System

Abstract

To provide a system.SOLUTION: The system includes: means for receiving input information including a destination or a purpose of a travel, or a preference, an interest, an age, or a gender of a user; means for acquiring a list of sightseeing spots or activities from a sightseeing spot database on the basis of the input information; means for suggesting a sightseeing spot or an activity likely to interest the user using a data generation model; means for presenting a route to the sightseeing spot or the activity in real time; and means for story-telling information on a legend or a history of the sightseeing spot or the activity.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional travel applications lack elements that can attract the interest of users, especially children, and educational elements, which means that users' travel experiences are not sufficiently rich. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing an application that acts as a virtual character that attracts the user's attention and supports exploration at a travel destination.

[0006] Specifically, based on user input, the system obtains a list of tourist attractions and activities and suggests tourist attractions and activities that the user may be interested in. It also presents routes to tourist attractions and activities in real time, displaying the appropriate route for the user to head to the destination. It also provides storytelling of legends and historical information about tourist attractions and activities, providing an environment where users can learn while having fun.

[0007] This will allow users, especially children, to enjoy traveling while keeping them interested, while also incorporating an element of learning, thus serving as a solution to the existing problems.

[0008] A "tourist destination database" is a database that stores information about tourist attractions and activities at travel destinations.

[0009] A "list of tourist attractions or activities" refers to a list of tourist attractions or activities selected based on the travel destination and purpose, the user's preferences and interests, age, gender, etc.

[0010] A "data generation model" is a chatbot built using artificial intelligence that suggests sightseeing spots and activities that users might be interested in through dialogue with them. One example of a "data generation model" is generative AI.

[0011] "Route" means an appropriate path or route to a destination, including, for example, the method of travel to a tourist attraction or activity in a travel destination and the time required to get there.

[0012] "Storytelling" is the act of conveying information in the form of a story. For example, telling the legends or history of a tourist spot or activity in a fun story format is expected to have an effect of educating children and attracting their interest. [Brief description of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. [Figure 11] 4 is a sequence diagram showing a process flow of the data processing system according to the first embodiment. FIG. [Figure 12] 11 is a sequence diagram showing a process flow of the data processing system in application example 1. FIG. [Figure 13] FIG. 11 is a sequence diagram showing the flow of processing of the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 11 is a sequence diagram showing the flow of processing in the data processing system in application example 2 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), etc.

[0017] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0018] 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.

[0019] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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 wide area network (WAN) and / or a local area network (LAN).

[0025] 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.

[0026] 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 (e.g., 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 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0031] 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.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] An embodiment for implementing the present invention includes the following elements.

[0035] 1. User input receiving means: This is the means by which the server receives input information from the user, such as the travel destination and purpose, the user's preferences and interests, age, and gender.

[0036] 2. Means for obtaining a list of tourist attractions and activities: This is the means by which the server obtains a list of tourist attractions and activities that meet the conditions from the tourist destination database based on the information input by the user.

[0037] 3. Suggestion means: This is a means in which the server uses a generative AI to suggest tourist spots and activities that the user may be interested in based on the acquired list of tourist spots and activities.

[0038] 4. Route display means: A means for the terminal to display routes to suggested tourist spots and activities in real time. The user can head to the destination by referring to the display on the terminal.

[0039] 5. Storytelling means: This is a means by which the server tells a story about the legends and history of the proposed tourist spots. Users can learn while having fun through the stories provided by the server. Examples of storytelling presentation means include displaying text on the terminal or outputting audio.

[0040] By combining the above elements, the system of the present invention can be realized, which receives user input, suggests tourist spots and activities that match the user's criteria, provides real-time routes, and performs storytelling to enrich the travel experience of users, especially children.

[0041] The process flow will be explained below.

[0042] Step 1: The server receives input information from the user, including the travel destination or purpose, or the user's preferences, interests, age, or gender. That is, the user inputs at least one of the travel destination or purpose, the user's preferences or interests, age, and gender.

[0043] Step 2: The server retrieves a list of tourist attractions and activities that meet the criteria. Specifically, the server retrieves a list of tourist attractions and activities that meet the criteria from the tourist destination database based on the received user input information.

[0044] Step 3: The server suggests tourist attractions and activities that the user may be interested in based on the acquired list of tourist attractions and activities.

[0045] If a user mentions that they like the sea, the server will suggest nearby beaches and aquariums. The server can also suggest nearby castles and museums if the user mentions that they are interested in history, for example.

[0046] Step 4: The device presents a route to the proposed tourist spots and activities in real time. Specifically, the device displays an appropriate route taking into account the user's current location and mode of transportation.

[0047] Step 5: The server tells a story about the legends and history of the proposed attractions and activities. For example, if the user indicates that they are interested in ancient ruins, the server might tell them the origins and myths of those ruins.

[0048] The output conditions for each step are as follows:

[0049] Step 1: User Input

[0050] Step 2: List of attractions and activities that fit your criteria

[0051] Step 3: Suggested attractions and activities

[0052] Step 4: Real-time route planning

[0053] Step 5: Information about the attraction or activity being storyteller

[0054] Example 1

[0055] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal."

[0056] In modern travel planning and navigation, many users find it difficult to find tourist attractions and activities that match their individual conditions such as interests, preferences, age, and gender. This tends to limit the user's travel experience. It is also difficult to obtain real-time information about the history and legends of a place. There is a need for a system that solves these problems and allows users to have a richer travel experience.

[0057] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0058] In this invention, the server includes a means for receiving input information including the user's travel destination, purpose, preferences, interests, age, and gender, a means for acquiring a list of tourist attractions or activities from a database, a means for using generative AI to suggest tourist attractions or activities that the user may be interested in, a means for presenting routes to the tourist attractions or activities in real time, and a means for storytelling information on the legends and history of the tourist attractions or activities. This not only makes it easier for the user to find tourist attractions or activities that meet their individual requirements, but also allows them to obtain information on the history and legends of the places in real time.

[0059] "User input information" refers to information including travel destination, purpose, preferences, interests, age, and gender.

[0060] A "tourist spot" is a famous place or facility at a travel destination that the user intends to visit.

[0061] "Activities" are attractions and recreational activities that can be undertaken at a tourist destination.

[0062] "Database" means an information source that holds information about attractions and activities.

[0063] "Generative AI" is an artificial intelligence model that generates appropriate suggestions based on user input information.

[0064] "Route presentation" is a function that displays the route to tourist spots and activities selected by the user in real time.

[0065] "Storytelling" is a means of providing legends and historical information related to attractions and activities.

[0066] The present invention provides a system for making travel planning more efficient and enriching a user's travel experience. The system includes a server, a terminal, and a series of means for receiving input information from a user and proposing appropriate sightseeing spots and activities.

[0067] Means of receiving user input information

[0068] The server receives input information from the user, such as travel destination, purpose, preferences, interests, age, gender, etc. The user enters the trip details, for example using a smartphone application. The input information is sent to the server and used in the next processing steps.

[0069] How to get a list of attractions and activities

[0070] The server retrieves a list of tourist attractions and activities that meet the criteria from a tourist attraction database based on the information input by the user. A general-purpose API (e.g., Google (registered trademark) Places API or Foursquare (registered trademark) API) is used as the tourist attraction database. The server generates a query based on the information input by the user, sends it to the database, and retrieves a list that meets the criteria.

[0071] Proposal means

[0072] The server uses a generative AI model (e.g., ChatGPT® by OpenAI®) to generate suggestions based on the list of attractions and activities that the user may be interested in. Specifically, the suggestions are generated using the following prompt:

[0073] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0074] The generated proposals are transmitted from the server to the user's terminal.

[0075] Route presentation method

[0076] The device will present routes to the suggested tourist spots and activities in real time. For example, the device will use the Google Maps API to calculate the optimal route from the user's current location to the destination and display it on a map. The user can use this route as a reference to head to the destination.

[0077] Storytelling Devices

[0078] The server will tell a story about the legends and history of the proposed tourist spots and activities. The terminal will provide the information to the user in the form of text display or audio output. For example, the terminal will play an audio commentary about the history and exhibits of the "Anime Museum." The user can learn while enjoying the story.

[0079] By combining the above means, the system of the present invention supports the user's travel planning and provides various information in real time during the trip, further enriching the user's travel experience and making it attractive especially for children and families.

[0080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0081] Step 1:

[0082] A user inputs travel information into a smartphone application.

[0083] Input: "Destination: Tokyo", "Purpose: Family trip", "Hobbies: Anime and history", "Age: 35", "Gender: Male"

[0084] Operation:

[0085] 1. The user enters their trip details into the app's form.

[0086] 2. The device sends this information to the server.

[0087] Output: User input sent to the server

[0088] Step 2:

[0089] The server sends a query to a tourist destination database based on the user's input information and retrieves a list of tourist attractions and activities that meet the criteria.

[0090] Input: User input information

[0091] Data processing / calculation:

[0092] 1. The server generates a query based on the user input information it receives.

[0093] 2. The server sends this query to a tourist destination database (e.g. Google Places API).

[0094] 3. The server filters the results returned from the database to create a list of attractions and activities that fit the criteria.

[0095] Output: A filtered list of attractions and activities

[0096] Step 3:

[0097] The server uses a generative AI model to make suggestions that might interest the user based on the list of tourist attractions and activities it has acquired.

[0098] Input: A filtered list of attractions and activities

[0099] Data processing / calculation:

[0100] 1. The server sends the following prompt to the generative AI model (e.g. ChatGPT):

[0101] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0102] 2. The generative AI model generates suggestions and returns a list of tourist attractions as a response.

[0103] Output: A list of suggested attractions and activities that may interest the user.

[0104] Step 4:

[0105] The server sends the suggestion list to the user's terminal, and the terminal presents a route to the spot selected by the user in real time.

[0106] Input: A list of suggested attractions and activities that might interest the user.

[0107] Operation:

[0108] 1. The server sends the proposal list to the user's device.

[0109] 2. The user selects the spot they want to visit from the list of suggestions.

[0110] 3. The device uses the Google Maps API to find the best route from the user's current location to the selected spot.

[0111] 4. The device will display the route in real time and begin navigation.

[0112] Output: Real-time directions to the selected spot

[0113] Step 5:

[0114] The server provides the legends and history of the proposed tourist attractions and activities, which the terminal conveys to the user by display or audio.

[0115] Input: Details of the suggested attraction or activity

[0116] Data processing / calculation:

[0117] 1. The server generates text and audio data of the legend and history of the proposed tourist spot.

[0118] 2. The server sends the generated data to the user's terminal.

[0119] 3. The device displays the text information or plays the information aloud.

[0120] Output: Provides the user with legends and history about attractions and activities.

[0121] (Application example 1)

[0122] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0123] Modern consumers have diverse interests and tastes, and it is difficult for them to efficiently find travel destinations, tourist attractions, and stores in shopping malls that meet their needs. In addition, it is difficult to obtain sufficient information about the history and background of the spots and stores to visit, which can limit their travel and shopping experiences. In particular, there is a demand to provide educational and enjoyable experiences for children and families.

[0124] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0125] In this invention, the server includes a means for receiving input information including a travel destination or purpose, or a user's preferences, interests, age, or gender, a means for acquiring a list of tourist attractions, activities, or stores from a tourist destination database or a store database based on the input information, a means for suggesting the tourist attractions, activities, or stores that the user may be interested in using a data generation model, a means for presenting a route to the tourist attractions, activities, or stores in real time, and a means for storytelling information about the tourist attractions, activities, or stores by voice or text. This allows users to find the best spots and stores according to their individual interests and preferences, and to learn about their history and background while having fun.

[0126] "Input information" refers to information such as the travel destination and purpose, the user's preferences, interests, age, and gender.

[0127] A "tourist destination database" refers to an information source that stores information about tourist attractions and activities.

[0128] "Store database" refers to an information source that stores information about shopping malls and physical stores.

[0129] "Tourist attractions" refer to places that tourists visit.

[0130] "Activities" refers to various experiential activities that take place at tourist spots.

[0131] "Store" refers to retail stores, restaurants, etc. located in shopping malls and commercial facilities.

[0132] A "data generation model" refers to an AI model that predicts user interests based on input information and makes appropriate suggestions.

[0133] "Suggestion means" refers to a function that selects and suggests spots, activities, or stores that may be of interest to the user from among the acquired spots, activities, or stores.

[0134] The "route presentation means" refers to a function that takes into account the user's current location and displays the optimal route to a specified location in real time.

[0135] "Storytelling Means" refers to features that provide audio or text information about the history or background of a tourist attraction, activity, or store.

[0136] The program of the system for implementing the present invention is configured as follows.

[0137] The system starts by receiving input information, such as the user's travel destination and purpose, the user's preferences, interests, age, and gender, using the user's smartphone or mobile device. This input information is sent to a server. The server accesses a tourist destination database or a store database to obtain a list of tourist attractions, activities, or stores that meet the criteria. A cloud database (e.g., Firebase (registered trademark)) can be used for this process.

[0138] It then uses a data generation model (e.g. ChatGPT by OpenAI) to suggest attractions, activities, or stores that the user might be interested in. The generated suggestions are sent to the user's smartphone in real time.

[0139] When the user selects a suggested spot or store, the system uses the smartphone's GPS function to display the optimal route to the destination in real time, using the GPS navigation API.

[0140] Additionally, the server will provide audio or text storytelling of history and background information about selected attractions, activities, or stores using voice output APIs and text data display capabilities.

[0141] For example, if a user enters the criteria "two adults, interested in art," the system will suggest art exhibitions and handmade accessory workshops held in the shopping mall. The system will also navigate the route to the events using the smartphone's map function. The origin and history of the art exhibitions can be explained through an audio guide.

[0142] Here is an example of a prompt to be input to the generative AI model:

[0143] "Based on the user's input, suggest appropriate stores and events in the mall near their current location. For example, if two adults are interested in art, suggest art exhibitions and craft workshops and use GPS navigation to guide them to the event."

[0144] In this way, the system of the present invention can provide a series of experiences, from suggesting optimal spots and stores that correspond to the user's interests and preferences to storytelling about those spots and stores.

[0145] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0146] Step 1:

[0147] The user uses a smartphone to input information such as the travel destination, purpose, interests, age, and gender.

[0148] Input: Information such as user interests, destination, age, gender, etc.

[0149] Output: The user input received by the server.

[0150] How it works: The smartphone interface accepts user input and sends that information to a server.

[0151] Step 2:

[0152] Based on the input information received by the server, a list of relevant tourist attractions, activities, or stores is obtained from a tourist attraction database or a store database.

[0153] Input: User input information.

[0154] Output: A list of attractions, activities, or stores that match the criteria.

[0155] How it works: The server queries a database based on the input information and receives a list of results. Example database: Firebase.

[0156] Step 3:

[0157] The server uses the data generation model to suggest tourist attractions, activities, or stores that may be of interest to the user.

[0158] Input: A list of attractions, activities, or stores that match your criteria.

[0159] Output: Suggested attractions, activities, or shops to the user.

[0160] How it works: The server prompts a data generative model (e.g. ChatGPT) and generates suggestions based on the model's output. Example prompt for generative AI model: "Based on the criteria entered by the user, suggest suitable stores and events in shopping malls near my current location."

[0161] Step 4:

[0162] Users receive suggestions via their smartphone and select the ones that interest them.

[0163] Input: Suggested attractions, activities, or stores.

[0164] Output: The user's selection.

[0165] How it works: The smartphone interface displays suggestions and the user selects the ones that interest them.

[0166] Step 5:

[0167] The server generates the optimal route to the selected tourist spot, activity, or store and transmits it to the smartphone in real time. Route generation uses GPS navigation API.

[0168] Input: The user's current location and selected destination.

[0169] Output: Optimal route information.

[0170] How it works: The server calls the GPS navigation API, calculates the optimal route from the current location to the destination, and sends it to the smartphone.

[0171] Step 6:

[0172] The smartphone displays route information to the user in real time.

[0173] Input: The route information sent by the server.

[0174] Output: Visualization of the route (e.g. a map display).

[0175] How it works: The smartphone displays route information on a map and navigates the user.

[0176] Step 7:

[0177] The server provides history and background information about a tourist attraction, activity, or store in a storytelling format.

[0178] Input: The attraction, activity, or store selected by the user.

[0179] Output: Text or audio data for storytelling.

[0180] How it works: The server collects information about the selected spot or store and provides it to the user using the voice output API and text display function.

[0181] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0182] An embodiment for implementing the present invention includes the following elements.

[0183] 1. Incorporating an emotion engine: By incorporating an emotion engine into the system, the system will be able to recognize the user's emotions.

[0184] 2. Emotion recognition means: The emotion engine provides a means of analyzing emotions from the user's speech, facial expressions, tone of voice, etc.

[0185] 3. Sentiment-based suggestion means: The server provides a means for tailoring the suggestions of tourist attractions or activities based on the user's emotions analyzed by the emotion engine, i.e., inferring the user's interests and preferences based on the user's emotions, and suggesting tourist attractions and activities that match the inferred interests and preferences.

[0186] 4. Storytelling Means According to Emotions: The server provides a means to adjust the content and style of storytelling according to the user's emotions analyzed by the emotion engine.

[0187] By combining the above elements, the system of the present invention can be realized, which can recognize the user's emotions, suggest tourist spots and activities based on the emotions, and tell stories according to the emotions, thereby further enriching the travel experience of users, especially children.

[0188] The process flow will be explained below.

[0189] Step 1: The system incorporates an emotion engine to recognize emotions from the user's speech, facial expressions, tone of voice, etc.

[0190] Step 2: The emotion engine analyzes the user's speech, facial expressions, tone of voice, etc. to analyze the user's emotions. Specifically, the emotion engine classifies the user's emotions into categories such as joy, sadness, surprise, and anger.

[0191] Step 3: The server suggests tourist spots and activities that match the user's interests and preferences based on the user's emotions analyzed by the emotion engine. For example, if the user shows an emotion of joy, the server suggests nearby theme parks and amusement parks. For example, if the user shows an emotion of sadness, the server suggests nearby relaxation spots and nature parks.

[0192] Step 4: The server adjusts the content and style of storytelling about tourist attractions and activities according to the user's emotions analyzed by the emotion engine. For example, if the user expresses surprise, the server will tell a story about the tourist attraction's surprising features and episodes. For example, if the user expresses anger, the server will tell a story about the historical background and solutions of the tourist attraction.

[0193] The output conditions for each step are as follows:

[0194] Step 1: Recognize emotions

[0195] Step 2: Sentiment analysis

[0196] Step 3: Emotion-based suggestions

[0197] Step 4: Emotional Storytelling

[0198] Example 2

[0199] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal."

[0200] Conventional travel recommendation systems often make general recommendations without considering the user's current emotional state, which makes it difficult to fully increase user satisfaction. In addition, they lack detailed information and storytelling for the suggested activities and tourist spots, making it difficult to provide users with an engaging travel experience.

[0201] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0202] In this invention, the server includes means for receiving user input (audio, video), means for collecting emotion data from the received user input, means for analyzing the collected emotion data using an emotion engine, means for estimating user interests and suggesting tourist attractions or activities based on the analysis results, and means for storytelling about the suggested tourist attractions or activities using a natural language generation model, thereby enabling appropriate and attractive suggestions and storytelling based on the user's emotions.

[0203] "User input (audio, video)" refers to audio and video data provided by the user to the system.

[0204] "Emotion data" refers to information about emotions extracted from input such as a user's voice or facial expression.

[0205] An "emotion engine" is software or hardware that analyzes a user's voice and video data to recognize emotions.

[0206] "Means for analyzing" refers to means having a function of analyzing collected emotion data using an emotion engine and identifying the user's emotional state.

[0207] The "means for estimating user interests" refers to a means for estimating tourist spots and activities that may be of interest to the user based on the analyzed emotion data.

[0208] A "means for suggesting" is a means having a function of providing a user with suitable tourist spots and activities based on the user's estimated interests.

[0209] A "natural language generation model" is a model or algorithm for generating appropriate language based on a user's emotional data and suggested information.

[0210] A "storytelling means" is a means that has the function of using a natural language generation model to construct a narrative about the proposed tourist attractions and activities and provide it to the user.

[0211] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0212] The following describes an embodiment of the invention.

[0213] The server first receives input from the user. User input refers to voice and video data. The data provided by the user on the terminal is captured through a device such as a smartphone or laptop. This device includes a camera and a microphone to collect the user's facial expressions and voice in real time.

[0214] The collected audio and video data is pre-processed on the device, which may include noise removal, image clipping, and transcoding the data to make it easier to analyze. The pre-processed data is then sent to the server.

[0215] The server analyzes the collected emotion data using an emotion engine, which uses image recognition software (e.g., OpenCV) and voice analysis tools (e.g., Google Cloud Speech-to-Text API) to recognize emotions from the user's voice and facial expressions.

[0216] Based on the emotion data analyzed by the emotion engine, the server evaluates the user's emotion and predicts tourist attractions and activities that the user may be interested in. In this process, a recommendation engine (e.g., TENSORFLOW®) is used to pick out suitable spots and activities based on the user's emotional state and past interests.

[0217] The server then uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities. This storytelling is tailored based on the analyzed emotion data of the user. For example, if the user is having fun, it will talk about the attractions and their features in a fun tone.

[0218] Here is a concrete example: When a family is planning a trip, a child says to the device camera, "I want to do something fun today!" This audio and video data is captured on the device, pre-processed with noise removal and video clipping, and then sent to the server.

[0219] The server uses an emotion engine (OpenCV and Google Cloud Speech-to-Text API) to analyze this data for smiling faces and excited voices and concludes that the user looks like they're having fun. It then uses TensorFlow to select a nearby amusement park as an appropriate suggestion.

[0220] Finally, OpenAI ChatGPT is used to generate storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and send it to the device. In this way, travel experience suggestions and storytelling based on the user's emotions are realized.

[0221] Example prompt:

[0222] "A family is planning a trip and the child says with a smile, 'I want to go to the zoo!' Explain how, based on this information, an emotion engine and a recommendation system can suggest a zoo and provide an interesting story about the zoo."

[0223] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0224] Processing Steps

[0225] Step 1: Receive user input

[0226] Specific description:

[0227] A user inputs voice and video data.

[0228] Input: User's audio and video data.

[0229] Output: The captured data on the device.

[0230] Specific action: The user says into the device's camera and microphone, "I want to have some fun today!"

[0231] Step 2: Collect sentiment data

[0232] Specific description:

[0233] Receives audio and video data captured by the device and performs pre-processing (such as noise removal and image clipping).

[0234] Input: The captured audio and video data.

[0235] Output: Pre-processed audio and video data.

[0236] Specific operation: The terminal removes noise from the audio data and clips the video data to only the necessary parts.

[0237] Step 3: Sentiment analysis

[0238] Specific description:

[0239] The server receives the preprocessed data and analyzes it using an emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API).

[0240] Input: Preprocessed audio and video data.

[0241] Output: Parsed emotion data (e.g., happiness, excitement).

[0242] How it works: The server recognizes the smile and analyzes the excited tone to determine that the user looks happy.

[0243] Step 4: Proposal Generation

[0244] Specific description:

[0245] The server uses a recommendation engine (e.g. TensorFlow) to select appropriate tourist attractions and activities based on the sentiment data.

[0246] Input: Parsed emotion data.

[0247] Output: Suggested attractions and activities for the user.

[0248] Specific operation: The server suggests nearby amusement parks based on the emotional data that indicates "it looks fun."

[0249] Step 5: Storytelling

[0250] Specific description:

[0251] The server uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities.

[0252] Input: Suggested attractions and activities.

[0253] Output: The generated storytelling text.

[0254] Specific operation: The server generates storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and sends it to the device.

[0255] (Application example 2)

[0256] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0257] Conventional shopping assistant and tourist assistant systems are not sufficiently equipped with functions for product suggestions and storytelling based on the user's emotions, making it difficult to improve the quality of the user experience. In addition, there is no system that can analyze the user's emotions and provide optimal recommendations and storytelling based on them, so there is a lack of services that meet the user's needs and emotions. Therefore, the problem that the present invention aims to solve is to propose products and services based on the user's emotions and enrich the user experience.

[0258] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0259] In this invention, the server includes a means for analyzing the user's emotions, a means for proposing products and services based on the emotions, a means for visually displaying the suggestions to the user, a means for generating storytelling content suitable for the emotions using a generative AI model, and a means for providing the generated storytelling to the user. This makes it possible to propose products and services that match the user's emotional state, thereby improving the quality of the user experience.

[0260] "User" refers to a person who uses the system and receives offers of products and services.

[0261] The "means for analyzing emotions" refers to a method or device for recognizing emotions by analyzing a user's facial expressions, tone of voice, and speech content.

[0262] The "means for suggesting products and services" refers to a method or device for selecting and suggesting optimal products and services based on the analyzed emotions.

[0263] A "means for visually displaying offers" is a method or device that visually conveys offers for selected goods or services to a user.

[0264] A "generative AI model" is an artificial intelligence model that learns from data and generates storytelling content based on user emotions.

[0265] A "means for generating storytelling content" is a method or device that uses a generative AI model to create storytelling that is tailored to a user's emotions.

[0266] A "means for providing storytelling" is a method or device that provides the generated storytelling to a user in an appropriate format.

[0267] The system that realizes this invention is a system that analyzes the user's emotions, suggests products and services based on the emotions, and enriches the user experience. This system is composed of the following elements.

[0268] System Configuration

[0269] 1. Means of analyzing emotions: Using a camera and microphone installed on the device (smartphone, smart glasses, head-mounted display, etc.), the user's facial expressions, tone of voice, and spoken content are captured, and the user's emotions are analyzed in real time using emotion analysis software (e.g., the EmotionAnalyzer library).

[0270] 2. Means of suggesting products and services: Based on the analyzed emotion data, a recommendation engine (e.g., the RecommendationEngine library) is used to select the most suitable product or service, using a generative AI model to recommend items or activities that match the user's emotion.

[0271] 3. A means to visually display the offers: The selected products and services are visually displayed on the user's device using the DisplayManager library in a form that the user can view interactively.

[0272] 4. Storytelling content generation method using generative AI model: Using generative AI model, generate storytelling content that matches the user's emotions. For example, if the user is enjoying themselves, generate storytelling content that will further enhance their enjoyment.

[0273] 5. Means of providing storytelling: The generated storytelling is presented to the user visually or audibly. This step also uses the DisplayManager and AudioManager libraries.

[0274] Example of operation

[0275] For example, a user planning a trip can wear smart glasses and use the system. If the system detects that the user is feeling depressed, it can suggest relaxation and mood-boosting products such as an aroma diffuser or a CD with relaxing music.

[0276] Also, if the user is having fun, the service suggests entertainment products and activities such as VR game sets and outdoor equipment.

[0277] Example prompt:

[0278] When a user is wearing smart glasses, detect their emotions and provide optimal shopping suggestions based on their emotions. For example, design an algorithm to suggest relaxation products if the user is depressed, and entertainment products if the user is happy.

[0279] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0280] Step 1:

[0281] The device captures the user's facial expressions, tone of voice, and speech. As input, it uses video and audio data from the camera and microphone. As data processing, it converts these data into a format that can be analyzed by the EmotionAnalyzer library. The output is preprocessed data that is passed to the analysis algorithm.

[0282] Step 2:

[0283] The device uses the EmotionAnalyzer library to analyze the user's emotions based on the preprocessed data. The input is the preprocessed data obtained in step 1. Data calculations include identifying the emotional state (e.g., happiness, sadness, excitement, etc.) using facial expression recognition and voice analysis techniques. The output is the analysis result indicating the user's emotions.

[0284] Step 3:

[0285] The server receives the analysis results and uses the RecommendationEngine library to select products and services based on emotions. The input is the user's emotional state obtained from step 2. As a data operation, product and service candidates corresponding to the emotional state are extracted from a database, and the most suitable suggestions are generated using an optimization algorithm. The output is a list of suggested products and services.

[0286] Step 4:

[0287] The device uses the DisplayManager library to visually display the suggested products and services to the user. The input is the list of products and services obtained in step 3. The data is processed by converting it into a visually understandable format (e.g., images, text, price information, etc.). The output is the information in a display format that the user can view.

[0288] Step 5:

[0289] The server uses the generative AI model to generate storytelling content that matches the user's emotions. The input is the user's emotional state obtained in step 2. For data calculation, a generative AI model (e.g. ChatGPT) is used to generate a story or explanatory text that matches the emotional state. The output is the storytelling content.

[0290] Step 6:

[0291] The device uses the DisplayManager and AudioManager libraries to provide the generated storytelling to the user. The input is the storytelling content generated in step 5. Data processing involves converting it into a format suitable for visual and auditory input. The output is the storytelling content that the user can view.

[0292] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0293] 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<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0294] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0295] [Second embodiment]

[0296] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0297] 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.

[0298] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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 wide area network (WAN) and / or a local area network (LAN).

[0299] 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.

[0300] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0301] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0302] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0303] Fig. 4 shows an example of 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.

[0304] 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 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.

[0305] 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.

[0306] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0307] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0308] An embodiment for implementing the present invention includes the following elements.

[0309] 1. User input receiving means: This is the means by which the server receives input information from the user, such as the travel destination and purpose, the user's preferences and interests, age, and gender.

[0310] 2. Means for obtaining a list of tourist attractions and activities: The server obtains a list of tourist attractions and activities that meet the conditions from the tourist destination database based on the user's input information.

[0311] It is a means to

[0312] 3. Suggestion means: This is a means in which the server uses a generative AI to suggest tourist spots and activities that the user may be interested in based on the acquired list of tourist spots and activities.

[0313] 4. Route display means: A means for the terminal to display routes to suggested tourist spots and activities in real time. The user can head to the destination by referring to the display on the terminal.

[0314] 5. Storytelling means: This is a means by which the server tells a story about the legends and history of the proposed tourist spots. Users can learn while having fun through the stories provided by the server. Examples of storytelling presentation means include displaying text on the terminal or outputting audio.

[0315] By combining the above elements, the system of the present invention can be realized, which receives user input, suggests tourist spots and activities that match the user's criteria, provides real-time routes, and performs storytelling to enrich the travel experience of users, especially children.

[0316] The process flow will be explained below.

[0317] Step 1: The server receives input information from the user, including the travel destination or purpose, or the user's preferences, interests, age, or gender. That is, the user inputs at least one of the travel destination or purpose, the user's preferences or interests, age, and gender.

[0318] Step 2: The server retrieves a list of tourist attractions and activities that meet the criteria. Specifically, the server retrieves a list of tourist attractions and activities that meet the criteria from the tourist destination database based on the received user input information.

[0319] Step 3: Based on the acquired list of tourist attractions and activities, the server suggests tourist attractions and activities that the user may be interested in. For example, if the user inputs that he / she likes the sea, the server suggests nearby beaches and aquariums. Also, if the user inputs that he / she is interested in history, the server suggests nearby castles and museums.

[0320] Step 4: The device presents a route to the proposed tourist spots and activities in real time. Specifically, the device displays an appropriate route taking into account the user's current location and mode of transportation.

[0321] Step 5: The server tells a story about the legends and history of the proposed attractions and activities. For example, if the user indicates that they are interested in ancient ruins, the server might tell them the origins and myths of those ruins.

[0322] The output conditions for each step are as follows:

[0323] Step 1: User Input

[0324] Step 2: List of attractions and activities that fit your criteria

[0325] Step 3: Suggested attractions and activities

[0326] Step 4: Real-time route planning

[0327] Step 5: Information about the attraction or activity being storyteller

[0328] Example 1

[0329] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0330] In modern travel planning and navigation, many users find it difficult to find tourist attractions and activities that match their individual conditions such as interests, preferences, age, and gender. This tends to limit the user's travel experience. It is also difficult to obtain real-time information about the history and legends of a place. There is a need for a system that solves these problems and allows users to have a richer travel experience.

[0331] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0332] In this invention, the server includes a means for receiving input information including the user's travel destination, purpose, preferences, interests, age, and gender, a means for acquiring a list of tourist attractions or activities from a database, a means for using generative AI to suggest tourist attractions or activities that the user may be interested in, a means for presenting routes to the tourist attractions or activities in real time, and a means for storytelling information on the legends and history of the tourist attractions or activities. This not only makes it easier for the user to find tourist attractions or activities that meet their individual requirements, but also allows them to obtain information on the history and legends of the places in real time.

[0333] "User input information" refers to information including travel destination, purpose, preferences, interests, age, and gender.

[0334] A "tourist spot" is a famous place or facility at a travel destination that the user intends to visit.

[0335] "Activities" are attractions and recreational activities that can be undertaken at a tourist destination.

[0336] "Database" means an information source that holds information about attractions and activities.

[0337] "Generative AI" is an artificial intelligence model that generates appropriate suggestions based on user input information.

[0338] "Route presentation" is a function that displays the route to tourist spots and activities selected by the user in real time.

[0339] "Storytelling" is a means of providing legends and historical information related to attractions and activities.

[0340] The present invention provides a system for making travel planning more efficient and enriching a user's travel experience. The system includes a server, a terminal, and a series of means for receiving input information from a user and proposing appropriate sightseeing spots and activities.

[0341] Means of receiving user input information

[0342] The server receives input information from the user, such as travel destination, purpose, preferences, interests, age, gender, etc. The user enters the trip details, for example using a smartphone application. The input information is sent to the server and used in the next processing steps.

[0343] How to get a list of attractions and activities

[0344] The server retrieves a list of tourist attractions and activities that match the criteria from a tourist attraction database based on the information entered by the user. A general-purpose API (e.g., Google Places API or Foursquare API) is used as the tourist attraction database. The server generates a query based on the information entered by the user, sends it to the database, and retrieves a list that matches the criteria.

[0345] Proposal means

[0346] The server uses a generative AI model (e.g., ChatGPT by OpenAI) to generate suggestions based on the list of attractions and activities that the user might be interested in. Specifically, the suggestions are generated using the following prompt:

[0347] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0348] The generated proposals are transmitted from the server to the user's terminal.

[0349] Route presentation method

[0350] The device will present routes to the suggested tourist spots and activities in real time. For example, the device will use the Google Maps API to calculate the optimal route from the user's current location to the destination and display it on a map. The user can use this route as a reference to head to the destination.

[0351] Storytelling Devices

[0352] The server will tell a story about the legends and history of the proposed tourist spots and activities. The terminal will provide the information to the user in the form of text display or audio output. For example, the terminal will play an audio commentary about the history and exhibits of the "Anime Museum." The user can learn while enjoying the story.

[0353] By combining the above means, the system of the present invention supports the user's travel planning and provides various information in real time during the trip, further enriching the user's travel experience and making it attractive especially for children and families.

[0354] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0355] Step 1:

[0356] A user inputs travel information into a smartphone application.

[0357] Input: "Destination: Tokyo", "Purpose: Family trip", "Hobbies: Anime and history", "Age: 35", "Gender: Male"

[0358] Operation:

[0359] 1. The user enters their trip details into the app's form.

[0360] 2. The device sends this information to the server.

[0361] Output: User input sent to the server

[0362] Step 2:

[0363] The server sends a query to a tourist destination database based on the user's input information and retrieves a list of tourist attractions and activities that meet the criteria.

[0364] Input: User input information

[0365] Data processing / calculation:

[0366] 1. The server generates a query based on the user input information it receives.

[0367] 2. The server sends this query to a tourist destination database (e.g. Google Places API).

[0368] 3. The server filters the results returned from the database to create a list of attractions and activities that fit the criteria.

[0369] Output: A filtered list of attractions and activities

[0370] Step 3:

[0371] The server uses a generative AI model to make suggestions that might interest the user based on the list of tourist attractions and activities it has acquired.

[0372] Input: A filtered list of attractions and activities

[0373] Data processing / calculation:

[0374] 1. The server sends the following prompt to the generative AI model (e.g. ChatGPT):

[0375] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0376] 2. The generative AI model generates suggestions and returns a list of tourist attractions as a response.

[0377] Output: A list of suggested attractions and activities that may interest the user.

[0378] Step 4:

[0379] The server sends the suggestion list to the user's terminal, and the terminal presents a route to the spot selected by the user in real time.

[0380] Input: A list of suggested attractions and activities that might interest the user.

[0381] Operation:

[0382] 1. The server sends the proposal list to the user's device.

[0383] 2. The user selects the spot they want to visit from the list of suggestions.

[0384] 3. The device uses the Google Maps API to find the best route from the user's current location to the selected spot.

[0385] 4. The device will display the route in real time and begin navigation.

[0386] Output: Real-time directions to the selected spot

[0387] Step 5:

[0388] The server provides the legends and history of the proposed tourist attractions and activities, which the terminal conveys to the user by display or audio.

[0389] Input: Details of the suggested attraction or activity

[0390] Data processing / calculation:

[0391] 1. The server generates text and audio data of the legend and history of the proposed tourist spot.

[0392] 2. The server sends the generated data to the user's terminal.

[0393] 3. The device displays the text information or plays the information aloud.

[0394] Output: Provides the user with legends and history about attractions and activities.

[0395] (Application example 1)

[0396] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0397] Modern consumers have diverse interests and tastes, and it is difficult for them to efficiently find travel destinations, tourist attractions, and stores in shopping malls that meet their needs. In addition, it is difficult to obtain sufficient information about the history and background of the spots and stores to visit, which can limit their travel and shopping experiences. In particular, there is a demand to provide educational and enjoyable experiences for children and families.

[0398] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0399] In this invention, the server includes a means for receiving input information including a travel destination or purpose, or a user's preferences, interests, age, or gender, a means for acquiring a list of tourist attractions, activities, or stores from a tourist destination database or a store database based on the input information, a means for suggesting the tourist attractions, activities, or stores that the user may be interested in using a data generation model, a means for presenting a route to the tourist attractions, activities, or stores in real time, and a means for storytelling information about the tourist attractions, activities, or stores by voice or text. This allows users to find the best spots and stores according to their individual interests and preferences, and to learn about their history and background while having fun.

[0400] "Input information" refers to information such as the travel destination and purpose, the user's preferences, interests, age, and gender.

[0401] A "tourist destination database" refers to an information source that stores information about tourist attractions and activities.

[0402] "Store database" refers to an information source that stores information about shopping malls and physical stores.

[0403] "Tourist attractions" refer to places that tourists visit.

[0404] "Activities" refers to various experiential activities that take place at tourist spots.

[0405] "Store" refers to retail stores, restaurants, etc. located in shopping malls and commercial facilities.

[0406] A "data generation model" refers to an AI model that predicts user interests based on input information and makes appropriate suggestions.

[0407] "Suggestion means" refers to a function that selects and suggests spots, activities, or stores that may be of interest to the user from among the acquired spots, activities, or stores.

[0408] The "route presentation means" refers to a function that takes into account the user's current location and displays the optimal route to a specified location in real time.

[0409] "Storytelling Means" refers to features that provide audio or text information about the history or background of a tourist attraction, activity, or store.

[0410] The program of the system for implementing the present invention is configured as follows.

[0411] It starts by receiving input information such as the user's travel destination and purpose, the user's preferences, interests, age, and gender using a smartphone or mobile device. This input information is sent to a server. The server accesses a tourist destination database or a store database to obtain a list of tourist attractions, activities, or stores that meet the criteria. A cloud database (e.g., Firebase) can be used for this process.

[0412] It then uses a data generation model (e.g. ChatGPT by OpenAI) to suggest attractions, activities, or stores that the user might be interested in. The generated suggestions are sent to the user's smartphone in real time.

[0413] When the user selects a suggested spot or store, the system uses the smartphone's GPS function to display the optimal route to the destination in real time, using the GPS navigation API.

[0414] Additionally, the server will provide audio or text storytelling of history and background information about selected attractions, activities, or stores using voice output APIs and text data display capabilities.

[0415] For example, if a user enters the criteria "two adults, interested in art," the system will suggest art exhibitions and handmade accessory workshops held in the shopping mall. The system will also navigate the route to the events using the smartphone's map function. The origin and history of the art exhibitions can be explained through an audio guide.

[0416] Here is an example of a prompt to be input to the generative AI model:

[0417] "Based on the user's input, suggest appropriate stores and events in the mall near their current location. For example, if two adults are interested in art, suggest art exhibitions and craft workshops and use GPS navigation to guide them to the event."

[0418] In this way, the system of the present invention can provide a series of experiences, from suggesting optimal spots and stores that correspond to the user's interests and preferences to storytelling about those spots and stores.

[0419] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0420] Step 1:

[0421] The user uses a smartphone to input information such as the travel destination, purpose, interests, age, and gender.

[0422] Input: Information such as user interests, destination, age, gender, etc.

[0423] Output: The user input received by the server.

[0424] How it works: The smartphone interface accepts user input and sends that information to a server.

[0425] Step 2:

[0426] Based on the input information received by the server, a list of relevant tourist attractions, activities, or stores is obtained from a tourist attraction database or a store database.

[0427] Input: User input information.

[0428] Output: A list of attractions, activities, or stores that match the criteria.

[0429] How it works: The server queries a database based on the input information and receives a list of results. Example database: Firebase.

[0430] Step 3:

[0431] The server uses the data generation model to suggest tourist attractions, activities, or stores that may be of interest to the user.

[0432] Input: A list of attractions, activities, or stores that match your criteria.

[0433] Output: Suggested attractions, activities, or shops to the user.

[0434] How it works: The server prompts a data generative model (e.g. ChatGPT) and generates suggestions based on the model's output. Example prompt for generative AI model: "Based on the criteria entered by the user, suggest suitable stores and events in shopping malls near my current location."

[0435] Step 4:

[0436] Users receive suggestions via their smartphone and select the ones that interest them.

[0437] Input: Suggested attractions, activities, or stores.

[0438] Output: The user's selection.

[0439] How it works: The smartphone interface displays suggestions and the user selects the ones that interest them.

[0440] Step 5:

[0441] The server generates the optimal route to the selected tourist spot, activity, or store and transmits it to the smartphone in real time. Route generation uses GPS navigation API.

[0442] Input: The user's current location and selected destination.

[0443] Output: Optimal route information.

[0444] How it works: The server calls the GPS navigation API, calculates the optimal route from the current location to the destination, and sends it to the smartphone.

[0445] Step 6:

[0446] The smartphone displays route information to the user in real time.

[0447] Input: The route information sent by the server.

[0448] Output: Visualization of the route (e.g. a map display).

[0449] How it works: The smartphone displays route information on a map and navigates the user.

[0450] Step 7:

[0451] The server provides history and background information about a tourist attraction, activity, or store in a storytelling format.

[0452] Input: The attraction, activity, or store selected by the user.

[0453] Output: Text or audio data for storytelling.

[0454] How it works: The server collects information about the selected spot or store and provides it to the user using the voice output API and text display function.

[0455] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0456] An embodiment for implementing the present invention includes the following elements.

[0457] 1. Incorporating an emotion engine: By incorporating an emotion engine into the system, the system can understand the user's emotions.

[0458] This realizes the function of recognizing

[0459] 2. Emotion recognition means: The emotion engine provides a means of analyzing emotions from the user's speech, facial expressions, tone of voice, etc.

[0460] 3. Sentiment-based suggestion means: The server provides a means for tailoring the suggestions of tourist attractions or activities based on the user's emotions analyzed by the emotion engine, i.e., inferring the user's interests and preferences based on the user's emotions, and suggesting tourist attractions and activities that match the inferred interests and preferences.

[0461] 4. Storytelling Means According to Emotions: The server provides a means to adjust the content and style of storytelling according to the user's emotions analyzed by the emotion engine.

[0462] By combining the above elements, the system of the present invention can be realized, which can recognize the user's emotions, suggest tourist spots and activities based on the emotions, and tell stories according to the emotions, thereby further enriching the travel experience of users, especially children.

[0463] The process flow will be explained below.

[0464] Step 1: The system incorporates an emotion engine to recognize emotions from the user's speech, facial expressions, tone of voice, etc.

[0465] Step 2: The emotion engine analyzes the user's speech, facial expressions, tone of voice, etc. to analyze the user's emotions. Specifically, the emotion engine classifies the user's emotions into categories such as joy, sadness, surprise, and anger.

[0466] Step 3: The server suggests tourist spots and activities that match the user's interests and preferences based on the user's emotions analyzed by the emotion engine. For example, if the user shows an emotion of joy, the server suggests nearby theme parks and amusement parks. For example, if the user shows an emotion of sadness, the server suggests nearby relaxation spots and nature parks.

[0467] Step 4: The server adjusts the content and style of storytelling about tourist attractions and activities according to the user's emotions analyzed by the emotion engine. For example, if the user expresses surprise, the server will tell a story about the tourist attraction's surprising features and episodes. For example, if the user expresses anger, the server will tell a story about the historical background and solutions of the tourist attraction.

[0468] The output conditions for each step are as follows:

[0469] Step 1: Recognize emotions

[0470] Step 2: Sentiment analysis

[0471] Step 3: Emotion-based suggestions

[0472] Step 4: Emotional Storytelling

[0473] Example 2

[0474] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0475] Conventional travel recommendation systems often make general recommendations without considering the user's current emotional state, which makes it difficult to fully increase user satisfaction. In addition, they lack detailed information and storytelling for the suggested activities and tourist spots, making it difficult to provide users with an engaging travel experience.

[0476] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0477] In this invention, the server includes means for receiving user input (audio, video), means for collecting emotion data from the received user input, means for analyzing the collected emotion data using an emotion engine, means for estimating user interests and suggesting tourist attractions or activities based on the analysis results, and means for storytelling about the suggested tourist attractions or activities using a natural language generation model, thereby enabling appropriate and attractive suggestions and storytelling based on the user's emotions.

[0478] "User input (audio, video)" refers to audio and video data provided by the user to the system.

[0479] "Emotion data" refers to information about emotions extracted from input such as a user's voice or facial expression.

[0480] An "emotion engine" is software or hardware that analyzes a user's voice and video data to recognize emotions.

[0481] "Means for analyzing" refers to means having a function of analyzing collected emotion data using an emotion engine and identifying the user's emotional state.

[0482] The "means for estimating user interests" refers to a means for estimating tourist spots and activities that may be of interest to the user based on the analyzed emotion data.

[0483] A "means for suggesting" is a means having a function of providing a user with suitable tourist spots and activities based on the user's estimated interests.

[0484] A "natural language generation model" is a model or algorithm for generating appropriate language based on a user's emotional data and suggested information.

[0485] A "storytelling means" is a means that has the function of using a natural language generation model to construct a narrative about the proposed tourist attractions and activities and provide it to the user.

[0486] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0487] The following describes an embodiment of the invention.

[0488] The server first receives input from the user. User input refers to voice and video data. The data provided by the user on the terminal is captured through a device such as a smartphone or laptop. This device includes a camera and a microphone to collect the user's facial expressions and voice in real time.

[0489] The collected audio and video data is pre-processed on the device, which may include noise removal, image clipping, and transcoding the data to make it easier to analyze. The pre-processed data is then sent to the server.

[0490] The server analyzes the collected emotion data using an emotion engine, which uses image recognition software (e.g., OpenCV) and voice analysis tools (e.g., Google Cloud Speech-to-Text API) to recognize emotions from the user's voice and facial expressions.

[0491] Based on the emotion data analyzed by the emotion engine, the server evaluates the user's emotions and predicts the attractions and activities he or she may be interested in. In this process, a recommendation engine (e.g., TensorFlow) is used to pick out suitable spots and activities based on the user's emotional state and past interests.

[0492] The server then uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities. This storytelling is tailored based on the analyzed emotion data of the user. For example, if the user is having fun, it will talk about the attractions and their features in a fun tone.

[0493] Here is a concrete example: When a family is planning a trip, a child says to the device camera, "I want to do something fun today!" This audio and video data is captured on the device, pre-processed with noise removal and video clipping, and then sent to the server.

[0494] The server uses an emotion engine (OpenCV and Google Cloud Speech-to-Text API) to analyze this data for smiling faces and excited voices and concludes that the user looks like they're having fun. It then uses TensorFlow to select a nearby amusement park as an appropriate suggestion.

[0495] Finally, OpenAI ChatGPT is used to generate storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and send it to the device. In this way, travel experience suggestions and storytelling based on the user's emotions are realized.

[0496] Example prompt:

[0497] "A family is planning a trip and the child says with a smile, 'I want to go to the zoo!' Explain how, based on this information, an emotion engine and a recommendation system can suggest a zoo and provide an interesting story about the zoo."

[0498] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0499] Processing Steps

[0500] Step 1: Receive user input

[0501] Specific description:

[0502] A user inputs voice and video data.

[0503] Input: User's audio and video data.

[0504] Output: The captured data on the device.

[0505] Specific action: The user says into the device's camera and microphone, "I want to have some fun today!"

[0506] Step 2: Collect sentiment data

[0507] Specific description:

[0508] Receives audio and video data captured by the device and performs pre-processing (such as noise removal and image clipping).

[0509] Input: The captured audio and video data.

[0510] Output: Pre-processed audio and video data.

[0511] Specific operation: The terminal removes noise from the audio data and clips the video data to only the necessary parts.

[0512] Step 3: Sentiment analysis

[0513] Specific description:

[0514] The server receives the preprocessed data and analyzes it using an emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API).

[0515] Input: Preprocessed audio and video data.

[0516] Output: Parsed emotion data (e.g., happiness, excitement).

[0517] How it works: The server recognizes the smile and analyzes the excited tone to determine that the user looks happy.

[0518] Step 4: Proposal Generation

[0519] Specific description:

[0520] The server uses a recommendation engine (e.g. TensorFlow) to select appropriate tourist attractions and activities based on the sentiment data.

[0521] Input: Parsed emotion data.

[0522] Output: Suggested attractions and activities for the user.

[0523] Specific operation: The server suggests nearby amusement parks based on the emotional data that indicates "it looks fun."

[0524] Step 5: Storytelling

[0525] Specific description:

[0526] The server uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities.

[0527] Input: Suggested attractions and activities.

[0528] Output: The generated storytelling text.

[0529] Specific operation: The server generates storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and sends it to the device.

[0530] (Application example 2)

[0531] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0532] Conventional shopping assistant and tourist assistant systems are not sufficiently equipped with functions for product suggestions and storytelling based on the user's emotions, making it difficult to improve the quality of the user experience. In addition, there is no system that can analyze the user's emotions and provide optimal recommendations and storytelling based on them, so there is a lack of services that meet the user's needs and emotions. Therefore, the problem that the present invention aims to solve is to propose products and services based on the user's emotions and enrich the user experience.

[0533] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0534] In this invention, the server includes a means for analyzing the user's emotions, a means for proposing products and services based on the emotions, a means for visually displaying the suggestions to the user, a means for generating storytelling content suitable for the emotions using a generative AI model, and a means for providing the generated storytelling to the user. This makes it possible to propose products and services that match the user's emotional state, thereby improving the quality of the user experience.

[0535] "User" refers to a person who uses the system and receives offers of products and services.

[0536] The "means for analyzing emotions" refers to a method or device for recognizing emotions by analyzing a user's facial expressions, tone of voice, and speech content.

[0537] The "means for suggesting products and services" refers to a method or device for selecting and suggesting optimal products and services based on the analyzed emotions.

[0538] A "means for visually displaying offers" is a method or device that visually conveys offers for selected goods or services to a user.

[0539] A "generative AI model" is an artificial intelligence model that learns from data and generates storytelling content based on user emotions.

[0540] A "means for generating storytelling content" is a method or device that uses a generative AI model to create storytelling that is tailored to a user's emotions.

[0541] A "means for providing storytelling" is a method or device that provides the generated storytelling to a user in an appropriate format.

[0542] The system that realizes this invention is a system that analyzes the user's emotions, suggests products and services based on the emotions, and enriches the user experience. This system is composed of the following elements.

[0543] System Configuration

[0544] 1. Means of analyzing emotions: Using a camera and microphone installed on the device (smartphone, smart glasses, head-mounted display, etc.), the user's facial expressions, tone of voice, and spoken content are captured, and the user's emotions are analyzed in real time using emotion analysis software (e.g., the EmotionAnalyzer library).

[0545] 2. Means of suggesting products and services: Based on the analyzed emotion data, a recommendation engine (e.g., the RecommendationEngine library) is used to select the most suitable product or service, using a generative AI model to recommend items or activities that match the user's emotion.

[0546] 3. A means to visually display the offers: The selected products and services are visually displayed on the user's device using the DisplayManager library in a form that the user can view interactively.

[0547] 4. Storytelling content generation method using generative AI model: Using generative AI model, generate storytelling content that matches the user's emotions. For example, if the user is enjoying themselves, generate storytelling content that will further enhance their enjoyment.

[0548] 5. Means of providing storytelling: The generated storytelling is presented to the user visually or audibly. This step also uses the DisplayManager and AudioManager libraries.

[0549] Example of operation

[0550] For example, a user planning a trip can wear smart glasses and use the system. If the system detects that the user is feeling depressed, it can suggest relaxation and mood-boosting products such as an aroma diffuser or a CD with relaxing music.

[0551] Also, if the user is having fun, the service suggests entertainment products and activities such as VR game sets and outdoor equipment.

[0552] Example prompt:

[0553] When a user is wearing smart glasses, detect their emotions and provide optimal shopping suggestions based on their emotions. For example, design an algorithm to suggest relaxation products if the user is depressed, and entertainment products if the user is happy.

[0554] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0555] Step 1:

[0556] The device captures the user's facial expressions, tone of voice, and speech. As input, it uses video and audio data from the camera and microphone. As data processing, it converts these data into a format that can be analyzed by the EmotionAnalyzer library. The output is preprocessed data that is passed to the analysis algorithm.

[0557] Step 2:

[0558] The device uses the EmotionAnalyzer library to analyze the user's emotions based on the preprocessed data. The input is the preprocessed data obtained in step 1. Data calculations include identifying the emotional state (e.g., happiness, sadness, excitement, etc.) using facial expression recognition and voice analysis techniques. The output is the analysis result indicating the user's emotions.

[0559] Step 3:

[0560] The server receives the analysis results and uses the RecommendationEngine library to select products and services based on emotions. The input is the user's emotional state obtained from step 2. As a data operation, product and service candidates corresponding to the emotional state are extracted from a database, and the most suitable suggestions are generated using an optimization algorithm. The output is a list of suggested products and services.

[0561] Step 4:

[0562] The device uses the DisplayManager library to visually display the suggested products and services to the user. The input is the list of products and services obtained in step 3. The data is processed by converting it into a visually understandable format (e.g., images, text, price information, etc.). The output is the information in a display format that the user can view.

[0563] Step 5:

[0564] The server uses the generative AI model to generate storytelling content that matches the user's emotions. The input is the user's emotional state obtained in step 2. For data calculation, a generative AI model (e.g. ChatGPT) is used to generate a story or explanatory text that matches the emotional state. The output is the storytelling content.

[0565] Step 6:

[0566] The device uses the DisplayManager and AudioManager libraries to provide the generated storytelling to the user. The input is the storytelling content generated in step 5. Data processing involves converting it into a format suitable for visual and auditory input. The output is the storytelling content that the user can view.

[0567] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0568] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0569] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0570] [Third embodiment]

[0571] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0572] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0573] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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 wide area network (WAN) and / or a local area network (LAN).

[0574] 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.

[0575] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0576] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0577] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0578] 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.

[0579] 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 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.

[0580] 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.

[0581] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0582] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server", and the headset type terminal 314 will be referred to as the "terminal".

[0583] An embodiment for implementing the present invention includes the following elements.

[0584] 1. User input receiving means: This is the means by which the server receives input information from the user, such as the travel destination and purpose, the user's preferences and interests, age, and gender.

[0585] 2. Means for obtaining a list of tourist attractions and activities: This is the means by which the server obtains a list of tourist attractions and activities that meet the conditions from the tourist destination database based on the information input by the user.

[0586] 3. Suggestion means: This is a means in which the server uses a generative AI to suggest tourist spots and activities that the user may be interested in based on the acquired list of tourist spots and activities.

[0587] 4. Route display means: A means for the terminal to display routes to suggested tourist spots and activities in real time. The user can head to the destination by referring to the display on the terminal.

[0588] 5. Storytelling means: This is a means by which the server tells a story about the legends and history of the proposed tourist spots. Users can learn while having fun through the stories provided by the server. Examples of storytelling presentation means include displaying text on the terminal or outputting audio.

[0589] By combining the above elements, the system of the present invention can be realized, which receives user input, suggests tourist spots and activities that match the user's criteria, provides real-time routes, and performs storytelling to enrich the travel experience of users, especially children.

[0590] The process flow will be explained below.

[0591] Step 1: The server receives input information from the user, including the travel destination or purpose, or the user's preferences, interests, age, or gender. That is, the user inputs at least one of the travel destination or purpose, the user's preferences or interests, age, and gender.

[0592] Step 2: The server retrieves a list of tourist attractions and activities that meet the criteria. Specifically, the server retrieves a list of tourist attractions and activities that meet the criteria from the tourist destination database based on the received user input information.

[0593] Step 3: Based on the acquired list of tourist attractions and activities, the server suggests tourist attractions and activities that the user may be interested in. For example, if the user inputs that he / she likes the sea, the server suggests nearby beaches and aquariums. Also, if the user inputs that he / she is interested in history, the server suggests nearby castles and museums.

[0594] Step 4: The device presents a route to the proposed tourist spots and activities in real time. Specifically, the device displays an appropriate route taking into account the user's current location and mode of transportation.

[0595] Step 5: The server tells a story about the legends and history of the proposed attractions and activities. For example, if the user indicates that they are interested in ancient ruins, the server might tell them the origins and myths of those ruins.

[0596] The output conditions for each step are as follows:

[0597] Step 1: User Input

[0598] Step 2: List of attractions and activities that fit your criteria

[0599] Step 3: Suggested attractions and activities

[0600] Step 4: Real-time route planning

[0601] Step 5: Information about the attraction or activity being storyteller

[0602] Example 1

[0603] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[0604] In modern travel planning and navigation, many users find it difficult to find tourist attractions and activities that match their individual conditions such as interests, preferences, age, and gender. This tends to limit the user's travel experience. It is also difficult to obtain real-time information about the history and legends of a place. There is a need for a system that solves these problems and allows users to have a richer travel experience.

[0605] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0606] In this invention, the server includes a means for receiving input information including the user's travel destination, purpose, preferences, interests, age, and gender, a means for acquiring a list of tourist attractions or activities from a database, a means for using generative AI to suggest tourist attractions or activities that the user may be interested in, a means for presenting routes to the tourist attractions or activities in real time, and a means for storytelling information on the legends and history of the tourist attractions or activities. This not only makes it easier for the user to find tourist attractions or activities that meet their individual requirements, but also allows them to obtain information on the history and legends of the places in real time.

[0607] "User input information" refers to information including travel destination, purpose, preferences, interests, age, and gender.

[0608] A "tourist spot" is a famous place or facility at a travel destination that the user intends to visit.

[0609] "Activities" are attractions and recreational activities that can be undertaken at a tourist destination.

[0610] "Database" means an information source that holds information about attractions and activities.

[0611] "Generative AI" is an artificial intelligence model that generates appropriate suggestions based on user input information.

[0612] "Route presentation" is a function that displays the route to tourist spots and activities selected by the user in real time.

[0613] "Storytelling" is a means of providing legends and historical information related to attractions and activities.

[0614] The present invention provides a system for making travel planning more efficient and enriching a user's travel experience. The system includes a server, a terminal, and a series of means for receiving input information from a user and proposing appropriate sightseeing spots and activities.

[0615] Means of receiving user input information

[0616] The server receives input information from the user, such as travel destination, purpose, preferences, interests, age, gender, etc. The user enters the trip details, for example using a smartphone application. The input information is sent to the server and used in the next processing steps.

[0617] How to get a list of attractions and activities

[0618] The server retrieves a list of tourist attractions and activities that match the criteria from a tourist attraction database based on the information entered by the user. A general-purpose API (e.g., Google Places API or Foursquare API) is used as the tourist attraction database. The server generates a query based on the information entered by the user, sends it to the database, and retrieves a list that matches the criteria.

[0619] Proposal means

[0620] The server uses a generative AI model (e.g., ChatGPT by OpenAI) to generate suggestions based on the list of attractions and activities that the user might be interested in. Specifically, the suggestions are generated using the following prompt:

[0621] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0622] The generated proposals are transmitted from the server to the user's terminal.

[0623] Route presentation method

[0624] The device will present routes to the suggested tourist spots and activities in real time. For example, the device will use the Google Maps API to calculate the optimal route from the user's current location to the destination and display it on a map. The user can use this route as a reference to head to the destination.

[0625] Storytelling Devices

[0626] The server will tell a story about the legends and history of the proposed tourist spots and activities. The terminal will provide the information to the user in the form of text display or audio output. For example, the terminal will play an audio commentary about the history and exhibits of the "Anime Museum." The user can learn while enjoying the story.

[0627] By combining the above means, the system of the present invention supports the user's travel planning and provides various information in real time during the trip, further enriching the user's travel experience and making it attractive especially for children and families.

[0628] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0629] Step 1:

[0630] A user inputs travel information into a smartphone application.

[0631] Input: "Destination: Tokyo", "Purpose: Family trip", "Hobbies: Anime and history", "Age: 35", "Gender: Male"

[0632] Operation:

[0633] 1. The user enters their trip details into the app's form.

[0634] 2. The device sends this information to the server.

[0635] Output: User input sent to the server

[0636] Step 2:

[0637] The server sends a query to a tourist destination database based on the user's input information and retrieves a list of tourist attractions and activities that meet the criteria.

[0638] Input: User input information

[0639] Data processing / calculation:

[0640] 1. The server generates a query based on the user input information it receives.

[0641] 2. The server sends this query to a tourist destination database (e.g. Google Places API).

[0642] 3. The server filters the results returned from the database to create a list of attractions and activities that fit the criteria.

[0643] Output: A filtered list of attractions and activities

[0644] Step 3:

[0645] The server uses a generative AI model to make suggestions that might interest the user based on the list of tourist attractions and activities it has acquired.

[0646] Input: A filtered list of attractions and activities

[0647] Data processing / calculation:

[0648] 1. The server sends the following prompt to the generative AI model (e.g. ChatGPT):

[0649] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0650] 2. The generative AI model generates suggestions and returns a list of tourist attractions as a response.

[0651] Output: A list of suggested attractions and activities that may interest the user.

[0652] Step 4:

[0653] The server sends the suggestion list to the user's terminal, and the terminal presents a route to the spot selected by the user in real time.

[0654] Input: A list of suggested attractions and activities that might interest the user.

[0655] Operation:

[0656] 1. The server sends the proposal list to the user's device.

[0657] 2. The user selects the spot they want to visit from the list of suggestions.

[0658] 3. The device uses the Google Maps API to find the best route from the user's current location to the selected spot.

[0659] 4. The device will display the route in real time and begin navigation.

[0660] Output: Real-time directions to the selected spot

[0661] Step 5:

[0662] The server provides the legends and history of the proposed tourist attractions and activities, which the terminal conveys to the user by display or audio.

[0663] Input: Details of the suggested attraction or activity

[0664] Data processing / calculation:

[0665] 1. The server generates text and audio data of the legend and history of the proposed tourist spot.

[0666] 2. The server sends the generated data to the user's terminal.

[0667] 3. The device displays the text information or plays the information aloud.

[0668] Output: Provides the user with legends and history about attractions and activities.

[0669] (Application example 1)

[0670] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0671] Modern consumers have diverse interests and tastes, and it is difficult for them to efficiently find travel destinations, tourist attractions, and stores in shopping malls that meet their needs. In addition, it is difficult to obtain sufficient information about the history and background of the spots and stores to visit, which can limit their travel and shopping experiences. In particular, there is a demand to provide educational and enjoyable experiences for children and families.

[0672] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0673] In this invention, the server includes a means for receiving input information including a travel destination or purpose, or a user's preferences, interests, age, or gender, a means for acquiring a list of tourist attractions, activities, or stores from a tourist destination database or a store database based on the input information, a means for suggesting the tourist attractions, activities, or stores that the user may be interested in using a data generation model, a means for presenting a route to the tourist attractions, activities, or stores in real time, and a means for storytelling information about the tourist attractions, activities, or stores by voice or text. This allows users to find the best spots and stores according to their individual interests and preferences, and to learn about their history and background while having fun.

[0674] "Input information" refers to information such as the travel destination and purpose, the user's preferences, interests, age, and gender.

[0675] A "tourist destination database" refers to an information source that stores information about tourist attractions and activities.

[0676] "Store database" refers to an information source that stores information about shopping malls and physical stores.

[0677] "Tourist attractions" refer to places that tourists visit.

[0678] "Activities" refers to various experiential activities that take place at tourist spots.

[0679] "Store" refers to retail stores, restaurants, etc. located in shopping malls and commercial facilities.

[0680] A "data generation model" refers to an AI model that predicts user interests based on input information and makes appropriate suggestions.

[0681] "Suggestion means" refers to a function that selects and suggests spots, activities, or stores that may be of interest to the user from among the acquired spots, activities, or stores.

[0682] The "route presentation means" refers to a function that takes into account the user's current location and displays the optimal route to a specified location in real time.

[0683] "Storytelling Means" refers to features that provide audio or text information about the history or background of a tourist attraction, activity, or store.

[0684] The program of the system for implementing the present invention is configured as follows.

[0685] It starts by receiving input information such as the user's travel destination and purpose, the user's preferences, interests, age, and gender using a smartphone or mobile device. This input information is sent to a server. The server accesses a tourist destination database or a store database to obtain a list of tourist attractions, activities, or stores that meet the criteria. A cloud database (e.g., Firebase) can be used for this process.

[0686] It then uses a data generation model (e.g. ChatGPT by OpenAI) to suggest attractions, activities, or stores that the user might be interested in. The generated suggestions are sent to the user's smartphone in real time.

[0687] When the user selects a suggested spot or store, the system uses the smartphone's GPS function to display the optimal route to the destination in real time, using the GPS navigation API.

[0688] Additionally, the server will provide audio or text storytelling of history and background information about selected attractions, activities, or stores using voice output APIs and text data display capabilities.

[0689] For example, if a user enters the criteria "two adults, interested in art," the system will suggest art exhibitions and handmade accessory workshops held in the shopping mall. The system will also navigate the route to the events using the smartphone's map function. The origin and history of the art exhibitions can be explained through an audio guide.

[0690] Here is an example of a prompt to be input to the generative AI model:

[0691] "Based on the user's input, suggest appropriate stores and events in the mall near their current location. For example, if two adults are interested in art, suggest art exhibitions and craft workshops and use GPS navigation to guide them to the event."

[0692] In this way, the system of the present invention can provide a series of experiences, from suggesting optimal spots and stores that correspond to the user's interests and preferences to storytelling about those spots and stores.

[0693] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0694] Step 1:

[0695] The user uses a smartphone to input information such as the travel destination, purpose, interests, age, and gender.

[0696] Input: Information such as user interests, destination, age, gender, etc.

[0697] Output: The user input received by the server.

[0698] How it works: The smartphone interface accepts user input and sends that information to a server.

[0699] Step 2:

[0700] Based on the input information received by the server, a list of relevant tourist attractions, activities, or stores is obtained from a tourist attraction database or a store database.

[0701] Input: User input information.

[0702] Output: A list of attractions, activities, or stores that match the criteria.

[0703] How it works: The server queries a database based on the input information and receives a list of results. Example database: Firebase.

[0704] Step 3:

[0705] The server uses the data generation model to suggest tourist attractions, activities, or stores that may be of interest to the user.

[0706] Input: A list of attractions, activities, or stores that match your criteria.

[0707] Output: Suggested attractions, activities, or shops to the user.

[0708] How it works: The server prompts a data generative model (e.g. ChatGPT) and generates suggestions based on the model's output. Example prompt for generative AI model: "Based on the criteria entered by the user, suggest suitable stores and events in shopping malls near my current location."

[0709] Step 4:

[0710] Users receive suggestions via their smartphone and select the ones that interest them.

[0711] Input: Suggested attractions, activities, or stores.

[0712] Output: The user's selection.

[0713] How it works: The smartphone interface displays suggestions and the user selects the ones that interest them.

[0714] Step 5:

[0715] The server generates the optimal route to the selected tourist spot, activity, or store and transmits it to the smartphone in real time. Route generation uses GPS navigation API.

[0716] Input: The user's current location and selected destination.

[0717] Output: Optimal route information.

[0718] How it works: The server calls the GPS navigation API, calculates the optimal route from the current location to the destination, and sends it to the smartphone.

[0719] Step 6:

[0720] The smartphone displays route information to the user in real time.

[0721] Input: The route information sent by the server.

[0722] Output: Visualization of the route (e.g. a map display).

[0723] How it works: The smartphone displays route information on a map and navigates the user.

[0724] Step 7:

[0725] The server provides history and background information about a tourist attraction, activity, or store in a storytelling format.

[0726] Input: The attraction, activity, or store selected by the user.

[0727] Output: Text or audio data for storytelling.

[0728] How it works: The server collects information about the selected spot or store and provides it to the user using the voice output API and text display function.

[0729] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0730] An embodiment for implementing the present invention includes the following elements.

[0731] 1. Incorporating an emotion engine: By incorporating an emotion engine into the system, the system will be able to recognize the user's emotions.

[0732] 2. Emotion recognition means: The emotion engine provides a means of analyzing emotions from the user's speech, facial expressions, tone of voice, etc.

[0733] 3. Sentiment-based suggestion means: The server provides a means for tailoring the suggestions of tourist attractions or activities based on the user's emotions analyzed by the emotion engine, i.e., inferring the user's interests and preferences based on the user's emotions, and suggesting tourist attractions and activities that match the inferred interests and preferences.

[0734] 4. Storytelling Means According to Emotions: The server provides a means to adjust the content and style of storytelling according to the user's emotions analyzed by the emotion engine.

[0735] By combining the above elements, the system of the present invention can be realized, which can recognize the user's emotions, suggest tourist spots and activities based on the emotions, and tell stories according to the emotions, thereby further enriching the travel experience of users, especially children.

[0736] The process flow will be explained below.

[0737] Step 1: The system recognizes emotions from the user's speech, facial expressions, tone of voice, etc.

[0738] Incorporate an emotion engine into.

[0739] Step 2: The emotion engine analyzes the user's speech, facial expressions, tone of voice, etc. to analyze the user's emotions. Specifically, the emotion engine classifies the user's emotions into categories such as joy, sadness, surprise, and anger.

[0740] Step 3: The server suggests tourist spots and activities that match the user's interests and preferences based on the user's emotions analyzed by the emotion engine. For example, if the user shows an emotion of joy, the server suggests nearby theme parks and amusement parks. For example, if the user shows an emotion of sadness, the server suggests nearby relaxation spots and nature parks.

[0741] Step 4: The server adjusts the content and style of storytelling about tourist attractions and activities according to the user's emotions analyzed by the emotion engine. For example, if the user expresses surprise, the server will tell a story about the tourist attraction's surprising features and episodes. For example, if the user expresses anger, the server will tell a story about the historical background and solutions of the tourist attraction.

[0742] The output conditions for each step are as follows:

[0743] Step 1: Recognize emotions

[0744] Step 2: Sentiment analysis

[0745] Step 3: Emotion-based suggestions

[0746] Step 4: Emotional Storytelling

[0747] Example 2

[0748] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[0749] Conventional travel recommendation systems often make general recommendations without considering the user's current emotional state, which makes it difficult to fully increase user satisfaction. In addition, they lack detailed information and storytelling for the suggested activities and tourist spots, making it difficult to provide users with an engaging travel experience.

[0750] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0751] In this invention, the server includes means for receiving user input (audio, video), means for collecting emotion data from the received user input, means for analyzing the collected emotion data using an emotion engine, means for estimating user interests and suggesting tourist attractions or activities based on the analysis results, and means for storytelling about the suggested tourist attractions or activities using a natural language generation model, thereby enabling appropriate and attractive suggestions and storytelling based on the user's emotions.

[0752] "User input (audio, video)" refers to audio and video data provided by the user to the system.

[0753] "Emotion data" refers to information about emotions extracted from input such as a user's voice or facial expression.

[0754] An "emotion engine" is software or hardware that analyzes a user's voice and video data to recognize emotions.

[0755] "Means for analyzing" refers to means having a function of analyzing collected emotion data using an emotion engine and identifying the user's emotional state.

[0756] The "means for estimating user interests" refers to a means for estimating tourist spots and activities that may be of interest to the user based on the analyzed emotion data.

[0757] A "means for suggesting" is a means having a function of providing a user with suitable tourist spots and activities based on the user's estimated interests.

[0758] A "natural language generation model" is a model or algorithm for generating appropriate language based on a user's emotional data and suggested information.

[0759] A "storytelling means" is a means that has the function of using a natural language generation model to construct a narrative about the proposed tourist attractions and activities and provide it to the user.

[0760] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0761] The following describes an embodiment of the invention.

[0762] The server first receives input from the user. User input refers to voice and video data. The data provided by the user on the terminal is captured through a device such as a smartphone or laptop. This device includes a camera and a microphone to collect the user's facial expressions and voice in real time.

[0763] The collected audio and video data is pre-processed on the device, which may include noise removal, image clipping, and transcoding the data to make it easier to analyze. The pre-processed data is then sent to the server.

[0764] The server analyzes the collected emotion data using an emotion engine, which uses image recognition software (e.g., OpenCV) and voice analysis tools (e.g., Google Cloud Speech-to-Text API) to recognize emotions from the user's voice and facial expressions.

[0765] Based on the emotion data analyzed by the emotion engine, the server evaluates the user's emotions and predicts the attractions and activities he or she may be interested in. In this process, a recommendation engine (e.g., TensorFlow) is used to pick out suitable spots and activities based on the user's emotional state and past interests.

[0766] The server then uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities. This storytelling is tailored based on the analyzed emotion data of the user. For example, if the user is having fun, it will talk about the attractions and their features in a fun tone.

[0767] Here is a concrete example: When a family is planning a trip, a child says to the device camera, "I want to do something fun today!" This audio and video data is captured on the device, pre-processed with noise removal and video clipping, and then sent to the server.

[0768] The server uses an emotion engine (OpenCV and Google Cloud Speech-to-Text API) to analyze this data for smiling faces and excited voices and concludes that the user looks like they're having fun. It then uses TensorFlow to select a nearby amusement park as an appropriate suggestion.

[0769] Finally, OpenAI ChatGPT is used to generate storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and send it to the device. In this way, travel experience suggestions and storytelling based on the user's emotions are realized.

[0770] Example prompt:

[0771] "A family is planning a trip and the child says with a smile, 'I want to go to the zoo!' Explain how, based on this information, an emotion engine and a recommendation system can suggest a zoo and provide an interesting story about the zoo."

[0772] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0773] Processing Steps

[0774] Step 1: Receive user input

[0775] Specific description:

[0776] A user inputs voice and video data.

[0777] Input: User's audio and video data.

[0778] Output: The captured data on the device.

[0779] Specific action: The user says into the device's camera and microphone, "I want to have some fun today!"

[0780] Step 2: Collect sentiment data

[0781] Specific description:

[0782] Receives audio and video data captured by the device and performs pre-processing (such as noise removal and image clipping).

[0783] Input: The captured audio and video data.

[0784] Output: Pre-processed audio and video data.

[0785] Specific operation: The terminal removes noise from the audio data and clips the video data to only the necessary parts.

[0786] Step 3: Sentiment analysis

[0787] Specific description:

[0788] The server receives the preprocessed data and analyzes it using an emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API).

[0789] Input: Preprocessed audio and video data.

[0790] Output: Parsed emotion data (e.g., happiness, excitement).

[0791] How it works: The server recognizes the smile and analyzes the excited tone to determine that the user looks happy.

[0792] Step 4: Proposal Generation

[0793] Specific description:

[0794] The server uses a recommendation engine (e.g. TensorFlow) to select appropriate tourist attractions and activities based on the sentiment data.

[0795] Input: Parsed emotion data.

[0796] Output: Suggested attractions and activities for the user.

[0797] Specific operation: The server suggests nearby amusement parks based on the emotional data that indicates "it looks fun."

[0798] Step 5: Storytelling

[0799] Specific description:

[0800] The server uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities.

[0801] Input: Suggested attractions and activities.

[0802] Output: The generated storytelling text.

[0803] Specific operation: The server generates storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and sends it to the device.

[0804] (Application example 2)

[0805] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[0806] Conventional shopping assistant and tourist assistant systems are not sufficiently equipped with functions for product suggestions and storytelling based on the user's emotions, making it difficult to improve the quality of the user experience. In addition, there is no system that can analyze the user's emotions and provide optimal recommendations and storytelling based on them, so there is a lack of services that meet the user's needs and emotions. Therefore, the problem that the present invention aims to solve is to propose products and services based on the user's emotions and enrich the user experience.

[0807] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0808] In this invention, the server includes a means for analyzing the user's emotions, a means for proposing products and services based on the emotions, a means for visually displaying the suggestions to the user, a means for generating storytelling content suitable for the emotions using a generative AI model, and a means for providing the generated storytelling to the user. This makes it possible to propose products and services that match the user's emotional state, thereby improving the quality of the user experience.

[0809] "User" refers to a person who uses the system and receives offers of products and services.

[0810] The "means for analyzing emotions" refers to a method or device for recognizing emotions by analyzing a user's facial expressions, tone of voice, and speech content.

[0811] The "means for suggesting products and services" refers to a method or device for selecting and suggesting optimal products and services based on the analyzed emotions.

[0812] A "means for visually displaying offers" is a method or device that visually conveys offers for selected goods or services to a user.

[0813] A "generative AI model" is an artificial intelligence model that learns from data and generates storytelling content based on user emotions.

[0814] A "means for generating storytelling content" is a method or device that uses a generative AI model to create storytelling that is tailored to a user's emotions.

[0815] A "means for providing storytelling" is a method or device that provides the generated storytelling to a user in an appropriate format.

[0816] The system that realizes this invention is a system that analyzes the user's emotions, suggests products and services based on the emotions, and enriches the user experience. This system is composed of the following elements.

[0817] System Configuration

[0818] 1. Means of analyzing emotions: Using a camera and microphone installed on the device (smartphone, smart glasses, head-mounted display, etc.), the user's facial expressions, tone of voice, and spoken content are captured, and the user's emotions are analyzed in real time using emotion analysis software (e.g., the EmotionAnalyzer library).

[0819] 2. Means of suggesting products and services: Based on the analyzed emotion data, a recommendation engine (e.g., the RecommendationEngine library) is used to select the most suitable product or service, using a generative AI model to recommend items or activities that match the user's emotion.

[0820] 3. A means to visually display the offers: The selected products and services are visually displayed on the user's device using the DisplayManager library in a form that the user can view interactively.

[0821] 4. Storytelling content generation method using generative AI model: Using generative AI model, generate storytelling content that matches the user's emotions. For example, if the user is enjoying themselves, generate storytelling content that will further enhance their enjoyment.

[0822] 5. Means of providing storytelling: The generated storytelling is presented to the user visually or audibly. This step also uses the DisplayManager and AudioManager libraries.

[0823] Example of operation

[0824] For example, a user planning a trip can wear smart glasses and use the system. If the system detects that the user is feeling depressed, it can suggest relaxation and mood-boosting products such as an aroma diffuser or a CD with relaxing music.

[0825] Also, if the user is having fun, the service suggests entertainment products and activities such as VR game sets and outdoor equipment.

[0826] Example prompt:

[0827] When a user is wearing smart glasses, detect their emotions and provide optimal shopping suggestions based on their emotions. For example, design an algorithm to suggest relaxation products if the user is depressed, and entertainment products if the user is happy.

[0828] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0829] Step 1:

[0830] The device captures the user's facial expressions, tone of voice, and speech. As input, it uses video and audio data from the camera and microphone. As data processing, it converts these data into a format that can be analyzed by the EmotionAnalyzer library. The output is preprocessed data that is passed to the analysis algorithm.

[0831] Step 2:

[0832] The device uses the EmotionAnalyzer library to analyze the user's emotions based on the preprocessed data. The input is the preprocessed data obtained in step 1. Data calculations include identifying the emotional state (e.g., happiness, sadness, excitement, etc.) using facial expression recognition and voice analysis techniques. The output is the analysis result indicating the user's emotions.

[0833] Step 3:

[0834] The server receives the analysis results and uses the RecommendationEngine library to select products and services based on emotions. The input is the user's emotional state obtained from step 2. As a data operation, product and service candidates corresponding to the emotional state are extracted from a database, and the most suitable suggestions are generated using an optimization algorithm. The output is a list of suggested products and services.

[0835] Step 4:

[0836] The device uses the DisplayManager library to visually display the suggested products and services to the user. The input is the list of products and services obtained in step 3. The data is processed by converting it into a visually understandable format (e.g., images, text, price information, etc.). The output is the information in a display format that the user can view.

[0837] Step 5:

[0838] The server uses the generative AI model to generate storytelling content that matches the user's emotions. The input is the user's emotional state obtained in step 2. For data calculation, a generative AI model (e.g. ChatGPT) is used to generate a story or explanatory text that matches the emotional state. The output is the storytelling content.

[0839] Step 6:

[0840] The device uses the DisplayManager and AudioManager libraries to provide the generated storytelling to the user. The input is the storytelling content generated in step 5. Data processing involves converting it into a format suitable for visual and auditory input. The output is the storytelling content that the user can view.

[0841] 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 voice indicating a user input for 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.

[0842] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0843] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0844] [Fourth embodiment]

[0845] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0846] 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.

[0847] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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 wide area network (WAN) and / or a local area network (LAN).

[0848] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0849] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0850] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0851] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0852] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[0853] Fig. 8 shows an example of 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.

[0854] 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 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.

[0855] 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.

[0856] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0857] Next, a description will be given of the specific processing by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[0858] An embodiment for implementing the present invention includes the following elements.

[0859] 1. User input receiving means: This is the means by which the server receives input information from the user, such as the travel destination and purpose, the user's preferences and interests, age, and gender.

[0860] 2. Means for obtaining a list of tourist attractions and activities: This is the means by which the server obtains a list of tourist attractions and activities that meet the conditions from the tourist destination database based on the information input by the user.

[0861] 3. Suggestion means: This is a means in which the server uses a generative AI to suggest tourist spots and activities that the user may be interested in based on the acquired list of tourist spots and activities.

[0862] 4. Route display means: A means for the terminal to display routes to suggested tourist spots and activities in real time. The user can head to the destination by referring to the display on the terminal.

[0863] 5. Storytelling means: This is a means by which the server tells a story about the legends and history of the proposed tourist spots. Users can learn while having fun through the stories provided by the server. An example of a means for presenting storytelling is audio output on the terminal.

[0864] By combining the above elements, the system of the present invention can be realized, which receives user input, suggests tourist spots and activities that match the user's criteria, provides real-time routes, and performs storytelling to enrich the travel experience of users, especially children.

[0865] The process flow will be explained below.

[0866] Step 1: The server receives input information from the user, including the travel destination or purpose, or the user's preferences, interests, age, or gender. That is, the user inputs at least one of the travel destination or purpose, the user's preferences or interests, age, and gender.

[0867] Step 2: The server retrieves a list of tourist attractions and activities that meet the criteria. Specifically, the server retrieves a list of tourist attractions and activities that meet the criteria from the tourist destination database based on the received user input information.

[0868] Step 3: Based on the acquired list of tourist attractions and activities, the server suggests tourist attractions and activities that the user may be interested in. For example, if the user inputs that he / she likes the sea, the server suggests nearby beaches and aquariums. Also, if the user inputs that he / she is interested in history, the server suggests nearby castles and museums.

[0869] Step 4: The device presents a route to the proposed tourist spots and activities in real time. Specifically, the device displays an appropriate route taking into account the user's current location and mode of transportation.

[0870] Step 5: The server tells a story about the legends and history of the proposed attractions and activities. For example, if the user indicates that they are interested in ancient ruins, the server might tell them the origins and myths of those ruins.

[0871] The output conditions for each step are as follows:

[0872] Step 1: User Input

[0873] Step 2: List of attractions and activities that fit your criteria

[0874] Step 3: Suggested attractions and activities

[0875] Step 4: Real-time route planning

[0876] Step 5: Information about the attraction or activity being storyteller

[0877] Example 1

[0878] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the robot 414 is referred to as a "terminal."

[0879] In modern travel planning and navigation, many users find it difficult to find tourist attractions and activities that match their individual conditions such as interests, preferences, age, and gender. This tends to limit the user's travel experience. It is also difficult to obtain real-time information about the history and legends of a place. There is a need for a system that solves these problems and allows users to have a richer travel experience.

[0880] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0881] In this invention, the server includes a means for receiving input information including the user's travel destination, purpose, preferences, interests, age, and gender, a means for acquiring a list of tourist attractions or activities from a database, a means for using generative AI to suggest tourist attractions or activities that the user may be interested in, a means for presenting routes to the tourist attractions or activities in real time, and a means for storytelling information on the legends and history of the tourist attractions or activities. This not only makes it easier for the user to find tourist attractions or activities that meet their individual requirements, but also allows them to obtain information on the history and legends of the places in real time.

[0882] "User input information" refers to information including travel destination, purpose, preferences, interests, age, and gender.

[0883] A "tourist spot" is a famous place or facility at a travel destination that the user intends to visit.

[0884] "Activities" are attractions and recreational activities that can be undertaken at a tourist destination.

[0885] "Database" means an information source that holds information about attractions and activities.

[0886] "Generative AI" is an artificial intelligence model that generates appropriate suggestions based on user input information.

[0887] "Route presentation" is a function that displays the route to tourist spots and activities selected by the user in real time.

[0888] "Storytelling" is a means of providing legends and historical information related to attractions and activities.

[0889] The present invention provides a system for making travel planning more efficient and enriching a user's travel experience. The system includes a server, a terminal, and a series of means for receiving input information from a user and proposing appropriate sightseeing spots and activities.

[0890] Means of receiving user input information

[0891] The server receives input information from the user, such as travel destination, purpose, preferences, interests, age, gender, etc. The user enters the trip details, for example using a smartphone application. The input information is sent to the server and used in the next processing steps.

[0892] How to get a list of attractions and activities

[0893] The server retrieves a list of tourist attractions and activities that match the criteria from a tourist attraction database based on the information entered by the user. A general-purpose API (e.g., Google Places API or Foursquare API) is used as the tourist attraction database. The server generates a query based on the information entered by the user, sends it to the database, and retrieves a list that matches the criteria.

[0894] Proposal means

[0895] The server uses a generative AI model (e.g., ChatGPT by OpenAI) to generate suggestions based on the list of attractions and activities that the user might be interested in. Specifically, the suggestions are generated using the following prompt:

[0896] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0897] The generated proposals are transmitted from the server to the user's terminal.

[0898] Route presentation method

[0899] The device will present routes to the suggested tourist spots and activities in real time. For example, the device will use the Google Maps API to calculate the optimal route from the user's current location to the destination and display it on a map. The user can use this route as a reference to head to the destination.

[0900] Storytelling Devices

[0901] The server will tell a story about the legends and history of the proposed tourist spots and activities. The terminal will provide the information to the user in the form of text display or audio output. For example, the terminal will play an audio commentary about the history and exhibits of the "Anime Museum." The user can learn while enjoying the story.

[0902] By combining the above means, the system of the present invention supports the user's travel planning and provides various information in real time during the trip, further enriching the user's travel experience and making it attractive especially for children and families.

[0903] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0904] Step 1:

[0905] A user inputs travel information into a smartphone application.

[0906] Input: "Destination: Tokyo", "Purpose: Family trip", "Hobbies: Anime and history", "Age: 35", "Gender: Male"

[0907] Operation:

[0908] 1. The user enters their trip details into the app's form.

[0909] 2. The device sends this information to the server.

[0910] Output: User input sent to the server

[0911] Step 2:

[0912] The server sends a query to a tourist destination database based on the user's input information and retrieves a list of tourist attractions and activities that meet the criteria.

[0913] Input: User input information

[0914] Data processing / calculation:

[0915] 1. The server generates a query based on the user input information it receives.

[0916] 2. The server sends this query to a tourist destination database (e.g. Google Places API).

[0917] 3. The server filters the results returned from the database to create a list of attractions and activities that fit the criteria.

[0918] Output: A filtered list of attractions and activities

[0919] Step 3:

[0920] The server uses a generative AI model to make suggestions that might interest the user based on the list of tourist attractions and activities it has acquired.

[0921] Input: A filtered list of attractions and activities

[0922] Data processing / calculation:

[0923] 1. The server sends the following prompt to the generative AI model (e.g. ChatGPT):

[0924] "Please suggest the best tourist spots in Tokyo for a 35-year-old user who likes anime and history."

[0925] 2. The generative AI model generates suggestions and returns a list of tourist attractions as a response.

[0926] Output: A list of suggested attractions and activities that may interest the user.

[0927] Step 4:

[0928] The server sends the suggestion list to the user's terminal, and the terminal presents a route to the spot selected by the user in real time.

[0929] Input: A list of suggested attractions and activities that might interest the user.

[0930] Operation:

[0931] 1. The server sends the proposal list to the user's device.

[0932] 2. The user selects the spot they want to visit from the list of suggestions.

[0933] 3. The device uses the Google Maps API to find the best route from the user's current location to the selected spot.

[0934] 4. The device will display the route in real time and begin navigation.

[0935] Output: Real-time directions to the selected spot

[0936] Step 5:

[0937] The server provides the legends and history of the proposed tourist attractions and activities, which the terminal conveys to the user by display or audio.

[0938] Input: Details of the suggested attraction or activity

[0939] Data processing / calculation:

[0940] 1. The server generates text and audio data of the legend and history of the proposed tourist spot.

[0941] 2. The server sends the generated data to the user's terminal.

[0942] 3. The device displays the text information or plays the information aloud.

[0943] Output: Provides the user with legends and history about attractions and activities.

[0944] (Application example 1)

[0945] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0946] Modern consumers have diverse interests and tastes, and it is difficult for them to efficiently find travel destinations, tourist attractions, and stores in shopping malls that meet their needs. In addition, it is difficult to obtain sufficient information about the history and background of the spots and stores to visit, which can limit their travel and shopping experiences. In particular, there is a demand to provide educational and enjoyable experiences for children and families.

[0947] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0948] In this invention, the server includes a means for receiving input information including a travel destination or purpose, or a user's preferences, interests, age, or gender, a means for acquiring a list of tourist attractions, activities, or stores from a tourist destination database or a store database based on the input information, a means for suggesting the tourist attractions, activities, or stores that the user may be interested in using a data generation model, a means for presenting a route to the tourist attractions, activities, or stores in real time, and a means for storytelling information about the tourist attractions, activities, or stores by voice or text. This allows users to find the best spots and stores according to their individual interests and preferences, and to learn about their history and background while having fun.

[0949] "Input information" refers to information such as the travel destination and purpose, the user's preferences, interests, age, and gender.

[0950] A "tourist destination database" refers to an information source that stores information about tourist attractions and activities.

[0951] "Store database" refers to an information source that stores information about shopping malls and physical stores.

[0952] "Tourist attractions" refer to places that tourists visit.

[0953] "Activities" refers to various experiential activities that take place at tourist spots.

[0954] "Store" refers to retail stores, restaurants, etc. located in shopping malls and commercial facilities.

[0955] A "data generation model" refers to an AI model that predicts user interests based on input information and makes appropriate suggestions.

[0956] "Suggestion means" refers to a function that selects and suggests spots, activities, or stores that may be of interest to the user from among the acquired spots, activities, or stores.

[0957] The "route presentation means" refers to a function that takes into account the user's current location and displays the optimal route to a specified location in real time.

[0958] "Storytelling Means" refers to features that provide audio or text information about the history or background of a tourist attraction, activity, or store.

[0959] The program of the system for implementing the present invention is configured as follows.

[0960] It starts by receiving input information such as the user's travel destination and purpose, the user's preferences, interests, age, and gender using a smartphone or mobile device. This input information is sent to a server. The server accesses a tourist destination database or a store database to obtain a list of tourist attractions, activities, or stores that meet the criteria. A cloud database (e.g., Firebase) can be used for this process.

[0961] It then uses a data generation model (e.g. ChatGPT by OpenAI) to suggest attractions, activities, or stores that the user might be interested in. The generated suggestions are sent to the user's smartphone in real time.

[0962] When the user selects a suggested spot or store, the system uses the smartphone's GPS function to display the optimal route to the destination in real time, using the GPS navigation API.

[0963] Additionally, the server will provide audio or text storytelling of history and background information about selected attractions, activities, or stores using voice output APIs and text data display capabilities.

[0964] For example, if a user enters the criteria "two adults, interested in art," the system will suggest art exhibitions and handmade accessory workshops held in the shopping mall. The system will also navigate the route to the events using the smartphone's map function. The origin and history of the art exhibitions can be explained through an audio guide.

[0965] Here is an example of a prompt to be input to the generative AI model:

[0966] "Based on the user's input, suggest appropriate stores and events in the mall near their current location. For example, if two adults are interested in art, suggest art exhibitions and craft workshops and use GPS navigation to guide them to the event."

[0967] In this way, the system of the present invention can provide a series of experiences, from suggesting optimal spots and stores that correspond to the user's interests and preferences to storytelling about those spots and stores.

[0968] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0969] Step 1:

[0970] The user uses a smartphone to input information such as the travel destination, purpose, interests, age, and gender.

[0971] Input: Information such as user interests, destination, age, gender, etc.

[0972] Output: The user input received by the server.

[0973] How it works: The smartphone interface accepts user input and sends that information to a server.

[0974] Step 2:

[0975] Based on the input information received by the server, a list of relevant tourist attractions, activities, or stores is obtained from a tourist attraction database or a store database.

[0976] Input: User input information.

[0977] Output: A list of attractions, activities, or stores that match the criteria.

[0978] How it works: The server queries a database based on the input information and receives a list of results. Example database: Firebase.

[0979] Step 3:

[0980] The server uses the data generation model to suggest tourist attractions, activities, or stores that may be of interest to the user.

[0981] Input: A list of attractions, activities, or stores that match your criteria.

[0982] Output: Suggested attractions, activities, or shops to the user.

[0983] How it works: The server prompts a data generative model (e.g. ChatGPT) and generates suggestions based on the model's output. Example prompt for generative AI model: "Based on the criteria entered by the user, suggest suitable stores and events in shopping malls near my current location."

[0984] Step 4:

[0985] Users receive suggestions via their smartphone and select the ones that interest them.

[0986] Input: Suggested attractions, activities, or stores.

[0987] Output: The user's selection.

[0988] How it works: The smartphone interface displays suggestions and the user selects the ones that interest them.

[0989] Step 5:

[0990] The server generates the optimal route to the selected tourist spot, activity, or store and transmits it to the smartphone in real time. Route generation uses GPS navigation API.

[0991] Input: The user's current location and selected destination.

[0992] Output: Optimal route information.

[0993] How it works: The server calls the GPS navigation API, calculates the optimal route from the current location to the destination, and sends it to the smartphone.

[0994] Step 6:

[0995] The smartphone displays route information to the user in real time.

[0996] Input: The route information sent by the server.

[0997] Output: Visualization of the route (e.g. a map display).

[0998] How it works: The smartphone displays route information on a map and navigates the user.

[0999] Step 7:

[1000] The server provides history and background information about a tourist attraction, activity, or store in a storytelling format.

[1001] Input: The attraction, activity, or store selected by the user.

[1002] Output: Text or audio data for storytelling.

[1003] How it works: The server collects information about the selected spot or store and provides it to the user using the voice output API and text display function.

[1004] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1005] An embodiment for implementing the present invention includes the following elements.

[1006] 1. Incorporating an emotion engine: By incorporating an emotion engine into the system, the system will be able to recognize the user's emotions.

[1007] 2. Emotion recognition means: The emotion engine provides a means of analyzing emotions from the user's speech, facial expressions, tone of voice, etc.

[1008] 3. Sentiment-based suggestion means: The server provides a means for tailoring the suggestions of tourist attractions or activities based on the user's emotions analyzed by the emotion engine, i.e., inferring the user's interests and preferences based on the user's emotions, and suggesting tourist attractions and activities that match the inferred interests and preferences.

[1009] 4. Storytelling Means According to Emotions: The server provides a means to adjust the content and style of storytelling according to the user's emotions analyzed by the emotion engine.

[1010] By combining the above elements, the system of the present invention can be realized, which can recognize the user's emotions, suggest tourist spots and activities based on the emotions, and tell stories according to the emotions, thereby further enriching the travel experience of users, especially children.

[1011] The process flow will be explained below.

[1012] Step 1: The system incorporates an emotion engine to recognize emotions from the user's speech, facial expressions, tone of voice, etc.

[1013] Step 2: The emotion engine analyzes the user's speech, facial expressions, tone of voice, etc. to analyze the user's emotions. Specifically, the emotion engine classifies the user's emotions into categories such as joy, sadness, surprise, and anger.

[1014] Step 3: The server suggests tourist spots and activities that match the user's interests and preferences based on the user's emotions analyzed by the emotion engine. For example, if the user shows an emotion of joy, the server suggests nearby theme parks and amusement parks. For example, if the user shows an emotion of sadness, the server suggests nearby relaxation spots and nature parks.

[1015] Step 4: The server adjusts the content and style of storytelling about tourist attractions and activities according to the user's emotions analyzed by the emotion engine. For example, if the user expresses surprise, the server will tell a story about the tourist attraction's surprising features and episodes. For example, if the user expresses anger, the server will tell a story about the historical background and solutions of the tourist attraction.

[1016] The output conditions for each step are as follows:

[1017] Step 1: Recognize emotions

[1018] Step 2: Sentiment analysis

[1019] Step 3: Emotion-based suggestions

[1020] Step 4: Emotional Storytelling

[1021] Example 2

[1022] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the robot 414 is referred to as a "terminal."

[1023] Conventional travel recommendation systems often make general recommendations without considering the user's current emotional state, which makes it difficult to fully increase user satisfaction. In addition, they lack detailed information and storytelling for the suggested activities and tourist spots, making it difficult to provide users with an engaging travel experience.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1025] In this invention, the server includes means for receiving user input (audio, video), means for collecting emotion data from the received user input, means for analyzing the collected emotion data using an emotion engine, means for estimating user interests and suggesting tourist attractions or activities based on the analysis results, and means for storytelling about the suggested tourist attractions or activities using a natural language generation model, thereby enabling appropriate and attractive suggestions and storytelling based on the user's emotions.

[1026] "User input (audio, video)" refers to audio and video data provided by the user to the system.

[1027] "Emotion data" refers to information about emotions extracted from input such as a user's voice or facial expression.

[1028] An "emotion engine" is software or hardware that analyzes a user's voice and video data to recognize emotions.

[1029] "Means for analyzing" refers to means having a function of analyzing collected emotion data using an emotion engine and identifying the user's emotional state.

[1030] The "means for estimating user interests" refers to a means for estimating tourist spots and activities that may be of interest to the user based on the analyzed emotion data.

[1031] A "means for suggesting" is a means having a function of providing a user with suitable tourist spots and activities based on the user's estimated interests.

[1032] A "natural language generation model" is a model or algorithm for generating appropriate language based on a user's emotional data and suggested information.

[1033] A "storytelling means" is a means that has the function of using a natural language generation model to construct a narrative about the proposed tourist attractions and activities and provide it to the user.

[1034] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1035] The following describes an embodiment of the invention.

[1036] The server first receives input from the user. User input refers to voice and video data. The data provided by the user on the terminal is captured through a device such as a smartphone or laptop. This device includes a camera and a microphone to collect the user's facial expressions and voice in real time.

[1037] The collected audio and video data is pre-processed on the device, which may include noise removal, image clipping, and transcoding the data to make it easier to analyze. The pre-processed data is then sent to the server.

[1038] The server analyzes the collected emotion data using an emotion engine, which uses image recognition software (e.g., OpenCV) and voice analysis tools (e.g., Google Cloud Speech-to-Text API) to recognize emotions from the user's voice and facial expressions.

[1039] Based on the emotion data analyzed by the emotion engine, the server evaluates the user's emotions and predicts the attractions and activities he or she may be interested in. In this process, a recommendation engine (e.g., TensorFlow) is used to pick out suitable spots and activities based on the user's emotional state and past interests.

[1040] The server then uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities. This storytelling is tailored based on the analyzed emotion data of the user. For example, if the user is having fun, it will talk about the attractions and their features in a fun tone.

[1041] Here is a concrete example: When a family is planning a trip, a child says to the device camera, "I want to do something fun today!" This audio and video data is captured on the device, pre-processed with noise removal and video clipping, and then sent to the server.

[1042] The server uses an emotion engine (OpenCV and Google Cloud Speech-to-Text API) to analyze this data for smiling faces and excited voices and concludes that the user looks like they're having fun. It then uses TensorFlow to select a nearby amusement park as an appropriate suggestion.

[1043] Finally, OpenAI ChatGPT is used to generate storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and send it to the device. In this way, travel experience suggestions and storytelling based on the user's emotions are realized.

[1044] Example prompt:

[1045] "A family is planning a trip and the child says with a smile, 'I want to go to the zoo!' Explain how, based on this information, an emotion engine and a recommendation system can suggest a zoo and provide an interesting story about the zoo."

[1046] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1047] Processing Steps

[1048] Step 1: Receive user input

[1049] Specific description:

[1050] A user inputs voice and video data.

[1051] Input: User's audio and video data.

[1052] Output: The captured data on the device.

[1053] Specific action: The user says into the device's camera and microphone, "I want to have some fun today!"

[1054] Step 2: Collect sentiment data

[1055] Specific description:

[1056] Receives audio and video data captured by the device and performs pre-processing (such as noise removal and image clipping).

[1057] Input: The captured audio and video data.

[1058] Output: Pre-processed audio and video data.

[1059] Specific operation: The terminal removes noise from the audio data and clips the video data to only the necessary parts.

[1060] Step 3: Sentiment analysis

[1061] Specific description:

[1062] The server receives the preprocessed data and analyzes it using an emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API).

[1063] Input: Preprocessed audio and video data.

[1064] Output: Parsed emotion data (e.g., happiness, excitement).

[1065] How it works: The server recognizes the smile and analyzes the excited tone to determine that the user looks happy.

[1066] Step 4: Proposal Generation

[1067] Specific description:

[1068] The server uses a recommendation engine (e.g. TensorFlow) to select appropriate tourist attractions and activities based on the sentiment data.

[1069] Input: Parsed emotion data.

[1070] Output: Suggested attractions and activities for the user.

[1071] Specific operation: The server suggests nearby amusement parks based on the emotional data that indicates "it looks fun."

[1072] Step 5: Storytelling

[1073] Specific description:

[1074] The server uses a natural language generation model (e.g., OpenAI ChatGPT) to generate storytelling about the suggested attractions and activities.

[1075] Input: Suggested attractions and activities.

[1076] Output: The generated storytelling text.

[1077] Specific operation: The server generates storytelling such as "Let's go to the amusement park today! There are lots of fun attractions there" and sends it to the device.

[1078] (Application example 2)

[1079] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1080] Conventional shopping assistant and tourist assistant systems are not sufficiently equipped with functions for product suggestions and storytelling based on the user's emotions, making it difficult to improve the quality of the user experience. In addition, there is no system that can analyze the user's emotions and provide optimal recommendations and storytelling based on them, so there is a lack of services that meet the user's needs and emotions. Therefore, the problem that the present invention aims to solve is to propose products and services based on the user's emotions and enrich the user experience.

[1081] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1082] In this invention, the server includes a means for analyzing the user's emotions, a means for proposing products and services based on the emotions, a means for visually displaying the suggestions to the user, a means for generating storytelling content suitable for the emotions using a generative AI model, and a means for providing the generated storytelling to the user. This makes it possible to propose products and services that match the user's emotional state, thereby improving the quality of the user experience.

[1083] "User" refers to a person who uses the system and receives offers of products and services.

[1084] The "means for analyzing emotions" refers to a method or device for recognizing emotions by analyzing a user's facial expressions, tone of voice, and speech content.

[1085] The "means for suggesting products and services" refers to a method or device for selecting and suggesting optimal products and services based on the analyzed emotions.

[1086] A "means for visually displaying offers" is a method or device that visually conveys offers for selected goods or services to a user.

[1087] A "generative AI model" is an artificial intelligence model that learns from data and generates storytelling content based on user emotions.

[1088] A "means for generating storytelling content" is a method or device that uses a generative AI model to create storytelling that is tailored to a user's emotions.

[1089] A "means for providing storytelling" is a method or device that provides the generated storytelling to a user in an appropriate format.

[1090] The system that realizes this invention is a system that analyzes the user's emotions, suggests products and services based on the emotions, and enriches the user experience. This system is composed of the following elements.

[1091] System Configuration

[1092] 1. Means of analyzing emotions: Using a camera and microphone installed on the device (smartphone, smart glasses, head-mounted display, etc.), the user's facial expressions, tone of voice, and spoken content are captured, and the user's emotions are analyzed in real time using emotion analysis software (e.g., the EmotionAnalyzer library).

[1093] 2. Means of suggesting products and services: Based on the analyzed emotion data, a recommendation engine (e.g., the RecommendationEngine library) is used to select the most suitable product or service, using a generative AI model to recommend items or activities that match the user's emotion.

[1094] 3. A means to visually display the offers: The selected products and services are visually displayed on the user's device using the DisplayManager library in a form that the user can view interactively.

[1095] 4. Storytelling content generation method using generative AI model: Using generative AI model, generate storytelling content that matches the user's emotions. For example, if the user is enjoying themselves, generate storytelling content that will further enhance their enjoyment.

[1096] 5. Means of providing storytelling: The generated storytelling is presented to the user visually or audibly. This step also uses the DisplayManager and AudioManager libraries.

[1097] Example of operation

[1098] For example, a user planning a trip can wear smart glasses and use the system. If the system detects that the user is feeling depressed, it can suggest relaxation and mood-boosting products such as an aroma diffuser or a CD with relaxing music.

[1099] Also, if the user is having fun, the service suggests entertainment products and activities such as VR game sets and outdoor equipment.

[1100] Example prompt:

[1101] When a user is wearing smart glasses, detect their emotions and provide optimal shopping suggestions based on their emotions. For example, design an algorithm to suggest relaxation products if the user is depressed, and entertainment products if the user is happy.

[1102] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1103] Step 1:

[1104] The device captures the user's facial expressions, tone of voice, and speech. As input, it uses video and audio data from the camera and microphone. As data processing, it converts these data into a format that can be analyzed by the EmotionAnalyzer library. The output is preprocessed data that is passed to the analysis algorithm.

[1105] Step 2:

[1106] The device uses the EmotionAnalyzer library to analyze the user's emotions based on the preprocessed data. The input is the preprocessed data obtained in step 1. Data calculations include identifying the emotional state (e.g., happiness, sadness, excitement, etc.) using facial expression recognition and voice analysis techniques. The output is the analysis result indicating the user's emotions.

[1107] Step 3:

[1108] The server receives the analysis results and uses the RecommendationEngine library to select products and services based on emotions. The input is the user's emotional state obtained from step 2. As a data operation, product and service candidates corresponding to the emotional state are extracted from a database, and the most suitable suggestions are generated using an optimization algorithm. The output is a list of suggested products and services.

[1109] Step 4:

[1110] The device uses the DisplayManager library to visually display the suggested products and services to the user. The input is the list of products and services obtained in step 3. The data is processed by converting it into a visually understandable format (e.g., images, text, price information, etc.). The output is the information in a display format that the user can view.

[1111] Step 5:

[1112] The server uses the generative AI model to generate storytelling content that matches the user's emotions. The input is the user's emotional state obtained in step 2. For data calculation, a generative AI model (e.g. ChatGPT) is used to generate a story or explanatory text that matches the emotional state. The output is the storytelling content.

[1113] Step 6:

[1114] The device uses the DisplayManager and AudioManager libraries to provide the generated storytelling to the user. The input is the storytelling content generated in step 5. Data processing involves converting it into a format suitable for visual and auditory input. The output is the storytelling content that the user can view.

[1115] 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 a voice indicating a user input for 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.

[1116] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1117] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the robot 414.

[1118] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[1119] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1120] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[1121] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[1122] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[1123] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[1124] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[1125] Although the system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, the system according to the present disclosure is not necessarily implemented in a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program that runs on a personal computer, or an application that runs on a smartphone or the like. The method according to the present disclosure may be provided to a user in the form of SaaS (Software as a Service).

[1126] In the above embodiment, an example is given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to input data.

[1127] 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 Universal Serial Bus (USB) 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.

[1128] In addition, 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 upon request from the data processing device 12.

[1129] 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.

[1130] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[1131] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[1132] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[1133] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[1134] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[1135] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference.

[1136] The following is further disclosed regarding the above embodiment.

[1137] (Appendix 1) means for receiving input information including travel destination or purpose, or user preferences, interests, age, or gender; A means for acquiring a list of tourist attractions or activities from a tourist destination database based on the input information; A means for suggesting tourist attractions or activities that may be of interest to the user using a data generation model; A means for displaying a route to the tourist spot or the activity in real time; A system including:

[1138] (Appendix 2) The system described in Appendix 1, wherein the means for presenting a route to the tourist spot or activity in real time presents an appropriate route taking into account the user's current location or means of transportation.

[1139] (Appendix 3) 3. The system of claim 1 or claim 2, further comprising a means for storytelling information about the legend or history of the tourist attraction or activity.

[1140] (Appendix 4) The system according to claim 1, further comprising an emotion engine for recognizing the emotions of the user.

[1141] (Appendix 5) 4. The system of claim 1, further comprising: using the emotion engine to adjust the tourist spot or activity suggestions based on the user's emotions.

[1142] (Appendix 6) Further comprising a means for storytelling information about the legend or history of the tourist attraction or the activity; The system of claim 4 or 5, characterized in that the emotion engine is used to adjust the content or style of storytelling of legendary or historical information about the tourist spot or activity depending on the user's emotions.

[1143] "Example 1"

[1144] (Claim 1) means for receiving input information including a user's travel destination, purpose, preferences, interests, age, and gender; A means for retrieving a list of tourist attractions or activities from a database based on the input information; A means for suggesting the tourist spots or activities that may be of interest to the user using a generative AI; A means for displaying a route to the tourist spot or the activity in real time; A means for storytelling information about the legends and history of said tourist spot or said activity; A system including:

[1145] (Claim 2) The system according to claim 1, characterized in that the means for presenting a route to the tourist spot or the activity in real time presents an appropriate route taking into account the user's current location and means of transportation.

[1146] (Claim 3) The system according to claim 1, further comprising means for providing information on the legend or history of the tourist spot or the activity as text information or audio information.

[1147] "Application example 1"

[1148] (Claim 1) means for receiving input information including travel destination or purpose, or user preferences, interests, age, or gender; A means for acquiring a list of tourist attractions, activities, or stores from a tourist destination database or a store database based on the input information; A means for suggesting the tourist spots, activities, or stores that may be of interest to the user using a data generation model; A means for displaying a route to the tourist spot, the activity, or the store in real time; A means for storytelling information about the tourist spots, the activities, or the stores by voice or text; A system including:

[1149] (Claim 2) The system according to claim 1, characterized in that the means for presenting a route to the tourist spot, the activity or the store in real time presents an appropriate route taking into account the user's current location or means of transportation.

[1150] (Claim 3) The system of claim 1 , further comprising a means for storytelling information about the legend or history of the tourist attraction, the activity, or the store.

[1151] "Example 2 of combining emotion engines"

[1152] (Claim 1) a means for receiving user input (audio, video); means for collecting emotion data from received user input; a means for analyzing the collected emotion data using an emotion engine; A means for estimating the user's interests and suggesting tourist spots or activities based on the analysis results; a means for storytelling about the proposed tourist attraction or activity using a natural language generation model; A system including:

[1153] (Claim 2) The system according to claim 1, characterized in that it collects user emotion data in real time and makes appropriate suggestions.

[1154] (Claim 3) The system according to claim 1, further comprising means for suggesting suitable tourist attractions or activities taking into account a user's current location or mode of transportation.

[1155] "Application example 2 when combining emotion engines"

[1156] (Claim 1) A means for analyzing user emotions; A means for suggesting products or services based on said emotions; means for visually displaying the suggestions to a user; means for generating storytelling content appropriate to said emotion using a generative AI model; a means for providing the generated storytelling to a user; A system including:

[1157] (Claim 2) 2. The system according to claim 1, wherein the means for analyzing the user's emotions performs analysis based on the user's facial expression, tone of voice, and speech content.

[1158] (Claim 3) 10. The system of claim 1, wherein the product and service suggestions generate a list of attractions, activities, and products that are optimized to match the user's emotions. [Explanation of symbols]

[1159] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving input information including travel destination or purpose, or user preferences, interests, age, or gender; A means for acquiring a list of tourist attractions or activities from a tourist destination database based on the input information; A means for suggesting tourist attractions or activities that may be of interest to the user using a data generation model; A means for displaying a route to the tourist spot or the activity in real time; a means for storytelling information about the legend or history of said tourist spot or said activity; A system including:

2. The system according to claim 1, characterized in that the means for presenting a route to the tourist spot or the activity in real time presents an appropriate route taking into account the user's current location or means of transportation.

3. The system according to claim 1, characterized in that the means for storytelling information about the legend or history of the tourist spot or the activity provides the information about the legend or history of the tourist spot or the activity as text information or audio information.

4. means for analyzing the emotion of the user using an emotion engine for recognizing the emotion of the user from the voice or video of the user; The system according to claim 1, characterized in that the means for suggesting tourist attractions or activities estimates the user's interests based on the user's emotions and suggests the tourist attractions or activities that the user is likely to be interested in.

Images