System

Abstract

A system is provided.SOLUTION: This system is provided with a means for acquiring the present location information of a user, a means for collecting peripheral information based on the acquired present location information, a means for generating a text from the peripheral information collected based on the interest and taste information of the user, a means for converting the generated text into voice data, and a means for providing the voice data to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, many users are looking for ways to spend their time on the move, whether commuting or sightseeing, more meaningfully. However, it can be difficult to see the screen of a smartphone while on the move, which can pose a safety risk, especially for public transportation users and drivers. Furthermore, effective advertising methods are limited for municipalities and businesses seeking to promote local tourist destinations, local specialties, and local industries. Therefore, it is necessary to provide users on the move with useful information tailored to their interests and preferences without relying on their visual sense, while at the same time providing a means to effectively incorporate local advertising. [Means for solving the problem]

[0005] The present invention provides a system including a means for acquiring a user's current location information, a means for collecting surrounding information based on the acquired current location information, a means for generating text from the collected surrounding information based on the user's hobby and preference information, a means for converting the generated text into voice data, and a means for providing the voice data to the user. Specifically, the user's current location information includes the direction of travel, and the collected surrounding information includes information on tourist spots, local specialties, and local industries. The generated text is generated using a generative AI model, and the voice data is provided in real time. The system also collects user feedback and updates the generative AI model to improve the quality of the information provided. The system also includes a means for generating local advertisements from the collected surrounding information. This system allows users on the move to obtain useful information without relying on their vision, enabling municipalities and businesses to advertise effectively.

[0006] A "user" is a person who uses this system to receive information provision services while traveling.

[0007] "Location information" means data that indicates the user's current geographic location, and may include latitude and longitude information.

[0008] "Movement direction" is information indicating the direction in which the user is currently moving.

[0009] "Nearby information" refers to information related to the user's current location and its surroundings, including information on tourist spots, local specialties, and local industries.

[0010] "Hobbies and Preference Information" is information about the interests and concerns that a user has set in advance or that are inferred from past usage history.

[0011] "Text generation" refers to creating text based on collected peripheral and advertising information, and may involve the use of generative AI models.

[0012] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate text or data based on input information.

[0013] "Audio data" means data that is provided to the user in the form of voice, converted from the generated text using speech synthesis technology.

[0014] "Real-time" refers to processing and providing information instantly according to the user's current situation.

[0015] "Feedback" refers to the evaluations and impressions provided by users after using a system, and is used to improve and optimize the system.

[0016] "Local advertising" refers to advertising information related to businesses and stores near the user's current location. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] 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.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] 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.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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.

[0031] 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 (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] 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.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. 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.

[0037] Next, a description will be given of the specific processing performed 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 smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for provision.

[0039] System Embodiments

[0040] System Overview

[0041] This system consists of a user's device, a server, and a communications network connecting them. The user's device has the ability to acquire current location information and direction of movement and send it to the server. The server collects surrounding information based on the received information and converts it into text using a generative AI model. The converted text is then converted into voice data and finally sent to the user's device.

[0042] Program processing flow

[0043] 1. Acquisition of user information

[0044] When a user launches the app, the device obtains the current location (latitude and longitude) and direction of travel using the GPS and compass functions.

[0045] 2. Transmission of information

[0046] The device sends information about the user's current location, direction of travel, and hobbies and preferences to a server via the Internet.

[0047] 3. Collection of Information

[0048] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, the tourist destination database can provide information on nearby famous places, while the local industry database can provide information on local specialties and businesses.

[0049] 4. Text Generation

[0050] Based on the surrounding information collected by the server and the user's hobbies and preferences, a generative AI model is used to generate text. The generative AI model uses natural language processing technology to generate information that is interesting to the user.

[0051] 5. Generating Audio Data

[0052] The server then passes the generated text to a speech synthesis engine, which converts it into voice data. The speech synthesis engine supports a variety of voice formats and is tailored to the language and accent selected by the user.

[0053] 6. Sending and Playing Audio Data

[0054] The server sends the generated audio data to the device, which then plays it back in real time, ensuring proper audio output even if the user is using a Bluetooth headset or car speakers.

[0055] 7. Gathering Feedback

[0056] The user inputs their satisfaction and thoughts about the provided information and sends it from the device to the server, thereby collecting user feedback.

[0057] 8. System Optimization

[0058] The server analyzes user feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0059] Specific examples

[0060] Use in tourist areas

[0061] 1. The user launches the app while in Kyoto City.

[0062] 2. The device acquires the current location information (latitude and longitude within Kyoto City) and the direction of movement northward.

[0063] 3. The device sends the acquired information to the server.

[0064] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[0065] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[0066] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0067] 7. The device plays the audio data it has received, and explains, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[0068] 8. The user enters their rating for the information provided into the app and sends it to the server.

[0069] 9. The server analyzes this feedback and optimizes the content of the next offering.

[0070] In this way, this system can provide useful information to users on the move without relying on vision, and can also provide an effective advertising tool for municipalities and businesses.In addition, by customizing information to suit the user's hobbies and preferences, it is possible to achieve even higher levels of satisfaction.

[0071] The processing flow will be explained below.

[0072] Program processing flow

[0073] Step 1:

[0074] The user launches the app.

[0075] The device obtains the current location information (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[0076] Step 2:

[0077] The device sends the current location information, direction of movement, and user preferences to the server. The communication protocol is HTTPS, and data is encrypted.

[0078] Step 3:

[0079] The server analyzes the received current location information and sends a query to a database of nearby tourist attractions to obtain tourist attraction information.

[0080] At the same time, queries are sent to a local industry database to obtain information on nearby specialties and companies.

[0081] Step 4:

[0082] Based on the surrounding area information acquired by the server and the user's hobbies and preferences, the generative AI model generates text to be provided to the user. For example, for a user who likes history, the system generates information such as "Many buildings from the Edo period remain in this area."

[0083] Step 5:

[0084] The system also generates local ads based on the information it collects, such as "A nearby souvenir shop sells local Japanese sweets."

[0085] Step 6:

[0086] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[0087] Step 7:

[0088] The server transmits the generated voice data to the terminal via the Internet.

[0089] Step 8:

[0090] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[0091] Step 9:

[0092] Users can provide feedback on the information provided by the app, leaving ratings and comments.

[0093] Step 10:

[0094] The terminal transmits the user's feedback information to the server.

[0095] Step 11:

[0096] The server analyzes the feedback and updates the generative AI model and database, which will result in even more accurate information being provided in future.

[0097] In this way, the system provides users with customized information based on their current location, travel direction, and preferences, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[0098] Example 1

[0099] 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 smart device 14 will be referred to as a "terminal."

[0100] Conventional information provision systems are limited to providing simple text information based on the user's current location, making it difficult to provide detailed, personalized information tailored to the user's preferences. Furthermore, because information is primarily acquired visually, it is difficult to obtain information effectively in situations where it is difficult to use one's eyes, such as while traveling or driving. Furthermore, there is a lack of a mechanism for improving the accuracy of the system based on user feedback.

[0101] 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.

[0102] In this invention, the server includes a means for acquiring the user's current location information, a means for collecting surrounding information based on the acquired current location information and travel direction information, a means for using a generative AI model to generate text from the collected surrounding information based on the user's interest and preference information, a means for using a speech synthesis engine to convert the generated text into speech data, a means for providing the generated speech data to the user, and a means for collecting user feedback and updating the generative AI model and database to improve the accuracy of information provision. This enables the provision of detailed, personalized speech information tailored to the user's interests and preferences. Furthermore, useful information can be obtained without relying on vision, improving the accuracy of the system.

[0103] "User's current location information" refers to the latitude and longitude data of the user's current location.

[0104] "Movement direction information" is information about the direction in which the user is currently moving, and is data obtained using a compass function or the like.

[0105] "Nearby information" is various data about the neighborhood collected based on the user's current location information and travel direction information.

[0106] "Hobbies and preferences information" is information that indicates the user's personal interests and concerns, such as favorite tourist spots and favorite foods.

[0107] A "generative AI model" is an artificial intelligence technology that generates text from surrounding information based on the user's hobbies and preferences.

[0108] A "speech synthesis engine" is a software or hardware technology for converting generated text into speech data.

[0109] "Feedback" refers to information that a user writes down about their satisfaction with and thoughts about the information provided and sends it to the server.

[0110] "Updating a database" means rewriting an existing database to the latest version based on newly collected data and feedback.

[0111] MODE FOR CARRYING OUT THE INVENTION

[0112] This invention relates to a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for delivery. This system operates via the user's terminal, a server, and a communication network.

[0113] Hardware and software used

[0114] Device: A device such as a smartphone or tablet held by a user, equipped with GPS and compass functions.

[0115] Server: Collects information and generates text and voice data using generative AI models and a speech synthesis engine. For example, a cloud server (AWS, GCP, etc.) is used.

[0116] Communication network: Terminals and servers exchange information via the Internet.

[0117] Processing Details

[0118] Getting user information

[0119] When a user launches the app, the device uses the GPS function to obtain the current location (latitude and longitude) and the compass function to obtain the direction of travel.

[0120] Sending information

[0121] The terminal transmits the acquired current location information, movement direction information, and user's hobbies and preferences information to a server via the Internet.

[0122] Collection of information

[0123] Based on the current location information and movement direction information received by the server, the server collects surrounding information from the tourist destination database and local industry database. For example, if the current location is Kyoto City, the server will obtain information on "Kinkakuji Temple" from the tourist destination database and "Kyoto specialty product stores" from the local industry database.

[0124] Text generation

[0125] The server generates text using a generative AI model (e.g., GPT-4) based on this surrounding information and the user's hobbies and preferences. An example of a prompt sentence is "Generate information about nearby tourist spots and souvenir shops for a user in Kyoto City."

[0126] Generating audio data

[0127] The server converts the generated text into speech data using a speech synthesis engine (e.g., Google Cloud Text-to-Speech). For example, the generated text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century" is converted into speech data.

[0128] Sending and playing audio data

[0129] The server sends the generated audio data to the device, which then plays the received audio data in real time.

[0130] Gathering feedback

[0131] The user inputs his / her satisfaction level and thoughts about the provided information and transmits them to the server via the terminal.

[0132] System optimization

[0133] The server analyzes the collected feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0134] Specific examples

[0135] Use in tourist areas

[0136] 1. The user launches the app while in Kyoto City.

[0137] 2. The device uses the GPS function to obtain current location information (latitude and longitude within Kyoto City) and the compass function to obtain the direction of movement northward.

[0138] 3. The device sends the acquired information to a server via the Internet.

[0139] 4. Based on the current location information, the server collects information on "Kinkaku-ji Temple" from the tourist destination database and "Kyoto specialty stores" from the local industry database.

[0140] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[0141] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0142] 7. The device plays back the received audio data in real time, and provides information such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[0143] 8. The user enters the rating into the app and sends it to the server.

[0144] 9. The server analyzes the feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0145] The system allows users to hear detailed, personalized information based on their current location, providing useful information without relying on vision, and allows for feedback to improve the system's accuracy.

[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0147] Step 1:

[0148] Getting user information

[0149] When a user launches the app, the device uses the GPS function to obtain current location information (latitude and longitude). The input is the user's action of launching the app. The output is current location information (e.g., 35.0116 degrees north latitude, 135.7681 degrees east longitude). In addition, the compass function is used to obtain movement direction information. The output is movement direction information (e.g., heading north).

[0150] Step 2:

[0151] Sending information

[0152] The device transmits the current location information, travel direction information, and user interest and preference information to a server via the Internet. The inputs are the current location information, travel direction information, and interest and preference information obtained by the device. The server receives this information as output.

[0153] Step 3:

[0154] Collection of information

[0155] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases and local industry databases. The inputs are current location information (latitude 35.0116 degrees north, longitude 135.7681 degrees east) and travel direction information (northbound). The output is surrounding information (e.g., information on Kinkaku-ji Temple and Kyoto specialty shops).

[0156] Step 4:

[0157] Text generation

[0158] The server inputs the surrounding area information collected and the user's hobbies and preferences into the generative AI model as prompts. The inputs include surrounding area information and hobbies and preferences. For example, a prompt might be generated that reads, "For a user in Kyoto City, please generate information about nearby tourist spots and souvenir shops." The output is the text generated by the generative AI model (for example, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[0159] Step 5:

[0160] Generating audio data

[0161] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the text generated by the generative AI model. The output is speech data (e.g., "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[0162] Step 6:

[0163] Sending and playing audio data

[0164] The server sends the generated audio data to the device. As input, there is audio data. As output, the device receives it and plays it in real time. The device outputs the audio using, for example, a Bluetooth headset or speaker.

[0165] Step 7:

[0166] Gathering feedback

[0167] The user inputs their satisfaction and thoughts about the provided information and sends it to the server via their terminal. The input is the user's feedback information, which the server receives as output.

[0168] Step 8:

[0169] System optimization

[0170] The server analyzes the feedback collected from users and updates the generative AI model and database. The input is the feedback information. The output is an updated generative AI model and database. This improves the accuracy of the next information provided.

[0171] (Application example 1)

[0172] 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."

[0173] When providing useful information to users in autonomous vehicles in real time, a method is needed that allows them to obtain the information without relying on vision. It is also necessary to improve user satisfaction by providing information that meets the individual preferences of each user. Furthermore, technology is also needed to improve the accuracy of text generation and speech synthesis.

[0174] 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.

[0175] In this invention, the server includes means for acquiring current location information and movement direction, means for collecting surrounding information, means for generating text based on user interest and preference information, means for generating text using a generative AI model, means for applying natural language processing technology using the generated text as a prompt sentence, means for converting the generated text into voice data, and means for providing the voice data, thereby enabling the user to obtain personalized information in real time as voice without relying on vision.

[0176] "Current location information" refers to location data acquired by the user's device, and specifically includes latitude and longitude information.

[0177] "Direction of movement" is information indicating the direction in which a user or autonomous vehicle is traveling, and is obtained using a compass or other position detection sensors.

[0178] "Local area information" is information collected based on the user's current location information, and includes information on tourist spots, local specialties, local industries, etc.

[0179] "Hobbies and Preference Information" includes information about the user's areas of interest, activities, preferences, etc. For example, information about hobbies and preferences such as history and food.

[0180] "Generative AI model" refers to an artificial intelligence model used to generate generated text, utilizing natural language processing techniques to construct content that is appropriate for the user.

[0181] A "prompt" is an instruction or question that a generative AI model uses to generate text, and serves as the starting point for text generation.

[0182] "Voice data" refers to data in the form of voice generated by a speech synthesis engine based on the generated text, and is provided to the user.

[0183] "Natural language processing technology" is a general term for technologies used by generative AI models to understand and generate human language, and is used for generating and analyzing sentences.

[0184] A "speech synthesis engine" is software that converts text into speech data and is adjusted according to the speech format.

[0185] "Independent of vision" means that the user can obtain information through sound or other means, meaning that the information can be obtained without the need for sight.

[0186] To implement this invention, a series of systems is required that acquires the user's current location information and direction of movement, collects surrounding information based on that information, generates text using a generative AI model, converts it into voice data, and provides it to the user. A specific embodiment of this system is shown below.

[0187] Hardware and Software Configuration

[0188] 1. Hardware Configuration

[0189] User device: Includes GPS sensor, compass, internet communication function, and audio output (vehicle audio system or Bluetooth headset).

[0190] Server: A server with high-performance data processing capabilities.

[0191] Communication network: Connects user terminals and servers via the Internet.

[0192] 2. Software Configuration

[0193] Software on the server: ambient information gathering module, generative AI model (e.g., GPT-4), speech synthesis engine (e.g., Google Text-to-Speech API), feedback gathering and analysis module.

[0194] Software on the user's device: location application, audio playback application, feedback input interface.

[0195] Processing flow and data calculation

[0196] 1. Obtaining current location information and direction of travel

[0197] When a user launches the application, the device uses the GPS sensor to obtain latitude and longitude and the compass to measure direction of movement.

[0198] 2. Gathering surrounding information

[0199] The terminal transmits the acquired current location information and direction of movement to the server.

[0200] The server's local information collection module collects appropriate local information from a tourist destination database and a local industry database.

[0201] 3. Text Generation

[0202] The server generates text using a generative AI model based on the collected information and the user's preferences, and specific prompts are used for the generative AI model.

[0203] Example: "The current location is Kyoto City, and the user is traveling north. The user's hobbies and interests are information about history and food. Under these conditions, generate a guide to provide to the user based on the collected tourist information and information about local food."

[0204] 4. Generating Audio Data

[0205] The server passes the generated text to a speech synthesis engine and converts it into voice data.

[0206] 5. Provision to Users

[0207] The server sends the generated audio data to the user's device, which then plays it through its audio system, allowing the user to obtain information without relying on vision.

[0208] 6. Gather feedback and optimize the system

[0209] Users enter feedback into the device and send it to the server, which analyzes it and uses it to update the generative AI model and database.

[0210] Specific examples

[0211] By using this system while riding in an autonomous vehicle in Kyoto City, a user can receive real-time, personalized information via voice, such as, "Kinkaku-ji is a Buddhist temple built in the 14th century. In addition, you can purchase carefully selected Japanese tea at a nearby store." This allows users to obtain useful information without relying on their vision, even while on the move, improving user satisfaction.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] When a user launches the application, the device uses the GPS sensor to obtain the current location (latitude and longitude) and the compass to measure the direction of movement. The input is the user's action of launching the application, and the output is the current location and direction of movement data.

[0215] Step 2:

[0216] The device transmits the acquired current location information and movement direction data to the server. This communication is carried out via the Internet. The input is the location information and direction information from the device, and the output is when this data reaches the server.

[0217] Step 3:

[0218] The server collects surrounding information from a tourist destination database and a regional industry database based on the current location information and movement direction data. This process receives location information and direction information as input and generates surrounding information data as output.

[0219] Step 4:

[0220] The server constructs a prompt sentence based on the user's interest and preference information, using the collected surrounding information and the generative AI model. The input is interest and preference information and surrounding information, and the output is the prompt sentence. An example of a specific prompt sentence is, "Current location: Kyoto City, traveling north. The user's interest and preference are information about history and food. Under these conditions, please generate a guide to provide to the user based on the collected tourist destination information and information about local food."

[0221] Step 5:

[0222] The server uses a generative AI model to generate text from the prompt. The input is the prompt, and the output is text data to be provided to the user. In this process, the generative AI model generates text using natural language processing techniques.

[0223] Step 6:

[0224] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the generated text, and the output is speech data. The speech synthesis engine converts the text into speech that is easy for the user to understand.

[0225] Step 7:

[0226] The server sends the generated audio data to the user's device, which then plays the received audio data and provides it to the user. The input is the audio data, and the output is the audio played from the device's audio system.

[0227] Step 8:

[0228] The user inputs feedback about the provided information, and the terminal sends the feedback to the server. The input is the user's feedback, and the output is the feedback data being sent to the server.

[0229] Step 9:

[0230] The server analyzes user feedback and uses it to update the generative AI model and database, thereby improving the accuracy of information provided next time. The input is feedback data, and the output is an updated generative AI model and database.

[0231] Furthermore, an emotion engine that estimates the user's emotion may be 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.

[0232] This system acquires a user's current location and direction of travel, collects surrounding information based on this, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Furthermore, by combining it with an emotion engine to recognize the user's emotions and adjust the content provided based on this information, a more personalized user experience is realized.

[0233] System Embodiments

[0234] System Overview

[0235] This system consists of the following elements:

[0236] 1. User's Device

[0237] It has the function of obtaining the user's current location information and direction of movement and sending it to the server.

[0238] It has a built-in emotion engine that recognizes the user's emotions.

[0239] 2. Server

[0240] Based on the received information, it gathers surrounding information and uses a generative AI model to generate customized text.

[0241] The generated text is converted into audio data and sent to the user's device.

[0242] 3. Communication Network

[0243] Infrastructure that connects users' devices to servers and enables data communication.

[0244] Program processing flow

[0245] 1. Acquisition of user information

[0246] The user launches the app.

[0247] The device obtains the current location (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[0248] The device uses its built-in emotion engine to analyze and recognize the user's emotional state based on voice tone, language patterns, facial expressions, etc.

[0249] 2. Transmission of information

[0250] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. The communication protocol is HTTPS, and data is encrypted.

[0251] 3. Collection of Information

[0252] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, information on tourist spots, local products, and local companies is collected.

[0253] 4. Text Generation

[0254] The server uses a generative AI model to generate text based on collected surrounding information, user preferences, and recognized emotional information, and the generative AI model also adjusts the tone and content of the text to match the user's emotional state.

[0255] For example, if the user is relaxed, it generates relaxed text such as "This area has beautiful gardens that are great for strolling."

[0256] 5. Generating Audio Data

[0257] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[0258] 6. Sending and Playing Audio Data

[0259] The server transmits the generated voice data to the terminal via the Internet.

[0260] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[0261] 7. Gathering Feedback

[0262] Users enter their satisfaction and opinions about the information provided into the app and write ratings and comments.

[0263] 8. System Optimization

[0264] The server analyzes user feedback and updates the generative AI model and database, ensuring that future information provided will be even more accurate.

[0265] Specific examples

[0266] Use in tourist areas

[0267] 1. The user launches the app while in Kyoto City.

[0268] 2. The device obtains the current location information (latitude and longitude within Kyoto City) and the direction of movement northward, and uses the built-in emotion engine to recognize the user's calm emotional state.

[0269] 3. The device sends the acquired information to the server.

[0270] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[0271] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and adds the sentiment-based content "Take a stroll through the beautiful gardens and relax," as well as generating advertisements for local souvenir shops.

[0272] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0273] 7. The device plays the audio data it received, and provides instructions such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Please take a relaxing stroll through the beautiful gardens. Here is information about souvenir shops."

[0274] 8. The user enters their rating for the information provided into the app and sends it to the server.

[0275] 9. The server analyzes this feedback and optimizes the content of the next offering.

[0276] In this way, the system provides users with customized audio information based on their current location, travel direction, hobbies, preferences, and even emotional state, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[0277] The processing flow will be explained below.

[0278] Program processing flow

[0279] Step 1:

[0280] The user launches the app.

[0281] The device obtains the current location information (latitude and longitude) and direction of movement. The current location information is obtained using the GPS sensor, and the direction of movement is obtained using the digital compass.

[0282] Step 2:

[0283] The device uses a built-in emotion engine to analyze the user's emotional state, including voice tone, language patterns, and facial expression recognition using the device's camera.

[0284] Step 3:

[0285] The device transmits the acquired current location information, direction of movement, hobbies and preferences, and recognized emotion information to the server. The communication protocol is HTTPS, and the data is encrypted.

[0286] Step 4:

[0287] The server analyzes the received location information.

[0288] The server sends a query to a tourist destination database to collect relevant tourist destination information.

[0289] At the same time, the server sends a query to a local industry database to collect information on nearby specialties and businesses.

[0290] Step 5:

[0291] The server considers the received hobby, preference and emotion information and selects content suitable for the user from the collected tourist spot information.

[0292] Step 6:

[0293] The server uses a generative AI model to generate text from the collected information.

[0294] For example, if the user is in a relaxed emotional state, it generates relaxing text such as "This area has beautiful gardens, perfect for strolling."

[0295] The server also generates local advertisement text at the same time, for example, "A nearby souvenir shop sells local Japanese sweets."

[0296] Step 7:

[0297] The server passes the generated text to a speech synthesis engine, which converts it into audio data, taking into account the user's language and tone of voice preferences.

[0298] Step 8:

[0299] The server transmits the generated voice data to the terminal via the Internet.

[0300] Step 9:

[0301] The device will play the received audio data in real time, and output it to the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[0302] Step 10:

[0303] Users enter ratings and comments about the information provided into the app.

[0304] Step 11:

[0305] The terminal transmits the input user feedback information to the server.

[0306] Step 12:

[0307] The server analyzes user feedback and updates the generative AI model and database, which improves the accuracy of future information provided.

[0308] Through the above process, the system provides users with customized information and voice data in real time based on their current location, direction of travel, emotional state, and hobbies and preferences, making travel time more meaningful and providing an effective advertising tool for local governments and businesses.

[0309] Example 2

[0310] 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 smart device 14 will be referred to as a "terminal."

[0311] Conventional systems could collect surrounding information based on a user's current location and preferences, and provide voice data. However, they were unable to provide information that took the user's emotional state into account. As a result, the information provided was sometimes inconsistent with the user's actual situation and emotions, resulting in a suboptimal user experience. Furthermore, the voice data provided was uniform, resulting in a lack of personalized information for individual users. To solve this issue, a system that recognizes a user's emotional state and provides customized information based on that state is needed.

[0312] 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.

[0313] In this invention, the server includes means for acquiring the user's current location information and direction of travel, means for collecting surrounding information, means for recognizing the user's emotional state, means for generating customized text based on the user's interest and preference information and the recognized emotional state, means for converting the generated text into voice data, and means for providing the voice data to the user. This makes it possible to provide personalized information that corresponds not only to the user's current location and direction of travel but also to the user's emotional state.

[0314] "Current location information" is latitude and longitude information that indicates the user's location.

[0315] "Movement direction" is information that indicates the direction in which the user is facing or moving.

[0316] "Nearby information" refers to information including tourist spot information, local product information, and local industry information collected based on the user's current location information and direction of travel.

[0317] "Emotional state" refers to the emotional state of a user as analyzed from their voice tone, language patterns, facial expressions, etc.

[0318] "Hobbies and Preference Information" is information about the user's interests and preferences.

[0319] "Customized text" is personalized text that is generated based on the user's preferences and perceived emotional state.

[0320] "Speech data" refers to speech information generated by a speech synthesis engine based on the generated text.

[0321] MODE FOR CARRYING OUT THE INVENTION

[0322] The present invention is a system that acquires a user's current location information and travel direction information, and collects surrounding information based on this information. Furthermore, the system generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Specific examples of embodiments of the present invention are described below.

[0323] System elements and the hardware and software used

[0324] 1. User's Device

[0325] The GPS sensor and digital compass are used to obtain current location information (latitude and longitude) and direction of movement.

[0326] To recognize emotions, we use a microphone for voice tone analysis and a front camera for facial expression analysis. We use publicly available emotion analysis software as the emotion engine.

[0327] 2. Server

[0328] Based on the received current location information and movement direction information, surrounding information is collected from tourist destination databases, local industry databases, etc. For this, a general database management system such as an SQL database is used.

[0329] Based on the collected information and the user's preferences and emotions, a generative AI model is used to generate text. For example, a Generative Pretrained Transformer (GPT) is used as the generative AI model.

[0330] A TTS (Text-to-Speech) engine is used to convert the generated text into audio data.

[0331] 3. Communication Network

[0332] A secure internet connection using the HTTPS protocol is used to connect the user's device to the server and transmit data.

[0333] System operation procedure

[0334] Getting user information

[0335] After the user launches the app, the device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement.

[0336] The device uses a built-in emotion engine to recognize the user's emotional state through voice tone and facial expression analysis.

[0337] Sending and collecting information

[0338] The device transmits the current location information, movement direction information, hobby and preference information, and emotional information acquired to the server via HTTPS.

[0339] The server queries the tourist destination database and the local industry database to collect surrounding information.

[0340] Text and audio data generation

[0341] The server uses the received information to input the prompt into a generative AI model to generate customized text, for example using the following prompt:

[0342] The user is using the app in Kyoto city. The current location is near Kinkakuji Temple, and the user's emotional state is relaxed. Please generate a guide message for the user.

[0343] The server passes the generated text to a TTS engine, which generates voice data tailored to the user's settings.

[0344] Sending and playing audio data

[0345] The server transmits the generated voice data to the terminal via the Internet.

[0346] The terminal provides the received audio data to the user and plays the audio on the appropriate device.

[0347] In this way, the system provides audio information tailored to the user's current location, travel direction, hobbies, preferences, and emotional state, making travel time more meaningful. It can also provide an efficient advertising tool for local governments and businesses.

[0348] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0349] System program processing steps

[0350] Step 1: Get the user's information

[0351] 1. The user launches the app. The input is the app's launch action and the output is the app's start screen.

[0352] A user taps an app installed on their smartphone or tablet to launch it, and the app's start screen appears.

[0353] 2. The device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement. The input is GPS data and compass data, and the output is latitude, longitude and direction information.

[0354] The device's GPS module receives signals from satellites and calculates latitude and longitude data, and then the digital compass detects the direction the device is facing.

[0355] Store the obtained latitude, longitude, and direction information in variables. Example: Latitude: 35.0116, Longitude: 135.7681, Direction: North

[0356] 3. The device uses a built-in emotion engine to analyze the user's emotional state. The input is voice tone, language patterns, and facial expression data, and the output is emotional information.

[0357] The microphone collects the user's voice and analyzes the tone and patterns of the voice, while the front camera captures facial expressions and runs facial recognition algorithms.

[0358] From the analysis results, the user's emotional state is classified as "relaxed," "excited," "sad," etc., and emotional information is obtained. Example: Emotion: Relaxed

[0359] Step 2: Submit your information

[0360] 1. The device sends current location information, movement direction information, hobbies, preferences information, and emotion information to the server. The input is the acquired user information, and the output is the transmission status to the server.

[0361] The device uses Wi-Fi or mobile data to send data to the server via the HTTPS protocol.

[0362] To confirm successful data transmission, a response code is received. Example: Status: 200 OK

[0363] Step 3: Gather information

[0364] 1. The server collects surrounding information based on the current location and direction of travel information received. The input is the user's current location and direction of travel information, and the output is surrounding information data.

[0365] The server queries the tourist destination database, local industry database, etc. to obtain information on nearby tourist destinations, local products, and companies. Example: Nearby tourist destination: Kinkakuji Temple, Local product: Kyoto sweets

[0366] Store the acquired surrounding information in a variable. Example: NearbyInfo: {"TouristSpot": "Kinkakuji Temple", "Specialty": "Kyoto sweets"}

[0367] Step 4: Generate text

[0368] 1. The server generates customized text using a generative AI model based on collected surrounding information, preferences, and emotional information. The input is a prompt sentence, and the output is customized text.

[0369] Input a prompt to the generative AI model. Example: The user is in Kyoto City and currently feels relaxed. Please generate a guide about Kinkakuji Temple.

[0370] The model generates customized text based on the prompt, e.g., "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and stroll through the gardens."

[0371] Step 5: Generate audio data

[0372] 1. The server passes the generated text to the TTS engine and converts it into speech data. The input is the generated text and the output is speech data.

[0373] The TTS engine converts text to speech. Example: Audio file: "kinkakuji.mp3"

[0374] Step 6: Sending and Playing Audio Data

[0375] 1. The server sends the generated voice data to the terminal via the Internet. The input is the voice data, and the output is the transmission status to the terminal.

[0376] The audio data is compressed and sent to the device over a secure channel. Example: Status: 200 OK

[0377] 2. The terminal plays back the received audio data in real time. The input is audio data, and the output is audio information provided to the user.

[0378] The device plays an audio file through the internal speaker or a Bluetooth headset. Example: "Start audio playback."

[0379] keyword

[0380] Generative AI model, prompt sentence

[0381] (Application example 2)

[0382] 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."

[0383] Conventional tourist information systems have limited content provided based on the user's current location and direction of travel, making it difficult to provide personalized information based on the user's emotions, hobbies, and preferences. Furthermore, in order for the information provided as tourist information to be interesting and effective for the user, the generated text content must be flexibly adjusted to match the user's emotional state. Effective methods are also needed for providing collected information on tourist destinations, local specialties, and local industries tailored to the user's movements and current location.

[0384] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring current location information and travel direction information of the user, means for collecting surrounding information based on the acquired current location information and travel direction information, means for generating text from the surrounding information collected based on the user's hobby, preference, and emotional information, means for converting the generated text into voice data using a generative AI model, means for providing the generated voice data to the user, and means for recognizing the user's emotions and adjusting the content to be provided based on the emotional information. This makes it possible to utilize emotion analysis to provide personalized tourist guidance tailored to the user's emotions, hobbies, and preferences, and is expected to improve the user experience.

[0385] "Current location information" refers to geographical information about the location where the user is currently located, and includes coordinate data such as latitude and longitude.

[0386] "Movement direction information" is data indicating the direction in which the user is moving, and is obtained using a compass or gyroscope.

[0387] "Nearby information" refers to information about tourist spots, local specialties, local industries, etc., collected based on the user's current location and direction of travel.

[0388] "Hobbies and Preference Information" is data that indicates a user's interests and preferences, and is obtained from the user's profile and past behavioral history.

[0389] "Emotional information" is data that indicates the user's current emotional state and is obtained using voice tone and facial expression analysis.

[0390] A "generative AI model" is a model that uses artificial intelligence to generate text, creating customized text based on user input and context.

[0391] "Text generation" is the process of creating sentences that are appropriate for the user based on collected peripheral information, the user's hobbies, preferences, and emotional information.

[0392] "Audio data" refers to data that has been converted from generated text into audio format, and is used to provide information to the user by audio.

[0393] "Emotion recognition" is the process of analyzing a user's emotional state and obtaining that information.

[0394] This invention is a system that acquires a user's current location information and travel direction information, collects surrounding information based on this information, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. This system provides personalized information to users in real time, making it particularly effective as a tourist guide.

[0395] System configuration

[0396] This system is broadly composed of the following components:

[0397] 1. User's Device

[0398] Obtaining current location and direction information

[0399] Emotion engine recognizes emotional states

[0400] Send the acquired information to the server

[0401] 2. Server

[0402] Collecting surrounding information based on received information

[0403] Generate customized text using generative AI models

[0404] Converts text into audio data and sends it to the user's device

[0405] 3. Communication Network

[0406] Connecting the user's device to the server

[0407] Hardware and software used

[0408] GPS sensor: Used to obtain the user's current location

[0409] Digital compass: Used to obtain the user's moving direction information

[0410] Emotion Engine: Used to recognize the user's emotional state based on their tone of voice and facial expression analysis.

[0411] Generative AI model (OpenAI API): Used to generate customized text based on user information

[0412] Text-to-Speech Engine (gTTS): Used to convert generated text into speech data

[0413] Communication protocol (HTTPS): used to send and receive data securely

[0414] Processing flow

[0415] 1. Processing on the user's device

[0416] When a user launches the application, the device's GPS sensor and digital compass are used to obtain information on the user's current location and direction of movement. The emotion engine then analyzes the user's tone of voice and facial expressions to recognize their emotional state. This information, along with the user's preferences, is then sent to the server.

[0417] 2. Processing on the server

[0418] The server collects information about the surrounding area from databases of tourist attractions and local specialties based on the received current location and direction of travel information. It then uses a generative AI model to generate customized text based on the user's preferences and emotions. This text is then passed to a speech synthesis engine and converted into voice data.

[0419] 3. Provision of audio data

[0420] The audio data generated by the server is sent to the user's device and played back in real time, allowing the user to receive personalized tourist information by audio.

[0421] Examples of concrete examples and prompts

[0422] For example, consider the case where a user arrives at the tourist spot "Kinkakuji Temple" in Kyoto City and launches the app. If the user is in a relaxed emotional state and has an interest in history as a hobby, the following prompt sentence will be input into the generative AI model.

[0423] Prompt statement:

[0424] The user is currently at Kinkakuji Temple. The user is in a relaxed state. There are beautiful gardens in the area. Provide information in a relaxing tone. Also, recommend nearby souvenir shops.

[0425] The generative AI model generates customized text based on this prompt, which is then converted into speech data and provided to the user: "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and enjoy a stroll through the beautiful gardens. Here is information about souvenir shops."

[0426] In this way, it is possible to realize customized tourist information according to the user's current location, direction of travel, and emotional state.

[0427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0428] Step 1:

[0429] The user launches the application. The device uses the GPS sensor and digital compass to obtain current location information (latitude and longitude) and direction of movement. The user's current location and direction of movement information are obtained as input, and as output, this data is processed into a format that can be sent to the server. Specifically, the device receives a GPS signal and recognizes the direction using the digital compass.

[0430] Step 2:

[0431] The device passes the current location and movement direction information it acquires to a built-in emotion engine, which then analyzes the user's voice tone and facial expressions to recognize their emotional state. The inputs are current location information, movement direction information, voice tone, and facial expression data, and the output is the user's recognized emotion information. Specifically, the emotion engine analyzes changes in voice tone and facial expressions to classify emotions.

[0432] Step 3:

[0433] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. All previously acquired information is used as input, and this information is securely sent to the server as output using the HTTPS protocol. Specifically, the device converts the data into a data format such as JSON and sends it over the Internet.

[0434] Step 4:

[0435] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases, local product databases, etc. The user's current location information and travel direction information are acquired as input, and information on the relevant tourist destinations and local products is obtained as output. Specifically, the server executes a database query to acquire relevant information.

[0436] Step 5:

[0437] The server uses a generative AI model based on the surrounding information, hobbies, preferences, and emotional information collected to generate customized text. The collected surrounding information, the user's hobbies, preferences, and emotional information are used as input, and text appropriate for the user is generated as output. Specifically, the system operates by inputting a prompt sentence into the generative AI model and obtaining the generated text.

[0438] Step 6:

[0439] The server passes the generated text to a speech synthesis engine and converts it into voice data. The text generated by the generative AI model is used as input, and voice data is obtained as output. Specifically, the speech synthesis engine analyzes the text and generates an audio file.

[0440] Step 7:

[0441] The server sends the generated voice data to the user's device. The server uses the voice data as input and sends the voice data to the device as output. Specifically, the server sends the voice file to the device via the Internet.

[0442] Step 8:

[0443] The device plays back audio data received in real time. The received audio data is used as input, and the audio is played back from a speaker or headset as output. Specifically, the audio data is played back using the device's audio playback function.

[0444] Step 9:

[0445] The user enters their satisfaction and thoughts about the information provided into the app and sends it to the server. The app obtains user feedback as input, and sends ratings and comments as output to the server. Specifically, the app uses the feedback function to collect user opinions and send them to the server.

[0446] Step 10:

[0447] The server analyzes user feedback and updates the generative AI model and database. It receives user feedback information as input and optimizes the generative AI model and database as output. Specifically, it analyzes the feedback data and adjusts the parameters of the generative AI model to provide more accurate information from the next time onwards.

[0448] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0449] 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0450] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0451] [Second embodiment]

[0452] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0453] 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.

[0454] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0455] 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.

[0456] 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 audio in accordance with instructions from the processor 46.

[0457] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0458] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0459] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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 smart glasses 214 will be referred to as the "terminal."

[0464] The present invention is a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for provision.

[0465] System Embodiments

[0466] System Overview

[0467] This system consists of a user's device, a server, and a communications network connecting them. The user's device has the ability to acquire current location information and direction of movement and send it to the server. The server collects surrounding information based on the received information and converts it into text using a generative AI model. The converted text is then converted into voice data and finally sent to the user's device.

[0468] Program processing flow

[0469] 1. Acquisition of user information

[0470] When a user launches the app, the device obtains the current location (latitude and longitude) and direction of travel using the GPS and compass functions.

[0471] 2. Transmission of information

[0472] The device sends information about the user's current location, direction of travel, and hobbies and preferences to a server via the Internet.

[0473] 3. Collection of Information

[0474] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, the tourist destination database can provide information on nearby famous places, while the local industry database can provide information on local specialties and businesses.

[0475] 4. Text Generation

[0476] Based on the surrounding information collected by the server and the user's hobbies and preferences, a generative AI model is used to generate text. The generative AI model uses natural language processing technology to generate information that is interesting to the user.

[0477] 5. Generating Audio Data

[0478] The server then passes the generated text to a speech synthesis engine, which converts it into voice data. The speech synthesis engine supports a variety of voice formats and is tailored to the language and accent selected by the user.

[0479] 6. Sending and Playing Audio Data

[0480] The server sends the generated audio data to the device, which then plays it back in real time, ensuring proper audio output even if the user is using a Bluetooth headset or car speakers.

[0481] 7. Gathering Feedback

[0482] The user inputs their satisfaction and thoughts about the provided information and sends it from the device to the server, thereby collecting user feedback.

[0483] 8. System Optimization

[0484] The server analyzes user feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0485] Specific examples

[0486] Use in tourist areas

[0487] 1. The user launches the app while in Kyoto City.

[0488] 2. The device acquires the current location information (latitude and longitude within Kyoto City) and the direction of movement northward.

[0489] 3. The device sends the acquired information to the server.

[0490] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[0491] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[0492] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0493] 7. The device plays the audio data it has received, and explains, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[0494] 8. The user enters their rating for the information provided into the app and sends it to the server.

[0495] 9. The server analyzes this feedback and optimizes the content of the next offering.

[0496] In this way, this system can provide useful information to users on the move without relying on vision, and can also provide an effective advertising tool for municipalities and businesses.In addition, by customizing information to suit the user's hobbies and preferences, it is possible to achieve even higher levels of satisfaction.

[0497] The processing flow will be explained below.

[0498] Program processing flow

[0499] Step 1:

[0500] The user launches the app.

[0501] The device obtains the current location information (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[0502] Step 2:

[0503] The device sends the current location information, direction of movement, and user preferences to the server. The communication protocol is HTTPS, and data is encrypted.

[0504] Step 3:

[0505] The server analyzes the received current location information and sends a query to a database of nearby tourist attractions to obtain tourist attraction information.

[0506] At the same time, queries are sent to a local industry database to obtain information on nearby specialties and companies.

[0507] Step 4:

[0508] Based on the surrounding area information acquired by the server and the user's hobbies and preferences, the generative AI model generates text to be provided to the user. For example, for a user who likes history, the system generates information such as "Many buildings from the Edo period remain in this area."

[0509] Step 5:

[0510] The system also generates local ads based on the information it collects, such as "A nearby souvenir shop sells local Japanese sweets."

[0511] Step 6:

[0512] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[0513] Step 7:

[0514] The server transmits the generated voice data to the terminal via the Internet.

[0515] Step 8:

[0516] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[0517] Step 9:

[0518] Users can provide feedback on the information provided by the app, leaving ratings and comments.

[0519] Step 10:

[0520] The terminal transmits the user's feedback information to the server.

[0521] Step 11:

[0522] The server analyzes the feedback and updates the generative AI model and database, which will result in even more accurate information being provided in future.

[0523] In this way, the system provides users with customized information based on their current location, travel direction, and preferences, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[0524] Example 1

[0525] 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 smart glasses 214 will be referred to as a "terminal."

[0526] Conventional information provision systems are limited to providing simple text information based on the user's current location, making it difficult to provide detailed, personalized information tailored to the user's preferences. Furthermore, because information is primarily acquired visually, it is difficult to obtain information effectively in situations where it is difficult to use one's eyes, such as while traveling or driving. Furthermore, there is a lack of a mechanism for improving the accuracy of the system based on user feedback.

[0527] 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.

[0528] In this invention, the server includes a means for acquiring the user's current location information, a means for collecting surrounding information based on the acquired current location information and travel direction information, a means for using a generative AI model to generate text from the collected surrounding information based on the user's interest and preference information, a means for using a speech synthesis engine to convert the generated text into speech data, a means for providing the generated speech data to the user, and a means for collecting user feedback and updating the generative AI model and database to improve the accuracy of information provision. This enables the provision of detailed, personalized speech information tailored to the user's interests and preferences. Furthermore, useful information can be obtained without relying on vision, improving the accuracy of the system.

[0529] "User's current location information" refers to the latitude and longitude data of the user's current location.

[0530] "Movement direction information" is information about the direction in which the user is currently moving, and is data obtained using a compass function or the like.

[0531] "Nearby information" is various data about the neighborhood collected based on the user's current location information and travel direction information.

[0532] "Hobbies and preferences information" is information that indicates the user's personal interests and concerns, such as favorite tourist spots and favorite foods.

[0533] A "generative AI model" is an artificial intelligence technology that generates text from surrounding information based on the user's hobbies and preferences.

[0534] A "speech synthesis engine" is a software or hardware technology for converting generated text into speech data.

[0535] "Feedback" refers to information that a user writes down about their satisfaction with and thoughts about the information provided and sends it to the server.

[0536] "Updating a database" means rewriting an existing database to the latest version based on newly collected data and feedback.

[0537] MODE FOR CARRYING OUT THE INVENTION

[0538] This invention relates to a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for delivery. This system operates via the user's terminal, a server, and a communication network.

[0539] Hardware and software used

[0540] Device: A device such as a smartphone or tablet held by a user, equipped with GPS and compass functions.

[0541] Server: Collects information and generates text and voice data using generative AI models and a speech synthesis engine. For example, a cloud server (AWS, GCP, etc.) is used.

[0542] Communication network: Terminals and servers exchange information via the Internet.

[0543] Processing Details

[0544] Getting user information

[0545] When a user launches the app, the device uses the GPS function to obtain the current location (latitude and longitude) and the compass function to obtain the direction of travel.

[0546] Sending information

[0547] The terminal transmits the acquired current location information, movement direction information, and user's hobbies and preferences information to a server via the Internet.

[0548] Collection of information

[0549] Based on the current location information and movement direction information received by the server, the server collects surrounding information from the tourist destination database and local industry database. For example, if the current location is Kyoto City, the server will obtain information on "Kinkakuji Temple" from the tourist destination database and "Kyoto specialty product stores" from the local industry database.

[0550] Text generation

[0551] The server generates text using a generative AI model (e.g., GPT-4) based on this surrounding information and the user's hobbies and preferences. An example of a prompt sentence is "Generate information about nearby tourist spots and souvenir shops for a user in Kyoto City."

[0552] Generating audio data

[0553] The server converts the generated text into speech data using a speech synthesis engine (e.g., Google Cloud Text-to-Speech). For example, the generated text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century" is converted into speech data.

[0554] Sending and playing audio data

[0555] The server sends the generated audio data to the device, which then plays the received audio data in real time.

[0556] Gathering feedback

[0557] The user inputs his / her satisfaction level and thoughts about the provided information and transmits them to the server via the terminal.

[0558] System optimization

[0559] The server analyzes the collected feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0560] Specific examples

[0561] Use in tourist areas

[0562] 1. The user launches the app while in Kyoto City.

[0563] 2. The device uses the GPS function to obtain current location information (latitude and longitude within Kyoto City) and the compass function to obtain the direction of movement northward.

[0564] 3. The device sends the acquired information to a server via the Internet.

[0565] 4. Based on the current location information, the server collects information on "Kinkaku-ji Temple" from the tourist destination database and "Kyoto specialty stores" from the local industry database.

[0566] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[0567] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0568] 7. The device plays back the received audio data in real time, and provides information such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[0569] 8. The user enters the rating into the app and sends it to the server.

[0570] 9. The server analyzes the feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0571] The system allows users to hear detailed, personalized information based on their current location, providing useful information without relying on vision, and allows for feedback to improve the system's accuracy.

[0572] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0573] Step 1:

[0574] Getting user information

[0575] When a user launches the app, the device uses the GPS function to obtain current location information (latitude and longitude). The input is the user's action of launching the app. The output is current location information (e.g., 35.0116 degrees north latitude, 135.7681 degrees east longitude). In addition, the compass function is used to obtain movement direction information. The output is movement direction information (e.g., heading north).

[0576] Step 2:

[0577] Sending information

[0578] The device transmits the current location information, travel direction information, and user interest and preference information to a server via the Internet. The inputs are the current location information, travel direction information, and interest and preference information obtained by the device. The server receives this information as output.

[0579] Step 3:

[0580] Collection of information

[0581] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases and local industry databases. The inputs are current location information (latitude 35.0116 degrees north, longitude 135.7681 degrees east) and travel direction information (northbound). The output is surrounding information (e.g., information on Kinkaku-ji Temple and Kyoto specialty shops).

[0582] Step 4:

[0583] Text generation

[0584] The server inputs the surrounding area information collected and the user's hobbies and preferences into the generative AI model as prompts. The inputs include surrounding area information and hobbies and preferences. For example, a prompt might be generated that reads, "For a user in Kyoto City, please generate information about nearby tourist spots and souvenir shops." The output is the text generated by the generative AI model (for example, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[0585] Step 5:

[0586] Generating audio data

[0587] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the text generated by the generative AI model. The output is speech data (e.g., "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[0588] Step 6:

[0589] Sending and playing audio data

[0590] The server sends the generated audio data to the device. As input, there is audio data. As output, the device receives it and plays it in real time. The device outputs the audio using, for example, a Bluetooth headset or speaker.

[0591] Step 7:

[0592] Gathering feedback

[0593] The user inputs their satisfaction and thoughts about the provided information and sends it to the server via their terminal. The input is the user's feedback information, which the server receives as output.

[0594] Step 8:

[0595] System optimization

[0596] The server analyzes the feedback collected from users and updates the generative AI model and database. The input is the feedback information. The output is an updated generative AI model and database. This improves the accuracy of the next information provided.

[0597] (Application example 1)

[0598] 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."

[0599] When providing useful information to users in autonomous vehicles in real time, a method is needed that allows them to obtain the information without relying on vision. It is also necessary to improve user satisfaction by providing information that meets the individual preferences of each user. Furthermore, technology is also needed to improve the accuracy of text generation and speech synthesis.

[0600] 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.

[0601] In this invention, the server includes means for acquiring current location information and movement direction, means for collecting surrounding information, means for generating text based on user interest and preference information, means for generating text using a generative AI model, means for applying natural language processing technology using the generated text as a prompt sentence, means for converting the generated text into voice data, and means for providing the voice data, thereby enabling the user to obtain personalized information in real time as voice without relying on vision.

[0602] "Current location information" refers to location data acquired by the user's device, and specifically includes latitude and longitude information.

[0603] "Direction of movement" is information indicating the direction in which a user or autonomous vehicle is traveling, and is obtained using a compass or other position detection sensors.

[0604] "Local area information" is information collected based on the user's current location information, and includes information on tourist spots, local specialties, local industries, etc.

[0605] "Hobbies and Preference Information" includes information about the user's areas of interest, activities, preferences, etc. For example, information about hobbies and preferences such as history and food.

[0606] "Generative AI model" refers to an artificial intelligence model used to generate generated text, utilizing natural language processing techniques to construct content that is appropriate for the user.

[0607] A "prompt" is an instruction or question that a generative AI model uses to generate text, and serves as the starting point for text generation.

[0608] "Voice data" refers to data in the form of voice generated by a speech synthesis engine based on the generated text, and is provided to the user.

[0609] "Natural language processing technology" is a general term for technologies used by generative AI models to understand and generate human language, and is used for generating and analyzing sentences.

[0610] A "speech synthesis engine" is software that converts text into speech data and is adjusted according to the speech format.

[0611] "Independent of vision" means that the user can obtain information through sound or other means, meaning that the information can be obtained without the need for sight.

[0612] To implement this invention, a series of systems is required that acquires the user's current location information and direction of movement, collects surrounding information based on that information, generates text using a generative AI model, converts it into voice data, and provides it to the user. A specific embodiment of this system is shown below.

[0613] Hardware and Software Configuration

[0614] 1. Hardware Configuration

[0615] User device: Includes GPS sensor, compass, internet communication function, and audio output (vehicle audio system or Bluetooth headset).

[0616] Server: A server with high-performance data processing capabilities.

[0617] Communication network: Connects user terminals and servers via the Internet.

[0618] 2. Software Configuration

[0619] Software on the server: ambient information gathering module, generative AI model (e.g., GPT-4), speech synthesis engine (e.g., Google Text-to-Speech API), feedback gathering and analysis module.

[0620] Software on the user's device: location application, audio playback application, feedback input interface.

[0621] Processing flow and data calculation

[0622] 1. Obtaining current location information and direction of travel

[0623] When a user launches the application, the device uses the GPS sensor to obtain latitude and longitude and the compass to measure direction of movement.

[0624] 2. Gathering surrounding information

[0625] The terminal transmits the acquired current location information and direction of movement to the server.

[0626] The server's local information collection module collects appropriate local information from a tourist destination database and a local industry database.

[0627] 3. Text Generation

[0628] The server generates text using a generative AI model based on the collected information and the user's preferences, and specific prompts are used for the generative AI model.

[0629] Example: "The current location is Kyoto City, and the user is traveling north. The user's hobbies and interests are information about history and food. Under these conditions, generate a guide to provide to the user based on the collected tourist information and information about local food."

[0630] 4. Generating Audio Data

[0631] The server passes the generated text to a speech synthesis engine and converts it into voice data.

[0632] 5. Provision to Users

[0633] The server sends the generated audio data to the user's device, which then plays it through its audio system, allowing the user to obtain information without relying on vision.

[0634] 6. Gather feedback and optimize the system

[0635] Users enter feedback into the device and send it to the server, which analyzes it and uses it to update the generative AI model and database.

[0636] Specific examples

[0637] By using this system while riding in an autonomous vehicle in Kyoto City, a user can receive real-time, personalized information via voice, such as, "Kinkaku-ji is a Buddhist temple built in the 14th century. In addition, you can purchase carefully selected Japanese tea at a nearby store." This allows users to obtain useful information without relying on their vision, even while on the move, improving user satisfaction.

[0638] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0639] Step 1:

[0640] When a user launches the application, the device uses the GPS sensor to obtain the current location (latitude and longitude) and the compass to measure the direction of movement. The input is the user's action of launching the application, and the output is the current location and direction of movement data.

[0641] Step 2:

[0642] The device transmits the acquired current location information and movement direction data to the server. This communication is carried out via the Internet. The input is the location information and direction information from the device, and the output is when this data reaches the server.

[0643] Step 3:

[0644] The server collects surrounding information from a tourist destination database and a regional industry database based on the current location information and movement direction data. This process receives location information and direction information as input and generates surrounding information data as output.

[0645] Step 4:

[0646] The server constructs a prompt sentence based on the user's interest and preference information, using the collected surrounding information and the generative AI model. The input is interest and preference information and surrounding information, and the output is the prompt sentence. An example of a specific prompt sentence is, "Current location: Kyoto City, traveling north. The user's interest and preference are information about history and food. Under these conditions, please generate a guide to provide to the user based on the collected tourist destination information and information about local food."

[0647] Step 5:

[0648] The server uses a generative AI model to generate text from the prompt. The input is the prompt, and the output is text data to be provided to the user. In this process, the generative AI model generates text using natural language processing techniques.

[0649] Step 6:

[0650] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the generated text, and the output is speech data. The speech synthesis engine converts the text into speech that is easy for the user to understand.

[0651] Step 7:

[0652] The server sends the generated audio data to the user's device, which then plays the received audio data and provides it to the user. The input is the audio data, and the output is the audio played from the device's audio system.

[0653] Step 8:

[0654] The user inputs feedback about the provided information, and the terminal sends the feedback to the server. The input is the user's feedback, and the output is the feedback data being sent to the server.

[0655] Step 9:

[0656] The server analyzes user feedback and uses it to update the generative AI model and database, thereby improving the accuracy of information provided next time. The input is feedback data, and the output is an updated generative AI model and database.

[0657] Furthermore, 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.

[0658] This system acquires a user's current location and direction of travel, collects surrounding information based on this, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Furthermore, by combining it with an emotion engine to recognize the user's emotions and adjust the content provided based on this information, a more personalized user experience is realized.

[0659] System Embodiments

[0660] System Overview

[0661] This system consists of the following elements:

[0662] 1. User's Device

[0663] It has the function of obtaining the user's current location information and direction of movement and sending it to the server.

[0664] It has a built-in emotion engine that recognizes the user's emotions.

[0665] 2. Server

[0666] Based on the received information, it gathers surrounding information and uses a generative AI model to generate customized text.

[0667] The generated text is converted into audio data and sent to the user's device.

[0668] 3. Communication Network

[0669] Infrastructure that connects users' devices to servers and enables data communication.

[0670] Program processing flow

[0671] 1. Acquisition of user information

[0672] The user launches the app.

[0673] The device obtains the current location (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[0674] The device uses its built-in emotion engine to analyze and recognize the user's emotional state based on voice tone, language patterns, facial expressions, etc.

[0675] 2. Transmission of information

[0676] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. The communication protocol is HTTPS, and data is encrypted.

[0677] 3. Collection of Information

[0678] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, information on tourist spots, local products, and local companies is collected.

[0679] 4. Text Generation

[0680] The server uses a generative AI model to generate text based on collected surrounding information, user preferences, and recognized emotional information, and the generative AI model also adjusts the tone and content of the text to match the user's emotional state.

[0681] For example, if the user is relaxed, it generates relaxed text such as "This area has beautiful gardens that are great for strolling."

[0682] 5. Generating Audio Data

[0683] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[0684] 6. Sending and Playing Audio Data

[0685] The server transmits the generated voice data to the terminal via the Internet.

[0686] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[0687] 7. Gathering Feedback

[0688] Users enter their satisfaction and opinions about the information provided into the app and write ratings and comments.

[0689] 8. System Optimization

[0690] The server analyzes user feedback and updates the generative AI model and database, ensuring that future information provided will be even more accurate.

[0691] Specific examples

[0692] Use in tourist areas

[0693] 1. The user launches the app while in Kyoto City.

[0694] 2. The device obtains the current location information (latitude and longitude within Kyoto City) and the direction of movement northward, and uses the built-in emotion engine to recognize the user's calm emotional state.

[0695] 3. The device sends the acquired information to the server.

[0696] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[0697] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and adds the sentiment-based content "Take a stroll through the beautiful gardens and relax," as well as generating advertisements for local souvenir shops.

[0698] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0699] 7. The device plays the audio data it received, and provides instructions such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Please take a relaxing stroll through the beautiful gardens. Here is information about souvenir shops."

[0700] 8. The user enters their rating for the information provided into the app and sends it to the server.

[0701] 9. The server analyzes this feedback and optimizes the content of the next offering.

[0702] In this way, the system provides users with customized audio information based on their current location, travel direction, hobbies, preferences, and even emotional state, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[0703] The processing flow will be explained below.

[0704] Program processing flow

[0705] Step 1:

[0706] The user launches the app.

[0707] The device obtains the current location information (latitude and longitude) and direction of movement. The current location information is obtained using the GPS sensor, and the direction of movement is obtained using the digital compass.

[0708] Step 2:

[0709] The device uses a built-in emotion engine to analyze the user's emotional state, including voice tone, language patterns, and facial expression recognition using the device's camera.

[0710] Step 3:

[0711] The device transmits the acquired current location information, direction of movement, hobbies and preferences, and recognized emotion information to the server. The communication protocol is HTTPS, and the data is encrypted.

[0712] Step 4:

[0713] The server analyzes the received location information.

[0714] The server sends a query to a tourist destination database to collect relevant tourist destination information.

[0715] At the same time, the server sends a query to a local industry database to collect information on nearby specialties and businesses.

[0716] Step 5:

[0717] The server considers the received hobby, preference and emotion information and selects content suitable for the user from the collected tourist spot information.

[0718] Step 6:

[0719] The server uses a generative AI model to generate text from the collected information.

[0720] For example, if the user is in a relaxed emotional state, it generates relaxing text such as "This area has beautiful gardens, perfect for strolling."

[0721] The server also generates local advertisement text at the same time, for example, "A nearby souvenir shop sells local Japanese sweets."

[0722] Step 7:

[0723] The server passes the generated text to a speech synthesis engine, which converts it into audio data, taking into account the user's language and tone of voice preferences.

[0724] Step 8:

[0725] The server transmits the generated voice data to the terminal via the Internet.

[0726] Step 9:

[0727] The device will play the received audio data in real time, and output it to the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[0728] Step 10:

[0729] Users enter ratings and comments about the information provided into the app.

[0730] Step 11:

[0731] The terminal transmits the input user feedback information to the server.

[0732] Step 12:

[0733] The server analyzes user feedback and updates the generative AI model and database, which improves the accuracy of future information provided.

[0734] Through the above process, the system provides users with customized information and voice data in real time based on their current location, direction of travel, emotional state, and hobbies and preferences, making travel time more meaningful and providing an effective advertising tool for local governments and businesses.

[0735] Example 2

[0736] 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 smart glasses 214 will be referred to as a "terminal."

[0737] Conventional systems could collect surrounding information based on a user's current location and preferences, and provide voice data. However, they were unable to provide information that took the user's emotional state into account. As a result, the information provided was sometimes inconsistent with the user's actual situation and emotions, resulting in a suboptimal user experience. Furthermore, the voice data provided was uniform, resulting in a lack of personalized information for individual users. To solve this issue, a system that recognizes a user's emotional state and provides customized information based on that state is needed.

[0738] 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.

[0739] In this invention, the server includes means for acquiring the user's current location information and direction of travel, means for collecting surrounding information, means for recognizing the user's emotional state, means for generating customized text based on the user's interest and preference information and the recognized emotional state, means for converting the generated text into voice data, and means for providing the voice data to the user. This makes it possible to provide personalized information that corresponds not only to the user's current location and direction of travel but also to the user's emotional state.

[0740] "Current location information" is latitude and longitude information that indicates the user's location.

[0741] "Movement direction" is information that indicates the direction in which the user is facing or moving.

[0742] "Nearby information" refers to information including tourist spot information, local product information, and local industry information collected based on the user's current location information and direction of travel.

[0743] "Emotional state" refers to the emotional state of a user as analyzed from their voice tone, language patterns, facial expressions, etc.

[0744] "Hobbies and Preference Information" is information about the user's interests and preferences.

[0745] "Customized text" is personalized text that is generated based on the user's preferences and perceived emotional state.

[0746] "Speech data" refers to speech information generated by a speech synthesis engine based on the generated text.

[0747] MODE FOR CARRYING OUT THE INVENTION

[0748] The present invention is a system that acquires a user's current location information and travel direction information, and collects surrounding information based on this information. Furthermore, the system generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Specific examples of embodiments of the present invention are described below.

[0749] System elements and the hardware and software used

[0750] 1. User's Device

[0751] The GPS sensor and digital compass are used to obtain current location information (latitude and longitude) and direction of movement.

[0752] To recognize emotions, we use a microphone for voice tone analysis and a front camera for facial expression analysis. We use publicly available emotion analysis software as the emotion engine.

[0753] 2. Server

[0754] Based on the received current location information and movement direction information, surrounding information is collected from tourist destination databases, local industry databases, etc. For this, a general database management system such as an SQL database is used.

[0755] Based on the collected information and the user's preferences and emotions, a generative AI model is used to generate text. For example, a Generative Pretrained Transformer (GPT) is used as the generative AI model.

[0756] A TTS (Text-to-Speech) engine is used to convert the generated text into audio data.

[0757] 3. Communication Network

[0758] A secure internet connection using the HTTPS protocol is used to connect the user's device to the server and transmit data.

[0759] System operation procedure

[0760] Getting user information

[0761] After the user launches the app, the device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement.

[0762] The device uses a built-in emotion engine to recognize the user's emotional state through voice tone and facial expression analysis.

[0763] Sending and collecting information

[0764] The device transmits the current location information, movement direction information, hobby and preference information, and emotional information acquired to the server via HTTPS.

[0765] The server queries the tourist destination database and the local industry database to collect surrounding information.

[0766] Text and audio data generation

[0767] The server uses the received information to input the prompt into a generative AI model to generate customized text, for example using the following prompt:

[0768] The user is using the app in Kyoto city. The current location is near Kinkakuji Temple, and the user's emotional state is relaxed. Please generate a guide message for the user.

[0769] The server passes the generated text to a TTS engine, which generates voice data tailored to the user's settings.

[0770] Sending and playing audio data

[0771] The server transmits the generated voice data to the terminal via the Internet.

[0772] The terminal provides the received audio data to the user and plays the audio on the appropriate device.

[0773] In this way, the system provides audio information tailored to the user's current location, travel direction, hobbies, preferences, and emotional state, making travel time more meaningful. It can also provide an efficient advertising tool for local governments and businesses.

[0774] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0775] System program processing steps

[0776] Step 1: Get the user's information

[0777] 1. The user launches the app. The input is the app's launch action and the output is the app's start screen.

[0778] A user taps an app installed on their smartphone or tablet to launch it, and the app's start screen appears.

[0779] 2. The device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement. The input is GPS data and compass data, and the output is latitude, longitude and direction information.

[0780] The device's GPS module receives signals from satellites and calculates latitude and longitude data, and then the digital compass detects the direction the device is facing.

[0781] Store the obtained latitude, longitude, and direction information in variables. Example: Latitude: 35.0116, Longitude: 135.7681, Direction: North

[0782] 3. The device uses a built-in emotion engine to analyze the user's emotional state. The input is voice tone, language patterns, and facial expression data, and the output is emotional information.

[0783] The microphone collects the user's voice and analyzes the tone and patterns of the voice, while the front camera captures facial expressions and runs facial recognition algorithms.

[0784] From the analysis results, the user's emotional state is classified as "relaxed," "excited," "sad," etc., and emotional information is obtained. Example: Emotion: Relaxed

[0785] Step 2: Submit your information

[0786] 1. The device sends current location information, movement direction information, hobbies, preferences information, and emotion information to the server. The input is the acquired user information, and the output is the transmission status to the server.

[0787] The device uses Wi-Fi or mobile data to send data to the server via the HTTPS protocol.

[0788] To confirm successful data transmission, a response code is received. Example: Status: 200 OK

[0789] Step 3: Gather information

[0790] 1. The server collects surrounding information based on the current location and direction of travel information received. The input is the user's current location and direction of travel information, and the output is surrounding information data.

[0791] The server queries the tourist destination database, local industry database, etc. to obtain information on nearby tourist destinations, local products, and companies. Example: Nearby tourist destination: Kinkakuji Temple, Local product: Kyoto sweets

[0792] Store the acquired surrounding information in a variable. Example: NearbyInfo: {"TouristSpot": "Kinkakuji Temple", "Specialty": "Kyoto sweets"}

[0793] Step 4: Generate text

[0794] 1. The server generates customized text using a generative AI model based on collected surrounding information, preferences, and emotional information. The input is a prompt sentence, and the output is customized text.

[0795] Input a prompt to the generative AI model. Example: The user is in Kyoto City and currently feels relaxed. Please generate a guide about Kinkakuji Temple.

[0796] The model generates customized text based on the prompt, e.g., "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and stroll through the gardens."

[0797] Step 5: Generate audio data

[0798] 1. The server passes the generated text to the TTS engine and converts it into speech data. The input is the generated text and the output is speech data.

[0799] The TTS engine converts text to speech. Example: Audio file: "kinkakuji.mp3"

[0800] Step 6: Sending and Playing Audio Data

[0801] 1. The server sends the generated voice data to the terminal via the Internet. The input is the voice data, and the output is the transmission status to the terminal.

[0802] The audio data is compressed and sent to the device over a secure channel. Example: Status: 200 OK

[0803] 2. The terminal plays back the received audio data in real time. The input is audio data, and the output is audio information provided to the user.

[0804] The device plays an audio file through the internal speaker or a Bluetooth headset. Example: "Start audio playback."

[0805] keyword

[0806] Generative AI model, prompt sentence

[0807] (Application example 2)

[0808] 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."

[0809] Conventional tourist information systems have limited content provided based on the user's current location and direction of travel, making it difficult to provide personalized information based on the user's emotions, hobbies, and preferences. Furthermore, in order for the information provided as tourist information to be interesting and effective for the user, the generated text content must be flexibly adjusted to match the user's emotional state. Effective methods are also needed for providing collected information on tourist destinations, local specialties, and local industries tailored to the user's movements and current location.

[0810] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring current location information and travel direction information of the user, means for collecting surrounding information based on the acquired current location information and travel direction information, means for generating text from the surrounding information collected based on the user's hobby, preference, and emotional information, means for converting the generated text into voice data using a generative AI model, means for providing the generated voice data to the user, and means for recognizing the user's emotions and adjusting the content to be provided based on the emotional information. This makes it possible to utilize emotion analysis to provide personalized tourist guidance tailored to the user's emotions, hobbies, and preferences, and is expected to improve the user experience.

[0811] "Current location information" refers to geographical information about the location where the user is currently located, and includes coordinate data such as latitude and longitude.

[0812] "Movement direction information" is data indicating the direction in which the user is moving, and is obtained using a compass or gyroscope.

[0813] "Nearby information" refers to information about tourist spots, local specialties, local industries, etc., collected based on the user's current location and direction of travel.

[0814] "Hobbies and Preference Information" is data that indicates a user's interests and preferences, and is obtained from the user's profile and past behavioral history.

[0815] "Emotional information" is data that indicates the user's current emotional state and is obtained using voice tone and facial expression analysis.

[0816] A "generative AI model" is a model that uses artificial intelligence to generate text, creating customized text based on user input and context.

[0817] "Text generation" is the process of creating sentences that are appropriate for the user based on collected peripheral information, the user's hobbies, preferences, and emotional information.

[0818] "Audio data" refers to data that has been converted from generated text into audio format, and is used to provide information to the user by audio.

[0819] "Emotion recognition" is the process of analyzing a user's emotional state and obtaining that information.

[0820] This invention is a system that acquires a user's current location information and travel direction information, collects surrounding information based on this information, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. This system provides personalized information to users in real time, making it particularly effective as a tourist guide.

[0821] System configuration

[0822] This system is broadly composed of the following components:

[0823] 1. User's Device

[0824] Obtaining current location and direction information

[0825] Emotion engine recognizes emotional states

[0826] Send the acquired information to the server

[0827] 2. Server

[0828] Collecting surrounding information based on received information

[0829] Generate customized text using generative AI models

[0830] Converts text into audio data and sends it to the user's device

[0831] 3. Communication Network

[0832] Connecting the user's device to the server

[0833] Hardware and software used

[0834] GPS sensor: Used to obtain the user's current location

[0835] Digital compass: Used to obtain the user's moving direction information

[0836] Emotion Engine: Used to recognize the user's emotional state based on their tone of voice and facial expression analysis.

[0837] Generative AI model (OpenAI API): Used to generate customized text based on user information

[0838] Text-to-Speech Engine (gTTS): Used to convert generated text into speech data

[0839] Communication protocol (HTTPS): used to send and receive data securely

[0840] Processing flow

[0841] 1. Processing on the user's device

[0842] When a user launches the application, the device's GPS sensor and digital compass are used to obtain information on the user's current location and direction of movement. The emotion engine then analyzes the user's tone of voice and facial expressions to recognize their emotional state. This information, along with the user's preferences, is then sent to the server.

[0843] 2. Processing on the server

[0844] The server collects information about the surrounding area from databases of tourist attractions and local specialties based on the received current location and direction of travel information. It then uses a generative AI model to generate customized text based on the user's preferences and emotions. This text is then passed to a speech synthesis engine and converted into voice data.

[0845] 3. Provision of audio data

[0846] The audio data generated by the server is sent to the user's device and played back in real time, allowing the user to receive personalized tourist information by audio.

[0847] Examples of concrete examples and prompts

[0848] For example, consider the case where a user arrives at the tourist spot "Kinkakuji Temple" in Kyoto City and launches the app. If the user is in a relaxed emotional state and has an interest in history as a hobby, the following prompt sentence will be input into the generative AI model.

[0849] Prompt statement:

[0850] The user is currently at Kinkakuji Temple. The user is in a relaxed state. There are beautiful gardens in the area. Provide information in a relaxing tone. Also, recommend nearby souvenir shops.

[0851] The generative AI model generates customized text based on this prompt, which is then converted into speech data and provided to the user: "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and enjoy a stroll through the beautiful gardens. Here is information about souvenir shops."

[0852] In this way, it is possible to realize customized tourist information according to the user's current location, direction of travel, and emotional state.

[0853] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0854] Step 1:

[0855] The user launches the application. The device uses the GPS sensor and digital compass to obtain current location information (latitude and longitude) and direction of movement. The user's current location and direction of movement information are obtained as input, and as output, this data is processed into a format that can be sent to the server. Specifically, the device receives a GPS signal and recognizes the direction using the digital compass.

[0856] Step 2:

[0857] The device passes the current location and movement direction information it acquires to a built-in emotion engine, which then analyzes the user's voice tone and facial expressions to recognize their emotional state. The inputs are current location information, movement direction information, voice tone, and facial expression data, and the output is the user's recognized emotion information. Specifically, the emotion engine analyzes changes in voice tone and facial expressions to classify emotions.

[0858] Step 3:

[0859] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. All previously acquired information is used as input, and this information is securely sent to the server as output using the HTTPS protocol. Specifically, the device converts the data into a data format such as JSON and sends it over the Internet.

[0860] Step 4:

[0861] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases, local product databases, etc. The user's current location information and travel direction information are acquired as input, and information on the relevant tourist destinations and local products is obtained as output. Specifically, the server executes a database query to acquire relevant information.

[0862] Step 5:

[0863] The server uses a generative AI model based on the surrounding information, hobbies, preferences, and emotional information collected to generate customized text. The collected surrounding information, the user's hobbies, preferences, and emotional information are used as input, and text appropriate for the user is generated as output. Specifically, the system operates by inputting a prompt sentence into the generative AI model and obtaining the generated text.

[0864] Step 6:

[0865] The server passes the generated text to a speech synthesis engine and converts it into voice data. The text generated by the generative AI model is used as input, and voice data is obtained as output. Specifically, the speech synthesis engine analyzes the text and generates an audio file.

[0866] Step 7:

[0867] The server sends the generated voice data to the user's device. The server uses the voice data as input and sends the voice data to the device as output. Specifically, the server sends the voice file to the device via the Internet.

[0868] Step 8:

[0869] The device plays back audio data received in real time. The received audio data is used as input, and the audio is played back from a speaker or headset as output. Specifically, the audio data is played back using the device's audio playback function.

[0870] Step 9:

[0871] The user enters their satisfaction and thoughts about the information provided into the app and sends it to the server. The app obtains user feedback as input, and sends ratings and comments as output to the server. Specifically, the app uses the feedback function to collect user opinions and send them to the server.

[0872] Step 10:

[0873] The server analyzes user feedback and updates the generative AI model and database. It receives user feedback information as input and optimizes the generative AI model and database as output. Specifically, it analyzes the feedback data and adjusts the parameters of the generative AI model to provide more accurate information from the next time onwards.

[0874] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0875] 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0876] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0877] [Third embodiment]

[0878] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0879] 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.

[0880] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0881] 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.

[0882] 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 audio in accordance with instructions from the processor 46.

[0883] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0884] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] In the headset type terminal 314, a 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.

[0889] 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."

[0890] The present invention is a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for provision.

[0891] System Embodiments

[0892] System Overview

[0893] This system consists of a user's device, a server, and a communications network connecting them. The user's device has the ability to acquire current location information and direction of movement and send it to the server. The server collects surrounding information based on the received information and converts it into text using a generative AI model. The converted text is then converted into voice data and finally sent to the user's device.

[0894] Program processing flow

[0895] 1. Acquisition of user information

[0896] When a user launches the app, the device obtains the current location (latitude and longitude) and direction of travel using the GPS and compass functions.

[0897] 2. Transmission of information

[0898] The device sends information about the user's current location, direction of travel, and hobbies and preferences to a server via the Internet.

[0899] 3. Collection of Information

[0900] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, the tourist destination database can provide information on nearby famous places, while the local industry database can provide information on local specialties and businesses.

[0901] 4. Text Generation

[0902] Based on the surrounding information collected by the server and the user's hobbies and preferences, a generative AI model is used to generate text. The generative AI model uses natural language processing technology to generate information that is interesting to the user.

[0903] 5. Generating Audio Data

[0904] The server then passes the generated text to a speech synthesis engine, which converts it into voice data. The speech synthesis engine supports a variety of voice formats and is tailored to the language and accent selected by the user.

[0905] 6. Sending and Playing Audio Data

[0906] The server sends the generated audio data to the device, which then plays it back in real time, ensuring proper audio output even if the user is using a Bluetooth headset or car speakers.

[0907] 7. Gathering Feedback

[0908] The user inputs their satisfaction and thoughts about the provided information and sends it from the device to the server, thereby collecting user feedback.

[0909] 8. System Optimization

[0910] The server analyzes user feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0911] Specific examples

[0912] Use in tourist areas

[0913] 1. The user launches the app while in Kyoto City.

[0914] 2. The device acquires the current location information (latitude and longitude within Kyoto City) and the direction of movement northward.

[0915] 3. The device sends the acquired information to the server.

[0916] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[0917] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[0918] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0919] 7. The device plays the audio data it has received, and explains, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[0920] 8. The user enters their rating for the information provided into the app and sends it to the server.

[0921] 9. The server analyzes this feedback and optimizes the content of the next offering.

[0922] In this way, this system can provide useful information to users on the move without relying on vision, and can also provide an effective advertising tool for municipalities and businesses.In addition, by customizing information to suit the user's hobbies and preferences, it is possible to achieve even higher levels of satisfaction.

[0923] The processing flow will be explained below.

[0924] Program processing flow

[0925] Step 1:

[0926] The user launches the app.

[0927] The device obtains the current location information (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[0928] Step 2:

[0929] The device sends the current location information, direction of movement, and user preferences to the server. The communication protocol is HTTPS, and data is encrypted.

[0930] Step 3:

[0931] The server analyzes the received current location information and sends a query to a database of nearby tourist attractions to obtain tourist attraction information.

[0932] At the same time, queries are sent to a local industry database to obtain information on nearby specialties and companies.

[0933] Step 4:

[0934] Based on the surrounding area information acquired by the server and the user's hobbies and preferences, the generative AI model generates text to be provided to the user. For example, for a user who likes history, the system generates information such as "Many buildings from the Edo period remain in this area."

[0935] Step 5:

[0936] The system also generates local ads based on the information it collects, such as "A nearby souvenir shop sells local Japanese sweets."

[0937] Step 6:

[0938] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[0939] Step 7:

[0940] The server transmits the generated voice data to the terminal via the Internet.

[0941] Step 8:

[0942] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[0943] Step 9:

[0944] Users can provide feedback on the information provided by the app, leaving ratings and comments.

[0945] Step 10:

[0946] The terminal transmits the user's feedback information to the server.

[0947] Step 11:

[0948] The server analyzes the feedback and updates the generative AI model and database, which will result in even more accurate information being provided in future.

[0949] In this way, the system provides users with customized information based on their current location, travel direction, and preferences, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[0950] Example 1

[0951] 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."

[0952] Conventional information provision systems are limited to providing simple text information based on the user's current location, making it difficult to provide detailed, personalized information tailored to the user's preferences. Furthermore, because information is primarily acquired visually, it is difficult to obtain information effectively in situations where it is difficult to use one's eyes, such as while traveling or driving. Furthermore, there is a lack of a mechanism for improving the accuracy of the system based on user feedback.

[0953] 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.

[0954] In this invention, the server includes a means for acquiring the user's current location information, a means for collecting surrounding information based on the acquired current location information and travel direction information, a means for using a generative AI model to generate text from the collected surrounding information based on the user's interest and preference information, a means for using a speech synthesis engine to convert the generated text into speech data, a means for providing the generated speech data to the user, and a means for collecting user feedback and updating the generative AI model and database to improve the accuracy of information provision. This enables the provision of detailed, personalized speech information tailored to the user's interests and preferences. Furthermore, useful information can be obtained without relying on vision, improving the accuracy of the system.

[0955] "User's current location information" refers to the latitude and longitude data of the user's current location.

[0956] "Movement direction information" is information about the direction in which the user is currently moving, and is data obtained using a compass function or the like.

[0957] "Nearby information" is various data about the neighborhood collected based on the user's current location information and travel direction information.

[0958] "Hobbies and preferences information" is information that indicates the user's personal interests and concerns, such as favorite tourist spots and favorite foods.

[0959] A "generative AI model" is an artificial intelligence technology that generates text from surrounding information based on the user's hobbies and preferences.

[0960] A "speech synthesis engine" is a software or hardware technology for converting generated text into speech data.

[0961] "Feedback" refers to information that a user writes down about their satisfaction with and thoughts about the information provided and sends it to the server.

[0962] "Updating a database" means rewriting an existing database to the latest version based on newly collected data and feedback.

[0963] MODE FOR CARRYING OUT THE INVENTION

[0964] This invention relates to a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for delivery. This system operates via the user's terminal, a server, and a communication network.

[0965] Hardware and software used

[0966] Device: A device such as a smartphone or tablet held by a user, equipped with GPS and compass functions.

[0967] Server: Collects information and generates text and voice data using generative AI models and a speech synthesis engine. For example, a cloud server (AWS, GCP, etc.) is used.

[0968] Communication network: Terminals and servers exchange information via the Internet.

[0969] Processing Details

[0970] Getting user information

[0971] When a user launches the app, the device uses the GPS function to obtain the current location (latitude and longitude) and the compass function to obtain the direction of travel.

[0972] Sending information

[0973] The terminal transmits the acquired current location information, movement direction information, and user's hobbies and preferences information to a server via the Internet.

[0974] Collection of information

[0975] Based on the current location information and movement direction information received by the server, the server collects surrounding information from the tourist destination database and local industry database. For example, if the current location is Kyoto City, the server will obtain information on "Kinkakuji Temple" from the tourist destination database and "Kyoto specialty product stores" from the local industry database.

[0976] Text generation

[0977] The server generates text using a generative AI model (e.g., GPT-4) based on this surrounding information and the user's hobbies and preferences. An example of a prompt sentence is "Generate information about nearby tourist spots and souvenir shops for a user in Kyoto City."

[0978] Generating audio data

[0979] The server converts the generated text into speech data using a speech synthesis engine (e.g., Google Cloud Text-to-Speech). For example, the generated text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century" is converted into speech data.

[0980] Sending and playing audio data

[0981] The server sends the generated audio data to the device, which then plays the received audio data in real time.

[0982] Gathering feedback

[0983] The user inputs his / her satisfaction level and thoughts about the provided information and transmits them to the server via the terminal.

[0984] System optimization

[0985] The server analyzes the collected feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0986] Specific examples

[0987] Use in tourist areas

[0988] 1. The user launches the app while in Kyoto City.

[0989] 2. The device uses the GPS function to obtain current location information (latitude and longitude within Kyoto City) and the compass function to obtain the direction of movement northward.

[0990] 3. The device sends the acquired information to a server via the Internet.

[0991] 4. Based on the current location information, the server collects information on "Kinkaku-ji Temple" from the tourist destination database and "Kyoto specialty stores" from the local industry database.

[0992] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[0993] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[0994] 7. The device plays back the received audio data in real time, and provides information such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[0995] 8. The user enters the rating into the app and sends it to the server.

[0996] 9. The server analyzes the feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[0997] The system allows users to hear detailed, personalized information based on their current location, providing useful information without relying on vision, and allows for feedback to improve the system's accuracy.

[0998] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0999] Step 1:

[1000] Getting user information

[1001] When a user launches the app, the device uses the GPS function to obtain current location information (latitude and longitude). The input is the user's action of launching the app. The output is current location information (e.g., 35.0116 degrees north latitude, 135.7681 degrees east longitude). In addition, the compass function is used to obtain movement direction information. The output is movement direction information (e.g., heading north).

[1002] Step 2:

[1003] Sending information

[1004] The device transmits the current location information, travel direction information, and user interest and preference information to a server via the Internet. The inputs are the current location information, travel direction information, and interest and preference information obtained by the device. The server receives this information as output.

[1005] Step 3:

[1006] Collection of information

[1007] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases and local industry databases. The inputs are current location information (latitude 35.0116 degrees north, longitude 135.7681 degrees east) and travel direction information (northbound). The output is surrounding information (e.g., information on Kinkaku-ji Temple and Kyoto specialty shops).

[1008] Step 4:

[1009] Text generation

[1010] The server inputs the surrounding area information collected and the user's hobbies and preferences into the generative AI model as prompts. The inputs include surrounding area information and hobbies and preferences. For example, a prompt might be generated that reads, "For a user in Kyoto City, please generate information about nearby tourist spots and souvenir shops." The output is the text generated by the generative AI model (for example, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[1011] Step 5:

[1012] Generating audio data

[1013] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the text generated by the generative AI model. The output is speech data (e.g., "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[1014] Step 6:

[1015] Sending and playing audio data

[1016] The server sends the generated audio data to the device. As input, there is audio data. As output, the device receives it and plays it in real time. The device outputs the audio using, for example, a Bluetooth headset or speaker.

[1017] Step 7:

[1018] Gathering feedback

[1019] The user inputs their satisfaction and thoughts about the provided information and sends it to the server via their terminal. The input is the user's feedback information, which the server receives as output.

[1020] Step 8:

[1021] System optimization

[1022] The server analyzes the feedback collected from users and updates the generative AI model and database. The input is the feedback information. The output is an updated generative AI model and database. This improves the accuracy of the next information provided.

[1023] (Application example 1)

[1024] 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."

[1025] When providing useful information to users in autonomous vehicles in real time, a method is needed that allows them to obtain the information without relying on vision. It is also necessary to improve user satisfaction by providing information that meets the individual preferences of each user. Furthermore, technology is also needed to improve the accuracy of text generation and speech synthesis.

[1026] 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.

[1027] In this invention, the server includes means for acquiring current location information and movement direction, means for collecting surrounding information, means for generating text based on user interest and preference information, means for generating text using a generative AI model, means for applying natural language processing technology using the generated text as a prompt sentence, means for converting the generated text into voice data, and means for providing the voice data, thereby enabling the user to obtain personalized information in real time as voice without relying on vision.

[1028] "Current location information" refers to location data acquired by the user's device, and specifically includes latitude and longitude information.

[1029] "Direction of movement" is information indicating the direction in which a user or autonomous vehicle is traveling, and is obtained using a compass or other position detection sensors.

[1030] "Local area information" is information collected based on the user's current location information, and includes information on tourist spots, local specialties, local industries, etc.

[1031] "Hobbies and Preference Information" includes information about the user's areas of interest, activities, preferences, etc. For example, information about hobbies and preferences such as history and food.

[1032] "Generative AI model" refers to an artificial intelligence model used to generate generated text, utilizing natural language processing techniques to construct content that is appropriate for the user.

[1033] A "prompt" is an instruction or question that a generative AI model uses to generate text, and serves as the starting point for text generation.

[1034] "Voice data" refers to data in the form of voice generated by a speech synthesis engine based on the generated text, and is provided to the user.

[1035] "Natural language processing technology" is a general term for technologies used by generative AI models to understand and generate human language, and is used for generating and analyzing sentences.

[1036] A "speech synthesis engine" is software that converts text into speech data and is adjusted according to the speech format.

[1037] "Independent of vision" means that the user can obtain information through sound or other means, meaning that the information can be obtained without the need for sight.

[1038] To implement this invention, a series of systems is required that acquires the user's current location information and direction of movement, collects surrounding information based on that information, generates text using a generative AI model, converts it into voice data, and provides it to the user. A specific embodiment of this system is shown below.

[1039] Hardware and Software Configuration

[1040] 1. Hardware Configuration

[1041] User device: Includes GPS sensor, compass, internet communication function, and audio output (vehicle audio system or Bluetooth headset).

[1042] Server: A server with high-performance data processing capabilities.

[1043] Communication network: Connects user terminals and servers via the Internet.

[1044] 2. Software Configuration

[1045] Software on the server: ambient information gathering module, generative AI model (e.g., GPT-4), speech synthesis engine (e.g., Google Text-to-Speech API), feedback gathering and analysis module.

[1046] Software on the user's device: location application, audio playback application, feedback input interface.

[1047] Processing flow and data calculation

[1048] 1. Obtaining current location information and direction of travel

[1049] When a user launches the application, the device uses the GPS sensor to obtain latitude and longitude and the compass to measure direction of movement.

[1050] 2. Gathering surrounding information

[1051] The terminal transmits the acquired current location information and direction of movement to the server.

[1052] The server's local information collection module collects appropriate local information from a tourist destination database and a local industry database.

[1053] 3. Text Generation

[1054] The server generates text using a generative AI model based on the collected information and the user's preferences, and specific prompts are used for the generative AI model.

[1055] Example: "The current location is Kyoto City, and the user is traveling north. The user's hobbies and interests are information about history and food. Under these conditions, generate a guide to provide to the user based on the collected tourist information and information about local food."

[1056] 4. Generating Audio Data

[1057] The server passes the generated text to a speech synthesis engine and converts it into voice data.

[1058] 5. Provision to Users

[1059] The server sends the generated audio data to the user's device, which then plays it through its audio system, allowing the user to obtain information without relying on vision.

[1060] 6. Gather feedback and optimize the system

[1061] Users enter feedback into the device and send it to the server, which analyzes it and uses it to update the generative AI model and database.

[1062] Specific examples

[1063] By using this system while riding in an autonomous vehicle in Kyoto City, a user can receive real-time, personalized information via voice, such as, "Kinkaku-ji is a Buddhist temple built in the 14th century. In addition, you can purchase carefully selected Japanese tea at a nearby store." This allows users to obtain useful information without relying on their vision, even while on the move, improving user satisfaction.

[1064] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1065] Step 1:

[1066] When a user launches the application, the device uses the GPS sensor to obtain the current location (latitude and longitude) and the compass to measure the direction of movement. The input is the user's action of launching the application, and the output is the current location and direction of movement data.

[1067] Step 2:

[1068] The device transmits the acquired current location information and movement direction data to the server. This communication is carried out via the Internet. The input is the location information and direction information from the device, and the output is when this data reaches the server.

[1069] Step 3:

[1070] The server collects surrounding information from a tourist destination database and a regional industry database based on the current location information and movement direction data. This process receives location information and direction information as input and generates surrounding information data as output.

[1071] Step 4:

[1072] The server constructs a prompt sentence based on the user's interest and preference information, using the collected surrounding information and the generative AI model. The input is interest and preference information and surrounding information, and the output is the prompt sentence. An example of a specific prompt sentence is, "Current location: Kyoto City, traveling north. The user's interest and preference are information about history and food. Under these conditions, please generate a guide to provide to the user based on the collected tourist destination information and information about local food."

[1073] Step 5:

[1074] The server uses a generative AI model to generate text from the prompt. The input is the prompt, and the output is text data to be provided to the user. In this process, the generative AI model generates text using natural language processing techniques.

[1075] Step 6:

[1076] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the generated text, and the output is speech data. The speech synthesis engine converts the text into speech that is easy for the user to understand.

[1077] Step 7:

[1078] The server sends the generated audio data to the user's device, which then plays the received audio data and provides it to the user. The input is the audio data, and the output is the audio played from the device's audio system.

[1079] Step 8:

[1080] The user inputs feedback about the provided information, and the terminal sends the feedback to the server. The input is the user's feedback, and the output is the feedback data being sent to the server.

[1081] Step 9:

[1082] The server analyzes user feedback and uses it to update the generative AI model and database, thereby improving the accuracy of information provided next time. The input is feedback data, and the output is an updated generative AI model and database.

[1083] Furthermore, 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.

[1084] This system acquires a user's current location and direction of travel, collects surrounding information based on this, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Furthermore, by combining it with an emotion engine to recognize the user's emotions and adjust the content provided based on this information, a more personalized user experience is realized.

[1085] System Embodiments

[1086] System Overview

[1087] This system consists of the following elements:

[1088] 1. User's Device

[1089] It has the function of obtaining the user's current location information and direction of movement and sending it to the server.

[1090] It has a built-in emotion engine that recognizes the user's emotions.

[1091] 2. Server

[1092] Based on the received information, it gathers surrounding information and uses a generative AI model to generate customized text.

[1093] The generated text is converted into audio data and sent to the user's device.

[1094] 3. Communication Network

[1095] Infrastructure that connects users' devices to servers and enables data communication.

[1096] Program processing flow

[1097] 1. Acquisition of user information

[1098] The user launches the app.

[1099] The device obtains the current location (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[1100] The device uses its built-in emotion engine to analyze and recognize the user's emotional state based on voice tone, language patterns, facial expressions, etc.

[1101] 2. Transmission of information

[1102] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. The communication protocol is HTTPS, and data is encrypted.

[1103] 3. Collection of Information

[1104] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, information on tourist spots, local products, and local companies is collected.

[1105] 4. Text Generation

[1106] The server uses a generative AI model to generate text based on collected surrounding information, user preferences, and recognized emotional information, and the generative AI model also adjusts the tone and content of the text to match the user's emotional state.

[1107] For example, if the user is relaxed, it generates relaxed text such as "This area has beautiful gardens that are great for strolling."

[1108] 5. Generating Audio Data

[1109] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[1110] 6. Sending and Playing Audio Data

[1111] The server transmits the generated voice data to the terminal via the Internet.

[1112] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[1113] 7. Gathering Feedback

[1114] Users enter their satisfaction and opinions about the information provided into the app and write ratings and comments.

[1115] 8. System Optimization

[1116] The server analyzes user feedback and updates the generative AI model and database, ensuring that future information provided will be even more accurate.

[1117] Specific examples

[1118] Use in tourist areas

[1119] 1. The user launches the app while in Kyoto City.

[1120] 2. The device obtains the current location information (latitude and longitude within Kyoto City) and the direction of movement northward, and uses the built-in emotion engine to recognize the user's calm emotional state.

[1121] 3. The device sends the acquired information to the server.

[1122] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[1123] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and adds the sentiment-based content "Take a stroll through the beautiful gardens and relax," as well as generating advertisements for local souvenir shops.

[1124] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[1125] 7. The device plays the audio data it received, and provides instructions such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Please take a relaxing stroll through the beautiful gardens. Here is information about souvenir shops."

[1126] 8. The user enters their rating for the information provided into the app and sends it to the server.

[1127] 9. The server analyzes this feedback and optimizes the content of the next offering.

[1128] In this way, the system provides users with customized audio information based on their current location, travel direction, hobbies, preferences, and even emotional state, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[1129] The processing flow will be explained below.

[1130] Program processing flow

[1131] Step 1:

[1132] The user launches the app.

[1133] The device obtains the current location information (latitude and longitude) and direction of movement. The current location information is obtained using the GPS sensor, and the direction of movement is obtained using the digital compass.

[1134] Step 2:

[1135] The device uses a built-in emotion engine to analyze the user's emotional state, including voice tone, language patterns, and facial expression recognition using the device's camera.

[1136] Step 3:

[1137] The device transmits the acquired current location information, direction of movement, hobbies and preferences, and recognized emotion information to the server. The communication protocol is HTTPS, and the data is encrypted.

[1138] Step 4:

[1139] The server analyzes the received location information.

[1140] The server sends a query to a tourist destination database to collect relevant tourist destination information.

[1141] At the same time, the server sends a query to a local industry database to collect information on nearby specialties and businesses.

[1142] Step 5:

[1143] The server considers the received hobby, preference and emotion information and selects content suitable for the user from the collected tourist spot information.

[1144] Step 6:

[1145] The server uses a generative AI model to generate text from the collected information.

[1146] For example, if the user is in a relaxed emotional state, it generates relaxing text such as "This area has beautiful gardens, perfect for strolling."

[1147] The server also generates local advertisement text at the same time, for example, "A nearby souvenir shop sells local Japanese sweets."

[1148] Step 7:

[1149] The server passes the generated text to a speech synthesis engine, which converts it into audio data, taking into account the user's language and tone of voice preferences.

[1150] Step 8:

[1151] The server transmits the generated voice data to the terminal via the Internet.

[1152] Step 9:

[1153] The device will play the received audio data in real time, and output it to the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[1154] Step 10:

[1155] Users enter ratings and comments about the information provided into the app.

[1156] Step 11:

[1157] The terminal transmits the input user feedback information to the server.

[1158] Step 12:

[1159] The server analyzes user feedback and updates the generative AI model and database, which improves the accuracy of future information provided.

[1160] Through the above process, the system provides users with customized information and voice data in real time based on their current location, direction of travel, emotional state, and hobbies and preferences, making travel time more meaningful and providing an effective advertising tool for local governments and businesses.

[1161] Example 2

[1162] 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."

[1163] Conventional systems could collect surrounding information based on a user's current location and preferences, and provide voice data. However, they were unable to provide information that took the user's emotional state into account. As a result, the information provided was sometimes inconsistent with the user's actual situation and emotions, resulting in a suboptimal user experience. Furthermore, the voice data provided was uniform, resulting in a lack of personalized information for individual users. To solve this issue, a system that recognizes a user's emotional state and provides customized information based on that state is needed.

[1164] 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.

[1165] In this invention, the server includes means for acquiring the user's current location information and direction of travel, means for collecting surrounding information, means for recognizing the user's emotional state, means for generating customized text based on the user's interest and preference information and the recognized emotional state, means for converting the generated text into voice data, and means for providing the voice data to the user. This makes it possible to provide personalized information that corresponds not only to the user's current location and direction of travel but also to the user's emotional state.

[1166] "Current location information" is latitude and longitude information that indicates the user's location.

[1167] "Movement direction" is information that indicates the direction in which the user is facing or moving.

[1168] "Nearby information" refers to information including tourist spot information, local product information, and local industry information collected based on the user's current location information and direction of travel.

[1169] "Emotional state" refers to the emotional state of a user as analyzed from their voice tone, language patterns, facial expressions, etc.

[1170] "Hobbies and Preference Information" is information about the user's interests and preferences.

[1171] "Customized text" is personalized text that is generated based on the user's preferences and perceived emotional state.

[1172] "Speech data" refers to speech information generated by a speech synthesis engine based on the generated text.

[1173] MODE FOR CARRYING OUT THE INVENTION

[1174] The present invention is a system that acquires a user's current location information and travel direction information, and collects surrounding information based on this information. Furthermore, the system generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Specific examples of embodiments of the present invention are described below.

[1175] System elements and the hardware and software used

[1176] 1. User's Device

[1177] The GPS sensor and digital compass are used to obtain current location information (latitude and longitude) and direction of movement.

[1178] To recognize emotions, we use a microphone for voice tone analysis and a front camera for facial expression analysis. We use publicly available emotion analysis software as the emotion engine.

[1179] 2. Server

[1180] Based on the received current location information and movement direction information, surrounding information is collected from tourist destination databases, local industry databases, etc. For this, a general database management system such as an SQL database is used.

[1181] Based on the collected information and the user's preferences and emotions, a generative AI model is used to generate text. For example, a Generative Pretrained Transformer (GPT) is used as the generative AI model.

[1182] A TTS (Text-to-Speech) engine is used to convert the generated text into audio data.

[1183] 3. Communication Network

[1184] A secure internet connection using the HTTPS protocol is used to connect the user's device to the server and transmit data.

[1185] System operation procedure

[1186] Getting user information

[1187] After the user launches the app, the device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement.

[1188] The device uses a built-in emotion engine to recognize the user's emotional state through voice tone and facial expression analysis.

[1189] Sending and collecting information

[1190] The device transmits the current location information, movement direction information, hobby and preference information, and emotional information acquired to the server via HTTPS.

[1191] The server queries the tourist destination database and the local industry database to collect surrounding information.

[1192] Text and audio data generation

[1193] The server uses the received information to input the prompt into a generative AI model to generate customized text, for example using the following prompt:

[1194] The user is using the app in Kyoto city. The current location is near Kinkakuji Temple, and the user's emotional state is relaxed. Please generate a guide message for the user.

[1195] The server passes the generated text to a TTS engine, which generates voice data tailored to the user's settings.

[1196] Sending and playing audio data

[1197] The server transmits the generated voice data to the terminal via the Internet.

[1198] The terminal provides the received audio data to the user and plays the audio on the appropriate device.

[1199] In this way, the system provides audio information tailored to the user's current location, travel direction, hobbies, preferences, and emotional state, making travel time more meaningful. It can also provide an efficient advertising tool for local governments and businesses.

[1200] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1201] System program processing steps

[1202] Step 1: Get the user's information

[1203] 1. The user launches the app. The input is the app's launch action and the output is the app's start screen.

[1204] A user taps an app installed on their smartphone or tablet to launch it, and the app's start screen appears.

[1205] 2. The device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement. The input is GPS data and compass data, and the output is latitude, longitude and direction information.

[1206] The device's GPS module receives signals from satellites and calculates latitude and longitude data, and then the digital compass detects the direction the device is facing.

[1207] Store the obtained latitude, longitude, and direction information in variables. Example: Latitude: 35.0116, Longitude: 135.7681, Direction: North

[1208] 3. The device uses a built-in emotion engine to analyze the user's emotional state. The input is voice tone, language patterns, and facial expression data, and the output is emotional information.

[1209] The microphone collects the user's voice and analyzes the tone and patterns of the voice, while the front camera captures facial expressions and runs facial recognition algorithms.

[1210] From the analysis results, the user's emotional state is classified as "relaxed," "excited," "sad," etc., and emotional information is obtained. Example: Emotion: Relaxed

[1211] Step 2: Submit your information

[1212] 1. The device sends current location information, movement direction information, hobbies, preferences information, and emotion information to the server. The input is the acquired user information, and the output is the transmission status to the server.

[1213] The device uses Wi-Fi or mobile data to send data to the server via the HTTPS protocol.

[1214] To confirm successful data transmission, a response code is received. Example: Status: 200 OK

[1215] Step 3: Gather information

[1216] 1. The server collects surrounding information based on the current location and direction of travel information received. The input is the user's current location and direction of travel information, and the output is surrounding information data.

[1217] The server queries the tourist destination database, local industry database, etc. to obtain information on nearby tourist destinations, local products, and companies. Example: Nearby tourist destination: Kinkakuji Temple, Local product: Kyoto sweets

[1218] Store the acquired surrounding information in a variable. Example: NearbyInfo: {"TouristSpot": "Kinkakuji Temple", "Specialty": "Kyoto sweets"}

[1219] Step 4: Generate text

[1220] 1. The server generates customized text using a generative AI model based on collected surrounding information, preferences, and emotional information. The input is a prompt sentence, and the output is customized text.

[1221] Input a prompt to the generative AI model. Example: The user is in Kyoto City and currently feels relaxed. Please generate a guide about Kinkakuji Temple.

[1222] The model generates customized text based on the prompt, e.g., "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and stroll through the gardens."

[1223] Step 5: Generate audio data

[1224] 1. The server passes the generated text to the TTS engine and converts it into speech data. The input is the generated text and the output is speech data.

[1225] The TTS engine converts text to speech. Example: Audio file: "kinkakuji.mp3"

[1226] Step 6: Sending and Playing Audio Data

[1227] 1. The server sends the generated voice data to the terminal via the Internet. The input is the voice data, and the output is the transmission status to the terminal.

[1228] The audio data is compressed and sent to the device over a secure channel. Example: Status: 200 OK

[1229] 2. The terminal plays back the received audio data in real time. The input is audio data, and the output is audio information provided to the user.

[1230] The device plays an audio file through the internal speaker or a Bluetooth headset. Example: "Start audio playback."

[1231] keyword

[1232] Generative AI model, prompt sentence

[1233] (Application example 2)

[1234] 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."

[1235] Conventional tourist information systems have limited content provided based on the user's current location and direction of travel, making it difficult to provide personalized information based on the user's emotions, hobbies, and preferences. Furthermore, in order for the information provided as tourist information to be interesting and effective for the user, the generated text content must be flexibly adjusted to match the user's emotional state. Effective methods are also needed for providing collected information on tourist destinations, local specialties, and local industries tailored to the user's movements and current location.

[1236] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring current location information and travel direction information of the user, means for collecting surrounding information based on the acquired current location information and travel direction information, means for generating text from the surrounding information collected based on the user's hobby, preference, and emotional information, means for converting the generated text into voice data using a generative AI model, means for providing the generated voice data to the user, and means for recognizing the user's emotions and adjusting the content to be provided based on the emotional information. This makes it possible to utilize emotion analysis to provide personalized tourist guidance tailored to the user's emotions, hobbies, and preferences, and is expected to improve the user experience.

[1237] "Current location information" refers to geographical information about the location where the user is currently located, and includes coordinate data such as latitude and longitude.

[1238] "Movement direction information" is data indicating the direction in which the user is moving, and is obtained using a compass or gyroscope.

[1239] "Nearby information" refers to information about tourist spots, local specialties, local industries, etc., collected based on the user's current location and direction of travel.

[1240] "Hobbies and Preference Information" is data that indicates a user's interests and preferences, and is obtained from the user's profile and past behavioral history.

[1241] "Emotional information" is data that indicates the user's current emotional state and is obtained using voice tone and facial expression analysis.

[1242] A "generative AI model" is a model that uses artificial intelligence to generate text, creating customized text based on user input and context.

[1243] "Text generation" is the process of creating sentences that are appropriate for the user based on collected peripheral information, the user's hobbies, preferences, and emotional information.

[1244] "Audio data" refers to data that has been converted from generated text into audio format, and is used to provide information to the user by audio.

[1245] "Emotion recognition" is the process of analyzing a user's emotional state and obtaining that information.

[1246] This invention is a system that acquires a user's current location information and travel direction information, collects surrounding information based on this information, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. This system provides personalized information to users in real time, making it particularly effective as a tourist guide.

[1247] System configuration

[1248] This system is broadly composed of the following components:

[1249] 1. User's Device

[1250] Obtaining current location and direction information

[1251] Emotion engine recognizes emotional states

[1252] Send the acquired information to the server

[1253] 2. Server

[1254] Collecting surrounding information based on received information

[1255] Generate customized text using generative AI models

[1256] Converts text into audio data and sends it to the user's device

[1257] 3. Communication Network

[1258] Connecting the user's device to the server

[1259] Hardware and software used

[1260] GPS sensor: Used to obtain the user's current location

[1261] Digital compass: Used to obtain the user's moving direction information

[1262] Emotion Engine: Used to recognize the user's emotional state based on their tone of voice and facial expression analysis.

[1263] Generative AI model (OpenAI API): Used to generate customized text based on user information

[1264] Text-to-Speech Engine (gTTS): Used to convert generated text into speech data

[1265] Communication protocol (HTTPS): used to send and receive data securely

[1266] Processing flow

[1267] 1. Processing on the user's device

[1268] When a user launches the application, the device's GPS sensor and digital compass are used to obtain information on the user's current location and direction of movement. The emotion engine then analyzes the user's tone of voice and facial expressions to recognize their emotional state. This information, along with the user's preferences, is then sent to the server.

[1269] 2. Processing on the server

[1270] The server collects information about the surrounding area from databases of tourist attractions and local specialties based on the received current location and direction of travel information. It then uses a generative AI model to generate customized text based on the user's preferences and emotions. This text is then passed to a speech synthesis engine and converted into voice data.

[1271] 3. Provision of audio data

[1272] The audio data generated by the server is sent to the user's device and played back in real time, allowing the user to receive personalized tourist information by audio.

[1273] Examples of concrete examples and prompts

[1274] For example, consider the case where a user arrives at the tourist spot "Kinkakuji Temple" in Kyoto City and launches the app. If the user is in a relaxed emotional state and has an interest in history as a hobby, the following prompt sentence will be input into the generative AI model.

[1275] Prompt statement:

[1276] The user is currently at Kinkakuji Temple. The user is in a relaxed state. There are beautiful gardens in the area. Provide information in a relaxing tone. Also, recommend nearby souvenir shops.

[1277] The generative AI model generates customized text based on this prompt, which is then converted into speech data and provided to the user: "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and enjoy a stroll through the beautiful gardens. Here is information about souvenir shops."

[1278] In this way, it is possible to realize customized tourist information according to the user's current location, direction of travel, and emotional state.

[1279] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1280] Step 1:

[1281] The user launches the application. The device uses the GPS sensor and digital compass to obtain current location information (latitude and longitude) and direction of movement. The user's current location and direction of movement information are obtained as input, and as output, this data is processed into a format that can be sent to the server. Specifically, the device receives a GPS signal and recognizes the direction using the digital compass.

[1282] Step 2:

[1283] The device passes the current location and movement direction information it acquires to a built-in emotion engine, which then analyzes the user's voice tone and facial expressions to recognize their emotional state. The inputs are current location information, movement direction information, voice tone, and facial expression data, and the output is the user's recognized emotion information. Specifically, the emotion engine analyzes changes in voice tone and facial expressions to classify emotions.

[1284] Step 3:

[1285] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. All previously acquired information is used as input, and this information is securely sent to the server as output using the HTTPS protocol. Specifically, the device converts the data into a data format such as JSON and sends it over the Internet.

[1286] Step 4:

[1287] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases, local product databases, etc. The user's current location information and travel direction information are acquired as input, and information on the relevant tourist destinations and local products is obtained as output. Specifically, the server executes a database query to acquire relevant information.

[1288] Step 5:

[1289] The server uses a generative AI model based on the surrounding information, hobbies, preferences, and emotional information collected to generate customized text. The collected surrounding information, the user's hobbies, preferences, and emotional information are used as input, and text appropriate for the user is generated as output. Specifically, the system operates by inputting a prompt sentence into the generative AI model and obtaining the generated text.

[1290] Step 6:

[1291] The server passes the generated text to a speech synthesis engine and converts it into voice data. The text generated by the generative AI model is used as input, and voice data is obtained as output. Specifically, the speech synthesis engine analyzes the text and generates an audio file.

[1292] Step 7:

[1293] The server sends the generated voice data to the user's device. The server uses the voice data as input and sends the voice data to the device as output. Specifically, the server sends the voice file to the device via the Internet.

[1294] Step 8:

[1295] The device plays back audio data received in real time. The received audio data is used as input, and the audio is played back from a speaker or headset as output. Specifically, the audio data is played back using the device's audio playback function.

[1296] Step 9:

[1297] The user enters their satisfaction and thoughts about the information provided into the app and sends it to the server. The app obtains user feedback as input, and sends ratings and comments as output to the server. Specifically, the app uses the feedback function to collect user opinions and send them to the server.

[1298] Step 10:

[1299] The server analyzes user feedback and updates the generative AI model and database. It receives user feedback information as input and optimizes the generative AI model and database as output. Specifically, it analyzes the feedback data and adjusts the parameters of the generative AI model to provide more accurate information from the next time onwards.

[1300] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1301] 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1302] 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.

[1303] [Fourth embodiment]

[1304] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1305] 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.

[1306] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1307] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1308] 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 audio in accordance with instructions from the processor 46.

[1309] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1310] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1311] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1312] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1313] 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.

[1314] 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.

[1315] In the robot 414, the processor 46 performs the reception output process. 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.

[1316] Next, a description will be given of the specific processing performed 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."

[1317] The present invention is a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for provision.

[1318] System Embodiments

[1319] System Overview

[1320] This system consists of a user's device, a server, and a communications network connecting them. The user's device has the ability to acquire current location information and direction of movement and send it to the server. The server collects surrounding information based on the received information and converts it into text using a generative AI model. The converted text is then converted into voice data and finally sent to the user's device.

[1321] Program processing flow

[1322] 1. Acquisition of user information

[1323] When a user launches the app, the device obtains the current location (latitude and longitude) and direction of travel using the GPS and compass functions.

[1324] 2. Transmission of information

[1325] The device sends information about the user's current location, direction of travel, and hobbies and preferences to a server via the Internet.

[1326] 3. Collection of Information

[1327] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, the tourist destination database can provide information on nearby famous places, while the local industry database can provide information on local specialties and businesses.

[1328] 4. Text Generation

[1329] Based on the surrounding information collected by the server and the user's hobbies and preferences, a generative AI model is used to generate text. The generative AI model uses natural language processing technology to generate information that is interesting to the user.

[1330] 5. Generating Audio Data

[1331] The server then passes the generated text to a speech synthesis engine, which converts it into voice data. The speech synthesis engine supports a variety of voice formats and is tailored to the language and accent selected by the user.

[1332] 6. Sending and Playing Audio Data

[1333] The server sends the generated audio data to the device, which then plays it back in real time, ensuring proper audio output even if the user is using a Bluetooth headset or car speakers.

[1334] 7. Gathering Feedback

[1335] The user inputs their satisfaction and thoughts about the provided information and sends it from the device to the server, thereby collecting user feedback.

[1336] 8. System Optimization

[1337] The server analyzes user feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[1338] Specific examples

[1339] Use in tourist areas

[1340] 1. The user launches the app while in Kyoto City.

[1341] 2. The device acquires the current location information (latitude and longitude within Kyoto City) and the direction of movement northward.

[1342] 3. The device sends the acquired information to the server.

[1343] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[1344] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[1345] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[1346] 7. The device plays the audio data it has received, and explains, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[1347] 8. The user enters their rating for the information provided into the app and sends it to the server.

[1348] 9. The server analyzes this feedback and optimizes the content of the next offering.

[1349] In this way, this system can provide useful information to users on the move without relying on vision, and can also provide an effective advertising tool for municipalities and businesses.In addition, by customizing information to suit the user's hobbies and preferences, it is possible to achieve even higher levels of satisfaction.

[1350] The processing flow will be explained below.

[1351] Program processing flow

[1352] Step 1:

[1353] The user launches the app.

[1354] The device obtains the current location information (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[1355] Step 2:

[1356] The device sends the current location information, direction of movement, and user preferences to the server. The communication protocol is HTTPS, and data is encrypted.

[1357] Step 3:

[1358] The server analyzes the received current location information and sends a query to a database of nearby tourist attractions to obtain tourist attraction information.

[1359] At the same time, queries are sent to a local industry database to obtain information on nearby specialties and companies.

[1360] Step 4:

[1361] Based on the surrounding area information acquired by the server and the user's hobbies and preferences, the generative AI model generates text to be provided to the user. For example, for a user who likes history, the system generates information such as "Many buildings from the Edo period remain in this area."

[1362] Step 5:

[1363] The system also generates local ads based on the information it collects, such as "A nearby souvenir shop sells local Japanese sweets."

[1364] Step 6:

[1365] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[1366] Step 7:

[1367] The server transmits the generated voice data to the terminal via the Internet.

[1368] Step 8:

[1369] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[1370] Step 9:

[1371] Users can provide feedback on the information provided by the app, leaving ratings and comments.

[1372] Step 10:

[1373] The terminal transmits the user's feedback information to the server.

[1374] Step 11:

[1375] The server analyzes the feedback and updates the generative AI model and database, which will result in even more accurate information being provided in future.

[1376] In this way, the system provides users with customized information based on their current location, travel direction, and preferences, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[1377] Example 1

[1378] 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 robot 414 will be referred to as a "terminal."

[1379] Conventional information provision systems are limited to providing simple text information based on the user's current location, making it difficult to provide detailed, personalized information tailored to the user's preferences. Furthermore, because information is primarily acquired visually, it is difficult to obtain information effectively in situations where it is difficult to use one's eyes, such as while traveling or driving. Furthermore, there is a lack of a mechanism for improving the accuracy of the system based on user feedback.

[1380] 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.

[1381] In this invention, the server includes a means for acquiring the user's current location information, a means for collecting surrounding information based on the acquired current location information and travel direction information, a means for using a generative AI model to generate text from the collected surrounding information based on the user's interest and preference information, a means for using a speech synthesis engine to convert the generated text into speech data, a means for providing the generated speech data to the user, and a means for collecting user feedback and updating the generative AI model and database to improve the accuracy of information provision. This enables the provision of detailed, personalized speech information tailored to the user's interests and preferences. Furthermore, useful information can be obtained without relying on vision, improving the accuracy of the system.

[1382] "User's current location information" refers to the latitude and longitude data of the user's current location.

[1383] "Movement direction information" is information about the direction in which the user is currently moving, and is data obtained using a compass function or the like.

[1384] "Nearby information" is various data about the neighborhood collected based on the user's current location information and travel direction information.

[1385] "Hobbies and preferences information" is information that indicates the user's personal interests and concerns, such as favorite tourist spots and favorite foods.

[1386] A "generative AI model" is an artificial intelligence technology that generates text from surrounding information based on the user's hobbies and preferences.

[1387] A "speech synthesis engine" is a software or hardware technology for converting generated text into speech data.

[1388] "Feedback" refers to information that a user writes down about their satisfaction with and thoughts about the information provided and sends it to the server.

[1389] "Updating a database" means rewriting an existing database to the latest version based on newly collected data and feedback.

[1390] MODE FOR CARRYING OUT THE INVENTION

[1391] This invention relates to a system that acquires a user's current location information, collects surrounding information based on that information, generates text based on the user's hobbies and preferences, and converts the generated text into audio data for delivery. This system operates via the user's terminal, a server, and a communication network.

[1392] Hardware and software used

[1393] Device: A device such as a smartphone or tablet held by a user, equipped with GPS and compass functions.

[1394] Server: Collects information and generates text and voice data using generative AI models and a speech synthesis engine. For example, a cloud server (AWS, GCP, etc.) is used.

[1395] Communication network: Terminals and servers exchange information via the Internet.

[1396] Processing Details

[1397] Getting user information

[1398] When a user launches the app, the device uses the GPS function to obtain the current location (latitude and longitude) and the compass function to obtain the direction of travel.

[1399] Sending information

[1400] The terminal transmits the acquired current location information, movement direction information, and user's hobbies and preferences information to a server via the Internet.

[1401] Collection of information

[1402] Based on the current location information and movement direction information received by the server, the server collects surrounding information from the tourist destination database and local industry database. For example, if the current location is Kyoto City, the server will obtain information on "Kinkakuji Temple" from the tourist destination database and "Kyoto specialty product stores" from the local industry database.

[1403] Text generation

[1404] The server generates text using a generative AI model (e.g., GPT-4) based on this surrounding information and the user's hobbies and preferences. An example of a prompt sentence is "Generate information about nearby tourist spots and souvenir shops for a user in Kyoto City."

[1405] Generating audio data

[1406] The server converts the generated text into speech data using a speech synthesis engine (e.g., Google Cloud Text-to-Speech). For example, the generated text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century" is converted into speech data.

[1407] Sending and playing audio data

[1408] The server sends the generated audio data to the device, which then plays the received audio data in real time.

[1409] Gathering feedback

[1410] The user inputs his / her satisfaction level and thoughts about the provided information and transmits them to the server via the terminal.

[1411] System optimization

[1412] The server analyzes the collected feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[1413] Specific examples

[1414] Use in tourist areas

[1415] 1. The user launches the app while in Kyoto City.

[1416] 2. The device uses the GPS function to obtain current location information (latitude and longitude within Kyoto City) and the compass function to obtain the direction of movement northward.

[1417] 3. The device sends the acquired information to a server via the Internet.

[1418] 4. Based on the current location information, the server collects information on "Kinkaku-ji Temple" from the tourist destination database and "Kyoto specialty stores" from the local industry database.

[1419] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and also generates advertising text "This Kyoto souvenir shop offers carefully selected Japanese tea."

[1420] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[1421] 7. The device plays back the received audio data in real time, and provides information such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Here is information about souvenir shops."

[1422] 8. The user enters the rating into the app and sends it to the server.

[1423] 9. The server analyzes the feedback and updates the generative AI model and database to improve the accuracy of the next information provided.

[1424] The system allows users to hear detailed, personalized information based on their current location, providing useful information without relying on vision, and allows for feedback to improve the system's accuracy.

[1425] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] Getting user information

[1428] When a user launches the app, the device uses the GPS function to obtain current location information (latitude and longitude). The input is the user's action of launching the app. The output is current location information (e.g., 35.0116 degrees north latitude, 135.7681 degrees east longitude). In addition, the compass function is used to obtain movement direction information. The output is movement direction information (e.g., heading north).

[1429] Step 2:

[1430] Sending information

[1431] The device transmits the current location information, travel direction information, and user interest and preference information to a server via the Internet. The inputs are the current location information, travel direction information, and interest and preference information obtained by the device. The server receives this information as output.

[1432] Step 3:

[1433] Collection of information

[1434] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases and local industry databases. The inputs are current location information (latitude 35.0116 degrees north, longitude 135.7681 degrees east) and travel direction information (northbound). The output is surrounding information (e.g., information on Kinkaku-ji Temple and Kyoto specialty shops).

[1435] Step 4:

[1436] Text generation

[1437] The server inputs the surrounding area information collected and the user's hobbies and preferences into the generative AI model as prompts. The inputs include surrounding area information and hobbies and preferences. For example, a prompt might be generated that reads, "For a user in Kyoto City, please generate information about nearby tourist spots and souvenir shops." The output is the text generated by the generative AI model (for example, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[1438] Step 5:

[1439] Generating audio data

[1440] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the text generated by the generative AI model. The output is speech data (e.g., "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Kyoto souvenir shops offer carefully selected Japanese tea.").

[1441] Step 6:

[1442] Sending and playing audio data

[1443] The server sends the generated audio data to the device. As input, there is audio data. As output, the device receives it and plays it in real time. The device outputs the audio using, for example, a Bluetooth headset or speaker.

[1444] Step 7:

[1445] Gathering feedback

[1446] The user inputs their satisfaction and thoughts about the provided information and sends it to the server via their terminal. The input is the user's feedback information, which the server receives as output.

[1447] Step 8:

[1448] System optimization

[1449] The server analyzes the feedback collected from users and updates the generative AI model and database. The input is the feedback information. The output is an updated generative AI model and database. This improves the accuracy of the next information provided.

[1450] (Application example 1)

[1451] 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."

[1452] When providing useful information to users in autonomous vehicles in real time, a method is needed that allows them to obtain the information without relying on vision. It is also necessary to improve user satisfaction by providing information that meets the individual preferences of each user. Furthermore, technology is also needed to improve the accuracy of text generation and speech synthesis.

[1453] 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.

[1454] In this invention, the server includes means for acquiring current location information and movement direction, means for collecting surrounding information, means for generating text based on user interest and preference information, means for generating text using a generative AI model, means for applying natural language processing technology using the generated text as a prompt sentence, means for converting the generated text into voice data, and means for providing the voice data, thereby enabling the user to obtain personalized information in real time as voice without relying on vision.

[1455] "Current location information" refers to location data acquired by the user's device, and specifically includes latitude and longitude information.

[1456] "Direction of movement" is information indicating the direction in which a user or autonomous vehicle is traveling, and is obtained using a compass or other position detection sensors.

[1457] "Local area information" is information collected based on the user's current location information, and includes information on tourist spots, local specialties, local industries, etc.

[1458] "Hobbies and Preference Information" includes information about the user's areas of interest, activities, preferences, etc. For example, information about hobbies and preferences such as history and food.

[1459] "Generative AI model" refers to an artificial intelligence model used to generate generated text, utilizing natural language processing techniques to construct content that is appropriate for the user.

[1460] A "prompt" is an instruction or question that a generative AI model uses to generate text, and serves as the starting point for text generation.

[1461] "Voice data" refers to data in the form of voice generated by a speech synthesis engine based on the generated text, and is provided to the user.

[1462] "Natural language processing technology" is a general term for technologies used by generative AI models to understand and generate human language, and is used for generating and analyzing sentences.

[1463] A "speech synthesis engine" is software that converts text into speech data and is adjusted according to the speech format.

[1464] "Independent of vision" means that the user can obtain information through sound or other means, meaning that the information can be obtained without the need for sight.

[1465] To implement this invention, a series of systems is required that acquires the user's current location information and direction of movement, collects surrounding information based on that information, generates text using a generative AI model, converts it into voice data, and provides it to the user. A specific embodiment of this system is shown below.

[1466] Hardware and Software Configuration

[1467] 1. Hardware Configuration

[1468] User device: Includes GPS sensor, compass, internet communication function, and audio output (vehicle audio system or Bluetooth headset).

[1469] Server: A server with high-performance data processing capabilities.

[1470] Communication network: Connects user terminals and servers via the Internet.

[1471] 2. Software Configuration

[1472] Software on the server: ambient information gathering module, generative AI model (e.g., GPT-4), speech synthesis engine (e.g., Google Text-to-Speech API), feedback gathering and analysis module.

[1473] Software on the user's device: location application, audio playback application, feedback input interface.

[1474] Processing flow and data calculation

[1475] 1. Obtaining current location information and direction of travel

[1476] When a user launches the application, the device uses the GPS sensor to obtain latitude and longitude and the compass to measure direction of movement.

[1477] 2. Gathering surrounding information

[1478] The terminal transmits the acquired current location information and direction of movement to the server.

[1479] The server's local information collection module collects appropriate local information from a tourist destination database and a local industry database.

[1480] 3. Text Generation

[1481] The server generates text using a generative AI model based on the collected information and the user's preferences, and specific prompts are used for the generative AI model.

[1482] Example: "The current location is Kyoto City, and the user is traveling north. The user's hobbies and interests are information about history and food. Under these conditions, generate a guide to provide to the user based on the collected tourist information and information about local food."

[1483] 4. Generating Audio Data

[1484] The server passes the generated text to a speech synthesis engine and converts it into voice data.

[1485] 5. Provision to Users

[1486] The server sends the generated audio data to the user's device, which then plays it through its audio system, allowing the user to obtain information without relying on vision.

[1487] 6. Gather feedback and optimize the system

[1488] Users enter feedback into the device and send it to the server, which analyzes it and uses it to update the generative AI model and database.

[1489] Specific examples

[1490] By using this system while riding in an autonomous vehicle in Kyoto City, a user can receive real-time, personalized information via voice, such as, "Kinkaku-ji is a Buddhist temple built in the 14th century. In addition, you can purchase carefully selected Japanese tea at a nearby store." This allows users to obtain useful information without relying on their vision, even while on the move, improving user satisfaction.

[1491] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1492] Step 1:

[1493] When a user launches the application, the device uses the GPS sensor to obtain the current location (latitude and longitude) and the compass to measure the direction of movement. The input is the user's action of launching the application, and the output is the current location and direction of movement data.

[1494] Step 2:

[1495] The device transmits the acquired current location information and movement direction data to the server. This communication is carried out via the Internet. The input is the location information and direction information from the device, and the output is when this data reaches the server.

[1496] Step 3:

[1497] The server collects surrounding information from a tourist destination database and a regional industry database based on the current location information and movement direction data. This process receives location information and direction information as input and generates surrounding information data as output.

[1498] Step 4:

[1499] The server constructs a prompt sentence based on the user's interest and preference information, using the collected surrounding information and the generative AI model. The input is interest and preference information and surrounding information, and the output is the prompt sentence. An example of a specific prompt sentence is, "Current location: Kyoto City, traveling north. The user's interest and preference are information about history and food. Under these conditions, please generate a guide to provide to the user based on the collected tourist destination information and information about local food."

[1500] Step 5:

[1501] The server uses a generative AI model to generate text from the prompt. The input is the prompt, and the output is text data to be provided to the user. In this process, the generative AI model generates text using natural language processing techniques.

[1502] Step 6:

[1503] The server passes the generated text to a speech synthesis engine, which converts it into speech data. The input is the generated text, and the output is speech data. The speech synthesis engine converts the text into speech that is easy for the user to understand.

[1504] Step 7:

[1505] The server sends the generated audio data to the user's device, which then plays the received audio data and provides it to the user. The input is the audio data, and the output is the audio played from the device's audio system.

[1506] Step 8:

[1507] The user inputs feedback about the provided information, and the terminal sends the feedback to the server. The input is the user's feedback, and the output is the feedback data being sent to the server.

[1508] Step 9:

[1509] The server analyzes user feedback and uses it to update the generative AI model and database, thereby improving the accuracy of information provided next time. The input is feedback data, and the output is an updated generative AI model and database.

[1510] Furthermore, 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.

[1511] This system acquires a user's current location and direction of travel, collects surrounding information based on this, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Furthermore, by combining it with an emotion engine to recognize the user's emotions and adjust the content provided based on this information, a more personalized user experience is realized.

[1512] System Embodiments

[1513] System Overview

[1514] This system consists of the following elements:

[1515] 1. User's Device

[1516] It has the function of obtaining the user's current location information and direction of movement and sending it to the server.

[1517] It has a built-in emotion engine that recognizes the user's emotions.

[1518] 2. Server

[1519] Based on the received information, it gathers surrounding information and uses a generative AI model to generate customized text.

[1520] The generated text is converted into audio data and sent to the user's device.

[1521] 3. Communication Network

[1522] Infrastructure that connects users' devices to servers and enables data communication.

[1523] Program processing flow

[1524] 1. Acquisition of user information

[1525] The user launches the app.

[1526] The device obtains the current location (latitude and longitude) and direction of movement using the GPS sensor and digital compass.

[1527] The device uses its built-in emotion engine to analyze and recognize the user's emotional state based on voice tone, language patterns, facial expressions, etc.

[1528] 2. Transmission of information

[1529] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. The communication protocol is HTTPS, and data is encrypted.

[1530] 3. Collection of Information

[1531] Based on the current location information received by the server, surrounding information is collected from tourist destination databases, local industry databases, etc. For example, information on tourist spots, local products, and local companies is collected.

[1532] 4. Text Generation

[1533] The server uses a generative AI model to generate text based on collected surrounding information, user preferences, and recognized emotional information, and the generative AI model also adjusts the tone and content of the text to match the user's emotional state.

[1534] For example, if the user is relaxed, it generates relaxed text such as "This area has beautiful gardens that are great for strolling."

[1535] 5. Generating Audio Data

[1536] The server passes the generated text to a speech synthesis engine, which converts it into audio data and adjusts it to match the user's language, tone of voice, and other settings.

[1537] 6. Sending and Playing Audio Data

[1538] The server transmits the generated voice data to the terminal via the Internet.

[1539] The device plays back the audio data it receives in real time, ensuring that the audio is played on the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[1540] 7. Gathering Feedback

[1541] Users enter their satisfaction and opinions about the information provided into the app and write ratings and comments.

[1542] 8. System Optimization

[1543] The server analyzes user feedback and updates the generative AI model and database, ensuring that future information provided will be even more accurate.

[1544] Specific examples

[1545] Use in tourist areas

[1546] 1. The user launches the app while in Kyoto City.

[1547] 2. The device obtains the current location information (latitude and longitude within Kyoto City) and the direction of movement northward, and uses the built-in emotion engine to recognize the user's calm emotional state.

[1548] 3. The device sends the acquired information to the server.

[1549] 4. Based on the current location information, the server collects information about Kinkaku-ji Temple from a tourist destination database, as well as information about local specialty shops.

[1550] 5. The server uses the generative AI model to generate the text "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century," and adds the sentiment-based content "Take a stroll through the beautiful gardens and relax," as well as generating advertisements for local souvenir shops.

[1551] 6. The server passes these texts to a speech synthesis engine and converts them into audio data.

[1552] 7. The device plays the audio data it received, and provides instructions such as, "Kinkaku-ji is a Buddhist temple built by Ashikaga Yoshimitsu in the 14th century. Please take a relaxing stroll through the beautiful gardens. Here is information about souvenir shops."

[1553] 8. The user enters their rating for the information provided into the app and sends it to the server.

[1554] 9. The server analyzes this feedback and optimizes the content of the next offering.

[1555] In this way, the system provides users with customized audio information based on their current location, travel direction, hobbies, preferences, and even emotional state, making travel time more meaningful. It also provides an efficient advertising tool for local governments and businesses.

[1556] The processing flow will be explained below.

[1557] Program processing flow

[1558] Step 1:

[1559] The user launches the app.

[1560] The device obtains the current location information (latitude and longitude) and direction of movement. The current location information is obtained using the GPS sensor, and the direction of movement is obtained using the digital compass.

[1561] Step 2:

[1562] The device uses a built-in emotion engine to analyze the user's emotional state, including voice tone, language patterns, and facial expression recognition using the device's camera.

[1563] Step 3:

[1564] The device transmits the acquired current location information, direction of movement, hobbies and preferences, and recognized emotion information to the server. The communication protocol is HTTPS, and the data is encrypted.

[1565] Step 4:

[1566] The server analyzes the received location information.

[1567] The server sends a query to a tourist destination database to collect relevant tourist destination information.

[1568] At the same time, the server sends a query to a local industry database to collect information on nearby specialties and businesses.

[1569] Step 5:

[1570] The server considers the received hobby, preference and emotion information and selects content suitable for the user from the collected tourist spot information.

[1571] Step 6:

[1572] The server uses a generative AI model to generate text from the collected information.

[1573] For example, if the user is in a relaxed emotional state, it generates relaxing text such as "This area has beautiful gardens, perfect for strolling."

[1574] The server also generates local advertisement text at the same time, for example, "A nearby souvenir shop sells local Japanese sweets."

[1575] Step 7:

[1576] The server passes the generated text to a speech synthesis engine, which converts it into audio data, taking into account the user's language and tone of voice preferences.

[1577] Step 8:

[1578] The server transmits the generated voice data to the terminal via the Internet.

[1579] Step 9:

[1580] The device will play the received audio data in real time, and output it to the appropriate device, whether the user is using a Bluetooth headset or car speakers.

[1581] Step 10:

[1582] Users enter ratings and comments about the information provided into the app.

[1583] Step 11:

[1584] The terminal transmits the input user feedback information to the server.

[1585] Step 12:

[1586] The server analyzes user feedback and updates the generative AI model and database, which improves the accuracy of future information provided.

[1587] Through the above process, the system provides users with customized information and voice data in real time based on their current location, direction of travel, emotional state, and hobbies and preferences, making travel time more meaningful and providing an effective advertising tool for local governments and businesses.

[1588] Example 2

[1589] 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 robot 414 will be referred to as a "terminal."

[1590] Conventional systems could collect surrounding information based on a user's current location and preferences, and provide voice data. However, they were unable to provide information that took the user's emotional state into account. As a result, the information provided was sometimes inconsistent with the user's actual situation and emotions, resulting in a suboptimal user experience. Furthermore, the voice data provided was uniform, resulting in a lack of personalized information for individual users. To solve this issue, a system that recognizes a user's emotional state and provides customized information based on that state is needed.

[1591] 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.

[1592] In this invention, the server includes means for acquiring the user's current location information and direction of travel, means for collecting surrounding information, means for recognizing the user's emotional state, means for generating customized text based on the user's interest and preference information and the recognized emotional state, means for converting the generated text into voice data, and means for providing the voice data to the user. This makes it possible to provide personalized information that corresponds not only to the user's current location and direction of travel but also to the user's emotional state.

[1593] "Current location information" is latitude and longitude information that indicates the user's location.

[1594] "Movement direction" is information that indicates the direction in which the user is facing or moving.

[1595] "Nearby information" refers to information including tourist spot information, local product information, and local industry information collected based on the user's current location information and direction of travel.

[1596] "Emotional state" refers to the emotional state of a user as analyzed from their voice tone, language patterns, facial expressions, etc.

[1597] "Hobbies and Preference Information" is information about the user's interests and preferences.

[1598] "Customized text" is personalized text that is generated based on the user's preferences and perceived emotional state.

[1599] "Speech data" refers to speech information generated by a speech synthesis engine based on the generated text.

[1600] MODE FOR CARRYING OUT THE INVENTION

[1601] The present invention is a system that acquires a user's current location information and travel direction information, and collects surrounding information based on this information. Furthermore, the system generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. Specific examples of embodiments of the present invention are described below.

[1602] System elements and the hardware and software used

[1603] 1. User's Device

[1604] The GPS sensor and digital compass are used to obtain current location information (latitude and longitude) and direction of movement.

[1605] To recognize emotions, we use a microphone for voice tone analysis and a front camera for facial expression analysis. We use publicly available emotion analysis software as the emotion engine.

[1606] 2. Server

[1607] Based on the received current location information and movement direction information, surrounding information is collected from tourist destination databases, local industry databases, etc. For this, a general database management system such as an SQL database is used.

[1608] Based on the collected information and the user's preferences and emotions, a generative AI model is used to generate text. For example, a Generative Pretrained Transformer (GPT) is used as the generative AI model.

[1609] A TTS (Text-to-Speech) engine is used to convert the generated text into audio data.

[1610] 3. Communication Network

[1611] A secure internet connection using the HTTPS protocol is used to connect the user's device to the server and transmit data.

[1612] System operation procedure

[1613] Getting user information

[1614] After the user launches the app, the device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement.

[1615] The device uses a built-in emotion engine to recognize the user's emotional state through voice tone and facial expression analysis.

[1616] Sending and collecting information

[1617] The device transmits the current location information, movement direction information, hobby and preference information, and emotional information acquired to the server via HTTPS.

[1618] The server queries the tourist destination database and the local industry database to collect surrounding information.

[1619] Text and audio data generation

[1620] The server uses the received information to input the prompt into a generative AI model to generate customized text, for example using the following prompt:

[1621] The user is using the app in Kyoto city. The current location is near Kinkakuji Temple, and the user's emotional state is relaxed. Please generate a guide message for the user.

[1622] The server passes the generated text to a TTS engine, which generates voice data tailored to the user's settings.

[1623] Sending and playing audio data

[1624] The server transmits the generated voice data to the terminal via the Internet.

[1625] The terminal provides the received audio data to the user and plays the audio on the appropriate device.

[1626] In this way, the system provides audio information tailored to the user's current location, travel direction, hobbies, preferences, and emotional state, making travel time more meaningful. It can also provide an efficient advertising tool for local governments and businesses.

[1627] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1628] System program processing steps

[1629] Step 1: Get the user's information

[1630] 1. The user launches the app. The input is the app's launch action and the output is the app's start screen.

[1631] A user taps an app installed on their smartphone or tablet to launch it, and the app's start screen appears.

[1632] 2. The device uses the GPS sensor and digital compass to obtain the current location information (latitude and longitude) and direction of movement. The input is GPS data and compass data, and the output is latitude, longitude and direction information.

[1633] The device's GPS module receives signals from satellites and calculates latitude and longitude data, and then the digital compass detects the direction the device is facing.

[1634] Store the obtained latitude, longitude, and direction information in variables. Example: Latitude: 35.0116, Longitude: 135.7681, Direction: North

[1635] 3. The device uses a built-in emotion engine to analyze the user's emotional state. The input is voice tone, language patterns, and facial expression data, and the output is emotional information.

[1636] The microphone collects the user's voice and analyzes the tone and patterns of the voice, while the front camera captures facial expressions and runs facial recognition algorithms.

[1637] From the analysis results, the user's emotional state is classified as "relaxed," "excited," "sad," etc., and emotional information is obtained. Example: Emotion: Relaxed

[1638] Step 2: Submit your information

[1639] 1. The device sends current location information, movement direction information, hobbies, preferences information, and emotion information to the server. The input is the acquired user information, and the output is the transmission status to the server.

[1640] The device uses Wi-Fi or mobile data to send data to the server via the HTTPS protocol.

[1641] To confirm successful data transmission, a response code is received. Example: Status: 200 OK

[1642] Step 3: Gather information

[1643] 1. The server collects surrounding information based on the current location and direction of travel information received. The input is the user's current location and direction of travel information, and the output is surrounding information data.

[1644] The server queries the tourist destination database, local industry database, etc. to obtain information on nearby tourist destinations, local products, and companies. Example: Nearby tourist destination: Kinkakuji Temple, Local product: Kyoto sweets

[1645] Store the acquired surrounding information in a variable. Example: NearbyInfo: {"TouristSpot": "Kinkakuji Temple", "Specialty": "Kyoto sweets"}

[1646] Step 4: Generate text

[1647] 1. The server generates customized text using a generative AI model based on collected surrounding information, preferences, and emotional information. The input is a prompt sentence, and the output is customized text.

[1648] Input a prompt to the generative AI model. Example: The user is in Kyoto City and currently feels relaxed. Please generate a guide about Kinkakuji Temple.

[1649] The model generates customized text based on the prompt, e.g., "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and stroll through the gardens."

[1650] Step 5: Generate audio data

[1651] 1. The server passes the generated text to the TTS engine and converts it into speech data. The input is the generated text and the output is speech data.

[1652] The TTS engine converts text to speech. Example: Audio file: "kinkakuji.mp3"

[1653] Step 6: Sending and Playing Audio Data

[1654] 1. The server sends the generated voice data to the terminal via the Internet. The input is the voice data, and the output is the transmission status to the terminal.

[1655] The audio data is compressed and sent to the device over a secure channel. Example: Status: 200 OK

[1656] 2. The terminal plays back the received audio data in real time. The input is audio data, and the output is audio information provided to the user.

[1657] The device plays an audio file through the internal speaker or a Bluetooth headset. Example: "Start audio playback."

[1658] keyword

[1659] Generative AI model, prompt sentence

[1660] (Application example 2)

[1661] 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."

[1662] Conventional tourist information systems have limited content provided based on the user's current location and direction of travel, making it difficult to provide personalized information based on the user's emotions, hobbies, and preferences. Furthermore, in order for the information provided as tourist information to be interesting and effective for the user, the generated text content must be flexibly adjusted to match the user's emotional state. Effective methods are also needed for providing collected information on tourist destinations, local specialties, and local industries tailored to the user's movements and current location.

[1663] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring current location information and travel direction information of the user, means for collecting surrounding information based on the acquired current location information and travel direction information, means for generating text from the surrounding information collected based on the user's hobby, preference, and emotional information, means for converting the generated text into voice data using a generative AI model, means for providing the generated voice data to the user, and means for recognizing the user's emotions and adjusting the content to be provided based on the emotional information. This makes it possible to utilize emotion analysis to provide personalized tourist guidance tailored to the user's emotions, hobbies, and preferences, and is expected to improve the user experience.

[1664] "Current location information" refers to geographical information about the location where the user is currently located, and includes coordinate data such as latitude and longitude.

[1665] "Movement direction information" is data indicating the direction in which the user is moving, and is obtained using a compass or gyroscope.

[1666] "Nearby information" refers to information about tourist spots, local specialties, local industries, etc., collected based on the user's current location and direction of travel.

[1667] "Hobbies and Preference Information" is data that indicates a user's interests and preferences, and is obtained from the user's profile and past behavioral history.

[1668] "Emotional information" is data that indicates the user's current emotional state and is obtained using voice tone and facial expression analysis.

[1669] A "generative AI model" is a model that uses artificial intelligence to generate text, creating customized text based on user input and context.

[1670] "Text generation" is the process of creating sentences that are appropriate for the user based on collected peripheral information, the user's hobbies, preferences, and emotional information.

[1671] "Audio data" refers to data that has been converted from generated text into audio format, and is used to provide information to the user by audio.

[1672] "Emotion recognition" is the process of analyzing a user's emotional state and obtaining that information.

[1673] This invention is a system that acquires a user's current location information and travel direction information, collects surrounding information based on this information, generates customized text based on the user's hobbies, preferences, and emotions, and converts this into voice data for delivery. This system provides personalized information to users in real time, making it particularly effective as a tourist guide.

[1674] System configuration

[1675] This system is broadly composed of the following components:

[1676] 1. User's Device

[1677] Obtaining current location and direction information

[1678] Emotion engine recognizes emotional states

[1679] Send the acquired information to the server

[1680] 2. Server

[1681] Collecting surrounding information based on received information

[1682] Generate customized text using generative AI models

[1683] Converts text into audio data and sends it to the user's device

[1684] 3. Communication Network

[1685] Connecting the user's device to the server

[1686] Hardware and software used

[1687] GPS sensor: Used to obtain the user's current location

[1688] Digital compass: Used to obtain the user's moving direction information

[1689] Emotion Engine: Used to recognize the user's emotional state based on their tone of voice and facial expression analysis.

[1690] Generative AI model (OpenAI API): Used to generate customized text based on user information

[1691] Text-to-Speech Engine (gTTS): Used to convert generated text into speech data

[1692] Communication protocol (HTTPS): used to send and receive data securely

[1693] Processing flow

[1694] 1. Processing on the user's device

[1695] When a user launches the application, the device's GPS sensor and digital compass are used to obtain information on the user's current location and direction of movement. The emotion engine then analyzes the user's tone of voice and facial expressions to recognize their emotional state. This information, along with the user's preferences, is then sent to the server.

[1696] 2. Processing on the server

[1697] The server collects information about the surrounding area from databases of tourist attractions and local specialties based on the received current location and direction of travel information. It then uses a generative AI model to generate customized text based on the user's preferences and emotions. This text is then passed to a speech synthesis engine and converted into voice data.

[1698] 3. Provision of audio data

[1699] The audio data generated by the server is sent to the user's device and played back in real time, allowing the user to receive personalized tourist information by audio.

[1700] Examples of concrete examples and prompts

[1701] For example, consider the case where a user arrives at the tourist spot "Kinkakuji Temple" in Kyoto City and launches the app. If the user is in a relaxed emotional state and has an interest in history as a hobby, the following prompt sentence will be input into the generative AI model.

[1702] Prompt statement:

[1703] The user is currently at Kinkakuji Temple. The user is in a relaxed state. There are beautiful gardens in the area. Provide information in a relaxing tone. Also, recommend nearby souvenir shops.

[1704] The generative AI model generates customized text based on this prompt, which is then converted into speech data and provided to the user: "Kinkaku-ji is a Buddhist temple built in the 14th century. Relax and enjoy a stroll through the beautiful gardens. Here is information about souvenir shops."

[1705] In this way, it is possible to realize customized tourist information according to the user's current location, direction of travel, and emotional state.

[1706] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1707] Step 1:

[1708] The user launches the application. The device uses the GPS sensor and digital compass to obtain current location information (latitude and longitude) and direction of movement. The user's current location and direction of movement information are obtained as input, and as output, this data is processed into a format that can be sent to the server. Specifically, the device receives a GPS signal and recognizes the direction using the digital compass.

[1709] Step 2:

[1710] The device passes the current location and movement direction information it acquires to a built-in emotion engine, which then analyzes the user's voice tone and facial expressions to recognize their emotional state. The inputs are current location information, movement direction information, voice tone, and facial expression data, and the output is the user's recognized emotion information. Specifically, the emotion engine analyzes changes in voice tone and facial expressions to classify emotions.

[1711] Step 3:

[1712] The device sends information about the current location, direction of movement, user preferences, and recognized emotions to the server. All previously acquired information is used as input, and this information is securely sent to the server as output using the HTTPS protocol. Specifically, the device converts the data into a data format such as JSON and sends it over the Internet.

[1713] Step 4:

[1714] Based on the current location information and travel direction information received by the server, surrounding information is collected from tourist destination databases, local product databases, etc. The user's current location information and travel direction information are acquired as input, and information on the relevant tourist destinations and local products is obtained as output. Specifically, the server executes a database query to acquire relevant information.

[1715] Step 5:

[1716] The server uses a generative AI model based on the surrounding information, hobbies, preferences, and emotional information collected to generate customized text. The collected surrounding information, the user's hobbies, preferences, and emotional information are used as input, and text appropriate for the user is generated as output. Specifically, the system operates by inputting a prompt sentence into the generative AI model and obtaining the generated text.

[1717] Step 6:

[1718] The server passes the generated text to a speech synthesis engine and converts it into voice data. The text generated by the generative AI model is used as input, and voice data is obtained as output. Specifically, the speech synthesis engine analyzes the text and generates an audio file.

[1719] Step 7:

[1720] The server sends the generated voice data to the user's device. The server uses the voice data as input and sends the voice data to the device as output. Specifically, the server sends the voice file to the device via the Internet.

[1721] Step 8:

[1722] The device plays back audio data received in real time. The received audio data is used as input, and the audio is played back from a speaker or headset as output. Specifically, the audio data is played back using the device's audio playback function.

[1723] Step 9:

[1724] The user enters their satisfaction and thoughts about the information provided into the app and sends it to the server. The app obtains user feedback as input, and sends ratings and comments as output to the server. Specifically, the app uses the feedback function to collect user opinions and send them to the server.

[1725] Step 10:

[1726] The server analyzes user feedback and updates the generative AI model and database. It receives user feedback information as input and optimizes the generative AI model and database as output. Specifically, it analyzes the feedback data and adjusts the parameters of the generative AI model to provide more accurate information from the next time onwards.

[1727] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1728] 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1729] 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 robot 414.

[1730] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1731] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1732] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1733] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1734] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1735] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1736] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1737] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on 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 running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1738] In the above embodiment, an example was 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 data may be generated in the external device in accordance with input data.

[1739] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1740] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1741] 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.

[1742] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1743] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1744] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1745] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1746] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1747] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1748] The following is further disclosed regarding the above embodiment.

[1749] (Claim 1)

[1750] A means for obtaining the user's current location information;

[1751] A means for collecting surrounding information based on the acquired current location information;

[1752] A means for generating text from peripheral information collected based on user's hobby and preference information;

[1753] means for converting the generated text into audio data;

[1754] A system including a means for providing audio data to a user.

[1755] (Claim 2)

[1756] 2. The system of claim 1, wherein the current location information also includes a direction of travel.

[1757] (Claim 3)

[1758] 2. The system according to claim 1, wherein the collecting means collects surrounding information including tourist destination information, local product information, and local industry information.

[1759] (Claim 4)

[1760] 10. The system of claim 1, wherein the means for generating text uses a generative AI model.

[1761] (Claim 5)

[1762] 2. The system of claim 1, wherein the means for providing audio data plays the audio data in real time.

[1763] (Claim 6)

[1764] The system of claim 1, further comprising: collecting user feedback and updating the generative AI model;

[1765] (Claim 7)

[1766] 10. The system of claim 1, further comprising means for generating local advertisements from the collected neighborhood information.

[1767] "Example 1"

[1768] (Claim 1)

[1769] A means for obtaining the user's current location information;

[1770] A means for collecting surrounding information based on the acquired current location information and movement direction information;

[1771] A method using a generative AI model that generates text from peripheral information collected based on the user's hobbies and preferences;

[1772] using a speech synthesis engine to convert the generated text into speech data;

[1773] The system includes a means for providing the generated audio data to a user.

[1774] (Claim 2)

[1775] 2. The system according to claim 1, wherein the collecting means collects surrounding information including tourist destination information, local product information, and local industry information.

[1776] (Claim 3)

[1777] 10. The system of claim 1, further comprising means for collecting user feedback and updating the generative AI model and / or database to improve accuracy of the information provided.

[1778] "Application Example 1"

[1779] (Claim 1)

[1780] A means for obtaining the user's current location information;

[1781] A means for collecting surrounding information based on the acquired current location information;

[1782] A means for generating text from peripheral information collected based on user's hobby and preference information;

[1783] means for converting the generated text into audio data;

[1784] A system including a means for providing audio data to a user.

[1785] (Claim 2)

[1786] 2. The system of claim 1, wherein the current location information also includes a direction of travel.

[1787] (Claim 3)

[1788] 2. The system according to claim 1, wherein the collecting means collects surrounding information including tourist destination information, local product information, and local industry information.

[1789] (Claim 4)

[1790] 2. The system of claim 1, wherein the text generation means generates text using a generative AI model.

[1791] (Claim 5)

[1792] 5. The system of claim 4, further comprising: applying natural language processing techniques using the generated text as a prompt sentence.

[1793] (Claim 6)

[1794] 2. The system according to claim 1, wherein the information providing means provides information to a user on the move by voice without relying on vision.

[1795] "Example 2: Combining Emotion Engines"

[1796] (Claim 1)

[1797] A means for acquiring the user's current location information and direction of movement;

[1798] A means for collecting surrounding information based on the acquired current location information and movement direction information;

[1799] a means for recognizing the emotional state of a user;

[1800] means for generating customized text based on the user's interest and preference information and the recognized emotional state;

[1801] means for converting the generated text into audio data;

[1802] A system including a means for providing audio data to a user.

[1803] (Claim 2)

[1804] The system according to claim 1, characterized in that the surrounding information includes information on tourist spots, local specialties, and local industries.

[1805] (Claim 3)

[1806] 10. The system of claim 1, wherein the system adjusts the tone and content of generated text based on the recognized emotional state.

[1807] "Application example 2 when combining emotion engines"

[1808] (Claim 1)

[1809] A means for acquiring user's current location information and movement direction information;

[1810] A means for collecting surrounding information based on the acquired current location information and movement direction information;

[1811] A means for generating text from peripheral information collected based on the user's hobby, preference, and emotion information;

[1812] a means for converting the generated text into speech data using a generative AI model;

[1813] a means for providing the generated audio data to a user;

[1814] A method to recognize user emotions and adjust the content provided based on that emotional information

[1815] Including system.

[1816] (Claim 2)

[1817] The system according to claim 1, characterized in that the collecting means collects surrounding information including tourist destination information, local product information, and local industry information.

[1818] (Claim 3)

[1819] The system of claim 1, wherein the collecting means uses a generative AI model to generate customized text based on surrounding information and adjusts the content of the text based on a prompt sentence. [Explanation of symbols]

[1820] 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. A means for obtaining the user's current location information; A means for collecting surrounding information based on the acquired current location information; A means for generating text from peripheral information collected based on user's hobby and preference information; means for converting the generated text into audio data; A system including a means for providing audio data to a user.

2. 2. The system of claim 1, wherein the current location information also includes a direction of travel.

3. 2. The system according to claim 1, wherein said collecting means collects surrounding information including tourist spot information, local product information, and local industry information.

4. 10. The system of claim 1, wherein the means for generating text uses a generative AI model.

5. 2. The system of claim 1, wherein said means for providing audio data reproduces the audio data in real time.

6. The system of claim 1, wherein the system collects user feedback and updates the generative AI model.

7. 10. The system of claim 1, further comprising means for generating local advertisements from the collected neighborhood information.

Images