate a balanced plan taking into account the preferences and interests of the group members. By proposing a plan that combines active activities and relaxing spots, it is possible to provide a group trip plan that takes into account the preferences of the user's friends and family.

[0059] The condition analysis unit can suggest the optimal time slot for the conditions entered by the user, taking into account real-time traffic information or congestion. For example, the generation AI analyzes real-time traffic information and suggests the optimal departure and return times for the conditions entered by the user. It can suggest time slots to avoid traffic congestion. The generation AI can also suggest tourist spots and places to eat that are best suited to the user's conditions, taking into account real-time congestion. It can also suggest time slots to avoid congestion. Furthermore, the generation AI can suggest the optimal means of transportation for the user's conditions, based on real-time traffic information and congestion. By suggesting public transportation or taxis that will avoid congestion, it can suggest the optimal time slot, taking into account real-time traffic information and congestion.

[0060] The re-suggestion unit acquires the user's location information in real time and can respond immediately to an excess stay time or a change in plans. For example, the generation AI acquires the user's location information in real time and responds immediately to an excess stay time or a change in plans. A new schedule can be proposed if the stay time at a tourist spot becomes longer. The generation AI can also propose the optimal means of transportation and route in real time based on the user's location information. A new means of transportation can be proposed to accommodate changes in plans. Furthermore, the generation AI can analyze the user's location information and suggest new tourist spots or places to eat to accommodate an excess stay time or a change in plans. By suggesting new spots to accommodate changes in plans, the generation AI can acquire the user's location information in real time and respond immediately to an excess stay time or a change in plans.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The condition analysis unit analyzes the conditions entered by the user, such as destination, stay time, departure time, and return time. For example, the condition analysis unit analyzes the destination and stay time entered by the user and generates basic data for a travel plan. The condition analysis unit also analyzes the conditions for generating an optimal travel plan based on the data entered by the user. Step 2: The plan generation unit generates an optimal travel plan based on the conditions analyzed by the condition analysis unit. For example, the plan generation unit uses generation AI to create a schedule that includes tourist attractions, places to eat, and means of transportation. The plan generation unit can also generate customized plans that take into account the user's preferences and past travel history. Step 3: The re-proposal unit re-proposes a new plan if the proposed stay time is exceeded or the plans are changed. For example, if the stay time at a tourist spot is longer than planned, the re-proposal unit creates a new schedule and proposes it to the user. The re-proposal unit can also obtain the user's location information in real time and respond immediately to the stay time being exceeded or the plans being changed. Step 4: The translation department analyzes the information on the Japanese website, translates it into a foreign language, and provides it to users. For example, the translation department collects data from a Japanese tourist information website and translates it into English or other languages ​​to suggest the best tourist spots for visitors to Japan. The translation department can also improve the accuracy of the translation by taking cultural backgrounds and nuances into account.

[0063] (Example 2) In the travel plan proposal system according to an embodiment of the present invention, a generation AI proposes an optimal travel plan based on conditions input by a user, and re-proposes the plan if the user exceeds the planned time or if the plan changes. This makes it easier for users to plan trips and outings, allowing them to enjoy their trips efficiently and enjoyably.

[0064] A travel plan proposal system according to an embodiment includes a condition analysis unit, a plan generation unit, a re-proposal unit, and a translation unit. The condition analysis unit analyzes conditions input by a user, such as destination, stay time, departure time, and return time. For example, the condition analysis unit analyzes the destination and stay time input by the user to generate basic data for a travel plan. The condition analysis unit analyzes conditions for generating an optimal travel plan based on the user's input data. The plan generation unit generates an optimal travel plan based on the conditions analyzed by the condition analysis unit. For example, the plan generation unit uses a generation AI to create a schedule including tourist spots, places to eat, and means of transportation. The plan generation unit can also generate a customized plan taking into account the user's preferences and past travel history. The re-proposal unit re-proposes a new plan if the proposed stay time is exceeded or the plans are changed. For example, the re-proposal unit creates a new schedule and proposes it to the user if the stay time at a tourist spot is longer than planned. The re-proposal unit can also acquire the user's location information in real time and respond immediately to an exceeded stay time or a change in plans. The translation unit analyzes information from Japanese websites, translates it into a foreign language, and provides it to users. For example, the translation unit collects data from Japanese tourist information websites and translates it into English or other languages ​​to suggest the best tourist spots for visitors to Japan. The translation unit can also improve translation accuracy by taking cultural backgrounds and nuances into account. As a result, the travel plan suggestion system according to the embodiment simplifies trip and outing planning, allowing users to enjoy their trips efficiently and enjoyably. For example, users can create an optimal schedule based on their destinations and stay time, and the system automatically re-proposes the plan if the plans change. Furthermore, the system can provide a more fulfilling travel experience for visitors to Japan by suggesting places that are only featured on Japanese websites.

[0065] The condition analysis unit can reflect the user's mood or physical condition based on data obtained from the wearable device. The condition analysis unit uses data such as heart rate, body temperature, and stress level obtained from the wearable device to allow the generation AI to suggest tourist spots and activities that are optimal for the user's physical condition. For example, if the user appears tired, it will prioritize places where they can relax. The condition analysis unit also analyzes data from the wearable device in real time to generate a plan based on the user's mood and physical condition. For example, if the user's heart rate is high, it will suggest taking a break in a quiet place. The condition analysis unit also uses data from the wearable device to suggest places to eat and means of transportation that suit the user's physical condition. For example, if the user's body temperature is high, it will suggest eating in a cool place. This makes it possible to provide an optimal travel plan based on the user's real-time mood and physical condition.

[0066] The plan generation unit can generate a customized plan based on the user's past reviews or ratings. For example, the plan generation unit analyzes reviews and ratings of places and activities the user has visited in the past and customizes a new plan based on the reviews and ratings. For example, the plan generation unit may propose a plan to revisit highly rated places. The plan generation unit may also propose similar places and activities based on the user's past reviews and ratings. For example, the plan generation unit may propose a new experience similar to an activity that the user has enjoyed in the past. The plan generation unit may also analyze the user's past reviews and ratings and customize the plan to avoid negative ratings. For example, the plan generation unit may exclude places that the user has been dissatisfied with in the past. This allows the provision of a more personalized travel plan based on the user's past reviews and ratings.

[0067] The plan generation unit can use the emotion estimation function to suggest relaxing spots or activities that match the user's emotional state. For example, the plan generation unit uses the emotion estimation function to analyze the user's emotional state in real time and suggest relaxing spots and activities. For example, if the user is highly stressed, the plan generation unit suggests a spa or hot spring. The plan generation unit also suggests places where the user can enjoy relaxing music and scenery based on the user's emotional state. For example, if the user is emotionally unstable, the plan generation unit suggests a walk in nature. The plan generation unit also uses the emotion estimation function to suggest relaxation activities that match the user's emotional state. For example, if the user is feeling depressed, the plan generation unit suggests yoga or meditation. This makes it possible to provide relaxing spots and activities that match the user's emotional state.

[0068] The plan generation unit can include optimal tourist spots depending on the season or weather. For example, the generation AI of the plan generation unit suggests optimal tourist spots based on seasonal and weather data. For example, it suggests cherry blossom spots in spring and beaches in summer. The plan generation unit also analyzes weather forecasts in real time and suggests indoor tourist spots when it rains. For example, it suggests art museums and shopping malls. The plan generation unit also takes seasonal events and festivals into consideration and the generation AI suggests optimal sightseeing plans. For example, it suggests autumn leaf viewing in autumn and illuminations in winter. This makes it possible to provide optimal tourist spots depending on the season and weather.

[0069] The plan generation unit can generate a plan for a group trip taking into account the preferences of the user's friends or family. For example, the plan generation unit analyzes the preferences of the user's friends and family and generates a plan that everyone in the group can enjoy based on that. For example, it suggests places to eat and activities that everyone likes. The plan generation unit also suggests tourist spots and activities that will satisfy everyone based on the group members' past travel history and ratings. For example, it suggests a plan to revisit places that everyone has given high ratings. The plan generation unit also generates a balanced plan taking into account the preferences and interests of the group members. For example, it suggests a plan that combines active activities with relaxing spots. This makes it possible to provide a group trip plan that takes into account the preferences of the user's friends and family.

[0070] The plan generation unit can use the emotion estimation function to suggest relaxation spots for reducing stress felt by the user during the trip. For example, the plan generation unit uses the emotion estimation function to analyze the stress felt by the user during the trip in real time and suggest relaxation spots. For example, if stress is high, the plan generation unit suggests a spa or hot spring. The plan generation unit also suggests relaxing walks or picnics in nature based on the user's emotional state. For example, if the user is emotionally unstable, the plan generation unit suggests a park or forest. The plan generation unit also uses the emotion estimation function to suggest relaxation activities for reducing stress felt by the user during the trip. For example, yoga or meditation is suggested. This makes it possible to provide relaxation spots for reducing stress felt by the user during the trip.

[0071] The condition analysis unit can suggest optimal conditions based on past travel data for the conditions entered by the user. For example, for the destination and length of stay entered by the user, the generation AI analyzes past travel data and suggests optimal conditions. For example, it suggests destinations and lengths of stay that have been highly rated by past travelers. The condition analysis unit also suggests the optimal departure and return times for the user's conditions based on past travel data. For example, it suggests the optimal time of day to avoid crowds based on past data. The condition analysis unit also suggests optimal tourist spots and places to eat based on past travel data for the conditions entered by the user. For example, it suggests spots that have been highly rated by past travelers. This allows the generation AI to suggest optimal conditions based on past travel data for the conditions entered by the user.

[0072] The condition analysis unit can suggest the optimal time slot for the conditions entered by the user, taking into account real-time traffic information or congestion. In the condition analysis unit, for example, the generation AI analyzes real-time traffic information and suggests the optimal departure time or return time for the conditions entered by the user. For example, it suggests a time slot to avoid traffic congestion. In addition, the condition analysis unit suggests tourist spots and places to eat that are optimal for the user's conditions, taking into account real-time congestion. For example, it suggests a time slot to avoid congestion. In addition, the condition analysis unit suggests the optimal means of transportation for the user's conditions, based on real-time traffic information and congestion. For example, it suggests public transportation or taxis to avoid congestion. This makes it possible to suggest the optimal time slot, taking into account real-time traffic information and congestion.

[0073] The condition analysis unit can use the emotion estimation function to suggest a relaxing destination or length of stay based on the user's current emotional state. The condition analysis unit, for example, uses the emotion estimation function to analyze the user's current emotional state and suggest a relaxing destination or length of stay. For example, if stress is high, it suggests staying in nature. The condition analysis unit also suggests relaxing tourist spots and activities based on the user's emotional state. For example, if the user is emotionally unstable, it suggests staying in a quiet place. The condition analysis unit also uses the emotion estimation function to suggest relaxing places to eat and means of transportation based on the user's current emotional state. For example, if the user is feeling depressed, it suggests a comfortable means of transportation. In this way, it is possible to suggest a relaxing destination or length of stay based on the user's current emotional state.

[0074] The condition analysis unit can suggest recommended conditions based on the reviews or ratings of past travelers for the conditions entered by the user. In the condition analysis unit, for example, the generation AI analyzes the reviews and ratings of past travelers and suggests recommended destinations and lengths of stay for the conditions entered by the user. For example, it suggests highly rated destinations and lengths of stay. In addition, in the condition analysis unit, the generation AI suggests recommended departure times and return times for the conditions entered by the user based on the reviews and ratings of past travelers. For example, it suggests time periods to avoid crowds. In addition, the condition analysis unit suggests tourist spots and places to eat that are best suited to the user's conditions based on the reviews and ratings of past travelers. For example, it suggests highly rated spots and places to eat. This makes it possible to suggest recommended conditions based on the reviews and ratings of past travelers.

[0075] The condition analysis unit can propose optimal conditions for different seasons or events based on the conditions entered by the user. In the condition analysis unit, for example, the generation AI analyzes different seasons and event data to propose optimal destinations and lengths of stay for the conditions entered by the user. For example, proposals are made that take seasonal events and festivals into consideration. In addition, the condition analysis unit proposes optimal departure times and return times for different seasons and events based on the conditions entered by the user. For example, proposals are made that match the times when events are held. In addition, the condition analysis unit proposes tourist spots and places to eat that are optimal for the user's conditions based on different seasons and event data. For example, it proposes recommended spots and events for each season. This makes it possible to propose optimal conditions for different seasons and events.

[0076] The condition analysis unit can use the emotion estimation function to suggest destinations or durations of stay that will maximize the enjoyment the user feels during the trip. For example, the condition analysis unit uses the emotion estimation function to analyze the user's emotional state and suggest destinations and durations of stay that will maximize the enjoyment the user feels during the trip. For example, it suggests places where positive emotions are strong. The condition analysis unit also suggests tourist spots and activities that will maximize enjoyment based on the user's emotional state. For example, it suggests active activities when the user is emotionally excited. The condition analysis unit also uses the emotion estimation function to suggest places to eat and means of transportation that will maximize enjoyment based on the user's emotional state. For example, it suggests special places to eat when the user is emotionally excited. This makes it possible to suggest destinations and durations of stay that will maximize the enjoyment the user feels during the trip.

[0077] The plan generation unit can reflect the user's past visit history or preferences. In the plan generation unit, for example, the generation AI analyzes the user's past visit history and suggests new tourist spots and places to eat based on that. For example, it suggests spots similar to places visited in the past. The plan generation unit also analyzes the user's preferences and suggests customized tourist spots and places to eat based on that. For example, it suggests restaurants that serve the user's favorite dishes. In addition, the plan generation unit uses the generation AI to suggest new tourist spots and places to eat based on the user's past visit history and preferences. For example, it suggests spots similar to places that the user has given high ratings in the past. This makes it possible to provide a more personalized travel plan based on the user's past visit history and preferences.

[0078] The plan generation unit can include options that take into account the user's physical strength or travel comfort. For example, the generation AI of the plan generation unit considers the user's physical strength and travel comfort and suggests the optimal means of transportation based on that. For example, it suggests a comfortable bus or taxi for long-distance travel. The plan generation unit also analyzes the user's physical strength and customizes the means of transportation based on that. For example, if the user's physical strength is low, it suggests shortening the walking distance. The generation AI of the plan generation unit also considers the user's travel comfort and suggests a comfortable means of transportation. For example, it suggests an air-conditioned vehicle or a train with reserved seats. This makes it possible to provide options that take into account the user's physical strength and travel comfort.

[0079] The plan generation unit can use the emotion estimation function to suggest spots that maximize emotional satisfaction at places the user visits. For example, the plan generation unit uses the emotion estimation function to analyze the user's emotional state and suggest spots that maximize emotional satisfaction at places the user visits. For example, it suggests places where positive emotions are strong. The plan generation unit also suggests tourist spots and activities that maximize emotional satisfaction based on the user's emotional state. For example, it suggests active activities when the user is emotionally excited. The plan generation unit also uses the emotion estimation function to suggest places to eat and means of transportation that maximize emotional satisfaction based on the user's emotional state. For example, it suggests special places to eat when the user is emotionally excited. This makes it possible to provide spots that maximize emotional satisfaction at places the user visits.

[0080] The plan generation unit can reflect recommendations from local people. For example, the generation AI in the plan generation unit analyzes reviews and ratings from local people and suggests tourist spots and places to eat based on that. For example, it suggests places that local people have given high ratings. The plan generation unit also collects information recommended by local people and suggests tourist spots and places to eat based on that. For example, it suggests hidden spots that locals often visit. The generation AI in the plan generation unit also reflects the opinions of local people and suggests tourist spots and places to eat. For example, it suggests restaurants and cafes recommended by local people. This makes it possible to provide travel plans that reflect the recommendations of local people.

[0081] The plan generation unit can include eco-friendly means of transportation. For example, the generation AI of the plan generation unit suggests eco-friendly means of transportation. For example, it may preferentially suggest electric bikes, bicycles, or public transportation. The plan generation unit also includes eco-friendly options in the user's means of transportation. For example, it may suggest means of transportation that reduce carbon footprints. The plan generation unit also suggests eco-friendly means of transportation and provides an environmentally friendly travel plan. For example, it may suggest electric cars or sharing services. This makes it possible to provide a travel plan that includes eco-friendly means of transportation.

[0082] The plan generation unit can use the emotion estimation function to suggest activities that maximize the excitement or enjoyment the user feels during the trip. For example, the plan generation unit uses the emotion estimation function to analyze the user's emotional state and suggest activities that maximize the excitement and enjoyment the user feels during the trip. For example, if the user is emotionally excited, the plan generation unit suggests active activities. The plan generation unit also suggests tourist spots and activities that maximize excitement and enjoyment based on the user's emotional state. For example, if the user is emotionally excited, the plan generation unit suggests adventure activities. The plan generation unit also uses the emotion estimation function to suggest places to eat and means of transportation that maximize excitement and enjoyment based on the user's emotional state. For example, if the user is emotionally excited, the plan generation unit suggests special places to eat. This makes it possible to provide activities that maximize the excitement and enjoyment the user feels during the trip.

[0083] The re-suggestion unit acquires the user's location information in real time and can immediately respond to an excess stay time or a change in plans. In the re-suggestion unit, for example, the generation AI acquires the user's location information in real time and can immediately respond to an excess stay time or a change in plans. For example, it proposes a new schedule if the stay time at a tourist spot becomes longer. In addition, the re-suggestion unit has the generation AI propose optimal means of transportation and routes in real time based on the user's location information. For example, it proposes new means of transportation to accommodate changes in plans. In addition, the re-suggestion unit has the generation AI analyze the user's location information and propose new tourist spots and places to eat to accommodate an excess stay time or a change in plans. For example, it proposes new spots to accommodate changes in plans. In this way, the user's location information can be acquired in real time and can immediately respond to an excess stay time or a change in plans.

[0084] The re-suggestion unit can analyze the user's current situation and make optimal re-suggestions by utilizing past data. In the re-suggestion unit, for example, the generation AI analyzes the user's current situation and makes optimal re-suggestions based on past data. For example, it proposes a new plan based on past travel history and ratings. In addition, the re-suggestion unit re-suggests optimal tourist spots and places to eat by utilizing past data based on the user's current situation. For example, it proposes a plan to revisit places that have been highly rated in the past. In addition, the re-suggestion unit can analyze the user's current situation and re-suggest optimal means of transportation and routes based on past data. For example, it proposes the optimal means of transportation from past data. In this way, the generation AI can analyze the user's current situation and make optimal re-suggestions by utilizing past data.

[0085] The re-suggestion unit can use the emotion estimation function to make optimal re-suggestions according to the user's emotional state. The re-suggestion unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and make optimal re-suggestions. For example, if the user is emotionally unstable, the re-suggestion unit re-suggests relaxing spots. The re-suggestion unit also re-suggests tourist spots and activities to maximize emotional satisfaction based on the user's emotional state. For example, if the user is emotionally excited, the re-suggestion unit re-suggests active activities. The re-suggestion unit also uses the emotion estimation function to re-suggest optimal places to eat and means of transportation based on the user's emotional state. For example, if the user is emotionally depressed, the re-suggestion unit re-suggests comfortable means of transportation. This makes it possible to make optimal re-suggestions according to the user's emotional state.

[0086] The re-suggestion unit can utilize real-time feedback from other travelers. In the re-suggestion unit, for example, the generation AI analyzes the real-time feedback from other travelers and proposes a new plan to accommodate changes in the user's plans. For example, it proposes new tourist spots based on the ratings of other travelers. Furthermore, the re-suggestion unit proposes optimal means of transportation and routes to accommodate changes in the user's plans based on the real-time feedback from other travelers. For example, it proposes new means of transportation based on the feedback of other travelers. Furthermore, the re-suggestion unit proposes new places to eat and activities to accommodate changes in the user's plans based on the real-time feedback of other travelers. For example, it proposes new places to eat based on the ratings of other travelers. In this way, optimal re-suggestions can be made by utilizing the real-time feedback of other travelers.

[0087] The re-proposal unit can propose a different means of transportation or route to accommodate a change in the user's plans. For example, the re-proposal unit causes the generation AI to propose a different means of transportation or route to accommodate a change in the user's plans. For example, it proposes a new public transportation or taxi to accommodate the change in plans. Furthermore, the re-proposal unit causes the generation AI to propose an optimal means of transportation or route based on the change in the user's plans. For example, it proposes a new means of transportation to accommodate the change in plans. Furthermore, the re-proposal unit causes the generation AI to propose a different means of transportation or route to accommodate a change in the user's plans. For example, it proposes a new means of transportation or route to accommodate the change in plans. This allows a different means of transportation or route to be proposed to accommodate a change in the user's plans.

[0088] The re-suggestion unit can use the emotion estimation function to make re-suggestions to reduce the stress the user feels due to the plan change. For example, the re-suggestion unit uses the emotion estimation function to analyze the user's emotional state in real time and make re-suggestions to reduce the stress the user feels due to the plan change. For example, if the user is highly stressed, the re-suggestion unit re-suggests relaxing spots. The re-suggestion unit also re-suggests tourist spots and activities to reduce stress based on the user's emotional state. For example, if the user is emotionally unstable, the re-suggestion unit re-suggests staying in a quiet place. The re-suggestion unit also uses the emotion estimation function to re-suggest places to eat and means of transportation to reduce stress based on the user's emotional state. For example, if the user is feeling depressed, the re-suggestion unit re-suggests comfortable means of transportation. In this way, re-suggestions can be made to reduce the stress the user feels due to the plan change.

[0089] The translation department analyzes information from Japanese websites and can suggest the best tourist spots for tourists visiting Japan. For example, the generation AI in the translation department analyzes tourist information from Japanese websites and suggests the best tourist spots for tourists visiting Japan. For example, it collects data from Japanese tourist information websites and translates it into English for suggestions. The translation department also analyzes information from Japanese websites and suggests recommended tourist spots for tourists visiting Japan. For example, it suggests the best spots based on Japanese reviews and ratings. The translation department also analyzes information from Japanese websites and can suggest the best tourist spots for tourists visiting Japan using the generation AI. For example, it translates tourist information from Japanese into English or other languages ​​for suggestions. This allows the information from Japanese websites to be analyzed and the best tourist spots to be suggested for tourists visiting Japan.

[0090] The translation unit can improve translation accuracy by taking cultural background or nuances into account when translating information on a Japanese website. For example, when the generation AI translates information on a Japanese website, the translation unit improves translation accuracy by taking cultural background and nuances into account. For example, it accurately translates information about Japanese culture and customs. Furthermore, when the generation AI translates information on a Japanese website, the translation unit improves translation accuracy by taking cultural background and nuances into account. For example, it accurately translates information about traditional Japanese events and festivals. Furthermore, when the generation AI translates information on a Japanese website, the translation unit improves translation accuracy by taking cultural background and nuances into account. For example, it accurately translates information about Japanese food culture and tourist spots. This allows translation accuracy to be improved by taking cultural background and nuances into account when translating information on a Japanese website.

[0091] The translation unit can use the emotion estimation function to suggest spots that will maximize emotional satisfaction at places visited by tourists visiting Japan. For example, the translation unit uses the emotion estimation function to analyze the emotional state of tourists visiting Japan and suggest spots that will maximize emotional satisfaction at places visited. For example, it suggests places where positive emotions are strong. The translation unit also suggests tourist spots and activities that will maximize emotional satisfaction based on the emotional state of tourists visiting Japan. For example, it suggests active activities if the emotions are high. The translation unit also uses the emotion estimation function to suggest places to eat and means of transportation that will maximize emotional satisfaction based on the emotional state of tourists visiting Japan. For example, it suggests special places to eat if the emotions are high. This makes it possible to provide spots that will maximize emotional satisfaction at places visited by tourists visiting Japan.

[0092] The translation department can analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan. For example, the generation AI analyzes information from Japanese websites and provides guides in different languages ​​for tourists visiting Japan. For example, Japanese tourist information is translated into English, French, Chinese, etc. The translation department can also analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan. For example, guides are provided in multiple languages ​​based on Japanese reviews and ratings. The translation department can also analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan. For example, Japanese tourist information is translated into multiple languages. This allows the generation AI to analyze information from Japanese websites and provide guides in different languages ​​for tourists visiting Japan.

[0093] The translation department can analyze information from Japanese websites and suggest recommended routes or plans for tourists visiting Japan. In the translation department, for example, a generation AI analyzes information from Japanese websites and suggests recommended routes and plans for tourists visiting Japan. For example, it suggests the best route based on tourist information in Japanese. In addition, the translation department can analyze information from Japanese websites and a generation AI suggests recommended routes and plans for tourists visiting Japan. For example, it suggests the best plan based on reviews and ratings in Japanese. In addition, the translation department can analyze information from Japanese websites and suggest recommended routes and plans for tourists visiting Japan. For example, it suggests the best route or plan based on tourist information in Japanese. In this way, it can analyze information from Japanese websites and suggest recommended routes and plans for tourists visiting Japan.

[0094] The translation unit can use the emotion estimation function to suggest activities that will maximize the enjoyment that visitors to Japan feel during their trip. For example, the translation unit uses the emotion estimation function to analyze the emotional state of visitors to Japan and suggest activities that will maximize the enjoyment that visitors to Japan feel during their trip. For example, if the visitors are emotionally excited, the translation unit suggests active activities. The translation unit also suggests tourist spots and activities that will maximize enjoyment based on the emotional state of the visitors to Japan. For example, if the visitors are emotionally excited, the translation unit suggests adventure activities. The translation unit also uses the emotion estimation function to suggest places to eat and means of transportation that will maximize enjoyment based on the emotional state of the visitors to Japan. For example, if the visitors are emotional, the translation unit suggests special places to eat. This makes it possible to provide activities that will maximize the enjoyment that visitors to Japan feel during their trip.

[0095] The plan generation unit can include options for maximizing the comfort or efficiency of the user's travel when providing detailed means of transportation and transfer information. For example, when the generation AI provides detailed means of transportation and transfer information, the plan generation unit includes options for maximizing the comfort or efficiency of the user's travel. For example, it suggests vehicles with comfortable seats or air conditioning. The plan generation unit also takes into account the user's travel comfort and provides the optimal means of transportation and transfer information. For example, it suggests comfortable buses or taxis for long-distance travel. The plan generation unit also provides means of transportation and transfer information that include options for maximizing the efficiency of the user's travel. For example, it suggests the shortest route or a route with the fewest transfers. This makes it possible to provide options for maximizing the comfort and efficiency of the user's travel.

[0096] The plan generation unit can reflect the user's past travel history or preferences when creating a detailed schedule. For example, the generation AI in the plan generation unit analyzes the user's past travel history and creates a detailed schedule based on it. For example, it reflects means of transportation and routes used in the past. The plan generation unit also analyzes the user's preferences and creates a customized schedule based on them. For example, it suggests means of transportation and routes that the user prefers. The plan generation unit also creates a detailed schedule based on the user's past travel history and preferences. For example, it reflects means of transportation and routes that have been highly rated in the past. This makes it possible to provide a detailed schedule based on the user's past travel history and preferences.

[0097] The plan generation unit can use the emotion estimation function to propose a schedule for reducing stress felt by the user while traveling. The plan generation unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and propose a schedule for reducing stress felt by the user while traveling. For example, if stress is high, the plan generation unit proposes a means of transportation that allows relaxation. The plan generation unit also proposes a means of transportation and a route for reducing stress based on the user's emotional state. For example, if the user is emotionally unstable, the plan generation unit proposes a comfortable means of transportation. The plan generation unit also uses the emotion estimation function to propose a schedule for reducing stress based on the user's emotional state. For example, if the user is feeling depressed, the plan generation unit proposes a comfortable means of transportation. In this way, a schedule for reducing stress felt by the user while traveling can be provided.

[0098] The plan generation unit can propose an optimal route that combines different means of transportation when providing detailed information on means of transportation or transfer information. For example, when the generation AI provides detailed information on means of transportation or transfer information, the plan generation unit proposes an optimal route that combines different means of transportation. For example, it proposes a route that combines trains and buses. Furthermore, the plan generation unit proposes an optimal route that combines different means of transportation to maximize the efficiency of the user's travel. For example, it proposes a route that combines taxis and trains. Furthermore, the plan generation unit proposes an optimal route that combines different means of transportation to maximize the comfort and efficiency of the user's travel. For example, it proposes a route that combines bicycles and trains. This makes it possible to provide an optimal route that combines different means of transportation.

[0099] When creating a detailed schedule, the plan generation unit can generate a schedule for a group trip by taking into account the travel history or preferences of the user's friends or family. For example, the generation AI of the plan generation unit analyzes the travel history and preferences of the user's friends and family and generates a schedule for a group trip based on that. For example, it proposes means of transportation and routes that will satisfy everyone. The plan generation unit also considers the preferences of the user's friends and family and creates a customized schedule for the group trip by the generation AI. For example, it proposes tourist spots and activities that everyone can enjoy. The plan generation unit also generates a schedule for a group trip by taking into account the travel history and preferences of the user's friends and family. For example, it reflects means of transportation and routes that everyone has given a high rating. This makes it possible to provide a schedule for a group trip that takes into account the travel history and preferences of the user's friends and family.

[0100] The plan generation unit can use the emotion estimation function to propose a route that maximizes the enjoyment the user feels while traveling. The plan generation unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and propose a route that maximizes the enjoyment the user feels while traveling. For example, if the user is emotionally excited, the plan generation unit proposes a scenic route. The plan generation unit also proposes a means of transportation and a route that maximizes the enjoyment based on the user's emotional state. For example, if the user is emotionally excited, the plan generation unit proposes a special means of transportation. The plan generation unit also uses the emotion estimation function to propose a route that maximizes the enjoyment based on the user's emotional state. For example, if the user is emotionally excited, the plan generation unit proposes a special means of transportation. In this way, a route that maximizes the enjoyment the user feels while traveling can be provided.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The plan generation unit can generate a customized travel plan by taking into account the user's past travel history and preferences. For example, it can analyze reviews and ratings of places and activities the user has visited in the past and customize a new plan based on them. It can also suggest plans to revisit highly rated places. It can also suggest similar places and activities based on the user's past reviews and ratings. It can suggest new experiences similar to activities that the user has enjoyed in the past. It can also analyze the user's past reviews and ratings and customize the plan to avoid negative ratings. By excluding places that the user has previously dissatisfied with, it can provide a more personalized travel plan.

[0103] The condition analysis unit can suggest optimal conditions based on past travel data for the conditions entered by the user. For example, the generation AI analyzes past travel data and suggests optimal conditions for the destination and length of stay entered by the user. It can suggest destinations and lengths of stay that have been highly rated by past travelers. The generation AI can also suggest departure and return times that are optimal for the user's conditions based on past travel data. It can also suggest optimal times to avoid crowds based on past data. Furthermore, the generation AI can suggest optimal tourist spots and places to eat for the conditions entered by the user based on past travel data. By suggesting spots that have been highly rated by past travelers, it can suggest optimal conditions for the conditions entered by the user based on past travel data.

[0104] The plan generation unit can use the emotion estimation function to suggest relaxing spots or activities according to the user's emotional state. For example, the emotion estimation function can be used to analyze the user's emotional state in real time and suggest relaxing spots and activities. If the user is highly stressed, a spa or hot spring can be suggested. It is also possible to suggest places where the user can enjoy relaxing music and scenery based on the user's emotional state. If the user is emotionally unstable, a walk in nature can be suggested. Furthermore, the emotion estimation function can also be used to suggest relaxation activities according to the user's emotional state. If the user is feeling depressed, yoga or meditation can be suggested, thereby providing relaxing spots and activities according to the user's emotional state.

[0105] The plan generation unit can include optimal tourist spots depending on the season or weather. For example, the generation AI can suggest optimal tourist spots based on season and weather data. It can suggest cherry blossom viewing spots in spring and beaches in summer. It can also analyze weather forecasts in real time and suggest indoor tourist spots when it rains. It can suggest museums and shopping malls. Furthermore, the generation AI can suggest optimal sightseeing plans taking into account seasonal events and festivals. By suggesting autumn leaf viewing in autumn and illuminations in winter, it can provide optimal tourist spots depending on the season and weather.

[0106] The plan generation unit can generate a plan for a group trip taking into account the preferences of the user's friends or family. For example, it can analyze the preferences of the user's friends and family and generate a plan that everyone in the group can enjoy based on that. It can suggest restaurants and activities that everyone likes. It can also suggest tourist spots and activities that everyone will enjoy based on the group members' past travel history and ratings. It can suggest a plan to revisit places that everyone has given high ratings to. It can also generate a balanced plan taking into account the preferences and interests of the group members. By proposing a plan that combines active activities and relaxing spots, it is possible to provide a group trip plan that takes into account the preferences of the user's friends and family.

[0107] The plan generation unit can use the emotion estimation function to suggest relaxation spots to help the user reduce stress felt during the trip. For example, the emotion estimation function can be used to analyze the stress felt by the user during the trip in real time and suggest relaxation spots. If stress is high, a spa or hot spring can be suggested. It is also possible to suggest a relaxing walk or picnic in nature based on the user's emotional state. If emotions are unstable, a park or forest can be suggested. Furthermore, the emotion estimation function can also be used to suggest relaxation activities to help the user reduce stress felt during the trip. By suggesting yoga or meditation, a relaxation spot can be provided to help the user reduce stress felt during the trip.

[0108] The condition analysis unit can suggest the optimal time slot for the conditions entered by the user, taking into account real-time traffic information or congestion. For example, the generation AI analyzes real-time traffic information and suggests the optimal departure and return times for the conditions entered by the user. It can suggest time slots to avoid traffic congestion. The generation AI can also suggest tourist spots and places to eat that are best suited to the user's conditions, taking into account real-time congestion. It can also suggest time slots to avoid congestion. Furthermore, the generation AI can suggest the optimal means of transportation for the user's conditions, based on real-time traffic information and congestion. By suggesting public transportation or taxis that will avoid congestion, it can suggest the optimal time slot, taking into account real-time traffic information and congestion.

[0109] The condition analysis unit can use the emotion estimation function to suggest a relaxing destination or length of stay based on the user's current emotional state. For example, the emotion estimation function can be used to analyze the user's current emotional state and suggest a relaxing destination or length of stay. If the user is highly stressed, a stay in nature can be suggested. It is also possible to suggest relaxing tourist spots and activities based on the user's emotional state. If the user is emotionally unstable, a stay in a quiet place can be suggested. Furthermore, the emotion estimation function can also be used to suggest relaxing places to eat and means of transportation based on the user's current emotional state. If the user is feeling depressed, a comfortable means of transportation can be suggested, thereby suggesting a relaxing destination or length of stay based on the user's current emotional state.

[0110] The re-suggestion unit acquires the user's location information in real time and can respond immediately to an excess stay time or a change in plans. For example, the generation AI acquires the user's location information in real time and responds immediately to an excess stay time or a change in plans. A new schedule can be proposed if the stay time at a tourist spot becomes longer. The generation AI can also propose the optimal means of transportation and route in real time based on the user's location information. A new means of transportation can be proposed to accommodate changes in plans. Furthermore, the generation AI can analyze the user's location information and suggest new tourist spots or places to eat to accommodate an excess stay time or a change in plans. By suggesting new spots to accommodate changes in plans, the generation AI can acquire the user's location information in real time and respond immediately to an excess stay time or a change in plans.

[0111] The re-suggestion unit can use the emotion estimation function to make optimal re-suggestions based on the user's emotional state. For example, the emotion estimation function can be used to analyze the user's emotional state in real time and make optimal re-suggestions. If the user is emotionally unstable, it can re-suggest relaxing spots. It is also possible to re-suggest tourist spots and activities that maximize emotional satisfaction based on the user's emotional state. If the user is emotionally excited, it can re-suggest active activities. Furthermore, the emotion estimation function can also be used to re-suggest optimal places to eat and means of transportation based on the user's emotional state. If the user is emotionally depressed, it can re-suggest comfortable means of transportation, thereby making optimal re-suggestions based on the user's emotional state.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The condition analysis unit analyzes the conditions entered by the user, such as destination, stay time, departure time, and return time. For example, the condition analysis unit analyzes the destination and stay time entered by the user and generates basic data for a travel plan. The condition analysis unit also analyzes the conditions for generating an optimal travel plan based on the data entered by the user. Step 2: The plan generation unit generates an optimal travel plan based on the conditions analyzed by the condition analysis unit. For example, the plan generation unit uses generation AI to create a schedule that includes tourist attractions, places to eat, and means of transportation. The plan generation unit can also generate customized plans that take into account the user's preferences and past travel history. Step 3: The re-proposal unit re-proposes a new plan if the proposed stay time is exceeded or the plans are changed. For example, if the stay time at a tourist spot is longer than planned, the re-proposal unit creates a new schedule and proposes it to the user. The re-proposal unit can also obtain the user's location information in real time and respond immediately to the stay time being exceeded or the plans being changed. Step 4: The translation department analyzes the information on the Japanese website, translates it into a foreign language, and provides it to users. For example, the translation department collects data from a Japanese tourist information website and translates it into English or other languages ​​to suggest the best tourist spots for visitors to Japan. The translation department can also improve the accuracy of the translation by taking cultural backgrounds and nuances into account.

[0114] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0133] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0134] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0141] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0143] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0158] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0166] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0171] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0172] 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.

[0173] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0174] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0175] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0176] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0179] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a condition analysis unit that analyzes conditions input by a user, such as destination, stay time, departure time, and return time; a plan generation unit that generates an optimal travel plan based on the conditions analyzed by the condition analysis unit; a re-proposal unit that re-proposes a new plan if the proposed stay time is exceeded or the plan is changed; A translation unit analyzes information on the Japanese site, translates it into a foreign language, and provides it to users. A system characterized by:

2. The condition analysis unit Reflecting the user's mood or physical condition based on data obtained from wearable devices 2. The system of claim 1.

3. The plan generation unit Generate customized plans based on users' past reviews or ratings 2. The system of claim 1.

4. The plan generation unit Suggest relaxing spots or activities based on the user's emotional state 2. The system of claim 1.

5. The plan generation unit Include the best attractions depending on the season or weather 2. The system of claim 1.

Images