System

Abstract

An object of a system according to an embodiment is for a user to make an optimal going-out plan while avoiding congestion.SOLUTION: A system according to an embodiment includes a user information acquisition unit, a course generation unit, and a proposal unit. The user information acquisition unit acquires information on a user. The course generation section generates a going-out course based on the information acquired by the user information acquisition section. The suggestion unit suggests the going-out course generated by the course generation unit 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 made it difficult for users to plan optimal outings while avoiding crowds, and it has been time-consuming to obtain information on local congestion and hidden spots.

[0005] The system according to the embodiment aims to enable users to make optimal outing plans while avoiding crowds. [Means for solving the problem]

[0006] The system according to the embodiment includes a user information acquisition unit, a course generation unit, and a suggestion unit. The user information acquisition unit acquires user information. The course generation unit generates an outing course based on the information acquired by the user information acquisition unit. The suggestion unit suggests the outing course generated by the course generation unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment allows the user to make optimal outing plans while avoiding crowds. [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) The outing advisor app according to an embodiment of the present invention is a system that uses a generation AI to propose optimal outing plans to users. This system acquires user information, and the generation AI generates and proposes optimal routes. This allows the outing advisor app to propose optimal outing plans to users.

[0029] The outing advisor app according to the embodiment includes a user information acquisition unit, a course generation unit, and a suggestion unit. The user information acquisition unit acquires user information. For example, the user information acquisition unit acquires user location information. The user information acquisition unit can also acquire the user's interests and past activity history. The user information acquisition unit can also acquire the user's health data. For example, the user information acquisition unit acquires the user's location information using GPS data. The user's interests and past activity history are acquired by analyzing the user's past visited places and activity patterns. The health data can be acquired from a fitness tracker or a smartwatch. The course generation unit generates an outing course based on the information acquired by the user information acquisition unit. For example, the course generation unit uses a generation AI to generate an optimal course based on the user's location information and interests. The course generation unit can also use the generation AI to generate an optimal course based on the user's past activity history and health data. The course generation unit can also use the generation AI to generate an optimal course taking real-time traffic and weather information into consideration. For example, the generation AI can suggest tourist attractions and restaurants near the user's current location based on the user's location information. The generation AI generates a course that includes spots that the user likes based on the user's interests and past behavior history. The generation AI suggests an optimal route that avoids traffic jams based on real-time traffic information. The generation AI suggests spots that are suitable for the weather based on weather information. The suggestion unit suggests the outing course generated by the course generation unit to the user. For example, the suggestion unit displays the course generated by the generation AI on the user's smartphone. The suggestion unit can also notify the user of the course generated by the generation AI. The suggestion unit can also add the course generated by the generation AI to the user's calendar. For example, the suggestion unit displays the course generated by the generation AI on the app interface. The suggestion unit notifies the user of the course generated by the generation AI via a push notification. The suggestion unit automatically adds the course generated by the generation AI to the user's calendar app. In this way, the outing advisor app according to the embodiment can suggest the optimal outing plan to the user.For example, users can check the best route through the app and enjoy a smooth outing. Users can receive the best route in real time using the app's notification function. Users can check the route added to the calendar app and make plans.

[0030] The user information acquisition unit can analyze the user's past movement history and suggest a course based on the user's preferences and behavioral patterns. For example, the user information acquisition unit uses a generation AI to analyze the user's past movement history and identify the user's preferences based on frequently visited places and the length of time spent there. For example, the unit suggests a course that includes similar places based on data on cafes and parks visited in the past. The user information acquisition unit can also analyze the user's movement history to determine trends in visits during specific seasons and times of day, and suggest optimal courses based on these patterns. For example, a spring cherry blossom viewing course can be suggested for a user who frequently visits cherry blossom viewing spots in the spring. The user information acquisition unit can also identify places the user tends to avoid based on the movement history and suggest a course that takes these into consideration. For example, for a user who has tended to avoid crowds in the past, a course that includes less crowded times and places can be suggested. This makes it possible to suggest courses based on the user's preferences and behavioral patterns.

[0031] The course generation unit can monitor traffic conditions in real time and dynamically recalculate the optimal route based on congestion and accident information. For example, the generation AI of the course generation unit monitors traffic conditions in real time and proposes the optimal route based on congestion and accident information. For example, it dynamically calculates an alternative route to avoid roads with congestion. The course generation unit also obtains traffic information in real time and proposes the shortest route from the user's current location to the destination. For example, if an accident occurs, it immediately reflects that information and proposes a new route. The generation AI of the course generation unit also monitors changes in traffic conditions in real time and recalculates the optimal route while the user is traveling. For example, if congestion occurs along the way, it proposes a new route on the spot. This makes it possible to monitor traffic conditions in real time and dynamically recalculate the optimal route.

[0032] The user information acquisition unit can analyze the user's health data and suggest courses that suit the user's health condition. For example, the generation AI in the user information acquisition unit analyzes the user's step count data and suggests courses that ensure a moderate amount of exercise. For example, a walking course is suggested for a user who does not usually take many steps. The user information acquisition unit also suggests courses that suit the user's health condition based on the user's heart rate data. For example, if the heart rate is high, a course that includes places to relax is suggested. The user information acquisition unit also analyzes the health data and suggests courses that include activities that are optimal for the user's health condition. For example, a hiking or cycling course is suggested for a user who is not getting enough exercise. This makes it possible to suggest courses that suit the user's health condition.

[0033] The user information acquisition unit can analyze the user's past reviews and ratings and suggest a course that prioritizes highly rated spots. For example, the generation AI in the user information acquisition unit analyzes the user's past reviews and ratings and suggests a course that prioritizes highly rated spots. For example, it suggests a course that includes restaurants and tourist spots that have been highly rated in the past. The user information acquisition unit also identifies highly rated spots based on the user's review history and suggests a course that includes them. For example, it analyzes the ratings of places visited in the past and suggests a course that includes spots with similar ratings. The user information acquisition unit also analyzes the user's rating data and suggests a course that prioritizes highly rated spots. For example, it suggests a course that includes highly rated spots in the same area based on spots that the user has highly rated. This makes it possible to suggest a course that includes highly rated spots based on the user's past reviews and ratings.

[0034] The user information acquisition unit can analyze a user's SNS posts, understand their interests, and make customized suggestions. For example, the generation AI in the user information acquisition unit analyzes a user's SNS posts, understands their interests, and makes customized suggestions. For example, for a user who posts frequently about travel, the unit can suggest travel destinations. The user information acquisition unit can also identify interests in specific themes or topics based on the user's SNS posts and make suggestions based on those interests. For example, for a user who posts frequently about food, the unit can suggest restaurants. The user information acquisition unit can also analyze a user's SNS posts, understand their interests, and make customized suggestions. For example, for a user who posts frequently about outdoor activities, the unit can suggest hiking and camping. This allows the generation AI to understand a user's interests based on the user's SNS posts and make customized suggestions.

[0035] The user information acquisition unit can analyze the user's purchasing history and make suggestions based on the purchased products and services. For example, the generation AI in the user information acquisition unit analyzes the user's purchasing history and makes suggestions based on the purchased products and services. For example, outdoor activities are suggested for a user who purchases a lot of outdoor equipment. The user information acquisition unit also makes suggestions regarding products and services in specific categories based on the user's purchasing history. For example, bookstores and libraries are suggested for a user who purchases a lot of books. The user information acquisition unit also analyzes the user's purchasing history and makes suggestions based on the purchased products and services. For example, health-related spots are suggested for a user who purchases a lot of health foods. This makes it possible to make suggestions based on the user's purchasing history.

[0036] The user information acquisition unit can analyze the user's music playlist and suggest spots that match the user's preferred music genre. For example, the generation AI in the user information acquisition unit analyzes the user's music playlist and suggests spots that match the user's preferred music genre. For example, for a user who likes jazz, it suggests jazz bars and live music venues. The user information acquisition unit also suggests spots related to specific music genres based on the user's music playlist. For example, for a user who likes classical music, it suggests concert halls and opera houses. The user information acquisition unit also analyzes the user's music playlist and suggests spots that match the user's preferred music genre. For example, for a user who likes rock, it suggests rock festivals and live music venues. In this way, it is possible to suggest spots that match the user's preferred music genre based on the user's music playlist.

[0037] The user information acquisition unit can analyze the user's reading history and suggest places related to books in the user's favorite genre. For example, the generation AI in the user information acquisition unit analyzes the user's reading history and suggests places related to books in the user's favorite genre. For example, for a user who likes mystery novels, mystery events and related tourist spots are suggested. The user information acquisition unit also suggests places related to a specific genre based on the user's reading history. For example, for a user who likes historical novels, historical tourist spots and museums are suggested. The user information acquisition unit also analyzes the user's reading history and suggests places related to books in the user's favorite genre. For example, for a user who likes fantasy novels, fantasy events and related tourist spots are suggested. In this way, places related to books in the user's favorite genre can be suggested based on the user's reading history.

[0038] The suggestion unit uses the generation AI to analyze social media posts and identify highly rated spots that are not generally known. For example, the suggestion unit analyzes social media posts using the generation AI to identify highly rated spots that are not generally known. For example, the suggestion unit suggests hidden attractions based on specific hashtags or keywords. The suggestion unit also analyzes user ratings and comments based on social media posts to identify highly rated spots. For example, the suggestion unit analyzes the content of word-of-mouth and reviews to suggest highly rated spots. The suggestion unit also analyzes social media data using the generation AI to identify highly rated spots that are not generally known. For example, the suggestion unit analyzes posts related to a specific region or theme to suggest hidden attractions. This makes it possible to identify highly rated spots that are not generally known based on social media posts.

[0039] The suggestion unit can use the generation AI to analyze local blogs and forums and identify spots only locals know about. For example, the suggestion unit can analyze local blogs and forums to identify spots only locals know about. For example, based on information posted by locals, the suggestion unit can suggest spots that are not listed in tourist guides. The suggestion unit can also identify and suggest spots recommended by locals based on posts on local blogs and forums. For example, the suggestion unit can analyze information on local events and shops to suggest hidden attractions. The suggestion unit can also analyze local blogs and forums to identify spots only locals know about. For example, based on information shared by locals, the suggestion unit can suggest spots that are not known to tourists. This makes it possible to identify spots only locals know about based on local blogs and forums.

[0040] The suggestion unit can use the generation AI to suggest hidden spots along a specific theme based on the user's hobbies and interests. For example, the generation AI analyzes the user's hobbies and interests to suggest hidden spots along a specific theme. For example, for a user who is interested in art, it suggests hidden galleries and art events. The suggestion unit also suggests hidden spots related to a specific theme based on the user's hobbies and interests. For example, for a user who likes outdoor activities, it suggests hidden hiking trails and campsites. The suggestion unit also analyzes the user's hobbies and interests to suggest hidden spots along a specific theme. For example, for a user who is interested in history, it suggests hidden historical places and museums. In this way, it is possible to suggest hidden spots along a specific theme based on the user's hobbies and interests.

[0041] The suggestion unit uses the generation AI to consider seasonal and event information and suggest spots that can only be enjoyed at specific times. For example, the generation AI analyzes seasonal and event information and suggests spots that can only be enjoyed at specific times. For example, during cherry blossom season, it suggests cherry blossom viewing spots. The suggestion unit also suggests spots that can be enjoyed at specific times based on seasonal and event information. For example, during summer festival season, it suggests local festivals and events. The suggestion unit also analyzes seasonal and event information and suggests spots that can only be enjoyed at specific times. For example, during autumn foliage season, it suggests places with beautiful autumn leaves. This makes it possible to suggest spots that can only be enjoyed at specific times based on seasonal and event information.

[0042] The route generation unit can provide a more accurate congestion forecast by combining past congestion data with real-time location information. For example, the generation AI of the route generation unit combines past congestion data with real-time location information to provide a more accurate congestion forecast. For example, based on past data, it predicts the congestion level for a specific time period or day of the week. The route generation unit also provides a congestion forecast for a specific location based on past congestion data and real-time location information. For example, based on current location information, it suggests the least crowded time period. The route generation unit also provides a more accurate congestion forecast by combining past congestion data with real-time location information. For example, based on past data, it predicts the congestion level for a specific event or season. In this way, by combining past congestion data with real-time location information, it is possible to provide a more accurate congestion forecast.

[0043] The course generation unit can analyze weather data and predict the impact of congestion due to changes in weather. For example, the generation AI of the course generation unit analyzes weather data and predicts the impact of congestion due to changes in weather. For example, it predicts that indoor facilities tend to be crowded on rainy days and suggests empty outdoor spots. The course generation unit also provides a congestion forecast under specific weather conditions based on the weather data. For example, it predicts that tourist spots tend to be crowded on sunny days and suggests empty time periods. The generation AI of the course generation unit also analyzes weather data and predicts the impact of congestion due to changes in weather. For example, it predicts congestion conditions under extreme weather conditions such as typhoons and heavy snow and suggests places to avoid. This makes it possible to predict the impact of congestion due to changes in weather based on weather data.

[0044] The course generation unit can analyze congestion data from different regions and countries and provide a congestion forecast from a global perspective. For example, the generation AI in the course generation unit analyzes congestion data from different regions and countries and provides a congestion forecast from a global perspective. For example, the congestion situation at a specific tourist destination is predicted based on international data. The course generation unit also provides a congestion forecast for a specific location based on congestion data from different regions and countries. For example, it provides a congestion forecast that takes into account the impact of international events and holidays. The course generation unit also analyzes congestion data from different regions and countries and provides a congestion forecast from a global perspective. For example, it compares the congestion situations at tourist destinations in different countries and suggests the optimal time to visit. This makes it possible to provide a congestion forecast from a global perspective based on congestion data from different regions and countries.

[0045] The course generation unit can provide a congestion forecast taking into account the impact of specific events and festivals. For example, the generation AI of the course generation unit analyzes the impact of specific events and festivals and provides a congestion forecast. For example, when a large-scale event is held, a congestion forecast taking into account the impact is provided. The course generation unit also provides a congestion forecast for specific locations based on event and festival data. For example, it predicts the congestion level when an event is held and suggests less crowded times. The course generation unit also provides a congestion forecast taking into account the impact of specific events and festivals using the generation AI. For example, it makes suggestions to avoid times when congestion is expected based on the event schedule. This makes it possible to provide a congestion forecast taking into account the impact of specific events and festivals.

[0046] The suggestion unit can use the generation AI to make suggestions that take into account the cultural background and customs according to the user's language setting. For example, the suggestion unit makes suggestions that take into account the cultural background and customs according to the user's language setting. For example, for a user whose language setting is Japanese, the suggestion unit makes suggestions based on Japanese culture and customs. The suggestion unit also makes suggestions related to specific cultures and customs based on the user's language setting. For example, for a user whose language setting is English, the suggestion unit makes suggestions based on the culture and customs of English-speaking countries. The suggestion unit also makes suggestions that take into account the cultural background and customs according to the user's language setting. For example, for a user whose language setting is Chinese, the suggestion unit makes suggestions based on Chinese culture and customs. This makes it possible to make suggestions that take into account the cultural background and customs based on the user's language setting.

[0047] The suggestion unit can use the generation AI to analyze user reviews in different languages ​​and suggest the best spots for each language. For example, the suggestion unit analyzes user reviews in different languages ​​using the generation AI and suggests the best spots for each language. For example, based on Japanese reviews, it suggests spots that are popular with Japanese tourists. The suggestion unit also suggests the best spots for users in a specific language-speaking region based on user reviews in different languages. For example, based on English reviews, it suggests spots that are popular with English-speaking tourists. The suggestion unit also analyzes user reviews in different languages ​​using the generation AI and suggests the best spots for each language. For example, based on Chinese reviews, it suggests spots that are popular with Chinese tourists. This makes it possible to suggest the best spots for each language based on user reviews in different languages.

[0048] The suggestion unit can use the generation AI to analyze tourist guides in different languages ​​and make suggestions customized for each language. For example, the suggestion unit analyzes tourist guides in different languages ​​using the generation AI and makes suggestions customized for each language. For example, based on a Japanese tourist guide, it makes suggestions that are optimal for Japanese tourists. Furthermore, the suggestion unit makes suggestions customized for users in specific language-speaking countries based on tourist guides in different languages. For example, based on an English tourist guide, it makes suggestions that are optimal for English-speaking tourists. Furthermore, the suggestion unit analyzes tourist guides in different languages ​​using the generation AI and makes suggestions customized for each language. For example, based on a Chinese tourist guide, it makes suggestions that are optimal for Chinese tourists. This makes it possible to make suggestions customized for each language based on tourist guides in different languages.

[0049] The suggestion unit can use the generation AI to analyze SNS posts in different languages ​​and suggest popular spots for each language. For example, the suggestion unit analyzes SNS posts in different languages ​​using the generation AI and suggests popular spots for each language. For example, based on SNS posts in Japanese, it suggests spots that are popular with Japanese tourists. The suggestion unit also suggests spots that are popular with users from a specific language area based on SNS posts in different languages. For example, based on SNS posts in English, it suggests spots that are popular with English-speaking tourists. The suggestion unit also analyzes SNS posts in different languages ​​using the generation AI and suggests popular spots for each language. For example, based on SNS posts in Chinese, it suggests spots that are popular with Chinese tourists. This makes it possible to suggest popular spots for each language based on SNS posts in different languages.

[0050] The course generation unit can analyze the user's current location and past movement history and propose the optimal route. In the course generation unit, for example, a generation AI analyzes the user's current location and past movement history and proposes the optimal route. For example, based on data of places visited in the past, the optimal route is proposed from the current location. The course generation unit also proposes the optimal route to a specific destination based on the user's current location and past movement history. For example, based on data of places visited in the past, the optimal route is proposed from the current location. In the course generation unit, a generation AI analyzes the user's current location and past movement history and proposes the optimal route. For example, based on data of places visited in the past, the optimal route is proposed from the current location. This makes it possible to propose the optimal route based on the user's current location and past movement history.

[0051] The course generation unit can analyze real-time information about the user's current location and surrounding area and suggest the best spots. For example, the generation AI of the course generation unit analyzes real-time information about the user's current location and surrounding area and suggest the best spots. For example, it suggests restaurants and tourist attractions close to the current location. The course generation unit also suggests the best spots for a specific destination based on real-time information about the user's current location and surrounding area. For example, it suggests tourist attractions and events close to the current location. The course generation unit also suggests real-time information about the user's current location and surrounding area and suggest the best spots. For example, it suggests restaurants and tourist attractions close to the current location. This makes it possible to suggest the best spots based on real-time information about the user's current location and surrounding area.

[0052] The course generation unit analyzes the user's current location and past visit history, and can suggest spots similar to places visited in the past. For example, the generation AI of the course generation unit analyzes the user's current location and past visit history, and suggests spots similar to places visited in the past. For example, based on data on cafes visited in the past, it suggests cafes close to the current location. The course generation unit also suggests the best spots to a specific destination based on the user's current location and past visit history. For example, based on data on tourist spots visited in the past, it suggests tourist spots close to the current location. The course generation unit also analyzes the user's current location and past visit history, and can suggest spots similar to places visited in the past. For example, based on data on restaurants visited in the past, it suggests restaurants close to the current location. This makes it possible to suggest spots similar to places visited in the past based on the user's current location and past visit history.

[0053] The course generation unit can analyze the user's current location and event information in the surrounding area and suggest the most suitable event. For example, the generation AI in the course generation unit analyzes the user's current location and event information in the surrounding area and suggest the most suitable event. For example, it suggests events or festivals close to the current location. The course generation unit also suggests the most suitable event for a specific destination based on the user's current location and event information in the surrounding area. For example, it suggests concerts or exhibition ... events or festivals close to the current location. This makes it possible to suggest the most suitable event based on the user's current location and event information in the surrounding area.

[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 user information acquisition unit can analyze a user's music playlist and suggest spots that match the user's preferred music genre. For example, for a user who likes jazz, jazz bars and live music venues can be suggested. The user information acquisition unit can also suggest spots related to specific music genres based on the user's music playlist. For example, for a user who likes classical music, concert halls and opera houses can be suggested. The user information acquisition unit can also use the generation AI to analyze the user's music playlist and suggest spots that match the user's preferred music genre. For example, for a user who likes rock, rock festivals and live music venues can be suggested. This makes it possible to suggest spots that match the user's preferred music genre based on the user's music playlist.

[0056] The user information acquisition unit can analyze the user's purchasing history and make suggestions based on the purchased products and services. For example, for a user who purchases a lot of outdoor equipment, outdoor activities can be suggested. The user information acquisition unit also makes suggestions about products and services in specific categories based on the user's purchasing history. For example, for a user who purchases a lot of books, bookstores and libraries can be suggested. The user information acquisition unit also uses the generation AI to analyze the user's purchasing history and make suggestions based on the purchased products and services. For example, for a user who purchases a lot of health foods, health-related spots can be suggested. This makes it possible to make suggestions based on the user's purchasing history.

[0057] The user information acquisition unit can analyze the user's reading history and suggest places related to books in a favorite genre. For example, for a user who likes mystery novels, mystery events and related tourist spots can be suggested. The user information acquisition unit also suggests places related to a specific genre based on the user's reading history. For example, for a user who likes historical novels, historical tourist spots and museums can be suggested. The user information acquisition unit also uses the generation AI to analyze the user's reading history and suggest places related to books in a favorite genre. For example, for a user who likes fantasy novels, fantasy events and related tourist spots can be suggested. This makes it possible to suggest places related to books in a favorite genre based on the user's reading history.

[0058] The suggestion unit uses the generation AI to analyze social media posts and identify highly rated spots that are not generally known. For example, it can suggest hidden attractions based on specific hashtags or keywords. The suggestion unit also analyzes user ratings and comments based on social media posts to identify highly rated spots. For example, it analyzes the content of word-of-mouth and reviews to suggest highly rated spots. The suggestion unit also uses the generation AI to analyze social media data to identify highly rated spots that are not generally known. For example, it can analyze posts related to a specific region or theme to suggest hidden attractions. This makes it possible to identify highly rated spots that are not generally known based on social media posts.

[0059] The suggestion unit uses the generation AI to analyze local blogs and forums and identify spots that only locals know about. For example, based on information posted by locals, it can suggest spots that are not listed in tourist guides. The suggestion unit also identifies and suggests spots recommended by locals based on posts on local blogs and forums. For example, it analyzes information about local events and shops and suggests hidden attractions. The suggestion unit also uses the generation AI to analyze local blogs and forums and identify spots that only locals know about. For example, it suggests spots that are not known to tourists based on information shared by locals. This makes it possible to identify spots that only locals know about based on local blogs and forums.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The user information acquisition unit acquires user information. For example, the user information acquisition unit acquires the user's location information, interests, past behavioral history, and health data. Location information is acquired using GPS data, and interests and behavioral history are acquired by analyzing previously visited places and behavioral patterns. Health data is acquired from a fitness tracker or smartwatch. Step 2: The course generation unit generates an outing course based on the information acquired by the user information acquisition unit. For example, the generation AI generates the optimal course by taking into account the user's location information, interests, past behavioral history, health data, and real-time traffic and weather information. The generation AI suggests tourist spots and restaurants close to the current location, spots the user prefers, routes that avoid traffic jams, and spots suitable for the weather. Step 3: The suggestion unit suggests the outing course generated by the course generation unit to the user. For example, the course generated by the generation AI is displayed on the user's smartphone, notified, and added to the calendar. The suggestion unit displays the course on the app interface, notifies the user via push notification, and automatically adds it to the calendar app.

[0062] (Example 2) The outing advisor app according to an embodiment of the present invention is a system that uses a generation AI to propose optimal outing plans to users. This system acquires user information, and the generation AI generates and proposes optimal routes. This allows the outing advisor app to propose optimal outing plans to users.

[0063] The outing advisor app according to the embodiment includes a user information acquisition unit, a course generation unit, and a suggestion unit. The user information acquisition unit acquires user information. For example, the user information acquisition unit acquires user location information. The user information acquisition unit can also acquire the user's interests and past activity history. The user information acquisition unit can also acquire the user's health data. For example, the user information acquisition unit acquires the user's location information using GPS data. The user's interests and past activity history are acquired by analyzing the user's past visited places and activity patterns. The health data can be acquired from a fitness tracker or a smartwatch. The course generation unit generates an outing course based on the information acquired by the user information acquisition unit. For example, the course generation unit uses a generation AI to generate an optimal course based on the user's location information and interests. The course generation unit can also use the generation AI to generate an optimal course based on the user's past activity history and health data. The course generation unit can also use the generation AI to generate an optimal course taking real-time traffic and weather information into consideration. For example, the generation AI can suggest tourist attractions and restaurants near the user's current location based on the user's location information. The generation AI generates a course that includes spots that the user likes based on the user's interests and past behavior history. The generation AI suggests an optimal route that avoids traffic jams based on real-time traffic information. The generation AI suggests spots that are suitable for the weather based on weather information. The suggestion unit suggests the outing course generated by the course generation unit to the user. For example, the suggestion unit displays the course generated by the generation AI on the user's smartphone. The suggestion unit can also notify the user of the course generated by the generation AI. The suggestion unit can also add the course generated by the generation AI to the user's calendar. For example, the suggestion unit displays the course generated by the generation AI on the app interface. The suggestion unit notifies the user of the course generated by the generation AI via a push notification. The suggestion unit automatically adds the course generated by the generation AI to the user's calendar app. In this way, the outing advisor app according to the embodiment can suggest the optimal outing plan to the user.For example, users can check the best route through the app and enjoy a smooth outing. Users can receive the best route in real time using the app's notification function. Users can check the route added to the calendar app and make plans.

[0064] The user information acquisition unit can analyze the user's past movement history and suggest a course based on the user's preferences and behavioral patterns. For example, the user information acquisition unit uses a generation AI to analyze the user's past movement history and identify the user's preferences based on frequently visited places and the length of time spent there. For example, the unit suggests a course that includes similar places based on data on cafes and parks visited in the past. The user information acquisition unit can also analyze the user's movement history to determine trends in visits during specific seasons and times of day, and suggest optimal courses based on these patterns. For example, a spring cherry blossom viewing course can be suggested for a user who frequently visits cherry blossom viewing spots in the spring. The user information acquisition unit can also identify places the user tends to avoid based on the movement history and suggest a course that takes these into consideration. For example, for a user who has tended to avoid crowds in the past, a course that includes less crowded times and places can be suggested. This makes it possible to suggest courses based on the user's preferences and behavioral patterns.

[0065] The course generation unit can monitor traffic conditions in real time and dynamically recalculate the optimal route based on congestion and accident information. For example, the generation AI of the course generation unit monitors traffic conditions in real time and proposes the optimal route based on congestion and accident information. For example, it dynamically calculates an alternative route to avoid roads with congestion. The course generation unit also obtains traffic information in real time and proposes the shortest route from the user's current location to the destination. For example, if an accident occurs, it immediately reflects that information and proposes a new route. The generation AI of the course generation unit also monitors changes in traffic conditions in real time and recalculates the optimal route while the user is traveling. For example, if congestion occurs along the way, it proposes a new route on the spot. This makes it possible to monitor traffic conditions in real time and dynamically recalculate the optimal route.

[0066] The suggestion unit can use the emotion estimation function to analyze the user's current mood and stress level and suggest a relaxing course. The suggestion unit, for example, uses the emotion estimation function to analyze the user's current mood and stress level and suggest a relaxing course. For example, if stress is high, the suggestion unit suggests a course that includes places with lots of nature and quiet places. The suggestion unit also suggests places that have a relaxing effect based on the user's emotion data. For example, the suggestion unit analyzes emotional reactions to places visited in the past and suggests a course that includes places that elicit positive emotions. The suggestion unit also uses the emotion estimation function to suggest activities that match the user's mood. For example, if the user wants to relax, the suggestion unit suggests a course that includes relaxing places such as a spa or cafe. This makes it possible to suggest relaxing courses that suit the user's mood and stress level.

[0067] The user information acquisition unit can analyze the user's health data and suggest courses that suit the user's health condition. For example, the generation AI in the user information acquisition unit analyzes the user's step count data and suggests courses that ensure a moderate amount of exercise. For example, a walking course is suggested for a user who does not usually take many steps. The user information acquisition unit also suggests courses that suit the user's health condition based on the user's heart rate data. For example, if the heart rate is high, a course that includes places to relax is suggested. The user information acquisition unit also analyzes the health data and suggests courses that include activities that are optimal for the user's health condition. For example, a hiking or cycling course is suggested for a user who is not getting enough exercise. This makes it possible to suggest courses that suit the user's health condition.

[0068] The user information acquisition unit can analyze the user's past reviews and ratings and suggest a course that prioritizes highly rated spots. For example, the generation AI in the user information acquisition unit analyzes the user's past reviews and ratings and suggests a course that prioritizes highly rated spots. For example, it suggests a course that includes restaurants and tourist spots that have been highly rated in the past. The user information acquisition unit also identifies highly rated spots based on the user's review history and suggests a course that includes them. For example, it analyzes the ratings of places visited in the past and suggests a course that includes spots with similar ratings. The user information acquisition unit also analyzes the user's rating data and suggests a course that prioritizes highly rated spots. For example, it suggests a course that includes highly rated spots in the same area based on spots that the user has highly rated. This makes it possible to suggest a course that includes highly rated spots based on the user's past reviews and ratings.

[0069] The suggestion unit can use the emotion estimation function to analyze the emotional reactions of the user at places visited in the past and suggest a course that elicits positive emotions. For example, the suggestion unit uses the emotion estimation function to analyze the emotional reactions of the user at places visited in the past and suggest a course that elicits positive emotions. For example, based on the emotion scores of places visited in the past, the suggestion unit suggests a course that includes places that elicit similar emotions. The suggestion unit also identifies spots that elicit positive emotions based on the user's emotion data and suggests a course that includes them. For example, the suggestion unit analyzes the emotional reactions of places visited in the past and suggests a course that includes spots that elicit positive emotions. The suggestion unit also uses the emotion estimation function to analyze the user's emotional reactions and suggest a course that elicits positive emotions. For example, based on the emotion scores of places visited in the past, the suggestion unit suggests a course that includes places that elicit similar emotions. In this way, it is possible to suggest a course that elicits positive emotions based on the user's past emotional reactions.

[0070] The user information acquisition unit can analyze a user's SNS posts, understand their interests, and make customized suggestions. For example, the generation AI in the user information acquisition unit analyzes a user's SNS posts, understands their interests, and makes customized suggestions. For example, for a user who posts frequently about travel, the unit can suggest travel destinations. The user information acquisition unit can also identify interests in specific themes or topics based on the user's SNS posts and make suggestions based on those interests. For example, for a user who posts frequently about food, the unit can suggest restaurants. The user information acquisition unit can also analyze a user's SNS posts, understand their interests, and make customized suggestions. For example, for a user who posts frequently about outdoor activities, the unit can suggest hiking and camping. This allows the generation AI to understand a user's interests based on the user's SNS posts and make customized suggestions.

[0071] The user information acquisition unit can analyze the user's purchasing history and make suggestions based on the purchased products and services. For example, the generation AI in the user information acquisition unit analyzes the user's purchasing history and makes suggestions based on the purchased products and services. For example, outdoor activities are suggested for a user who purchases a lot of outdoor equipment. The user information acquisition unit also makes suggestions regarding products and services in specific categories based on the user's purchasing history. For example, bookstores and libraries are suggested for a user who purchases a lot of books. The user information acquisition unit also analyzes the user's purchasing history and makes suggestions based on the purchased products and services. For example, health-related spots are suggested for a user who purchases a lot of health foods. This makes it possible to make suggestions based on the user's purchasing history.

[0072] The suggestion unit can use the emotion estimation function to analyze facial expressions in the user's past photos and make suggestions based on the moment the user enjoyed the most. For example, the suggestion unit can use the emotion estimation function to analyze facial expressions in the user's past photos and make suggestions based on the moment the user enjoyed the most. For example, the suggestion unit can suggest a course that includes places with many smiling photos. The suggestion unit can also analyze the user's past photos to identify moments with strong positive emotions and make suggestions based on these. For example, the suggestion unit can suggest a course that includes places with many happy-looking photos. The suggestion unit can also use the emotion estimation function to analyze facial expressions in the user's past photos and make suggestions based on the moment the user enjoyed the most. For example, the suggestion unit can suggest a course that includes places with many smiling photos. In this way, the suggestion unit can analyze the moment the user enjoyed the most based on the user's past photos and make suggestions.

[0073] The user information acquisition unit can analyze the user's music playlist and suggest spots that match the user's preferred music genre. For example, the generation AI in the user information acquisition unit analyzes the user's music playlist and suggests spots that match the user's preferred music genre. For example, for a user who likes jazz, it suggests jazz bars and live music venues. The user information acquisition unit also suggests spots related to specific music genres based on the user's music playlist. For example, for a user who likes classical music, it suggests concert halls and opera houses. The user information acquisition unit also analyzes the user's music playlist and suggests spots that match the user's preferred music genre. For example, for a user who likes rock, it suggests rock festivals and live music venues. In this way, it is possible to suggest spots that match the user's preferred music genre based on the user's music playlist.

[0074] The user information acquisition unit can analyze the user's reading history and suggest places related to books in the user's favorite genre. For example, the generation AI in the user information acquisition unit analyzes the user's reading history and suggests places related to books in the user's favorite genre. For example, for a user who likes mystery novels, mystery events and related tourist spots are suggested. The user information acquisition unit also suggests places related to a specific genre based on the user's reading history. For example, for a user who likes historical novels, historical tourist spots and museums are suggested. The user information acquisition unit also analyzes the user's reading history and suggests places related to books in the user's favorite genre. For example, for a user who likes fantasy novels, fantasy events and related tourist spots are suggested. In this way, places related to books in the user's favorite genre can be suggested based on the user's reading history.

[0075] The suggestion unit can use the emotion estimation function to analyze the emotional reactions of the user at places visited in the past and suggest spots that elicit positive emotions. For example, the suggestion unit can use the emotion estimation function to analyze the emotional reactions of the user at places visited in the past and suggest spots that elicit positive emotions. For example, based on the emotion scores of places visited in the past, spots that elicit similar emotions are suggested. The suggestion unit can also identify spots that elicit positive emotions based on the user's emotion data and suggest them. For example, the suggestion unit can analyze the emotional reactions of the user at places visited in the past and suggest spots that elicit positive emotions. The suggestion unit can also use the emotion estimation function to analyze the user's emotional reactions and suggest spots that elicit positive emotions. For example, based on the emotion scores of places visited in the past, spots that elicit similar emotions are suggested. In this way, spots that elicit positive emotions can be suggested based on the user's past emotional reactions.

[0076] The suggestion unit uses the generation AI to analyze social media posts and identify highly rated spots that are not generally known. For example, the suggestion unit analyzes social media posts using the generation AI to identify highly rated spots that are not generally known. For example, the suggestion unit suggests hidden attractions based on specific hashtags or keywords. The suggestion unit also analyzes user ratings and comments based on social media posts to identify highly rated spots. For example, the suggestion unit analyzes the content of word-of-mouth and reviews to suggest highly rated spots. The suggestion unit also analyzes social media data using the generation AI to identify highly rated spots that are not generally known. For example, the suggestion unit analyzes posts related to a specific region or theme to suggest hidden attractions. This makes it possible to identify highly rated spots that are not generally known based on social media posts.

[0077] The suggestion unit can use the generation AI to analyze local blogs and forums and identify spots only locals know about. For example, the suggestion unit can analyze local blogs and forums to identify spots only locals know about. For example, based on information posted by locals, the suggestion unit can suggest spots that are not listed in tourist guides. The suggestion unit can also identify and suggest spots recommended by locals based on posts on local blogs and forums. For example, the suggestion unit can analyze information on local events and shops to suggest hidden attractions. The suggestion unit can also analyze local blogs and forums to identify spots only locals know about. For example, based on information shared by locals, the suggestion unit can suggest spots that are not known to tourists. This makes it possible to identify spots only locals know about based on local blogs and forums.

[0078] The suggestion unit can use the emotion estimation function to identify and suggest spots that elicit positive emotions from the user's past visit history. The suggestion unit, for example, uses the emotion estimation function to identify and suggest spots that elicit positive emotions from the user's past visit history. For example, the suggestion unit suggests spots that elicit similar emotions based on the emotion scores of places visited in the past. The suggestion unit also identifies and suggests spots that elicit positive emotions based on the user's emotion data. For example, the suggestion unit analyzes the emotional reactions of places visited in the past and suggests spots that elicit positive emotions. The suggestion unit also uses the emotion estimation function to analyze the user's emotional reactions and suggests spots that elicit positive emotions. For example, the suggestion unit suggests spots that elicit similar emotions based on the emotion scores of places visited in the past. In this way, spots that elicit positive emotions can be identified and suggested based on the user's past visit history.

[0079] The suggestion unit can use the generation AI to suggest hidden spots along a specific theme based on the user's hobbies and interests. For example, the generation AI analyzes the user's hobbies and interests to suggest hidden spots along a specific theme. For example, for a user who is interested in art, it suggests hidden galleries and art events. The suggestion unit also suggests hidden spots related to a specific theme based on the user's hobbies and interests. For example, for a user who likes outdoor activities, it suggests hidden hiking trails and campsites. The suggestion unit also analyzes the user's hobbies and interests to suggest hidden spots along a specific theme. For example, for a user who is interested in history, it suggests hidden historical places and museums. In this way, it is possible to suggest hidden spots along a specific theme based on the user's hobbies and interests.

[0080] The suggestion unit uses the generation AI to consider seasonal and event information and suggest spots that can only be enjoyed at specific times. For example, the generation AI analyzes seasonal and event information and suggests spots that can only be enjoyed at specific times. For example, during cherry blossom season, it suggests cherry blossom viewing spots. The suggestion unit also suggests spots that can be enjoyed at specific times based on seasonal and event information. For example, during summer festival season, it suggests local festivals and events. The suggestion unit also analyzes seasonal and event information and suggests spots that can only be enjoyed at specific times. For example, during autumn foliage season, it suggests places with beautiful autumn leaves. This makes it possible to suggest spots that can only be enjoyed at specific times based on seasonal and event information.

[0081] The suggestion unit can use the emotion estimation function to analyze the emotional reactions of the user at places they have visited in the past and suggest little-known spots that elicit positive emotions. For example, the suggestion unit can use the emotion estimation function to analyze the emotional reactions of the user at places they have visited in the past and suggest little-known spots that elicit positive emotions. For example, based on the emotion scores of places they have visited in the past, the suggestion unit can suggest little-known spots that elicit similar emotions. The suggestion unit can also identify little-known spots that elicit positive emotions based on the user's emotion data and suggest them. For example, the suggestion unit can analyze the emotional reactions of places they have visited in the past and suggest little-known spots that elicit positive emotions. The suggestion unit can also use the emotion estimation function to analyze the user's emotional reactions and suggest little-known spots that elicit positive emotions. For example, based on the emotion scores of places they have visited in the past, the suggestion unit can suggest little-known spots that elicit similar emotions. In this way, little-known spots that elicit positive emotions can be suggested based on the user's past emotional reactions.

[0082] The route generation unit can provide a more accurate congestion forecast by combining past congestion data with real-time location information. For example, the generation AI of the route generation unit combines past congestion data with real-time location information to provide a more accurate congestion forecast. For example, based on past data, it predicts the congestion level for a specific time period or day of the week. The route generation unit also provides a congestion forecast for a specific location based on past congestion data and real-time location information. For example, based on current location information, it suggests the least crowded time period. The route generation unit also provides a more accurate congestion forecast by combining past congestion data with real-time location information. For example, based on past data, it predicts the congestion level for a specific event or season. In this way, by combining past congestion data with real-time location information, it is possible to provide a more accurate congestion forecast.

[0083] The course generation unit can analyze weather data and predict the impact of congestion due to changes in weather. For example, the generation AI of the course generation unit analyzes weather data and predicts the impact of congestion due to changes in weather. For example, it predicts that indoor facilities tend to be crowded on rainy days and suggests empty outdoor spots. The course generation unit also provides a congestion forecast under specific weather conditions based on the weather data. For example, it predicts that tourist spots tend to be crowded on sunny days and suggests empty time periods. The generation AI of the course generation unit also analyzes weather data and predicts the impact of congestion due to changes in weather. For example, it predicts congestion conditions under extreme weather conditions such as typhoons and heavy snow and suggests places to avoid. This makes it possible to predict the impact of congestion due to changes in weather based on weather data.

[0084] The suggestion unit can use the emotion estimation function to analyze the user's stress level and suggest the optimal time period to avoid crowds. For example, the suggestion unit uses the emotion estimation function to analyze the user's stress level and suggest the optimal time period to avoid crowds. For example, if stress is high, it suggests an empty time period. The suggestion unit also analyzes the stress level based on the user's emotion data and suggests the optimal time period to avoid crowds. For example, it suggests a time period with low stress based on past data. The suggestion unit also uses the emotion estimation function to analyze the user's stress level and suggest the optimal time period to avoid crowds. For example, if stress is high, it suggests an empty location. In this way, it is possible to suggest the optimal time period to avoid crowds based on the user's stress level.

[0085] The course generation unit can analyze congestion data from different regions and countries and provide a congestion forecast from a global perspective. For example, the generation AI in the course generation unit analyzes congestion data from different regions and countries and provides a congestion forecast from a global perspective. For example, the congestion situation at a specific tourist destination is predicted based on international data. The course generation unit also provides a congestion forecast for a specific location based on congestion data from different regions and countries. For example, it provides a congestion forecast that takes into account the impact of international events and holidays. The course generation unit also analyzes congestion data from different regions and countries and provides a congestion forecast from a global perspective. For example, it compares the congestion situations at tourist destinations in different countries and suggests the optimal time to visit. This makes it possible to provide a congestion forecast from a global perspective based on congestion data from different regions and countries.

[0086] The course generation unit can provide a congestion forecast taking into account the impact of specific events and festivals. For example, the generation AI of the course generation unit analyzes the impact of specific events and festivals and provides a congestion forecast. For example, when a large-scale event is held, a congestion forecast taking into account the impact is provided. The course generation unit also provides a congestion forecast for specific locations based on event and festival data. For example, it predicts the congestion level when an event is held and suggests less crowded times. The course generation unit also provides a congestion forecast taking into account the impact of specific events and festivals using the generation AI. For example, it makes suggestions to avoid times when congestion is expected based on the event schedule. This makes it possible to provide a congestion forecast taking into account the impact of specific events and festivals.

[0087] The suggestion unit can use the emotion estimation function to analyze the emotional reactions of the user at places visited in the past and provide a congestion forecast to elicit positive emotions. The suggestion unit, for example, uses the emotion estimation function to analyze the emotional reactions of the user at places visited in the past and provide a congestion forecast to elicit positive emotions. For example, the suggestion unit suggests an optimal time period to avoid crowds based on the emotion scores of places visited in the past. The suggestion unit also provides a congestion forecast to elicit positive emotions based on the user's emotion data. For example, the suggestion unit analyzes the emotional reactions of the user at places visited in the past and provides a congestion forecast to elicit positive emotions. The suggestion unit also uses the emotion estimation function to analyze the user's emotional reactions and provide a congestion forecast to elicit positive emotions. For example, the suggestion unit suggests an optimal time period to avoid crowds based on the emotion scores of places visited in the past. In this way, a congestion forecast to elicit positive emotions can be provided based on the user's past emotional reactions.

[0088] The suggestion unit can use the generation AI to make suggestions that take into account the cultural background and customs according to the user's language setting. For example, the suggestion unit makes suggestions that take into account the cultural background and customs according to the user's language setting. For example, for a user whose language setting is Japanese, the suggestion unit makes suggestions based on Japanese culture and customs. The suggestion unit also makes suggestions related to specific cultures and customs based on the user's language setting. For example, for a user whose language setting is English, the suggestion unit makes suggestions based on the culture and customs of English-speaking countries. The suggestion unit also makes suggestions that take into account the cultural background and customs according to the user's language setting. For example, for a user whose language setting is Chinese, the suggestion unit makes suggestions based on Chinese culture and customs. This makes it possible to make suggestions that take into account the cultural background and customs based on the user's language setting.

[0089] The suggestion unit can use the generation AI to analyze user reviews in different languages ​​and suggest the best spots for each language. For example, the suggestion unit analyzes user reviews in different languages ​​using the generation AI and suggests the best spots for each language. For example, based on Japanese reviews, it suggests spots that are popular with Japanese tourists. The suggestion unit also suggests the best spots for users in a specific language-speaking region based on user reviews in different languages. For example, based on English reviews, it suggests spots that are popular with English-speaking tourists. The suggestion unit also analyzes user reviews in different languages ​​using the generation AI and suggests the best spots for each language. For example, based on Chinese reviews, it suggests spots that are popular with Chinese tourists. This makes it possible to suggest the best spots for each language based on user reviews in different languages.

[0090] The suggestion unit can use the emotion estimation function to analyze the emotional reactions of users of different languages ​​and make suggestions that elicit positive emotions. The suggestion unit, for example, uses the emotion estimation function to analyze the emotional reactions of users of different languages ​​and make suggestions that elicit positive emotions. For example, a suggestion that elicits positive emotions is made based on emotion data of a Japanese user. The suggestion unit also makes suggestions that elicit positive emotions based on emotion data of users of different languages. For example, a suggestion that elicits positive emotions is made based on emotion data of an English user. The suggestion unit also uses the emotion estimation function to analyze the emotional reactions of users of different languages ​​and make suggestions that elicit positive emotions. For example, a suggestion that elicits positive emotions is made based on emotion data of a Chinese user. This makes it possible to make suggestions that elicit positive emotions based on the emotional reactions of users of different languages.

[0091] The suggestion unit can use the generation AI to analyze tourist guides in different languages ​​and make suggestions customized for each language. For example, the suggestion unit analyzes tourist guides in different languages ​​using the generation AI and makes suggestions customized for each language. For example, based on a Japanese tourist guide, it makes suggestions that are optimal for Japanese tourists. Furthermore, the suggestion unit makes suggestions customized for users in specific language-speaking countries based on tourist guides in different languages. For example, based on an English tourist guide, it makes suggestions that are optimal for English-speaking tourists. Furthermore, the suggestion unit analyzes tourist guides in different languages ​​using the generation AI and makes suggestions customized for each language. For example, based on a Chinese tourist guide, it makes suggestions that are optimal for Chinese tourists. This makes it possible to make suggestions customized for each language based on tourist guides in different languages.

[0092] The suggestion unit can use the generation AI to analyze SNS posts in different languages ​​and suggest popular spots for each language. For example, the suggestion unit analyzes SNS posts in different languages ​​using the generation AI and suggests popular spots for each language. For example, based on SNS posts in Japanese, it suggests spots that are popular with Japanese tourists. The suggestion unit also suggests spots that are popular with users from a specific language area based on SNS posts in different languages. For example, based on SNS posts in English, it suggests spots that are popular with English-speaking tourists. The suggestion unit also analyzes SNS posts in different languages ​​using the generation AI and suggests popular spots for each language. For example, based on SNS posts in Chinese, it suggests spots that are popular with Chinese tourists. This makes it possible to suggest popular spots for each language based on SNS posts in different languages.

[0093] The suggestion unit can use the emotion estimation function to analyze emotional reactions of users of different languages ​​at places they have previously visited, and make suggestions that elicit positive emotions. The suggestion unit, for example, uses the emotion estimation function to analyze emotional reactions of users of different languages ​​at places they have previously visited, and make suggestions that elicit positive emotions. For example, the suggestion unit makes suggestions that elicit positive emotions based on emotional data of Japanese users. The suggestion unit also makes suggestions that elicit positive emotions based on emotional data of users of different languages. For example, the suggestion unit makes suggestions that elicit positive emotions based on emotional data of English users. The suggestion unit also uses the emotion estimation function to analyze emotional reactions of users of different languages ​​at places they have previously visited, and make suggestions that elicit positive emotions. For example, the suggestion unit makes suggestions that elicit positive emotions based on emotional data of Chinese users. This makes it possible to make suggestions that elicit positive emotions based on the emotional reactions of users of different languages.

[0094] The course generation unit can analyze the user's current location and past movement history and propose the optimal route. In the course generation unit, for example, a generation AI analyzes the user's current location and past movement history and proposes the optimal route. For example, based on data of places visited in the past, the optimal route is proposed from the current location. The course generation unit also proposes the optimal route to a specific destination based on the user's current location and past movement history. For example, based on data of places visited in the past, the optimal route is proposed from the current location. In the course generation unit, a generation AI analyzes the user's current location and past movement history and proposes the optimal route. For example, based on data of places visited in the past, the optimal route is proposed from the current location. This makes it possible to propose the optimal route based on the user's current location and past movement history.

[0095] The course generation unit can analyze real-time information about the user's current location and surrounding area and suggest the best spots. For example, the generation AI of the course generation unit analyzes real-time information about the user's current location and surrounding area and suggest the best spots. For example, it suggests restaurants and tourist attractions close to the current location. The course generation unit also suggests the best spots for a specific destination based on real-time information about the user's current location and surrounding area. For example, it suggests tourist attractions and events close to the current location. The course generation unit also suggests real-time information about the user's current location and surrounding area and suggest the best spots. For example, it suggests restaurants and tourist attractions close to the current location. This makes it possible to suggest the best spots based on real-time information about the user's current location and surrounding area.

[0096] The suggestion unit can use the emotion estimation function to analyze the emotional response at the user's current location and suggest spots that elicit positive emotions. The suggestion unit, for example, uses the emotion estimation function to analyze the emotional response at the user's current location and suggest spots that elicit positive emotions. For example, spots that elicit positive emotions are suggested based on an emotion score at the current location. The suggestion unit also identifies spots that elicit positive emotions at the current location based on the user's emotion data and suggests them. For example, it analyzes the emotional response at the current location and suggests spots that elicit positive emotions. The suggestion unit also uses the emotion estimation function to analyze the user's emotional response and suggest spots that elicit positive emotions at the current location. For example, it suggests spots that elicit positive emotions based on an emotion score at the current location. In this way, spots that elicit positive emotions can be suggested based on the user's emotional response at the current location.

[0097] The course generation unit analyzes the user's current location and past visit history, and can suggest spots similar to places visited in the past. For example, the generation AI of the course generation unit analyzes the user's current location and past visit history, and suggests spots similar to places visited in the past. For example, based on data on cafes visited in the past, it suggests cafes close to the current location. The course generation unit also suggests the best spots to a specific destination based on the user's current location and past visit history. For example, based on data on tourist spots visited in the past, it suggests tourist spots close to the current location. The course generation unit also analyzes the user's current location and past visit history, and can suggest spots similar to places visited in the past. For example, based on data on restaurants visited in the past, it suggests restaurants close to the current location. This makes it possible to suggest spots similar to places visited in the past based on the user's current location and past visit history.

[0098] The course generation unit can analyze the user's current location and event information in the surrounding area and suggest the most suitable event. For example, the generation AI in the course generation unit analyzes the user's current location and event information in the surrounding area and suggest the most suitable event. For example, it suggests events or festivals close to the current location. The course generation unit also suggests the most suitable event for a specific destination based on the user's current location and event information in the surrounding area. For example, it suggests concerts or exhibition ... events or festivals close to the current location. This makes it possible to suggest the most suitable event based on the user's current location and event information in the surrounding area.

[0099] The suggestion unit can use the emotion estimation function to analyze the emotional reaction at the user's current location and suggest a route that will elicit positive emotions. The suggestion unit, for example, uses the emotion estimation function to analyze the emotional reaction at the user's current location and suggest a route that will elicit positive emotions. For example, the suggestion unit suggests a route that will elicit positive emotions based on an emotion score at the current location. The suggestion unit also identifies and suggests a route that will elicit positive emotions at the current location based on the user's emotion data. For example, the suggestion unit analyzes the emotional reaction at the current location and suggests a route that will elicit positive emotions. The suggestion unit also uses the emotion estimation function to analyze the user's emotional reaction and suggest a route that will elicit positive emotions at the current location. For example, the suggestion unit suggests a route that will elicit positive emotions based on an emotion score at the current location. This makes it possible to suggest a route that will elicit positive emotions based on the user's emotional reaction at the current location.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The user information acquisition unit can analyze a user's music playlist and suggest spots that match the user's preferred music genre. For example, for a user who likes jazz, jazz bars and live music venues can be suggested. The user information acquisition unit can also suggest spots related to specific music genres based on the user's music playlist. For example, for a user who likes classical music, concert halls and opera houses can be suggested. The user information acquisition unit can also use the generation AI to analyze the user's music playlist and suggest spots that match the user's preferred music genre. For example, for a user who likes rock, rock festivals and live music venues can be suggested. This makes it possible to suggest spots that match the user's preferred music genre based on the user's music playlist.

[0102] The suggestion unit can use the emotion estimation function to analyze the user's current mood and stress level and suggest a relaxing course. For example, if stress is high, the suggestion unit can suggest a course that includes places with lots of nature and quiet places. The suggestion unit can also suggest places that have a relaxing effect based on the user's emotion data. For example, the suggestion unit can analyze the emotional reactions to places visited in the past and suggest a course that includes places that elicit positive emotions. The suggestion unit can also use the emotion estimation function to suggest activities that match the user's mood. For example, if the user wants to relax, the suggestion unit can suggest a course that includes relaxing places such as a spa or cafe. This makes it possible to suggest a relaxing course that suits the user's mood and stress level.

[0103] The user information acquisition unit can analyze the user's purchasing history and make suggestions based on the purchased products and services. For example, for a user who purchases a lot of outdoor equipment, outdoor activities can be suggested. The user information acquisition unit also makes suggestions about products and services in specific categories based on the user's purchasing history. For example, for a user who purchases a lot of books, bookstores and libraries can be suggested. The user information acquisition unit also uses the generation AI to analyze the user's purchasing history and make suggestions based on the purchased products and services. For example, for a user who purchases a lot of health foods, health-related spots can be suggested. This makes it possible to make suggestions based on the user's purchasing history.

[0104] The suggestion unit can use the emotion estimation function to analyze the emotional reactions of the user at places visited in the past and suggest a course that elicits positive emotions. For example, based on the emotion scores of places visited in the past, the suggestion unit can suggest a course that includes places that elicit similar emotions. The suggestion unit can also identify spots that elicit positive emotions based on the user's emotion data and suggest a course that includes them. For example, the suggestion unit can analyze the emotional reactions of the user at places visited in the past and suggest a course that includes spots that elicit positive emotions. The suggestion unit can also use the emotion estimation function to analyze the user's emotional reactions and suggest a course that elicits positive emotions. For example, based on the emotion scores of places visited in the past, the suggestion unit can suggest a course that includes places that elicit similar emotions. In this way, it is possible to suggest a course that elicits positive emotions based on the user's past emotional reactions.

[0105] The user information acquisition unit can analyze the user's reading history and suggest places related to books in a favorite genre. For example, for a user who likes mystery novels, mystery events and related tourist spots can be suggested. The user information acquisition unit also suggests places related to a specific genre based on the user's reading history. For example, for a user who likes historical novels, historical tourist spots and museums can be suggested. The user information acquisition unit also uses the generation AI to analyze the user's reading history and suggest places related to books in a favorite genre. For example, for a user who likes fantasy novels, fantasy events and related tourist spots can be suggested. This makes it possible to suggest places related to books in a favorite genre based on the user's reading history.

[0106] The suggestion unit uses the emotion estimation function to analyze facial expressions in the user's past photos and make suggestions based on the moment the user enjoyed the most. For example, the suggestion unit suggests a course that includes places where there are many smiling photos. The suggestion unit also analyzes the user's past photos to identify moments when positive emotions were strong and makes suggestions based on these. For example, the suggestion unit suggests a course that includes places where there are many photos with happy expressions. The suggestion unit also uses the emotion estimation function to analyze facial expressions in the user's past photos and make suggestions based on the moment the user enjoyed the most. For example, the suggestion unit suggests a course that includes places where there are many smiling photos. This makes it possible to analyze the moment the user enjoyed the most based on the user's past photos and make suggestions.

[0107] The suggestion unit uses the generation AI to analyze social media posts and identify highly rated spots that are not generally known. For example, it can suggest hidden attractions based on specific hashtags or keywords. The suggestion unit also analyzes user ratings and comments based on social media posts to identify highly rated spots. For example, it analyzes the content of word-of-mouth and reviews to suggest highly rated spots. The suggestion unit also uses the generation AI to analyze social media data to identify highly rated spots that are not generally known. For example, it can analyze posts related to a specific region or theme to suggest hidden attractions. This makes it possible to identify highly rated spots that are not generally known based on social media posts.

[0108] The suggestion unit can use the emotion estimation function to analyze the user's stress level and suggest the optimal time period to avoid crowds. For example, if stress is high, it suggests an empty time period. The suggestion unit can also analyze the stress level based on the user's emotion data and suggest the optimal time period to avoid crowds. For example, it can suggest a time period with low stress based on past data. The suggestion unit can also use the emotion estimation function to analyze the user's stress level and suggest the optimal time period to avoid crowds. For example, if stress is high, it can suggest an empty location. This makes it possible to suggest the optimal time period to avoid crowds based on the user's stress level.

[0109] The suggestion unit uses the generation AI to analyze local blogs and forums and identify spots that only locals know about. For example, based on information posted by locals, it can suggest spots that are not listed in tourist guides. The suggestion unit also identifies and suggests spots recommended by locals based on posts on local blogs and forums. For example, it analyzes information about local events and shops and suggests hidden attractions. The suggestion unit also uses the generation AI to analyze local blogs and forums and identify spots that only locals know about. For example, it suggests spots that are not known to tourists based on information shared by locals. This makes it possible to identify spots that only locals know about based on local blogs and forums.

[0110] The suggestion unit can use the emotion estimation function to identify and suggest spots that elicit positive emotions from the user's past visit history. For example, based on the emotion scores of places visited in the past, it can suggest spots that elicit similar emotions. The suggestion unit can also identify and suggest spots that elicit positive emotions based on the user's emotion data. For example, it can analyze the emotional reactions of places visited in the past and suggest spots that elicit positive emotions. The suggestion unit can also use the emotion estimation function to analyze the user's emotional reactions and suggest spots that elicit positive emotions. For example, it can suggest spots that elicit similar emotions based on the emotion scores of places visited in the past. This makes it possible to identify and suggest spots that elicit positive emotions based on the user's past visit history.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The user information acquisition unit acquires user information. For example, the user information acquisition unit acquires the user's location information, interests, past behavioral history, and health data. Location information is acquired using GPS data, and interests and behavioral history are acquired by analyzing previously visited places and behavioral patterns. Health data is acquired from a fitness tracker or smartwatch. Step 2: The course generation unit generates an outing course based on the information acquired by the user information acquisition unit. For example, the generation AI generates the optimal course by taking into account the user's location information, interests, past behavioral history, health data, and real-time traffic and weather information. The generation AI suggests tourist spots and restaurants close to the current location, spots the user prefers, routes that avoid traffic jams, and spots suitable for the weather. Step 3: The suggestion unit suggests the outing course generated by the course generation unit to the user. For example, the course generated by the generation AI is displayed on the user's smartphone, notified, and added to the calendar. The suggestion unit displays the course on the app interface, notifies the user via push notification, and automatically adds it to the calendar app.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 AI 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.

[0130] 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.

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

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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 AI 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.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0158] 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.

[0159] 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.

[0160] 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 AI 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0167] 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."

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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]

[0180] 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. This system uses generative AI to propose optimal outing plans to users. a user information acquisition unit that acquires user information; a course generation unit that generates an outing course based on the information acquired by the user information acquisition unit; a suggestion unit that suggests the outing course generated by the course generation unit to the user. A system characterized by:

2. The user information acquisition unit Analyzing the user's past travel history and proposing a course based on the user's preferences and behavioral patterns 2. The system of claim 1.

3. The course generation unit Monitor traffic conditions in real time and dynamically recalculate optimal routes based on congestion and accident information 2. The system of claim 1.

4. The proposal unit Analyzing the user's current mood and stress level and suggesting the relaxing course 2. The system of claim 1.

5. The user information acquisition unit Analyzing the health data of the user and proposing the course according to the health condition 2. The system of claim 1.

6. The user information acquisition unit Analyzing the user's past reviews and ratings, and suggesting the course that prioritizes spots with high ratings 2. The system of claim 1.

7. The proposal unit Analyze the user's emotional reactions to places they have visited in the past and suggest courses that will elicit positive emotions.

2. The system of claim 1.

8. The user information acquisition unit Analyzing the user's SNS posts, understanding their interests and concerns, and making the customized proposal 2. The system of claim 1.

Images