System

Abstract

A system is provided.SOLUTION: A system comprising: voice recognition means for analyzing a user's speech and suggesting a route suitable for driving; data collection means for collecting map information, surrounding environment information, landscape information, and user's emotion information; route generation means for analyzing the collected data and generating candidate routes with a good landscape and a good driving feeling; navigation means for selecting and navigating an optimal route for the user from the candidate routes; and feedback collection means for collecting evaluation feedback from the user and reflecting the evaluation feedback in the next route generation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional car navigation systems are primarily designed to suggest the shortest and fastest route to a destination, which is insufficient for users who just want to enjoy driving. In particular, to find a route with good scenery and a pleasant driving experience, users must research multiple information sources and manually set the route, which is extremely time-consuming. Therefore, there is a need for a system that automatically suggests scenic routes to improve the quality of the driving experience. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by using the following means.

[0006] A voice recognition system that analyzes the user's speech and suggests suitable routes for driving.

[0007] Data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information;

[0008] a route generation means for analyzing the collected data and generating candidate routes that have good scenery and a good driving experience;

[0009] A navigation method that selects the optimal route for the user from among candidate routes and navigates the user.

[0010] A feedback collection method to collect user evaluation feedback and reflect it in the next route generation.

[0011] By providing a system that includes these measures, users can enjoy the optimal driving route without any hassle.

[0012] The "voice recognition means" is a module that has the function of analyzing the user's speech and converting it into text data.

[0013] "Data collection means" refers to means for collecting map information, surrounding environment information, landscape information, and user emotion information.

[0014] The "route generation means" is a means having a function of generating candidate routes that have beautiful scenery and a good driving feel based on collected data.

[0015] The "navigation means" is a means for selecting the most suitable route for the user from the generated candidate routes and guiding the user along that route.

[0016] The "feedback collection means" is a means for collecting evaluation feedback from users and reflecting that data in the next route generation.

[0017] "Map information" is data that indicates geographical locations such as roads, points, topography, and tourist spots.

[0018] "Surrounding environment information" refers to environmental data that affects driving, such as the scenery around the road, traffic conditions, and weather.

[0019] "Scenery information" is data about places and scenery that can be visually enjoyed.

[0020] "User emotional information" is data including evaluations and emotional expressions of routes previously designated by the user.

[0021] "Candidate routes" are multiple route options generated based on user requests and collected data. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[0044] System Configuration

[0045] The system consists of the following main components:

[0046] 1. Voice Recognition Method

[0047] 2. Data Collection Methods

[0048] 3. Route Generation Method

[0049] 4. Navigation Methods

[0050] 5. Feedback Collection Methods

[0051] Program processing

[0052] Receiving a user's speech request

[0053] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[0054] Voice recognition and data transmission

[0055] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[0056] Request content analysis

[0057] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[0058] Data collection

[0059] The server then collects the following information using data collection means:

[0060] Map information: Location information of roads and tourist spots around the destination

[0061] Surrounding area information: specific road width, traffic conditions, weather

[0062] GPS movement information: All users' movement data, including speed and number of stops

[0063] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[0064] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[0065] Route Generation

[0066] The server analyzes the collected data and generates multiple candidate routes. This route generation method selects roads with good scenery and a good driving experience, and also considers the user's past preferences and ratings to select the optimal route. The final route is determined using a route generation AI model.

[0067] Route provision and navigation

[0068] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[0069] Specific examples

[0070] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[0071] 1. The device converts the voice data into text data and sends it to the server.

[0072] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[0073] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, and past user feedback.

[0074] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[0075] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention provides a fulfilling driving experience by generating advanced routes based on the user's requests and ratings.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[0079] Step 2:

[0080] The device uses a microphone to capture the user's speech as audio data.

[0081] Step 3:

[0082] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[0083] Step 4:

[0084] The terminal sends the converted text data to the server, and sends the request content to the server via an HTTP request.

[0085] Step 5:

[0086] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and begins collecting the necessary information.

[0087] Step 6:

[0088] The server accesses a map information database to obtain road information around the destination, including road width, traffic conditions, and weather information.

[0089] Step 7:

[0090] The server analyzes positive posts and images from social media and collects information on places that are considered to have beautiful views.

[0091] Step 8:

[0092] The server analyzes the GPS movement information of all users and collects road information (speed, number of stops, etc.) that allows users to drive comfortably.

[0093] Step 9:

[0094] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[0095] Step 10:

[0096] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[0097] Step 11:

[0098] The server selects the best route for the user from among several candidate routes based on the user's past preferences and ratings.

[0099] Step 12:

[0100] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[0101] Step 13:

[0102] The device displays the received route information to the user, and displays a route map on the screen to provide visual guidance to the user.

[0103] Step 14:

[0104] The device will then begin voice guidance and guide the user along the generated driving route, providing specific voice guidance such as "Turn left at the next intersection."

[0105] Step 15:

[0106] After the user completes a drive, the device prompts the user for feedback, asking for their opinion in the form of "How did you like this route?"

[0107] Step 16:

[0108] The user inputs feedback, such as "It was very pleasant" or "I would like to pass through a place with a better view."

[0109] Step 17:

[0110] The device sends the input feedback to the server via an HTTP request.

[0111] Step 18:

[0112] The server analyzes the received feedback and stores it in a database as new data, which is then used to generate future routes.

[0113] Through these steps, users can easily enjoy the optimal driving route with beautiful scenery and a great driving experience.

[0114] Example 1

[0115] 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."

[0116] Current car navigation systems do not adequately consider user preferences and driving experience when proposing routes, and have difficulty dynamically reflecting scenic beauty and road conditions. In particular, the accuracy of feedback and data analysis required to propose routes that match the specific scenery and driving experience desired by the user is insufficient, resulting in failure to increase user satisfaction.

[0117] 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.

[0118] In this invention, the server includes a voice recognition means for analyzing the user's speech and proposing routes suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting the most suitable route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and a means for generating multiple candidate routes based on the analysis results and determining the most suitable route using a generation AI model. This makes it possible to provide the most suitable driving route with good scenery based on the user's preferences and past evaluations.

[0119] A "voice recognition means" is a means for analyzing a user's speech and converting it into text data.

[0120] "Data collection means" refers to means for collecting map information, surrounding environment information, landscape information, and user emotion information.

[0121] The "route generation means" is a means for analyzing collected data and generating candidate routes that offer good scenery and a pleasant driving experience.

[0122] A "navigation means" is a means for selecting the most suitable route for a user from among candidate routes and navigating the user along that route.

[0123] The "feedback collection means" is a means for collecting evaluation feedback from users and reflecting it in the next route generation.

[0124] "Analysis results" refer to information and conclusions drawn from collected data.

[0125] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal routes.

[0126] The "optimal route" is a route with beautiful scenery and a good driving experience, determined based on collected data and the user's preferences and ratings.

[0127] "Scenic information" refers to information about the beauty of the scenery and surrounding environment at a particular route or point.

[0128] "Surrounding environment information" is comprehensive information such as road conditions, weather, and traffic conditions at specific routes and locations.

[0129] A car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[0130] System Configuration

[0131] The system consists of the following main components:

[0132] 1. Voice Recognition Method

[0133] 2. Data Collection Methods

[0134] 3. Route Generation Method

[0135] 4. Navigation Methods

[0136] 5. Feedback Collection Methods

[0137] 6. Generative AI Models

[0138] Program processing

[0139] Receiving a user's speech request

[0140] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[0141] Voice recognition and data transmission

[0142] The device converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. Voice recognition uses a highly sensitive microphone and voice capture software (e.g., a voice recognition API).

[0143] Request content analysis

[0144] The server analyzes the received text data and identifies the user's request. For example, it uses a natural language processing tool (e.g., a natural language processing API) to extract and recognize the keyword "scenic driving route."

[0145] Data collection

[0146] The server then collects the following information using data collection means:

[0147] Map information: Location information of roads and tourist spots around the destination. Uses the Map Information API.

[0148] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[0149] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[0150] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses the SNS information API.

[0151] User rating feedback and sentiment information: Collect past user ratings and sentiment information from the feedback database.

[0152] Route Generation

[0153] The server analyzes the collected data and generates multiple candidate routes. The server uses a generative AI model (e.g., AI model API) to select a route with good scenery and a good driving experience. The server also considers the user's past preferences and ratings to select the optimal route.

[0154] Route provision and navigation

[0155] The device receives the route information sent from the server and displays it to the user. It also provides audio and visual guidance along the route, navigating the user using Google Maps navigation features.

[0156] Specific examples

[0157] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[0158] 1. The device converts the voice data into text data and sends it to the server using a speech recognition API.

[0159] 2. The server analyzes the request and detects the keyword "Route with a view of Mt. Fuji." It uses a natural language processing API for the analysis.

[0160] 3. The server uses the map information API, weather information API, and SNS information API to collect map information, landscape information, and surrounding environment information, and also refers to past user feedback.

[0161] 4. The server generates the optimal route based on the collected data. Using a generative AI model, it selects the optimal route, including one with a view of Mt. Fuji.

[0162] 5. The device displays the optimal route and navigates the user with audio and visual guidance, using Google Maps.

[0163] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention generates sophisticated routes based on the user's requests and ratings, providing a fulfilling driving experience.

[0164] Prompt Sentence Examples

[0165] "Please collect map information, landscape information, road conditions, positive posts on social media, and user feedback from all over Japan, and generate scenic driving routes that meet user requests. For example, please suggest the best route for a request like 'I want to drive to Hakone from a route that gives me a view of Mt. Fuji.'"

[0166] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0167] Step 1: Receiving a user's speech request

[0168] A user speaks to a car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. The device acquires the voice data using voice capture software (e.g., a voice recognition API).

[0169] Step 2: Voice recognition and data transmission

[0170] The terminal converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. The input is voice data and the output is text data. Specifically, the terminal uses a voice recognition API to send data to the server via a network module.

[0171] Step 3: Parsing the request

[0172] The server analyzes the received text data and identifies the user's request. For example, a natural language processing tool is used to extract the keyword "scenic driving route." The input is text data, and the output is the analyzed keyword. The server performs the analysis using a natural language processing API.

[0173] Step 4: Data collection

[0174] The server collects the following information using data collection methods:

[0175] Map information: Location information of roads and tourist spots around the destination. Uses map information API.

[0176] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[0177] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[0178] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses SNS information API.

[0179] User rating feedback and sentiment information: Past user ratings and sentiment expressions. Obtained from the feedback database.

[0180] The input is the request content, and the output is various collected data. The server collects information through each API.

[0181] Step 5: Route Generation

[0182] The server analyzes the collected data and generates multiple candidate routes. The input is the collected data, and the output is the candidate routes. The server uses a generative AI model to generate roads with beautiful scenery and a great driving experience. It also takes into account the user's past preferences and ratings to select the optimal route.

[0183] Step 6: Route provision and navigation

[0184] The device receives the determined route sent from the server and displays it to the user. It also provides audio and visual guidance along the generated route to navigate the user. The input is the determined route data, and the output is the display and audio guidance on the device. The device uses the navigation function of Google Maps.

[0185] This process allows users to find a comfortable and scenic driving route without any hassle.

[0186] (Application example 1)

[0187] 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."

[0188] Conventional car navigation systems lacked the ability to suggest routes based on user requests and provide feedback on user evaluations, making it difficult to provide routes with beautiful scenery and a comfortable driving experience. Furthermore, while autonomous vehicles are required to provide safer and more comfortable driving routes, there were limitations to achieving this. This made it difficult for users to have a satisfying driving experience.

[0189] 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.

[0190] In this invention, the server includes a voice recognition means, a data collection means for collecting geographic information, traffic information, visual information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes that are scenic and comfortable to drive, a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting the feedback in the next route generation, a means for providing the generated route for the autonomous vehicle and providing visual and audio guidance, a means for optimizing the candidate route using a generative AI model, and a means for inputting prompt sentences into the generative AI model and generating the optimal route. This enables high-quality route suggestions and navigation for autonomous vehicles based on user requests, making it possible to provide a highly satisfying driving experience.

[0191] "Voice recognition means" is a technology that analyzes a user's speech and converts it into text data.

[0192] "Geographic information" refers to road and location information around the destination, as well as location information for tourist spots, etc.

[0193] "Traffic information" refers to data that includes information on the traffic conditions, passability, and traffic congestion of specific roads.

[0194] "Visual information" refers to information including images and videos of landscapes, as well as content about landscapes posted on social media.

[0195] "User emotional information" refers to information such as user ratings and emotional expressions obtained from past driving data.

[0196] "Data collection means" refers to technologies that collect geographical information, traffic information, visual information, and user emotional information.

[0197] The "route generation means" is a technology that generates candidate routes that are scenic and comfortable to drive based on collected data.

[0198] "Navigation means" refers to technology that selects the optimal route for the user from among candidate routes and navigates through it.

[0199] "Feedback collection means" refers to technology that collects user evaluations and feedback and reflects them in the next route generation.

[0200] "Means for providing routes generated for automated driving vehicles and providing visual and audio guidance" refers to technology that provides optimal routes and provides visual and audio guidance to automated driving vehicles so that they can travel safely and comfortably.

[0201] A "generative AI model" is an artificial intelligence model that analyzes data and generates optimal solutions or answers based on conditions.

[0202] A "prompt sentence" is an instruction sentence used by a generative AI model when generating a route.

[0203] To implement the present invention, a speech recognition means, a data collection means, a route generation means, a navigation means, a feedback collection means, a route provision and guidance means for an autonomous vehicle are required, and a means for generating prompt sentences to optimize candidate routes using a generative AI model.

[0204] System Configuration

[0205] The system consists of the following main components:

[0206] 1. Speech recognition means: Analyzes the user's speech and converts it into text data.

[0207] 2. Data collection methods: collect geographical information, traffic information, visual information and user emotional information.

[0208] 3. Route generation method: Analyze the collected data and generate candidate routes that are scenic and comfortable to drive.

[0209] 4. Navigation method: Select the best route for the user from the candidate routes and navigate.

[0210] 5. Feedback collection method: Collect evaluation feedback from users and reflect it in the next route generation.

[0211] 6. Route provision and guidance for autonomous vehicles: Provides generated routes to autonomous vehicles and provides visual and audio guidance.

[0212] 7. Generative AI model and prompt sentence generation means: The generative AI model is used to optimize the candidate routes, and the prompt sentence is input to generate the optimal route.

[0213] Hardware and software used

[0214] Hardware: Smartphone (including microphone, speaker, and GPS function), cloud server

[0215] software:

[0216] Google Cloud Speech-to-Text API (voice recognition)

[0217] OpenAI GPT-4 (Natural Language Analysis and Route Generation)

[0218] Node.js (server-side scripting)

[0219] Map API (geography and navigation)

[0220] Program processing

[0221] 1. Voice input and recognition:

[0222] The user speaks a request into their smartphone, such as "I want to take a scenic route to my destination."

[0223] The smartphone's microphone captures this audio and converts it into text data using the Google Cloud Speech-to-Text API.

[0224] 2. Send to server:

[0225] The text data is sent to a cloud server in real time, and the request content is analyzed.

[0226] 3. Data Collection and Analysis:

[0227] The cloud server collects geographic information, traffic information, visual information, and user emotional information using data collection means.

[0228] Based on this data, the route generation means generates a plurality of candidate routes that are scenic and comfortable to drive.

[0229] 4. Route generation and provisioning:

[0230] Based on the collected data, prompts are input into the OpenAI GPT-4 model to generate the optimal route.

[0231] For example, enter the following prompt:

[0232] The user wants to reach their destination by a scenic route. Generate a scenic route.

[0233] The generated route is provided to the autonomous vehicle from a cloud server.

[0234] 5. Navigation and Feedback:

[0235] The route is displayed on the smartphone and navigation is provided visually and audibly.

[0236] After a drive is completed, user ratings and feedback are collected and reflected in the next route generation.

[0237] Specific examples

[0238] If a user requests a drive to Hakone with a route that gives a view of Mt. Fuji, the system will:

[0239] 1. The smartphone converts the voice data into text and sends it to a cloud server.

[0240] 2. The cloud server analyzes the request and generates multiple candidates, including routes from which Mount Fuji can be seen.

[0241] 3. Select the best route based on geographic, visual, traffic, and past feedback.

[0242] 4. The optimal route will be displayed on your smartphone and navigation will begin.

[0243] In this way, the system of the present invention allows the user to easily enjoy a scenic and comfortable drive.

[0244] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0245] Step 1:

[0246] Voice Input and Recognition

[0247] Input: A user speaks a request into their smartphone: "I want to take a scenic route to my destination."

[0248] Processing: The device's microphone captures this audio data and converts it to text using the Google Cloud Speech-to-Text API.

[0249] Output: The text data generated is "I want to take a scenic road to my destination."

[0250] Step 2:

[0251] Sending to the server

[0252] Input: Text data generated by a speech recognition means.

[0253] Processing: The device sends this text data to the cloud server in real time.

[0254] Output: Text data is sent to the server.

[0255] Step 3:

[0256] Request content analysis

[0257] Input: The text data sent to the server.

[0258] Processing: The server analyzes the text data and identifies the user's request, for example, extracting keywords such as "scenic" and "destination."

[0259] Output: The analysis results clarify the user's request.

[0260] Step 4:

[0261] Data collection

[0262] Input: Search criteria based on the request content.

[0263] Processing: The server collects geographical information, traffic information, visual information, and user emotional information. Specifically, it uses map APIs, social media posts, and weather information services to collect the necessary data.

[0264] Output: Various data collected.

[0265] Step 5:

[0266] Route Generation

[0267] Input: The data collected and what you request.

[0268] Processing: The server generates an optimal route by inputting the following prompt into the OpenAI GPT-4 model: "The user wants to reach their destination by a scenic route. Please generate a route with beautiful scenery." The generative AI model outputs candidate routes.

[0269] Output: Multiple candidate routes with good scenery and comfortable driving.

[0270] Step 6:

[0271] Route Selection

[0272] Input: Multiple generated candidate routes and past user ratings and feedback.

[0273] Processing: The server compares the candidate routes with the rating data and selects the optimal route.

[0274] Output: The route that is determined to be optimal.

[0275] Step 7:

[0276] Navigation provided

[0277] Input: The selected optimal route.

[0278] Processing: The device receives this route information and provides visual and audio guidance to the user, using a map API to display the route and a text-to-speech API to provide guidance.

[0279] Output: Visual and audio guidance to the user.

[0280] Step 8:

[0281] Feedback collection

[0282] Input: User post-drive ratings and feedback.

[0283] Processing: The server collects this feedback data and stores it in a database to be used in the next route generation.

[0284] Output: Collected feedback data.

[0285] 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.

[0286] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[0287] System Configuration

[0288] The system consists of the following main components:

[0289] 1. Voice Recognition Method

[0290] 2. Data Collection Methods

[0291] 3. Route Generation Method

[0292] 4. Navigation Methods

[0293] 5. Feedback Collection Methods

[0294] 6. Emotion Engine

[0295] Program processing

[0296] Receiving a user's speech request

[0297] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[0298] Voice recognition and data transmission

[0299] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[0300] Request content analysis

[0301] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[0302] Data collection

[0303] The server then collects the following information using data collection means:

[0304] Map information: Location information of roads and tourist spots around the destination

[0305] Surrounding area information: specific road width, traffic conditions, weather

[0306] GPS movement information: All users' movement data, including speed and number of stops

[0307] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[0308] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[0309] emotion recognition

[0310] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. For example, it can determine whether the user is relaxed or tense from voice data. It can also infer the user's emotional state from the frequency of sudden braking and acceleration.

[0311] Route Generation

[0312] The server analyzes the collected data and emotional information to generate multiple candidate routes. This route generation method selects roads with beautiful scenery and a great driving experience, and also considers the user's past preferences, ratings, and emotional information to select the optimal route. The final route is determined using a route generation AI model.

[0313] Route provision and navigation

[0314] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[0315] Specific examples

[0316] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[0317] 1. The device converts the voice data into text data and sends it to the server.

[0318] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[0319] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, emotional information, and past user feedback.

[0320] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[0321] In addition, the emotion engine recognizes the user's emotions during the drive and when making a request. For example, if the driver's desire to relax is recognized, the system will prioritize quieter and more scenic roads. Emotional information from previous driving experiences is also taken into account, providing the user with the most comfortable route.

[0322] This system allows users to enjoy a hassle-free, comfortable, and scenic drive.In this way, the present invention provides a fulfilling driving experience by generating an advanced route based on the user's requests, ratings, and emotional information.

[0323] The processing flow will be explained below.

[0324] Step 1:

[0325] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[0326] Step 2:

[0327] The device uses a microphone to capture the user's speech as audio data.

[0328] Step 3:

[0329] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[0330] Step 4:

[0331] The terminal sends the converted text data to the server via an HTTP request.

[0332] Step 5:

[0333] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and prepares to collect appropriate information.

[0334] Step 6:

[0335] The server accesses a map information database to obtain road information around the destination and location information for tourist spots, including road width, traffic conditions, and weather information.

[0336] Step 7:

[0337] The server analyzes positive posts and images from social media and collects information on places with beautiful views, based on hashtags and location information.

[0338] Step 8:

[0339] The server analyzes the GPS movement information of all users and collects information on roads where users can comfortably drive (speed, number of stops, etc.).

[0340] Step 9:

[0341] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[0342] Step 10:

[0343] The emotion engine recognizes the user's emotional state from their speech data and driving behavior data. For example, it can determine whether the user is relaxed or tense from their voice data, and infer their emotional state from the frequency of sudden braking and acceleration.

[0344] Step 11:

[0345] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[0346] Step 12:

[0347] The server selects the optimal route from the generated candidate routes based on the user's emotional state and past preferences and ratings.

[0348] Step 13:

[0349] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[0350] Step 14:

[0351] The device then displays the received route information to the user, displaying a map and route on the screen to provide visual guidance to the user.

[0352] Step 15:

[0353] The device will then begin voice guidance and guide the user along the generated driving route, providing specific instructions such as "Turn left at the next intersection."

[0354] Step 16:

[0355] After the drive is complete, the device prompts the user for feedback, for example, asking, "How did you like the route?"

[0356] Step 17:

[0357] The user inputs feedback, such as "It felt really good" or "I'd like to pass through places with better scenery."

[0358] Step 18:

[0359] The device sends the input feedback to the server via an HTTP request.

[0360] Step 19:

[0361] The server analyzes the received feedback and stores it in a database as new data, which is then used for subsequent route generation.

[0362] This way, users can enjoy a hassle-free, comfortable and scenic drive, and the system will continue to evolve based on their feedback.

[0363] Example 2

[0364] 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."

[0365] Conventional car navigation systems have difficulty proposing routes based on the user's emotions and preferences, and often simply provide the shortest or fastest route. Furthermore, data collection and analysis to find scenic routes are insufficient, making it difficult to provide users with a satisfying driving experience. Furthermore, previous systems lacked a mechanism for utilizing user feedback and emotional information when generating the next route.

[0366] 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.

[0367] In this invention, the server includes: a speech recognition means for analyzing a user's speech and proposing a route suitable for driving; a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information; a route generation means for analyzing the collected data and generating candidate routes with beautiful landscapes and a good driving experience; a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route; a feedback collection means for collecting evaluation feedback from the user and reflecting this in the next route generation; an emotion recognition means for analyzing the user's speech and driving behavior data to recognize the user's emotional state and reflecting this in route selection; and a route generation AI model that includes an artificial intelligence model used for route generation and uses prompt sentences as input to generate the optimal route. This enables advanced route suggestions based on the user's emotions and preferences, providing a fulfilling driving experience.

[0368] A "voice recognition means" is a device or system that analyzes a user's speech and converts it into text data.

[0369] The "data collection means" is a device or system that collects map information, surrounding environment information, landscape information, and user emotion information.

[0370] The "route generation means" is a device or system that analyzes collected data and generates candidate routes that offer beautiful scenery and a pleasant driving experience.

[0371] A "navigation means" is a device or system that selects the most suitable route for a user from among candidate routes and navigates the user.

[0372] The "feedback collection means" is a device or system that collects evaluation feedback from users and reflects it in the next route generation.

[0373] An "emotion recognition means" is a device or system that analyzes the user's speech and driving behavior data to recognize their emotional state and reflects this in route selection.

[0374] A "route generation AI model" is an artificial intelligence model used for route generation, which uses prompt sentences as input to generate the optimal route.

[0375] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[0376] System Configuration

[0377] The system consists of the following main components:

[0378] 1. Voice Recognition Method

[0379] 2. Data Collection Methods

[0380] 3. Route Generation Method

[0381] 4. Navigation Methods

[0382] 5. Feedback Collection Methods

[0383] 6. Emotion recognition means

[0384] 7. Route Generation AI Model

[0385] Voice recognition means

[0386] The device is equipped with a microphone to capture the user's speech. The captured voice data is converted into text data by speech recognition software (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text), and the converted text data is sent to a server.

[0387] Data collection methods

[0388] The server uses various APIs (e.g., Google Maps API for map information, Increment P's traffic information API for traffic information, Weather Underground's weather API for weather information, Twitter API and Instagram Graph API for social media information) to collect map information around the destination, road width, traffic conditions, weather, GPS movement information, SNS landscape information, and past user evaluation feedback and sentiment information.

[0389] Route Generation Method

[0390] Based on the information collected by the data collection method, the server uses Dijkstra's algorithm, A-search algorithm, and a personalized model using deep learning to generate multiple candidate routes that offer beautiful scenery and a comfortable ride. It then uses a route generation AI model to select the optimal route, taking into account the user's past preferences, ratings, and emotional information. Finally, it determines the optimal route for the user.

[0391] Navigation methods

[0392] The device receives the confirmed route sent from the server. The route information is displayed on the screen and voice guidance is provided to navigate the user. Specifically, an interface similar to the navigation function of Google Maps is used to display the next intersection and the distance to the destination on the screen. Voice guidance is also provided to give instructions such as "Turn left at the next intersection."

[0393] Feedback collection methods

[0394] The device collects user feedback and sends it to the server, which uses this feedback information to generate the next route.

[0395] emotion recognition means

[0396] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. Specifically, it uses the Microsoft Azure Emotion API and Face++ emotion recognition API to analyze the tone and rhythm of the user's voice to determine whether they are relaxed or tense. It also estimates their stress level based on the frequency of sudden braking and acceleration while driving.

[0397] Route generation AI model

[0398] The route generation AI model uses prompts based on collected data to generate optimal routes, allowing for advanced route suggestions based on user sentiment and preferences.

[0399] Specific examples

[0400] For example, if a user requests a drive to Hakone with a route that allows for a view of Mt. Fuji, the system operates as follows:

[0401] 1. The device converts the voice data into text data using the Google Cloud Speech-to-Text API and sends it to the server.

[0402] 2. The server analyzes the received text data using the BERT model and extracts "Routes to see Mt. Fuji" and "To Hakone."

[0403] 3. The server obtains road information around Mount Fuji from the Google Maps API and also collects landscape and traffic information from social media.

[0404] 4. The emotion engine recognizes from the user's tone of voice that they want to relax and prioritizes quieter, more scenic routes.

[0405] 5. The route generation AI model inputs emotional and landscape information into Dijkstra's algorithm to generate the optimal route.

[0406] 6. The device displays the determined route to the user and provides voice navigation.

[0407] Prompt Sentence Examples

[0408] Example prompts fed to a generative AI model:

[0409] "A user has requested a drive to Hakone with a route that allows for a view of Mt. Fuji. Generate the optimal route using the following information:

[0410] Map information: Roads around Mt. Fuji and Hakone location information

[0411] Landscape information on social media: Posts of places where Mount Fuji is said to be visible

[0412] Surrounding environment information: traffic conditions, weather, road width

[0413] User feedback: Evaluation information on routes that have been moderately relaxing in the past

[0414] Emotional information: the user's current level of relaxation

[0415] In this way, the system generates an advanced route that combines the user's voice request and emotional state, providing a scenic and comfortable driving experience.

[0416] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0417] Step 1:

[0418] The user issues a voice request to the car navigation device, such as "Tell me about a scenic driving route." This request is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. Specifically, the user speaks into the microphone of the head unit or smartphone app.

[0419] Step 2:

[0420] The device converts the captured voice data into text data in real time using the Google Cloud Speech-to-Text API. The input is the captured voice data, and the output is text data generated by speech recognition. Specifically, the device sends the voice data to the API and stores the returned text data in an internal buffer.

[0421] Step 3:

[0422] The terminal sends text data to the server. The input is the text data, and the output is the status of completion of transmission. In concrete terms, the terminal sends data to the server via the network.

[0423] Step 4:

[0424] The server analyzes the received text data using the BERT model to identify the user's request. The input is text data, and the output is the analyzed request information (e.g., "Scenic driving route"). Specifically, the server runs an NLP (natural language processing) algorithm to extract keywords and the intent of the request from the text data.

[0425] Step 5:

[0426] The server uses data collection methods to collect the following information: map information from the Google Maps API, surrounding environment information from a traffic information service, weather information from Weather Underground's weather API, and social media information from the Twitter API and Instagram Graph API. The input is the request information, and the output is the various collected information data. Specifically, the server calls the various APIs, obtains the necessary information from each data source, and stores it.

[0427] Step 6:

[0428] The server uses an emotion engine to analyze the user's speech and driving behavior data to recognize the user's emotional state. The input is the user's text data and behavioral data, and the output is the user's emotional state data. Specifically, the server sends the acquired data to the Microsoft Azure Emotion API or Face++ emotion recognition API to determine the emotional state.

[0429] Step 7:

[0430] The server integrates the collected data and emotional information to generate multiple candidate routes using a route generation AI model. The input is the aggregated data and emotional information, and the output is multiple candidate routes. Specifically, the server inputs the data into Dijkstra's algorithm and A-search algorithm to generate candidate routes.

[0431] Step 8:

[0432] The server selects the optimal route from the candidate routes and provides it to the user. The input is multiple candidate routes, and the output is the optimal route. Specifically, the server calculates the optimal route by taking into account the user's past feedback, evaluation, and emotional state.

[0433] Step 9:

[0434] The terminal receives the optimal route sent from the server and displays it to the user. The input is the optimal route, and the output is the display on the user interface and voice guidance. In concrete terms, the terminal displays the route on the screen and provides voice navigation instructions.

[0435] Step 10:

[0436] After the trip, the device receives user feedback and sends it to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. Specifically, the device allows the user to input the evaluation through the user interface and sends it to the server via the network.

[0437] Step 11:

[0438] The server analyzes the received feedback and reflects it in the next route generation. The input is the feedback data, and the output is an updated evaluation database. Specifically, the server analyzes the feedback information and stores it in the database for use in the next route generation algorithm.

[0439] (Application example 2)

[0440] 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."

[0441] Conventional car navigation systems primarily focus on suggesting the shortest or fastest route, making it difficult to propose routes that take into account the user's emotions and scenic preferences. In particular, autonomous vehicles are required to provide routes that not only transport users to their destination but also adapt to the user's comfort and emotional state. To meet these requirements, it is necessary to collect and analyze user emotional information and generate an optimal route based on this information. However, there is still a lack of technology that utilizes user utterances and feedback in real time to propose routes that correspond to the user's emotional state. Therefore, there is a need for the development of a system that allows users to enjoy a comfortable and scenic drive without hassle.

[0442] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0443] In this invention, the server includes a speech recognition means for analyzing a user's speech and proposing a route suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting an optimal route for the user from the candidate routes and controlling the autonomous vehicle, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and an emotion engine for analyzing the user's emotions and optimizing navigation based on the analysis results. This makes it possible to provide a comfortable and scenic driving route that takes the user's emotional state into consideration.

[0444] "Speech recognition means" refers to a device or software that analyzes a user's speech, converts it into text data, and understands its content.

[0445] "Data collection means" refers to a device or software for collecting map information, surrounding environment information, landscape information, and user emotion information.

[0446] The "route generation means" is a device or software that analyzes collected data and generates candidate routes that offer good scenery and a pleasant driving experience.

[0447] "Navigation means" refers to a device or software that selects the optimal route for the user from among candidate routes and controls the autonomous vehicle.

[0448] The "feedback collection means" is a device or software that collects evaluation feedback from users and reflects it in the next route generation.

[0449] An "emotion engine" is a device or software that analyzes a user's emotions and optimizes navigation based on the analysis results.

[0450] This invention is a system for proposing an optimal driving route for an autonomous vehicle based on the user's speech and emotional information. The configuration and operation of this system are described in detail below.

[0451] System configuration

[0452] The system consists of the following main components:

[0453] 1. Voice Recognition Method

[0454] 2. Data Collection Methods

[0455] 3. Route Generation Method

[0456] 4. Navigation Methods

[0457] 5. Feedback Collection Methods

[0458] 6. Emotion Engine

[0459] Hardware and software used

[0460] 1. Voice Recognition Method

[0461] Hardware: Microphones in autonomous vehicles

[0462] Software: speech_recognition package, speech recognition API

[0463] 2. Data Collection Methods

[0464] Hardware: Vehicle sensors (GPS, camera)

[0465] Software: Map information API, surrounding environment information API, SNS analysis software

[0466] 3. Route Generation Method

[0467] Software: Route generation AI model

[0468] 4. Navigation Methods

[0469] Hardware: Vehicle control system

[0470] Software: Navigation software

[0471] 5. Feedback Collection Methods

[0472] Software: Feedback Management Software

[0473] 6. Emotion Engine

[0474] Software: Sentiment analysis software

[0475] How it works

[0476] First, the user speaks from inside the vehicle, saying, "Tell me about a driving route along the Shonan coast." This speech is converted into text data by a speech recognition means. Next, a data collection means collects map information, surrounding environment information, landscape information, and user emotion information. For example, the scenery of a specific coastline and traffic conditions are acquired in conjunction with GPS.

[0477] The route generator analyzes the collected data and generates multiple candidate routes based on the user's request. The emotion engine analyzes the user's speech and past feedback to recommend the most suitable route. For example, if the emotion of wanting to relax is recognized, a quiet and scenic route will be prioritized.

[0478] The generated route is sent to the autonomous vehicle's control system by the navigation means. The vehicle drives according to the navigation and is provided with audio and visual guidance. At the same time, after the drive is completed, the feedback collection means collects evaluation feedback from the user and reflects it in the next route generation.

[0479] Examples of concrete examples and prompts

[0480] For example, if a user requests a smartphone app to "tell me about a driving route along the Shonan coast," the request is converted into text data using voice recognition. If the app then recognizes that the user is feeling relaxed, it will recommend a quiet route along the coast.

[0481] Examples of prompt sentences include:

[0482] User utterance: "Tell me about a driving route along the Shonan coast."

[0483] Emotional state: "Relaxed"

[0484] Recommended route: "Prefer quiet coastal roads"

[0485] In this way, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[0486] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0487] Step 1:

[0488] The user speaks to the system, "Tell me about a driving course along the Shonan coast."

[0489] Input: User utterance

[0490] Output: Audio data

[0491] Step 2:

[0492] The terminal captures the user's voice data through a microphone and converts it into text data using a voice recognition means.

[0493] Input: Audio data

[0494] Output: Text data

[0495] How it works: The device's microphone captures audio, and a speech recognition API (e.g., speech_recognition package) converts the audio data into text data.

[0496] Step 3:

[0497] The server receives the text data and analyzes the request. For example, it extracts keywords such as "Driving courses along the Shonan coast."

[0498] Input: Text data

[0499] Output: Request content (keywords)

[0500] How it works: The server analyzes the text data and uses natural language processing to determine the user's intent.

[0501] Step 4:

[0502] The server uses the data collection means to collect map information, surrounding environment information, landscape information, and user emotion information.

[0503] Input: Request content (keywords)

[0504] Output: Map information, surrounding environment information, landscape information, emotion information

[0505] How it works: The server collects relevant data using multiple APIs (e.g., map information API, environmental information API, SNS analysis software).

[0506] Step 5:

[0507] The server uses an emotion engine to analyze the user's emotions, for example, by using voice data and past feedback to determine whether the user is relaxed.

[0508] Input: Voice data, past feedback

[0509] Output: User's emotional state

[0510] How it works: Emotion analysis software analyzes the user's voice tone and past driving behavior data to identify their emotional state.

[0511] Step 6:

[0512] The server uses a route generation means to analyze the collected data and the user's emotion information and generate a plurality of candidate routes.

[0513] Input: Map information, surrounding environment information, landscape information, emotional information

[0514] Output: candidate routes

[0515] How it works: A route generation AI model combines each piece of data and generates multiple candidate routes.

[0516] Step 7:

[0517] The server selects the route that best suits the user's emotional state and request content from the candidate routes.

[0518] Input: candidate routes, user's emotional state, request content

[0519] Output: Optimal route

[0520] Operation: The server evaluates the generated routes based on their scenery and driving experience, and selects the optimal route.

[0521] Step 8:

[0522] The terminal receives the optimal route and transmits it to the autonomous vehicle's control system.

[0523] Input: Optimal Route

[0524] Output: Vehicle control signal

[0525] How it works: Navigation software sends the optimal route to the autonomous vehicle's control system, which then controls the vehicle.

[0526] Step 9:

[0527] The terminal navigates while providing audio and visual guidance to the user.

[0528] Input: control signal, optimal route

[0529] Output: Audio guidance, visual guidance

[0530] How it works: The device uses the vehicle's display and speaker to provide navigation instructions to the user.

[0531] Step 10:

[0532] The server collects user evaluation feedback after each trip and reflects it in the next route generation.

[0533] Input: User rating feedback

[0534] Output: Updated feedback data

[0535] How it works: The feedback collection tool stores user ratings in a database and uses them for analysis.

[0536] Through the above steps, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[0537] 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.

[0538] 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.

[0539] 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.

[0540] [Second embodiment]

[0541] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0542] 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.

[0543] 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).

[0544] 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.

[0545] 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.

[0546] 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).

[0547] 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.

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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."

[0553] The car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[0554] System Configuration

[0555] The system consists of the following main components:

[0556] 1. Voice Recognition Method

[0557] 2. Data Collection Methods

[0558] 3. Route Generation Method

[0559] 4. Navigation Methods

[0560] 5. Feedback Collection Methods

[0561] Program processing

[0562] Receiving a user's speech request

[0563] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[0564] Voice recognition and data transmission

[0565] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[0566] Request content analysis

[0567] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[0568] Data collection

[0569] The server then collects the following information using data collection means:

[0570] Map information: Location information of roads and tourist spots around the destination

[0571] Surrounding area information: specific road width, traffic conditions, weather

[0572] GPS movement information: All users' movement data, including speed and number of stops

[0573] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[0574] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[0575] Route Generation

[0576] The server analyzes the collected data and generates multiple candidate routes. This route generation method selects roads with good scenery and a good driving experience, and also considers the user's past preferences and ratings to select the optimal route. The final route is determined using a route generation AI model.

[0577] Route provision and navigation

[0578] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[0579] Specific examples

[0580] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[0581] 1. The device converts the voice data into text data and sends it to the server.

[0582] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[0583] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, and past user feedback.

[0584] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[0585] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention provides a fulfilling driving experience by generating advanced routes based on the user's requests and ratings.

[0586] The processing flow will be explained below.

[0587] Step 1:

[0588] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[0589] Step 2:

[0590] The device uses a microphone to capture the user's speech as audio data.

[0591] Step 3:

[0592] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[0593] Step 4:

[0594] The terminal sends the converted text data to the server, and sends the request content to the server via an HTTP request.

[0595] Step 5:

[0596] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and begins collecting the necessary information.

[0597] Step 6:

[0598] The server accesses a map information database to obtain road information around the destination, including road width, traffic conditions, and weather information.

[0599] Step 7:

[0600] The server analyzes positive posts and images from social media and collects information on places that are considered to have beautiful views.

[0601] Step 8:

[0602] The server analyzes the GPS movement information of all users and collects road information (speed, number of stops, etc.) that allows users to drive comfortably.

[0603] Step 9:

[0604] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[0605] Step 10:

[0606] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[0607] Step 11:

[0608] The server selects the best route for the user from among several candidate routes based on the user's past preferences and ratings.

[0609] Step 12:

[0610] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[0611] Step 13:

[0612] The device displays the received route information to the user, and displays a route map on the screen to provide visual guidance to the user.

[0613] Step 14:

[0614] The device will then begin voice guidance and guide the user along the generated driving route, providing specific voice guidance such as "Turn left at the next intersection."

[0615] Step 15:

[0616] After the user completes a drive, the device prompts the user for feedback, asking for their opinion in the form of "How did you like this route?"

[0617] Step 16:

[0618] The user inputs feedback, such as "It was very pleasant" or "I would like to pass through a place with a better view."

[0619] Step 17:

[0620] The device sends the input feedback to the server via an HTTP request.

[0621] Step 18:

[0622] The server analyzes the received feedback and stores it in a database as new data, which is then used to generate future routes.

[0623] Through these steps, users can easily enjoy the optimal driving route with beautiful scenery and a great driving experience.

[0624] Example 1

[0625] 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."

[0626] Current car navigation systems do not adequately consider user preferences and driving experience when proposing routes, and have difficulty dynamically reflecting scenic beauty and road conditions. In particular, the accuracy of feedback and data analysis required to propose routes that match the specific scenery and driving experience desired by the user is insufficient, resulting in failure to increase user satisfaction.

[0627] 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.

[0628] In this invention, the server includes a voice recognition means for analyzing the user's speech and proposing routes suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting the most suitable route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and a means for generating multiple candidate routes based on the analysis results and determining the most suitable route using a generation AI model. This makes it possible to provide the most suitable driving route with good scenery based on the user's preferences and past evaluations.

[0629] A "voice recognition means" is a means for analyzing a user's speech and converting it into text data.

[0630] "Data collection means" refers to means for collecting map information, surrounding environment information, landscape information, and user emotion information.

[0631] The "route generation means" is a means for analyzing collected data and generating candidate routes that offer good scenery and a pleasant driving experience.

[0632] A "navigation means" is a means for selecting the most suitable route for a user from among candidate routes and navigating the user along that route.

[0633] The "feedback collection means" is a means for collecting evaluation feedback from users and reflecting it in the next route generation.

[0634] "Analysis results" refer to information and conclusions drawn from collected data.

[0635] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal routes.

[0636] The "optimal route" is a route with beautiful scenery and a good driving experience, determined based on collected data and the user's preferences and ratings.

[0637] "Scenic information" refers to information about the beauty of the scenery and surrounding environment at a particular route or point.

[0638] "Surrounding environment information" is comprehensive information such as road conditions, weather, and traffic conditions at specific routes and locations.

[0639] A car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[0640] System Configuration

[0641] The system consists of the following main components:

[0642] 1. Voice Recognition Method

[0643] 2. Data Collection Methods

[0644] 3. Route Generation Method

[0645] 4. Navigation Methods

[0646] 5. Feedback Collection Methods

[0647] 6. Generative AI Models

[0648] Program processing

[0649] Receiving a user's speech request

[0650] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[0651] Voice recognition and data transmission

[0652] The device converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. Voice recognition uses a highly sensitive microphone and voice capture software (e.g., a voice recognition API).

[0653] Request content analysis

[0654] The server analyzes the received text data and identifies the user's request. For example, it uses a natural language processing tool (e.g., a natural language processing API) to extract and recognize the keyword "scenic driving route."

[0655] Data collection

[0656] The server then collects the following information using data collection means:

[0657] Map information: Location information of roads and tourist spots around the destination. Uses the Map Information API.

[0658] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[0659] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[0660] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses the SNS information API.

[0661] User rating feedback and sentiment information: Collect past user ratings and sentiment information from the feedback database.

[0662] Route Generation

[0663] The server analyzes the collected data and generates multiple candidate routes. The server uses a generative AI model (e.g., AI model API) to select a route with good scenery and a good driving experience. The server also considers the user's past preferences and ratings to select the optimal route.

[0664] Route provision and navigation

[0665] The device receives the route information sent from the server and displays it to the user. It also provides audio and visual guidance along the route, navigating the user using Google Maps navigation features.

[0666] Specific examples

[0667] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[0668] 1. The device converts the voice data into text data and sends it to the server using a speech recognition API.

[0669] 2. The server analyzes the request and detects the keyword "Route with a view of Mt. Fuji." It uses a natural language processing API for the analysis.

[0670] 3. The server uses the map information API, weather information API, and SNS information API to collect map information, landscape information, and surrounding environment information, and also refers to past user feedback.

[0671] 4. The server generates the optimal route based on the collected data. Using a generative AI model, it selects the optimal route, including one with a view of Mt. Fuji.

[0672] 5. The device displays the optimal route and navigates the user with audio and visual guidance, using Google Maps.

[0673] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention generates sophisticated routes based on the user's requests and ratings, providing a fulfilling driving experience.

[0674] Prompt Sentence Examples

[0675] "Please collect map information, landscape information, road conditions, positive posts on social media, and user feedback from all over Japan, and generate scenic driving routes that meet user requests. For example, please suggest the best route for a request like 'I want to drive to Hakone from a route that gives me a view of Mt. Fuji.'"

[0676] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0677] Step 1: Receiving a user's speech request

[0678] A user speaks to a car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. The device acquires the voice data using voice capture software (e.g., a voice recognition API).

[0679] Step 2: Voice recognition and data transmission

[0680] The terminal converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. The input is voice data and the output is text data. Specifically, the terminal uses a voice recognition API to send data to the server via a network module.

[0681] Step 3: Parsing the request

[0682] The server analyzes the received text data and identifies the user's request. For example, a natural language processing tool is used to extract the keyword "scenic driving route." The input is text data, and the output is the analyzed keyword. The server performs the analysis using a natural language processing API.

[0683] Step 4: Data collection

[0684] The server collects the following information using data collection methods:

[0685] Map information: Location information of roads and tourist spots around the destination. Uses map information API.

[0686] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[0687] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[0688] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses SNS information API.

[0689] User rating feedback and sentiment information: Past user ratings and sentiment expressions. Obtained from the feedback database.

[0690] The input is the request content, and the output is various collected data. The server collects information through each API.

[0691] Step 5: Route Generation

[0692] The server analyzes the collected data and generates multiple candidate routes. The input is the collected data, and the output is the candidate routes. The server uses a generative AI model to generate roads with beautiful scenery and a great driving experience. It also takes into account the user's past preferences and ratings to select the optimal route.

[0693] Step 6: Route provision and navigation

[0694] The device receives the determined route sent from the server and displays it to the user. It also provides audio and visual guidance along the generated route to navigate the user. The input is the determined route data, and the output is the display and audio guidance on the device. The device uses the navigation function of Google Maps.

[0695] This process allows users to find a comfortable and scenic driving route without any hassle.

[0696] (Application example 1)

[0697] 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."

[0698] Conventional car navigation systems lacked the ability to suggest routes based on user requests and provide feedback on user evaluations, making it difficult to provide routes with beautiful scenery and a comfortable driving experience. Furthermore, while autonomous vehicles are required to provide safer and more comfortable driving routes, there were limitations to achieving this. This made it difficult for users to have a satisfying driving experience.

[0699] 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.

[0700] In this invention, the server includes a voice recognition means, a data collection means for collecting geographic information, traffic information, visual information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes that are scenic and comfortable to drive, a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting the feedback in the next route generation, a means for providing the generated route for the autonomous vehicle and providing visual and audio guidance, a means for optimizing the candidate route using a generative AI model, and a means for inputting prompt sentences into the generative AI model and generating the optimal route. This enables high-quality route suggestions and navigation for autonomous vehicles based on user requests, making it possible to provide a highly satisfying driving experience.

[0701] "Voice recognition means" is a technology that analyzes a user's speech and converts it into text data.

[0702] "Geographic information" refers to road and location information around the destination, as well as location information for tourist spots, etc.

[0703] "Traffic information" refers to data that includes information on the traffic conditions, passability, and traffic congestion of specific roads.

[0704] "Visual information" refers to information including images and videos of landscapes, as well as content about landscapes posted on social media.

[0705] "User emotional information" refers to information such as user ratings and emotional expressions obtained from past driving data.

[0706] "Data collection means" refers to technologies that collect geographical information, traffic information, visual information, and user emotional information.

[0707] The "route generation means" is a technology that generates candidate routes that are scenic and comfortable to drive based on collected data.

[0708] "Navigation means" refers to technology that selects the optimal route for the user from among candidate routes and navigates through it.

[0709] "Feedback collection means" refers to technology that collects user evaluations and feedback and reflects them in the next route generation.

[0710] "Means for providing routes generated for automated driving vehicles and providing visual and audio guidance" refers to technology that provides optimal routes and provides visual and audio guidance to automated driving vehicles so that they can travel safely and comfortably.

[0711] A "generative AI model" is an artificial intelligence model that analyzes data and generates optimal solutions or answers based on conditions.

[0712] A "prompt sentence" is an instruction sentence used by a generative AI model when generating a route.

[0713] To implement the present invention, a speech recognition means, a data collection means, a route generation means, a navigation means, a feedback collection means, a route provision and guidance means for an autonomous vehicle are required, and a means for generating prompt sentences to optimize candidate routes using a generative AI model.

[0714] System Configuration

[0715] The system consists of the following main components:

[0716] 1. Speech recognition means: Analyzes the user's speech and converts it into text data.

[0717] 2. Data collection methods: collect geographical information, traffic information, visual information and user emotional information.

[0718] 3. Route generation method: Analyze the collected data and generate candidate routes that are scenic and comfortable to drive.

[0719] 4. Navigation method: Select the best route for the user from the candidate routes and navigate.

[0720] 5. Feedback collection method: Collect evaluation feedback from users and reflect it in the next route generation.

[0721] 6. Route provision and guidance for autonomous vehicles: Provides generated routes to autonomous vehicles and provides visual and audio guidance.

[0722] 7. Generative AI model and prompt sentence generation means: The generative AI model is used to optimize the candidate routes, and the prompt sentence is input to generate the optimal route.

[0723] Hardware and software used

[0724] Hardware: Smartphone (including microphone, speaker, and GPS function), cloud server

[0725] software:

[0726] Google Cloud Speech-to-Text API (voice recognition)

[0727] OpenAI GPT-4 (Natural Language Analysis and Route Generation)

[0728] Node.js (server-side scripting)

[0729] Map API (geography and navigation)

[0730] Program processing

[0731] 1. Voice input and recognition:

[0732] The user speaks a request into their smartphone, such as "I want to take a scenic route to my destination."

[0733] The smartphone's microphone captures this audio and converts it into text data using the Google Cloud Speech-to-Text API.

[0734] 2. Send to server:

[0735] The text data is sent to a cloud server in real time, and the request content is analyzed.

[0736] 3. Data Collection and Analysis:

[0737] The cloud server collects geographic information, traffic information, visual information, and user emotional information using data collection means.

[0738] Based on this data, the route generation means generates a plurality of candidate routes that are scenic and comfortable to drive.

[0739] 4. Route generation and provisioning:

[0740] Based on the collected data, prompts are input into the OpenAI GPT-4 model to generate the optimal route.

[0741] For example, enter the following prompt:

[0742] The user wants to reach their destination by a scenic route. Generate a scenic route.

[0743] The generated route is provided to the autonomous vehicle from a cloud server.

[0744] 5. Navigation and Feedback:

[0745] The route is displayed on the smartphone and navigation is provided visually and audibly.

[0746] After a drive is completed, user ratings and feedback are collected and reflected in the next route generation.

[0747] Specific examples

[0748] If a user requests a drive to Hakone with a route that gives a view of Mt. Fuji, the system will:

[0749] 1. The smartphone converts the voice data into text and sends it to a cloud server.

[0750] 2. The cloud server analyzes the request and generates multiple candidates, including routes from which Mount Fuji can be seen.

[0751] 3. Select the best route based on geographic, visual, traffic, and past feedback.

[0752] 4. The optimal route will be displayed on your smartphone and navigation will begin.

[0753] In this way, the system of the present invention allows the user to easily enjoy a scenic and comfortable drive.

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Step 1:

[0756] Voice Input and Recognition

[0757] Input: A user speaks a request into their smartphone: "I want to take a scenic route to my destination."

[0758] Processing: The device's microphone captures this audio data and converts it to text using the Google Cloud Speech-to-Text API.

[0759] Output: The text data generated is "I want to take a scenic road to my destination."

[0760] Step 2:

[0761] Sending to the server

[0762] Input: Text data generated by a speech recognition means.

[0763] Processing: The device sends this text data to the cloud server in real time.

[0764] Output: Text data is sent to the server.

[0765] Step 3:

[0766] Request content analysis

[0767] Input: The text data sent to the server.

[0768] Processing: The server analyzes the text data and identifies the user's request, for example, extracting keywords such as "scenic" and "destination."

[0769] Output: The analysis results clarify the user's request.

[0770] Step 4:

[0771] Data collection

[0772] Input: Search criteria based on the request content.

[0773] Processing: The server collects geographical information, traffic information, visual information, and user emotional information. Specifically, it uses map APIs, social media posts, and weather information services to collect the necessary data.

[0774] Output: Various data collected.

[0775] Step 5:

[0776] Route Generation

[0777] Input: The data collected and what you request.

[0778] Processing: The server generates an optimal route by inputting the following prompt into the OpenAI GPT-4 model: "The user wants to reach their destination by a scenic route. Please generate a route with beautiful scenery." The generative AI model outputs candidate routes.

[0779] Output: Multiple candidate routes with good scenery and comfortable driving.

[0780] Step 6:

[0781] Route Selection

[0782] Input: Multiple generated candidate routes and past user ratings and feedback.

[0783] Processing: The server compares the candidate routes with the rating data and selects the optimal route.

[0784] Output: The route that is determined to be optimal.

[0785] Step 7:

[0786] Navigation provided

[0787] Input: The selected optimal route.

[0788] Processing: The device receives this route information and provides visual and audio guidance to the user, using a map API to display the route and a text-to-speech API to provide guidance.

[0789] Output: Visual and audio guidance to the user.

[0790] Step 8:

[0791] Feedback collection

[0792] Input: User post-drive ratings and feedback.

[0793] Processing: The server collects this feedback data and stores it in a database to be used in the next route generation.

[0794] Output: Collected feedback data.

[0795] 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.

[0796] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[0797] System Configuration

[0798] The system consists of the following main components:

[0799] 1. Voice Recognition Method

[0800] 2. Data Collection Methods

[0801] 3. Route Generation Method

[0802] 4. Navigation Methods

[0803] 5. Feedback Collection Methods

[0804] 6. Emotion Engine

[0805] Program processing

[0806] Receiving a user's speech request

[0807] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[0808] Voice recognition and data transmission

[0809] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[0810] Request content analysis

[0811] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[0812] Data collection

[0813] The server then collects the following information using data collection means:

[0814] Map information: Location information of roads and tourist spots around the destination

[0815] Surrounding area information: specific road width, traffic conditions, weather

[0816] GPS movement information: All users' movement data, including speed and number of stops

[0817] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[0818] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[0819] emotion recognition

[0820] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. For example, it can determine whether the user is relaxed or tense from voice data. It can also infer the user's emotional state from the frequency of sudden braking and acceleration.

[0821] Route Generation

[0822] The server analyzes the collected data and emotional information to generate multiple candidate routes. This route generation method selects roads with beautiful scenery and a great driving experience, and also considers the user's past preferences, ratings, and emotional information to select the optimal route. The final route is determined using a route generation AI model.

[0823] Route provision and navigation

[0824] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[0825] Specific examples

[0826] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[0827] 1. The device converts the voice data into text data and sends it to the server.

[0828] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[0829] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, emotional information, and past user feedback.

[0830] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[0831] In addition, the emotion engine recognizes the user's emotions during the drive and when making a request. For example, if the driver's desire to relax is recognized, the system will prioritize quieter and more scenic roads. Emotional information from previous driving experiences is also taken into account, providing the user with the most comfortable route.

[0832] This system allows users to enjoy a hassle-free, comfortable, and scenic drive.In this way, the present invention provides a fulfilling driving experience by generating an advanced route based on the user's requests, ratings, and emotional information.

[0833] The processing flow will be explained below.

[0834] Step 1:

[0835] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[0836] Step 2:

[0837] The device uses a microphone to capture the user's speech as audio data.

[0838] Step 3:

[0839] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[0840] Step 4:

[0841] The terminal sends the converted text data to the server via an HTTP request.

[0842] Step 5:

[0843] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and prepares to collect appropriate information.

[0844] Step 6:

[0845] The server accesses a map information database to obtain road information around the destination and location information for tourist spots, including road width, traffic conditions, and weather information.

[0846] Step 7:

[0847] The server analyzes positive posts and images from social media and collects information on places with beautiful views, based on hashtags and location information.

[0848] Step 8:

[0849] The server analyzes the GPS movement information of all users and collects information on roads where users can comfortably drive (speed, number of stops, etc.).

[0850] Step 9:

[0851] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[0852] Step 10:

[0853] The emotion engine recognizes the user's emotional state from their speech data and driving behavior data. For example, it can determine whether the user is relaxed or tense from their voice data, and infer their emotional state from the frequency of sudden braking and acceleration.

[0854] Step 11:

[0855] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[0856] Step 12:

[0857] The server selects the optimal route from the generated candidate routes based on the user's emotional state and past preferences and ratings.

[0858] Step 13:

[0859] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[0860] Step 14:

[0861] The device then displays the received route information to the user, displaying a map and route on the screen to provide visual guidance to the user.

[0862] Step 15:

[0863] The device will then begin voice guidance and guide the user along the generated driving route, providing specific instructions such as "Turn left at the next intersection."

[0864] Step 16:

[0865] After the drive is complete, the device prompts the user for feedback, for example, asking, "How did you like the route?"

[0866] Step 17:

[0867] The user inputs feedback, such as "It felt really good" or "I'd like to pass through places with better scenery."

[0868] Step 18:

[0869] The device sends the input feedback to the server via an HTTP request.

[0870] Step 19:

[0871] The server analyzes the received feedback and stores it in a database as new data, which is then used for subsequent route generation.

[0872] This way, users can enjoy a hassle-free, comfortable and scenic drive, and the system will continue to evolve based on their feedback.

[0873] Example 2

[0874] 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."

[0875] Conventional car navigation systems have difficulty proposing routes based on the user's emotions and preferences, and often simply provide the shortest or fastest route. Furthermore, data collection and analysis to find scenic routes are insufficient, making it difficult to provide users with a satisfying driving experience. Furthermore, previous systems lacked a mechanism for utilizing user feedback and emotional information when generating the next route.

[0876] 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.

[0877] In this invention, the server includes: a speech recognition means for analyzing a user's speech and proposing a route suitable for driving; a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information; a route generation means for analyzing the collected data and generating candidate routes with beautiful landscapes and a good driving experience; a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route; a feedback collection means for collecting evaluation feedback from the user and reflecting this in the next route generation; an emotion recognition means for analyzing the user's speech and driving behavior data to recognize the user's emotional state and reflecting this in route selection; and a route generation AI model that includes an artificial intelligence model used for route generation and uses prompt sentences as input to generate the optimal route. This enables advanced route suggestions based on the user's emotions and preferences, providing a fulfilling driving experience.

[0878] A "voice recognition means" is a device or system that analyzes a user's speech and converts it into text data.

[0879] The "data collection means" is a device or system that collects map information, surrounding environment information, landscape information, and user emotion information.

[0880] The "route generation means" is a device or system that analyzes collected data and generates candidate routes that offer beautiful scenery and a pleasant driving experience.

[0881] A "navigation means" is a device or system that selects the most suitable route for a user from among candidate routes and navigates the user.

[0882] The "feedback collection means" is a device or system that collects evaluation feedback from users and reflects it in the next route generation.

[0883] An "emotion recognition means" is a device or system that analyzes the user's speech and driving behavior data to recognize their emotional state and reflects this in route selection.

[0884] A "route generation AI model" is an artificial intelligence model used for route generation, which uses prompt sentences as input to generate the optimal route.

[0885] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[0886] System Configuration

[0887] The system consists of the following main components:

[0888] 1. Voice Recognition Method

[0889] 2. Data Collection Methods

[0890] 3. Route Generation Method

[0891] 4. Navigation Methods

[0892] 5. Feedback Collection Methods

[0893] 6. Emotion recognition means

[0894] 7. Route Generation AI Model

[0895] Voice recognition means

[0896] The device is equipped with a microphone to capture the user's speech. The captured voice data is converted into text data by speech recognition software (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text), and the converted text data is sent to a server.

[0897] Data collection methods

[0898] The server uses various APIs (e.g., Google Maps API for map information, Increment P's traffic information API for traffic information, Weather Underground's weather API for weather information, Twitter API and Instagram Graph API for social media information) to collect map information around the destination, road width, traffic conditions, weather, GPS movement information, SNS landscape information, and past user evaluation feedback and sentiment information.

[0899] Route Generation Method

[0900] Based on the information collected by the data collection method, the server uses Dijkstra's algorithm, A-search algorithm, and a personalized model using deep learning to generate multiple candidate routes that offer beautiful scenery and a comfortable ride. It then uses a route generation AI model to select the optimal route, taking into account the user's past preferences, ratings, and emotional information. Finally, it determines the optimal route for the user.

[0901] Navigation methods

[0902] The device receives the confirmed route sent from the server. The route information is displayed on the screen and voice guidance is provided to navigate the user. Specifically, an interface similar to the navigation function of Google Maps is used to display the next intersection and the distance to the destination on the screen. Voice guidance is also provided to give instructions such as "Turn left at the next intersection."

[0903] Feedback collection methods

[0904] The device collects user feedback and sends it to the server, which uses this feedback information to generate the next route.

[0905] emotion recognition means

[0906] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. Specifically, it uses the Microsoft Azure Emotion API and Face++ emotion recognition API to analyze the tone and rhythm of the user's voice to determine whether they are relaxed or tense. It also estimates their stress level based on the frequency of sudden braking and acceleration while driving.

[0907] Route generation AI model

[0908] The route generation AI model uses prompts based on collected data to generate optimal routes, allowing for advanced route suggestions based on user sentiment and preferences.

[0909] Specific examples

[0910] For example, if a user requests a drive to Hakone with a route that allows for a view of Mt. Fuji, the system operates as follows:

[0911] 1. The device converts the voice data into text data using the Google Cloud Speech-to-Text API and sends it to the server.

[0912] 2. The server analyzes the received text data using the BERT model and extracts "Routes to see Mt. Fuji" and "To Hakone."

[0913] 3. The server obtains road information around Mount Fuji from the Google Maps API and also collects landscape and traffic information from social media.

[0914] 4. The emotion engine recognizes from the user's tone of voice that they want to relax and prioritizes quieter, more scenic routes.

[0915] 5. The route generation AI model inputs emotional and landscape information into Dijkstra's algorithm to generate the optimal route.

[0916] 6. The device displays the determined route to the user and provides voice navigation.

[0917] Prompt Sentence Examples

[0918] Example prompts fed to a generative AI model:

[0919] "A user has requested a drive to Hakone with a route that allows for a view of Mt. Fuji. Generate the optimal route using the following information:

[0920] Map information: Roads around Mt. Fuji and Hakone location information

[0921] Landscape information on social media: Posts of places where Mount Fuji is said to be visible

[0922] Surrounding environment information: traffic conditions, weather, road width

[0923] User feedback: Evaluation information on routes that have been moderately relaxing in the past

[0924] Emotional information: the user's current level of relaxation

[0925] In this way, the system generates an advanced route that combines the user's voice request and emotional state, providing a scenic and comfortable driving experience.

[0926] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0927] Step 1:

[0928] The user issues a voice request to the car navigation device, such as "Tell me about a scenic driving route." This request is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. Specifically, the user speaks into the microphone of the head unit or smartphone app.

[0929] Step 2:

[0930] The device converts the captured voice data into text data in real time using the Google Cloud Speech-to-Text API. The input is the captured voice data, and the output is text data generated by speech recognition. Specifically, the device sends the voice data to the API and stores the returned text data in an internal buffer.

[0931] Step 3:

[0932] The terminal sends text data to the server. The input is the text data, and the output is the status of completion of transmission. In concrete terms, the terminal sends data to the server via the network.

[0933] Step 4:

[0934] The server analyzes the received text data using the BERT model to identify the user's request. The input is text data, and the output is the analyzed request information (e.g., "Scenic driving route"). Specifically, the server runs an NLP (natural language processing) algorithm to extract keywords and the intent of the request from the text data.

[0935] Step 5:

[0936] The server uses data collection methods to collect the following information: map information from the Google Maps API, surrounding environment information from a traffic information service, weather information from Weather Underground's weather API, and social media information from the Twitter API and Instagram Graph API. The input is the request information, and the output is the various collected information data. Specifically, the server calls the various APIs, obtains the necessary information from each data source, and stores it.

[0937] Step 6:

[0938] The server uses an emotion engine to analyze the user's speech and driving behavior data to recognize the user's emotional state. The input is the user's text data and behavioral data, and the output is the user's emotional state data. Specifically, the server sends the acquired data to the Microsoft Azure Emotion API or Face++ emotion recognition API to determine the emotional state.

[0939] Step 7:

[0940] The server integrates the collected data and emotional information to generate multiple candidate routes using a route generation AI model. The input is the aggregated data and emotional information, and the output is multiple candidate routes. Specifically, the server inputs the data into Dijkstra's algorithm and A-search algorithm to generate candidate routes.

[0941] Step 8:

[0942] The server selects the optimal route from the candidate routes and provides it to the user. The input is multiple candidate routes, and the output is the optimal route. Specifically, the server calculates the optimal route by taking into account the user's past feedback, evaluation, and emotional state.

[0943] Step 9:

[0944] The terminal receives the optimal route sent from the server and displays it to the user. The input is the optimal route, and the output is the display on the user interface and voice guidance. In concrete terms, the terminal displays the route on the screen and provides voice navigation instructions.

[0945] Step 10:

[0946] After the trip, the device receives user feedback and sends it to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. Specifically, the device allows the user to input the evaluation through the user interface and sends it to the server via the network.

[0947] Step 11:

[0948] The server analyzes the received feedback and reflects it in the next route generation. The input is the feedback data, and the output is an updated evaluation database. Specifically, the server analyzes the feedback information and stores it in the database for use in the next route generation algorithm.

[0949] (Application example 2)

[0950] 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."

[0951] Conventional car navigation systems primarily focus on suggesting the shortest or fastest route, making it difficult to propose routes that take into account the user's emotions and scenic preferences. In particular, autonomous vehicles are required to provide routes that not only transport users to their destination but also adapt to the user's comfort and emotional state. To meet these requirements, it is necessary to collect and analyze user emotional information and generate an optimal route based on this information. However, there is still a lack of technology that utilizes user utterances and feedback in real time to propose routes that correspond to the user's emotional state. Therefore, there is a need for the development of a system that allows users to enjoy a comfortable and scenic drive without hassle.

[0952] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0953] In this invention, the server includes a speech recognition means for analyzing a user's speech and proposing a route suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting an optimal route for the user from the candidate routes and controlling the autonomous vehicle, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and an emotion engine for analyzing the user's emotions and optimizing navigation based on the analysis results. This makes it possible to provide a comfortable and scenic driving route that takes the user's emotional state into consideration.

[0954] "Speech recognition means" refers to a device or software that analyzes a user's speech, converts it into text data, and understands its content.

[0955] "Data collection means" refers to a device or software for collecting map information, surrounding environment information, landscape information, and user emotion information.

[0956] The "route generation means" is a device or software that analyzes collected data and generates candidate routes that offer good scenery and a pleasant driving experience.

[0957] "Navigation means" refers to a device or software that selects the optimal route for the user from among candidate routes and controls the autonomous vehicle.

[0958] The "feedback collection means" is a device or software that collects evaluation feedback from users and reflects it in the next route generation.

[0959] An "emotion engine" is a device or software that analyzes a user's emotions and optimizes navigation based on the analysis results.

[0960] This invention is a system for proposing an optimal driving route for an autonomous vehicle based on the user's speech and emotional information. The configuration and operation of this system are described in detail below.

[0961] System configuration

[0962] The system consists of the following main components:

[0963] 1. Voice Recognition Method

[0964] 2. Data Collection Methods

[0965] 3. Route Generation Method

[0966] 4. Navigation Methods

[0967] 5. Feedback Collection Methods

[0968] 6. Emotion Engine

[0969] Hardware and software used

[0970] 1. Voice Recognition Method

[0971] Hardware: Microphones in autonomous vehicles

[0972] Software: speech_recognition package, speech recognition API

[0973] 2. Data Collection Methods

[0974] Hardware: Vehicle sensors (GPS, camera)

[0975] Software: Map information API, surrounding environment information API, SNS analysis software

[0976] 3. Route Generation Method

[0977] Software: Route generation AI model

[0978] 4. Navigation Methods

[0979] Hardware: Vehicle control system

[0980] Software: Navigation software

[0981] 5. Feedback Collection Methods

[0982] Software: Feedback Management Software

[0983] 6. Emotion Engine

[0984] Software: Sentiment analysis software

[0985] How it works

[0986] First, the user speaks from inside the vehicle, saying, "Tell me about a driving route along the Shonan coast." This speech is converted into text data by a speech recognition means. Next, a data collection means collects map information, surrounding environment information, landscape information, and user emotion information. For example, the scenery of a specific coastline and traffic conditions are acquired in conjunction with GPS.

[0987] The route generator analyzes the collected data and generates multiple candidate routes based on the user's request. The emotion engine analyzes the user's speech and past feedback to recommend the most suitable route. For example, if the emotion of wanting to relax is recognized, a quiet and scenic route will be prioritized.

[0988] The generated route is sent to the autonomous vehicle's control system by the navigation means. The vehicle drives according to the navigation and is provided with audio and visual guidance. At the same time, after the drive is completed, the feedback collection means collects evaluation feedback from the user and reflects it in the next route generation.

[0989] Examples of concrete examples and prompts

[0990] For example, if a user requests a smartphone app to "tell me about a driving route along the Shonan coast," the request is converted into text data using voice recognition. If the app then recognizes that the user is feeling relaxed, it will recommend a quiet route along the coast.

[0991] Examples of prompt sentences include:

[0992] User utterance: "Tell me about a driving route along the Shonan coast."

[0993] Emotional state: "Relaxed"

[0994] Recommended route: "Prefer quiet coastal roads"

[0995] In this way, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[0996] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0997] Step 1:

[0998] The user speaks to the system, "Tell me about a driving course along the Shonan coast."

[0999] Input: User utterance

[1000] Output: Audio data

[1001] Step 2:

[1002] The terminal captures the user's voice data through a microphone and converts it into text data using a voice recognition means.

[1003] Input: Audio data

[1004] Output: Text data

[1005] How it works: The device's microphone captures audio, and a speech recognition API (e.g., speech_recognition package) converts the audio data into text data.

[1006] Step 3:

[1007] The server receives the text data and analyzes the request. For example, it extracts keywords such as "Driving courses along the Shonan coast."

[1008] Input: Text data

[1009] Output: Request content (keywords)

[1010] How it works: The server analyzes the text data and uses natural language processing to determine the user's intent.

[1011] Step 4:

[1012] The server uses the data collection means to collect map information, surrounding environment information, landscape information, and user emotion information.

[1013] Input: Request content (keywords)

[1014] Output: Map information, surrounding environment information, landscape information, emotion information

[1015] How it works: The server collects relevant data using multiple APIs (e.g., map information API, environmental information API, SNS analysis software).

[1016] Step 5:

[1017] The server uses an emotion engine to analyze the user's emotions, for example, by using voice data and past feedback to determine whether the user is relaxed.

[1018] Input: Voice data, past feedback

[1019] Output: User's emotional state

[1020] How it works: Emotion analysis software analyzes the user's voice tone and past driving behavior data to identify their emotional state.

[1021] Step 6:

[1022] The server uses a route generation means to analyze the collected data and the user's emotion information and generate a plurality of candidate routes.

[1023] Input: Map information, surrounding environment information, landscape information, emotional information

[1024] Output: candidate routes

[1025] How it works: A route generation AI model combines each piece of data and generates multiple candidate routes.

[1026] Step 7:

[1027] The server selects the route that best suits the user's emotional state and request content from the candidate routes.

[1028] Input: candidate routes, user's emotional state, request content

[1029] Output: Optimal route

[1030] Operation: The server evaluates the generated routes based on their scenery and driving experience, and selects the optimal route.

[1031] Step 8:

[1032] The terminal receives the optimal route and transmits it to the autonomous vehicle's control system.

[1033] Input: Optimal Route

[1034] Output: Vehicle control signal

[1035] How it works: Navigation software sends the optimal route to the autonomous vehicle's control system, which then controls the vehicle.

[1036] Step 9:

[1037] The terminal navigates while providing audio and visual guidance to the user.

[1038] Input: control signal, optimal route

[1039] Output: Audio guidance, visual guidance

[1040] How it works: The device uses the vehicle's display and speaker to provide navigation instructions to the user.

[1041] Step 10:

[1042] The server collects user evaluation feedback after each trip and reflects it in the next route generation.

[1043] Input: User rating feedback

[1044] Output: Updated feedback data

[1045] How it works: The feedback collection tool stores user ratings in a database and uses them for analysis.

[1046] Through the above steps, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[1047] 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.

[1048] 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.

[1049] 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.

[1050] [Third embodiment]

[1051] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1052] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1053] 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).

[1054] 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.

[1055] 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.

[1056] 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).

[1057] 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.

[1058] 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.

[1059] 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.

[1060] 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.

[1061] 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.

[1062] 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."

[1063] The car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[1064] System Configuration

[1065] The system consists of the following main components:

[1066] 1. Voice Recognition Method

[1067] 2. Data Collection Methods

[1068] 3. Route Generation Method

[1069] 4. Navigation Methods

[1070] 5. Feedback Collection Methods

[1071] Program processing

[1072] Receiving a user's speech request

[1073] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[1074] Voice recognition and data transmission

[1075] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[1076] Request content analysis

[1077] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[1078] Data collection

[1079] The server then collects the following information using data collection means:

[1080] Map information: Location information of roads and tourist spots around the destination

[1081] Surrounding area information: specific road width, traffic conditions, weather

[1082] GPS movement information: All users' movement data, including speed and number of stops

[1083] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[1084] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[1085] Route Generation

[1086] The server analyzes the collected data and generates multiple candidate routes. This route generation method selects roads with good scenery and a good driving experience, and also considers the user's past preferences and ratings to select the optimal route. The final route is determined using a route generation AI model.

[1087] Route provision and navigation

[1088] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[1089] Specific examples

[1090] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[1091] 1. The device converts the voice data into text data and sends it to the server.

[1092] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[1093] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, and past user feedback.

[1094] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[1095] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention provides a fulfilling driving experience by generating advanced routes based on the user's requests and ratings.

[1096] The processing flow will be explained below.

[1097] Step 1:

[1098] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[1099] Step 2:

[1100] The device uses a microphone to capture the user's speech as audio data.

[1101] Step 3:

[1102] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[1103] Step 4:

[1104] The terminal sends the converted text data to the server, and sends the request content to the server via an HTTP request.

[1105] Step 5:

[1106] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and begins collecting the necessary information.

[1107] Step 6:

[1108] The server accesses a map information database to obtain road information around the destination, including road width, traffic conditions, and weather information.

[1109] Step 7:

[1110] The server analyzes positive posts and images from social media and collects information on places that are considered to have beautiful views.

[1111] Step 8:

[1112] The server analyzes the GPS movement information of all users and collects road information (speed, number of stops, etc.) that allows users to drive comfortably.

[1113] Step 9:

[1114] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[1115] Step 10:

[1116] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[1117] Step 11:

[1118] The server selects the best route for the user from among several candidate routes based on the user's past preferences and ratings.

[1119] Step 12:

[1120] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[1121] Step 13:

[1122] The device displays the received route information to the user, and displays a route map on the screen to provide visual guidance to the user.

[1123] Step 14:

[1124] The device will then begin voice guidance and guide the user along the generated driving route, providing specific voice guidance such as "Turn left at the next intersection."

[1125] Step 15:

[1126] After the user completes a drive, the device prompts the user for feedback, asking for their opinion in the form of "How did you like this route?"

[1127] Step 16:

[1128] The user inputs feedback, such as "It was very pleasant" or "I would like to pass through a place with a better view."

[1129] Step 17:

[1130] The device sends the input feedback to the server via an HTTP request.

[1131] Step 18:

[1132] The server analyzes the received feedback and stores it in a database as new data, which is then used to generate future routes.

[1133] Through these steps, users can easily enjoy the optimal driving route with beautiful scenery and a great driving experience.

[1134] Example 1

[1135] 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."

[1136] Current car navigation systems do not adequately consider user preferences and driving experience when proposing routes, and have difficulty dynamically reflecting scenic beauty and road conditions. In particular, the accuracy of feedback and data analysis required to propose routes that match the specific scenery and driving experience desired by the user is insufficient, resulting in failure to increase user satisfaction.

[1137] 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.

[1138] In this invention, the server includes a voice recognition means for analyzing the user's speech and proposing routes suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting the most suitable route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and a means for generating multiple candidate routes based on the analysis results and determining the most suitable route using a generation AI model. This makes it possible to provide the most suitable driving route with good scenery based on the user's preferences and past evaluations.

[1139] A "voice recognition means" is a means for analyzing a user's speech and converting it into text data.

[1140] "Data collection means" refers to means for collecting map information, surrounding environment information, landscape information, and user emotion information.

[1141] The "route generation means" is a means for analyzing collected data and generating candidate routes that offer good scenery and a pleasant driving experience.

[1142] A "navigation means" is a means for selecting the most suitable route for a user from among candidate routes and navigating the user along that route.

[1143] The "feedback collection means" is a means for collecting evaluation feedback from users and reflecting it in the next route generation.

[1144] "Analysis results" refer to information and conclusions drawn from collected data.

[1145] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal routes.

[1146] The "optimal route" is a route with beautiful scenery and a good driving experience, determined based on collected data and the user's preferences and ratings.

[1147] "Scenic information" refers to information about the beauty of the scenery and surrounding environment at a particular route or point.

[1148] "Surrounding environment information" is comprehensive information such as road conditions, weather, and traffic conditions at specific routes and locations.

[1149] A car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[1150] System Configuration

[1151] The system consists of the following main components:

[1152] 1. Voice Recognition Method

[1153] 2. Data Collection Methods

[1154] 3. Route Generation Method

[1155] 4. Navigation Methods

[1156] 5. Feedback Collection Methods

[1157] 6. Generative AI Models

[1158] Program processing

[1159] Receiving a user's speech request

[1160] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[1161] Voice recognition and data transmission

[1162] The device converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. Voice recognition uses a highly sensitive microphone and voice capture software (e.g., a voice recognition API).

[1163] Request content analysis

[1164] The server analyzes the received text data and identifies the user's request. For example, it uses a natural language processing tool (e.g., a natural language processing API) to extract and recognize the keyword "scenic driving route."

[1165] Data collection

[1166] The server then collects the following information using data collection means:

[1167] Map information: Location information of roads and tourist spots around the destination. Uses the Map Information API.

[1168] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[1169] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[1170] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses the SNS information API.

[1171] User rating feedback and sentiment information: Collect past user ratings and sentiment information from the feedback database.

[1172] Route Generation

[1173] The server analyzes the collected data and generates multiple candidate routes. The server uses a generative AI model (e.g., AI model API) to select a route with good scenery and a good driving experience. The server also considers the user's past preferences and ratings to select the optimal route.

[1174] Route provision and navigation

[1175] The device receives the route information sent from the server and displays it to the user. It also provides audio and visual guidance along the route, navigating the user using Google Maps navigation features.

[1176] Specific examples

[1177] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[1178] 1. The device converts the voice data into text data and sends it to the server using a speech recognition API.

[1179] 2. The server analyzes the request and detects the keyword "Route with a view of Mt. Fuji." It uses a natural language processing API for the analysis.

[1180] 3. The server uses the map information API, weather information API, and SNS information API to collect map information, landscape information, and surrounding environment information, and also refers to past user feedback.

[1181] 4. The server generates the optimal route based on the collected data. Using a generative AI model, it selects the optimal route, including one with a view of Mt. Fuji.

[1182] 5. The device displays the optimal route and navigates the user with audio and visual guidance, using Google Maps.

[1183] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention generates sophisticated routes based on the user's requests and ratings, providing a fulfilling driving experience.

[1184] Prompt Sentence Examples

[1185] "Please collect map information, landscape information, road conditions, positive posts on social media, and user feedback from all over Japan, and generate scenic driving routes that meet user requests. For example, please suggest the best route for a request like 'I want to drive to Hakone from a route that gives me a view of Mt. Fuji.'"

[1186] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1187] Step 1: Receiving a user's speech request

[1188] A user speaks to a car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. The device acquires the voice data using voice capture software (e.g., a voice recognition API).

[1189] Step 2: Voice recognition and data transmission

[1190] The terminal converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. The input is voice data and the output is text data. Specifically, the terminal uses a voice recognition API to send data to the server via a network module.

[1191] Step 3: Parsing the request

[1192] The server analyzes the received text data and identifies the user's request. For example, a natural language processing tool is used to extract the keyword "scenic driving route." The input is text data, and the output is the analyzed keyword. The server performs the analysis using a natural language processing API.

[1193] Step 4: Data collection

[1194] The server collects the following information using data collection methods:

[1195] Map information: Location information of roads and tourist spots around the destination. Uses map information API.

[1196] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[1197] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[1198] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses SNS information API.

[1199] User rating feedback and sentiment information: Past user ratings and sentiment expressions. Obtained from the feedback database.

[1200] The input is the request content, and the output is various collected data. The server collects information through each API.

[1201] Step 5: Route Generation

[1202] The server analyzes the collected data and generates multiple candidate routes. The input is the collected data, and the output is the candidate routes. The server uses a generative AI model to generate roads with beautiful scenery and a great driving experience. It also takes into account the user's past preferences and ratings to select the optimal route.

[1203] Step 6: Route provision and navigation

[1204] The device receives the determined route sent from the server and displays it to the user. It also provides audio and visual guidance along the generated route to navigate the user. The input is the determined route data, and the output is the display and audio guidance on the device. The device uses the navigation function of Google Maps.

[1205] This process allows users to find a comfortable and scenic driving route without any hassle.

[1206] (Application example 1)

[1207] 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."

[1208] Conventional car navigation systems lacked the ability to suggest routes based on user requests and provide feedback on user evaluations, making it difficult to provide routes with beautiful scenery and a comfortable driving experience. Furthermore, while autonomous vehicles are required to provide safer and more comfortable driving routes, there were limitations to achieving this. This made it difficult for users to have a satisfying driving experience.

[1209] 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.

[1210] In this invention, the server includes a voice recognition means, a data collection means for collecting geographic information, traffic information, visual information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes that are scenic and comfortable to drive, a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting the feedback in the next route generation, a means for providing the generated route for the autonomous vehicle and providing visual and audio guidance, a means for optimizing the candidate route using a generative AI model, and a means for inputting prompt sentences into the generative AI model and generating the optimal route. This enables high-quality route suggestions and navigation for autonomous vehicles based on user requests, making it possible to provide a highly satisfying driving experience.

[1211] "Voice recognition means" is a technology that analyzes a user's speech and converts it into text data.

[1212] "Geographic information" refers to road and location information around the destination, as well as location information for tourist spots, etc.

[1213] "Traffic information" refers to data that includes information on the traffic conditions, passability, and traffic congestion of specific roads.

[1214] "Visual information" refers to information including images and videos of landscapes, as well as content about landscapes posted on social media.

[1215] "User emotional information" refers to information such as user ratings and emotional expressions obtained from past driving data.

[1216] "Data collection means" refers to technologies that collect geographical information, traffic information, visual information, and user emotional information.

[1217] The "route generation means" is a technology that generates candidate routes that are scenic and comfortable to drive based on collected data.

[1218] "Navigation means" refers to technology that selects the optimal route for the user from among candidate routes and navigates through it.

[1219] "Feedback collection means" refers to technology that collects user evaluations and feedback and reflects them in the next route generation.

[1220] "Means for providing routes generated for automated driving vehicles and providing visual and audio guidance" refers to technology that provides optimal routes and provides visual and audio guidance to automated driving vehicles so that they can travel safely and comfortably.

[1221] A "generative AI model" is an artificial intelligence model that analyzes data and generates optimal solutions or answers based on conditions.

[1222] A "prompt sentence" is an instruction sentence used by a generative AI model when generating a route.

[1223] To implement the present invention, a speech recognition means, a data collection means, a route generation means, a navigation means, a feedback collection means, a route provision and guidance means for an autonomous vehicle are required, and a means for generating prompt sentences to optimize candidate routes using a generative AI model.

[1224] System Configuration

[1225] The system consists of the following main components:

[1226] 1. Speech recognition means: Analyzes the user's speech and converts it into text data.

[1227] 2. Data collection methods: collect geographical information, traffic information, visual information and user emotional information.

[1228] 3. Route generation method: Analyze the collected data and generate candidate routes that are scenic and comfortable to drive.

[1229] 4. Navigation method: Select the best route for the user from the candidate routes and navigate.

[1230] 5. Feedback collection method: Collect evaluation feedback from users and reflect it in the next route generation.

[1231] 6. Route provision and guidance for autonomous vehicles: Provides generated routes to autonomous vehicles and provides visual and audio guidance.

[1232] 7. Generative AI model and prompt sentence generation means: The generative AI model is used to optimize the candidate routes, and the prompt sentence is input to generate the optimal route.

[1233] Hardware and software used

[1234] Hardware: Smartphone (including microphone, speaker, and GPS function), cloud server

[1235] software:

[1236] Google Cloud Speech-to-Text API (voice recognition)

[1237] OpenAI GPT-4 (Natural Language Analysis and Route Generation)

[1238] Node.js (server-side scripting)

[1239] Map API (geography and navigation)

[1240] Program processing

[1241] 1. Voice input and recognition:

[1242] The user speaks a request into their smartphone, such as "I want to take a scenic route to my destination."

[1243] The smartphone's microphone captures this audio and converts it into text data using the Google Cloud Speech-to-Text API.

[1244] 2. Send to server:

[1245] The text data is sent to a cloud server in real time, and the request content is analyzed.

[1246] 3. Data Collection and Analysis:

[1247] The cloud server collects geographic information, traffic information, visual information, and user emotional information using data collection means.

[1248] Based on this data, the route generation means generates a plurality of candidate routes that are scenic and comfortable to drive.

[1249] 4. Route generation and provisioning:

[1250] Based on the collected data, prompts are input into the OpenAI GPT-4 model to generate the optimal route.

[1251] For example, enter the following prompt:

[1252] The user wants to reach their destination by a scenic route. Generate a scenic route.

[1253] The generated route is provided to the autonomous vehicle from a cloud server.

[1254] 5. Navigation and Feedback:

[1255] The route is displayed on the smartphone and navigation is provided visually and audibly.

[1256] After a drive is completed, user ratings and feedback are collected and reflected in the next route generation.

[1257] Specific examples

[1258] If a user requests a drive to Hakone with a route that gives a view of Mt. Fuji, the system will:

[1259] 1. The smartphone converts the voice data into text and sends it to a cloud server.

[1260] 2. The cloud server analyzes the request and generates multiple candidates, including routes from which Mount Fuji can be seen.

[1261] 3. Select the best route based on geographic, visual, traffic, and past feedback.

[1262] 4. The optimal route will be displayed on your smartphone and navigation will begin.

[1263] In this way, the system of the present invention allows the user to easily enjoy a scenic and comfortable drive.

[1264] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1265] Step 1:

[1266] Voice Input and Recognition

[1267] Input: A user speaks a request into their smartphone: "I want to take a scenic route to my destination."

[1268] Processing: The device's microphone captures this audio data and converts it to text using the Google Cloud Speech-to-Text API.

[1269] Output: The text data generated is "I want to take a scenic road to my destination."

[1270] Step 2:

[1271] Sending to the server

[1272] Input: Text data generated by a speech recognition means.

[1273] Processing: The device sends this text data to the cloud server in real time.

[1274] Output: Text data is sent to the server.

[1275] Step 3:

[1276] Request content analysis

[1277] Input: The text data sent to the server.

[1278] Processing: The server analyzes the text data and identifies the user's request, for example, extracting keywords such as "scenic" and "destination."

[1279] Output: The analysis results clarify the user's request.

[1280] Step 4:

[1281] Data collection

[1282] Input: Search criteria based on the request content.

[1283] Processing: The server collects geographical information, traffic information, visual information, and user emotional information. Specifically, it uses map APIs, social media posts, and weather information services to collect the necessary data.

[1284] Output: Various data collected.

[1285] Step 5:

[1286] Route Generation

[1287] Input: The data collected and what you request.

[1288] Processing: The server generates an optimal route by inputting the following prompt into the OpenAI GPT-4 model: "The user wants to reach their destination by a scenic route. Please generate a route with beautiful scenery." The generative AI model outputs candidate routes.

[1289] Output: Multiple candidate routes with good scenery and comfortable driving.

[1290] Step 6:

[1291] Route Selection

[1292] Input: Multiple generated candidate routes and past user ratings and feedback.

[1293] Processing: The server compares the candidate routes with the rating data and selects the optimal route.

[1294] Output: The route that is determined to be optimal.

[1295] Step 7:

[1296] Navigation provided

[1297] Input: The selected optimal route.

[1298] Processing: The device receives this route information and provides visual and audio guidance to the user, using a map API to display the route and a text-to-speech API to provide guidance.

[1299] Output: Visual and audio guidance to the user.

[1300] Step 8:

[1301] Feedback collection

[1302] Input: User post-drive ratings and feedback.

[1303] Processing: The server collects this feedback data and stores it in a database to be used in the next route generation.

[1304] Output: Collected feedback data.

[1305] 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.

[1306] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[1307] System Configuration

[1308] The system consists of the following main components:

[1309] 1. Voice Recognition Method

[1310] 2. Data Collection Methods

[1311] 3. Route Generation Method

[1312] 4. Navigation Methods

[1313] 5. Feedback Collection Methods

[1314] 6. Emotion Engine

[1315] Program processing

[1316] Receiving a user's speech request

[1317] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[1318] Voice recognition and data transmission

[1319] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[1320] Request content analysis

[1321] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[1322] Data collection

[1323] The server then collects the following information using data collection means:

[1324] Map information: Location information of roads and tourist spots around the destination

[1325] Surrounding area information: specific road width, traffic conditions, weather

[1326] GPS movement information: All users' movement data, including speed and number of stops

[1327] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[1328] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[1329] emotion recognition

[1330] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. For example, it can determine whether the user is relaxed or tense from voice data. It can also infer the user's emotional state from the frequency of sudden braking and acceleration.

[1331] Route Generation

[1332] The server analyzes the collected data and emotional information to generate multiple candidate routes. This route generation method selects roads with beautiful scenery and a great driving experience, and also considers the user's past preferences, ratings, and emotional information to select the optimal route. The final route is determined using a route generation AI model.

[1333] Route provision and navigation

[1334] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[1335] Specific examples

[1336] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[1337] 1. The device converts the voice data into text data and sends it to the server.

[1338] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[1339] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, emotional information, and past user feedback.

[1340] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[1341] In addition, the emotion engine recognizes the user's emotions during the drive and when making a request. For example, if the driver's desire to relax is recognized, the system will prioritize quieter and more scenic roads. Emotional information from previous driving experiences is also taken into account, providing the user with the most comfortable route.

[1342] This system allows users to enjoy a hassle-free, comfortable, and scenic drive.In this way, the present invention provides a fulfilling driving experience by generating an advanced route based on the user's requests, ratings, and emotional information.

[1343] The processing flow will be explained below.

[1344] Step 1:

[1345] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[1346] Step 2:

[1347] The device uses a microphone to capture the user's speech as audio data.

[1348] Step 3:

[1349] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[1350] Step 4:

[1351] The terminal sends the converted text data to the server via an HTTP request.

[1352] Step 5:

[1353] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and prepares to collect appropriate information.

[1354] Step 6:

[1355] The server accesses a map information database to obtain road information around the destination and location information for tourist spots, including road width, traffic conditions, and weather information.

[1356] Step 7:

[1357] The server analyzes positive posts and images from social media and collects information on places with beautiful views, based on hashtags and location information.

[1358] Step 8:

[1359] The server analyzes the GPS movement information of all users and collects information on roads where users can comfortably drive (speed, number of stops, etc.).

[1360] Step 9:

[1361] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[1362] Step 10:

[1363] The emotion engine recognizes the user's emotional state from their speech data and driving behavior data. For example, it can determine whether the user is relaxed or tense from their voice data, and infer their emotional state from the frequency of sudden braking and acceleration.

[1364] Step 11:

[1365] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[1366] Step 12:

[1367] The server selects the optimal route from the generated candidate routes based on the user's emotional state and past preferences and ratings.

[1368] Step 13:

[1369] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[1370] Step 14:

[1371] The device then displays the received route information to the user, displaying a map and route on the screen to provide visual guidance to the user.

[1372] Step 15:

[1373] The device will then begin voice guidance and guide the user along the generated driving route, providing specific instructions such as "Turn left at the next intersection."

[1374] Step 16:

[1375] After the drive is complete, the device prompts the user for feedback, for example, asking, "How did you like the route?"

[1376] Step 17:

[1377] The user inputs feedback, such as "It felt really good" or "I'd like to pass through places with better scenery."

[1378] Step 18:

[1379] The device sends the input feedback to the server via an HTTP request.

[1380] Step 19:

[1381] The server analyzes the received feedback and stores it in a database as new data, which is then used for subsequent route generation.

[1382] This way, users can enjoy a hassle-free, comfortable and scenic drive, and the system will continue to evolve based on their feedback.

[1383] Example 2

[1384] 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."

[1385] Conventional car navigation systems have difficulty proposing routes based on the user's emotions and preferences, and often simply provide the shortest or fastest route. Furthermore, data collection and analysis to find scenic routes are insufficient, making it difficult to provide users with a satisfying driving experience. Furthermore, previous systems lacked a mechanism for utilizing user feedback and emotional information when generating the next route.

[1386] 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.

[1387] In this invention, the server includes: a speech recognition means for analyzing a user's speech and proposing a route suitable for driving; a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information; a route generation means for analyzing the collected data and generating candidate routes with beautiful landscapes and a good driving experience; a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route; a feedback collection means for collecting evaluation feedback from the user and reflecting this in the next route generation; an emotion recognition means for analyzing the user's speech and driving behavior data to recognize the user's emotional state and reflecting this in route selection; and a route generation AI model that includes an artificial intelligence model used for route generation and uses prompt sentences as input to generate the optimal route. This enables advanced route suggestions based on the user's emotions and preferences, providing a fulfilling driving experience.

[1388] A "voice recognition means" is a device or system that analyzes a user's speech and converts it into text data.

[1389] The "data collection means" is a device or system that collects map information, surrounding environment information, landscape information, and user emotion information.

[1390] The "route generation means" is a device or system that analyzes collected data and generates candidate routes that offer beautiful scenery and a pleasant driving experience.

[1391] A "navigation means" is a device or system that selects the most suitable route for a user from among candidate routes and navigates the user.

[1392] The "feedback collection means" is a device or system that collects evaluation feedback from users and reflects it in the next route generation.

[1393] An "emotion recognition means" is a device or system that analyzes the user's speech and driving behavior data to recognize their emotional state and reflects this in route selection.

[1394] A "route generation AI model" is an artificial intelligence model used for route generation, which uses prompt sentences as input to generate the optimal route.

[1395] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[1396] System Configuration

[1397] The system consists of the following main components:

[1398] 1. Voice Recognition Method

[1399] 2. Data Collection Methods

[1400] 3. Route Generation Method

[1401] 4. Navigation Methods

[1402] 5. Feedback Collection Methods

[1403] 6. Emotion recognition means

[1404] 7. Route Generation AI Model

[1405] Voice recognition means

[1406] The device is equipped with a microphone to capture the user's speech. The captured voice data is converted into text data by speech recognition software (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text), and the converted text data is sent to a server.

[1407] Data collection methods

[1408] The server uses various APIs (e.g., Google Maps API for map information, Increment P's traffic information API for traffic information, Weather Underground's weather API for weather information, Twitter API and Instagram Graph API for social media information) to collect map information around the destination, road width, traffic conditions, weather, GPS movement information, SNS landscape information, and past user evaluation feedback and sentiment information.

[1409] Route Generation Method

[1410] Based on the information collected by the data collection method, the server uses Dijkstra's algorithm, A-search algorithm, and a personalized model using deep learning to generate multiple candidate routes that offer beautiful scenery and a comfortable ride. It then uses a route generation AI model to select the optimal route, taking into account the user's past preferences, ratings, and emotional information. Finally, it determines the optimal route for the user.

[1411] Navigation methods

[1412] The device receives the confirmed route sent from the server. The route information is displayed on the screen and voice guidance is provided to navigate the user. Specifically, an interface similar to the navigation function of Google Maps is used to display the next intersection and the distance to the destination on the screen. Voice guidance is also provided to give instructions such as "Turn left at the next intersection."

[1413] Feedback collection methods

[1414] The device collects user feedback and sends it to the server, which uses this feedback information to generate the next route.

[1415] emotion recognition means

[1416] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. Specifically, it uses the Microsoft Azure Emotion API and Face++ emotion recognition API to analyze the tone and rhythm of the user's voice to determine whether they are relaxed or tense. It also estimates their stress level based on the frequency of sudden braking and acceleration while driving.

[1417] Route generation AI model

[1418] The route generation AI model uses prompts based on collected data to generate optimal routes, allowing for advanced route suggestions based on user sentiment and preferences.

[1419] Specific examples

[1420] For example, if a user requests a drive to Hakone with a route that allows for a view of Mt. Fuji, the system operates as follows:

[1421] 1. The device converts the voice data into text data using the Google Cloud Speech-to-Text API and sends it to the server.

[1422] 2. The server analyzes the received text data using the BERT model and extracts "Routes to see Mt. Fuji" and "To Hakone."

[1423] 3. The server obtains road information around Mount Fuji from the Google Maps API and also collects landscape and traffic information from social media.

[1424] 4. The emotion engine recognizes from the user's tone of voice that they want to relax and prioritizes quieter, more scenic routes.

[1425] 5. The route generation AI model inputs emotional and landscape information into Dijkstra's algorithm to generate the optimal route.

[1426] 6. The device displays the determined route to the user and provides voice navigation.

[1427] Prompt Sentence Examples

[1428] Example prompts fed to a generative AI model:

[1429] "A user has requested a drive to Hakone with a route that allows for a view of Mt. Fuji. Generate the optimal route using the following information:

[1430] Map information: Roads around Mt. Fuji and Hakone location information

[1431] Landscape information on social media: Posts of places where Mount Fuji is said to be visible

[1432] Surrounding environment information: traffic conditions, weather, road width

[1433] User feedback: Evaluation information on routes that have been moderately relaxing in the past

[1434] Emotional information: the user's current level of relaxation

[1435] In this way, the system generates an advanced route that combines the user's voice request and emotional state, providing a scenic and comfortable driving experience.

[1436] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1437] Step 1:

[1438] The user issues a voice request to the car navigation device, such as "Tell me about a scenic driving route." This request is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. Specifically, the user speaks into the microphone of the head unit or smartphone app.

[1439] Step 2:

[1440] The device converts the captured voice data into text data in real time using the Google Cloud Speech-to-Text API. The input is the captured voice data, and the output is text data generated by speech recognition. Specifically, the device sends the voice data to the API and stores the returned text data in an internal buffer.

[1441] Step 3:

[1442] The terminal sends text data to the server. The input is the text data, and the output is the status of completion of transmission. In concrete terms, the terminal sends data to the server via the network.

[1443] Step 4:

[1444] The server analyzes the received text data using the BERT model to identify the user's request. The input is text data, and the output is the analyzed request information (e.g., "Scenic driving route"). Specifically, the server runs an NLP (natural language processing) algorithm to extract keywords and the intent of the request from the text data.

[1445] Step 5:

[1446] The server uses data collection methods to collect the following information: map information from the Google Maps API, surrounding environment information from a traffic information service, weather information from Weather Underground's weather API, and social media information from the Twitter API and Instagram Graph API. The input is the request information, and the output is the various collected information data. Specifically, the server calls the various APIs, obtains the necessary information from each data source, and stores it.

[1447] Step 6:

[1448] The server uses an emotion engine to analyze the user's speech and driving behavior data to recognize the user's emotional state. The input is the user's text data and behavioral data, and the output is the user's emotional state data. Specifically, the server sends the acquired data to the Microsoft Azure Emotion API or Face++ emotion recognition API to determine the emotional state.

[1449] Step 7:

[1450] The server integrates the collected data and emotional information to generate multiple candidate routes using a route generation AI model. The input is the aggregated data and emotional information, and the output is multiple candidate routes. Specifically, the server inputs the data into Dijkstra's algorithm and A-search algorithm to generate candidate routes.

[1451] Step 8:

[1452] The server selects the optimal route from the candidate routes and provides it to the user. The input is multiple candidate routes, and the output is the optimal route. Specifically, the server calculates the optimal route by taking into account the user's past feedback, evaluation, and emotional state.

[1453] Step 9:

[1454] The terminal receives the optimal route sent from the server and displays it to the user. The input is the optimal route, and the output is the display on the user interface and voice guidance. In concrete terms, the terminal displays the route on the screen and provides voice navigation instructions.

[1455] Step 10:

[1456] After the trip, the device receives user feedback and sends it to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. Specifically, the device allows the user to input the evaluation through the user interface and sends it to the server via the network.

[1457] Step 11:

[1458] The server analyzes the received feedback and reflects it in the next route generation. The input is the feedback data, and the output is an updated evaluation database. Specifically, the server analyzes the feedback information and stores it in the database for use in the next route generation algorithm.

[1459] (Application example 2)

[1460] 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."

[1461] Conventional car navigation systems primarily focus on suggesting the shortest or fastest route, making it difficult to propose routes that take into account the user's emotions and scenic preferences. In particular, autonomous vehicles are required to provide routes that not only transport users to their destination but also adapt to the user's comfort and emotional state. To meet these requirements, it is necessary to collect and analyze user emotional information and generate an optimal route based on this information. However, there is still a lack of technology that utilizes user utterances and feedback in real time to propose routes that correspond to the user's emotional state. Therefore, there is a need for the development of a system that allows users to enjoy a comfortable and scenic drive without hassle.

[1462] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1463] In this invention, the server includes a speech recognition means for analyzing a user's speech and proposing a route suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting an optimal route for the user from the candidate routes and controlling the autonomous vehicle, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and an emotion engine for analyzing the user's emotions and optimizing navigation based on the analysis results. This makes it possible to provide a comfortable and scenic driving route that takes the user's emotional state into consideration.

[1464] "Speech recognition means" refers to a device or software that analyzes a user's speech, converts it into text data, and understands its content.

[1465] "Data collection means" refers to a device or software for collecting map information, surrounding environment information, landscape information, and user emotion information.

[1466] The "route generation means" is a device or software that analyzes collected data and generates candidate routes that offer good scenery and a pleasant driving experience.

[1467] "Navigation means" refers to a device or software that selects the optimal route for the user from among candidate routes and controls the autonomous vehicle.

[1468] The "feedback collection means" is a device or software that collects evaluation feedback from users and reflects it in the next route generation.

[1469] An "emotion engine" is a device or software that analyzes a user's emotions and optimizes navigation based on the analysis results.

[1470] This invention is a system for proposing an optimal driving route for an autonomous vehicle based on the user's speech and emotional information. The configuration and operation of this system are described in detail below.

[1471] System configuration

[1472] The system consists of the following main components:

[1473] 1. Voice Recognition Method

[1474] 2. Data Collection Methods

[1475] 3. Route Generation Method

[1476] 4. Navigation Methods

[1477] 5. Feedback Collection Methods

[1478] 6. Emotion Engine

[1479] Hardware and software used

[1480] 1. Voice Recognition Method

[1481] Hardware: Microphones in autonomous vehicles

[1482] Software: speech_recognition package, speech recognition API

[1483] 2. Data Collection Methods

[1484] Hardware: Vehicle sensors (GPS, camera)

[1485] Software: Map information API, surrounding environment information API, SNS analysis software

[1486] 3. Route Generation Method

[1487] Software: Route generation AI model

[1488] 4. Navigation Methods

[1489] Hardware: Vehicle control system

[1490] Software: Navigation software

[1491] 5. Feedback Collection Methods

[1492] Software: Feedback Management Software

[1493] 6. Emotion Engine

[1494] Software: Sentiment analysis software

[1495] How it works

[1496] First, the user speaks from inside the vehicle, saying, "Tell me about a driving route along the Shonan coast." This speech is converted into text data by a speech recognition means. Next, a data collection means collects map information, surrounding environment information, landscape information, and user emotion information. For example, the scenery of a specific coastline and traffic conditions are acquired in conjunction with GPS.

[1497] The route generator analyzes the collected data and generates multiple candidate routes based on the user's request. The emotion engine analyzes the user's speech and past feedback to recommend the most suitable route. For example, if the emotion of wanting to relax is recognized, a quiet and scenic route will be prioritized.

[1498] The generated route is sent to the autonomous vehicle's control system by the navigation means. The vehicle drives according to the navigation and is provided with audio and visual guidance. At the same time, after the drive is completed, the feedback collection means collects evaluation feedback from the user and reflects it in the next route generation.

[1499] Examples of concrete examples and prompts

[1500] For example, if a user requests a smartphone app to "tell me about a driving route along the Shonan coast," the request is converted into text data using voice recognition. If the app then recognizes that the user is feeling relaxed, it will recommend a quiet route along the coast.

[1501] Examples of prompt sentences include:

[1502] User utterance: "Tell me about a driving route along the Shonan coast."

[1503] Emotional state: "Relaxed"

[1504] Recommended route: "Prefer quiet coastal roads"

[1505] In this way, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[1506] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1507] Step 1:

[1508] The user speaks to the system, "Tell me about a driving course along the Shonan coast."

[1509] Input: User utterance

[1510] Output: Audio data

[1511] Step 2:

[1512] The terminal captures the user's voice data through a microphone and converts it into text data using a voice recognition means.

[1513] Input: Audio data

[1514] Output: Text data

[1515] How it works: The device's microphone captures audio, and a speech recognition API (e.g., speech_recognition package) converts the audio data into text data.

[1516] Step 3:

[1517] The server receives the text data and analyzes the request. For example, it extracts keywords such as "Driving courses along the Shonan coast."

[1518] Input: Text data

[1519] Output: Request content (keywords)

[1520] How it works: The server analyzes the text data and uses natural language processing to determine the user's intent.

[1521] Step 4:

[1522] The server uses the data collection means to collect map information, surrounding environment information, landscape information, and user emotion information.

[1523] Input: Request content (keywords)

[1524] Output: Map information, surrounding environment information, landscape information, emotion information

[1525] How it works: The server collects relevant data using multiple APIs (e.g., map information API, environmental information API, SNS analysis software).

[1526] Step 5:

[1527] The server uses an emotion engine to analyze the user's emotions, for example, by using voice data and past feedback to determine whether the user is relaxed.

[1528] Input: Voice data, past feedback

[1529] Output: User's emotional state

[1530] How it works: Emotion analysis software analyzes the user's voice tone and past driving behavior data to identify their emotional state.

[1531] Step 6:

[1532] The server uses a route generation means to analyze the collected data and the user's emotion information and generate a plurality of candidate routes.

[1533] Input: Map information, surrounding environment information, landscape information, emotional information

[1534] Output: candidate routes

[1535] How it works: A route generation AI model combines each piece of data and generates multiple candidate routes.

[1536] Step 7:

[1537] The server selects the route that best suits the user's emotional state and request content from the candidate routes.

[1538] Input: candidate routes, user's emotional state, request content

[1539] Output: Optimal route

[1540] Operation: The server evaluates the generated routes based on their scenery and driving experience, and selects the optimal route.

[1541] Step 8:

[1542] The terminal receives the optimal route and transmits it to the autonomous vehicle's control system.

[1543] Input: Optimal Route

[1544] Output: Vehicle control signal

[1545] How it works: Navigation software sends the optimal route to the autonomous vehicle's control system, which then controls the vehicle.

[1546] Step 9:

[1547] The terminal navigates while providing audio and visual guidance to the user.

[1548] Input: control signal, optimal route

[1549] Output: Audio guidance, visual guidance

[1550] How it works: The device uses the vehicle's display and speaker to provide navigation instructions to the user.

[1551] Step 10:

[1552] The server collects user evaluation feedback after each trip and reflects it in the next route generation.

[1553] Input: User rating feedback

[1554] Output: Updated feedback data

[1555] How it works: The feedback collection tool stores user ratings in a database and uses them for analysis.

[1556] Through the above steps, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] [Fourth embodiment]

[1561] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1562] 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.

[1563] 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).

[1564] 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.

[1565] 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.

[1566] 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).

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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."

[1574] The car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[1575] System Configuration

[1576] The system consists of the following main components:

[1577] 1. Voice Recognition Method

[1578] 2. Data Collection Methods

[1579] 3. Route Generation Method

[1580] 4. Navigation Methods

[1581] 5. Feedback Collection Methods

[1582] Program processing

[1583] Receiving a user's speech request

[1584] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[1585] Voice recognition and data transmission

[1586] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[1587] Request content analysis

[1588] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[1589] Data collection

[1590] The server then collects the following information using data collection means:

[1591] Map information: Location information of roads and tourist spots around the destination

[1592] Surrounding area information: specific road width, traffic conditions, weather

[1593] GPS movement information: All users' movement data, including speed and number of stops

[1594] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[1595] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[1596] Route Generation

[1597] The server analyzes the collected data and generates multiple candidate routes. This route generation method selects roads with good scenery and a good driving experience, and also considers the user's past preferences and ratings to select the optimal route. The final route is determined using a route generation AI model.

[1598] Route provision and navigation

[1599] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[1600] Specific examples

[1601] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[1602] 1. The device converts the voice data into text data and sends it to the server.

[1603] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[1604] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, and past user feedback.

[1605] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[1606] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention provides a fulfilling driving experience by generating advanced routes based on the user's requests and ratings.

[1607] The processing flow will be explained below.

[1608] Step 1:

[1609] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[1610] Step 2:

[1611] The device uses a microphone to capture the user's speech as audio data.

[1612] Step 3:

[1613] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[1614] Step 4:

[1615] The terminal sends the converted text data to the server, and sends the request content to the server via an HTTP request.

[1616] Step 5:

[1617] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and begins collecting the necessary information.

[1618] Step 6:

[1619] The server accesses a map information database to obtain road information around the destination, including road width, traffic conditions, and weather information.

[1620] Step 7:

[1621] The server analyzes positive posts and images from social media and collects information on places that are considered to have beautiful views.

[1622] Step 8:

[1623] The server analyzes the GPS movement information of all users and collects road information (speed, number of stops, etc.) that allows users to drive comfortably.

[1624] Step 9:

[1625] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[1626] Step 10:

[1627] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[1628] Step 11:

[1629] The server selects the best route for the user from among several candidate routes based on the user's past preferences and ratings.

[1630] Step 12:

[1631] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[1632] Step 13:

[1633] The device displays the received route information to the user, and displays a route map on the screen to provide visual guidance to the user.

[1634] Step 14:

[1635] The device will then begin voice guidance and guide the user along the generated driving route, providing specific voice guidance such as "Turn left at the next intersection."

[1636] Step 15:

[1637] After the user completes a drive, the device prompts the user for feedback, asking for their opinion in the form of "How did you like this route?"

[1638] Step 16:

[1639] The user inputs feedback, such as "It was very pleasant" or "I would like to pass through a place with a better view."

[1640] Step 17:

[1641] The device sends the input feedback to the server via an HTTP request.

[1642] Step 18:

[1643] The server analyzes the received feedback and stores it in a database as new data, which is then used to generate future routes.

[1644] Through these steps, users can easily enjoy the optimal driving route with beautiful scenery and a great driving experience.

[1645] Example 1

[1646] 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."

[1647] Current car navigation systems do not adequately consider user preferences and driving experience when proposing routes, and have difficulty dynamically reflecting scenic beauty and road conditions. In particular, the accuracy of feedback and data analysis required to propose routes that match the specific scenery and driving experience desired by the user is insufficient, resulting in failure to increase user satisfaction.

[1648] 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.

[1649] In this invention, the server includes a voice recognition means for analyzing the user's speech and proposing routes suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting the most suitable route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and a means for generating multiple candidate routes based on the analysis results and determining the most suitable route using a generation AI model. This makes it possible to provide the most suitable driving route with good scenery based on the user's preferences and past evaluations.

[1650] A "voice recognition means" is a means for analyzing a user's speech and converting it into text data.

[1651] "Data collection means" refers to means for collecting map information, surrounding environment information, landscape information, and user emotion information.

[1652] The "route generation means" is a means for analyzing collected data and generating candidate routes that offer good scenery and a pleasant driving experience.

[1653] A "navigation means" is a means for selecting the most suitable route for a user from among candidate routes and navigating the user along that route.

[1654] The "feedback collection means" is a means for collecting evaluation feedback from users and reflecting it in the next route generation.

[1655] "Analysis results" refer to information and conclusions drawn from collected data.

[1656] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal routes.

[1657] The "optimal route" is a route with beautiful scenery and a good driving experience, determined based on collected data and the user's preferences and ratings.

[1658] "Scenic information" refers to information about the beauty of the scenery and surrounding environment at a particular route or point.

[1659] "Surrounding environment information" is comprehensive information such as road conditions, weather, and traffic conditions at specific routes and locations.

[1660] A car navigation system according to the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on a user's spoken request. Specific embodiments of the system are described below.

[1661] System Configuration

[1662] The system consists of the following main components:

[1663] 1. Voice Recognition Method

[1664] 2. Data Collection Methods

[1665] 3. Route Generation Method

[1666] 4. Navigation Methods

[1667] 5. Feedback Collection Methods

[1668] 6. Generative AI Models

[1669] Program processing

[1670] Receiving a user's speech request

[1671] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[1672] Voice recognition and data transmission

[1673] The device converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. Voice recognition uses a highly sensitive microphone and voice capture software (e.g., a voice recognition API).

[1674] Request content analysis

[1675] The server analyzes the received text data and identifies the user's request. For example, it uses a natural language processing tool (e.g., a natural language processing API) to extract and recognize the keyword "scenic driving route."

[1676] Data collection

[1677] The server then collects the following information using data collection means:

[1678] Map information: Location information of roads and tourist spots around the destination. Uses the Map Information API.

[1679] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[1680] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[1681] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses the SNS information API.

[1682] User rating feedback and sentiment information: Collect past user ratings and sentiment information from the feedback database.

[1683] Route Generation

[1684] The server analyzes the collected data and generates multiple candidate routes. The server uses a generative AI model (e.g., AI model API) to select a route with good scenery and a good driving experience. The server also considers the user's past preferences and ratings to select the optimal route.

[1685] Route provision and navigation

[1686] The device receives the route information sent from the server and displays it to the user. It also provides audio and visual guidance along the route, navigating the user using Google Maps navigation features.

[1687] Specific examples

[1688] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[1689] 1. The device converts the voice data into text data and sends it to the server using a speech recognition API.

[1690] 2. The server analyzes the request and detects the keyword "Route with a view of Mt. Fuji." It uses a natural language processing API for the analysis.

[1691] 3. The server uses the map information API, weather information API, and SNS information API to collect map information, landscape information, and surrounding environment information, and also refers to past user feedback.

[1692] 4. The server generates the optimal route based on the collected data. Using a generative AI model, it selects the optimal route, including one with a view of Mt. Fuji.

[1693] 5. The device displays the optimal route and navigates the user with audio and visual guidance, using Google Maps.

[1694] This system allows users to enjoy a hassle-free, comfortable, and scenic drive. In this way, the present invention generates sophisticated routes based on the user's requests and ratings, providing a fulfilling driving experience.

[1695] Prompt Sentence Examples

[1696] "Please collect map information, landscape information, road conditions, positive posts on social media, and user feedback from all over Japan, and generate scenic driving routes that meet user requests. For example, please suggest the best route for a request like 'I want to drive to Hakone from a route that gives me a view of Mt. Fuji.'"

[1697] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1698] Step 1: Receiving a user's speech request

[1699] A user speaks to a car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. The device acquires the voice data using voice capture software (e.g., a voice recognition API).

[1700] Step 2: Voice recognition and data transmission

[1701] The terminal converts the captured voice data into text data using a voice recognition means and sends the converted text data to the server. The input is voice data and the output is text data. Specifically, the terminal uses a voice recognition API to send data to the server via a network module.

[1702] Step 3: Parsing the request

[1703] The server analyzes the received text data and identifies the user's request. For example, a natural language processing tool is used to extract the keyword "scenic driving route." The input is text data, and the output is the analyzed keyword. The server performs the analysis using a natural language processing API.

[1704] Step 4: Data collection

[1705] The server collects the following information using data collection methods:

[1706] Map information: Location information of roads and tourist spots around the destination. Uses map information API.

[1707] Surrounding environment information: specific road width, traffic conditions, and weather information. Uses weather information API and traffic condition API.

[1708] GPS Trip Information: Trip data for all users, including speed and number of stops, pulled from existing trip record databases.

[1709] SNS scenery information: Information on places that are considered to have beautiful scenery based on positive posts and images. Uses SNS information API.

[1710] User rating feedback and sentiment information: Past user ratings and sentiment expressions. Obtained from the feedback database.

[1711] The input is the request content, and the output is various collected data. The server collects information through each API.

[1712] Step 5: Route Generation

[1713] The server analyzes the collected data and generates multiple candidate routes. The input is the collected data, and the output is the candidate routes. The server uses a generative AI model to generate roads with beautiful scenery and a great driving experience. It also takes into account the user's past preferences and ratings to select the optimal route.

[1714] Step 6: Route provision and navigation

[1715] The device receives the determined route sent from the server and displays it to the user. It also provides audio and visual guidance along the generated route to navigate the user. The input is the determined route data, and the output is the display and audio guidance on the device. The device uses the navigation function of Google Maps.

[1716] This process allows users to find a comfortable and scenic driving route without any hassle.

[1717] (Application example 1)

[1718] 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."

[1719] Conventional car navigation systems lacked the ability to suggest routes based on user requests and provide feedback on user evaluations, making it difficult to provide routes with beautiful scenery and a comfortable driving experience. Furthermore, while autonomous vehicles are required to provide safer and more comfortable driving routes, there were limitations to achieving this. This made it difficult for users to have a satisfying driving experience.

[1720] 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.

[1721] In this invention, the server includes a voice recognition means, a data collection means for collecting geographic information, traffic information, visual information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes that are scenic and comfortable to drive, a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route, a feedback collection means for collecting evaluation feedback from the user and reflecting the feedback in the next route generation, a means for providing the generated route for the autonomous vehicle and providing visual and audio guidance, a means for optimizing the candidate route using a generative AI model, and a means for inputting prompt sentences into the generative AI model and generating the optimal route. This enables high-quality route suggestions and navigation for autonomous vehicles based on user requests, making it possible to provide a highly satisfying driving experience.

[1722] "Voice recognition means" is a technology that analyzes a user's speech and converts it into text data.

[1723] "Geographic information" refers to road and location information around the destination, as well as location information for tourist spots, etc.

[1724] "Traffic information" refers to data that includes information on the traffic conditions, passability, and traffic congestion of specific roads.

[1725] "Visual information" refers to information including images and videos of landscapes, as well as content about landscapes posted on social media.

[1726] "User emotional information" refers to information such as user ratings and emotional expressions obtained from past driving data.

[1727] "Data collection means" refers to technologies that collect geographical information, traffic information, visual information, and user emotional information.

[1728] The "route generation means" is a technology that generates candidate routes that are scenic and comfortable to drive based on collected data.

[1729] "Navigation means" refers to technology that selects the optimal route for the user from among candidate routes and navigates through it.

[1730] "Feedback collection means" refers to technology that collects user evaluations and feedback and reflects them in the next route generation.

[1731] "Means for providing routes generated for automated driving vehicles and providing visual and audio guidance" refers to technology that provides optimal routes and provides visual and audio guidance to automated driving vehicles so that they can travel safely and comfortably.

[1732] A "generative AI model" is an artificial intelligence model that analyzes data and generates optimal solutions or answers based on conditions.

[1733] A "prompt sentence" is an instruction sentence used by a generative AI model when generating a route.

[1734] To implement the present invention, a speech recognition means, a data collection means, a route generation means, a navigation means, a feedback collection means, a route provision and guidance means for an autonomous vehicle are required, and a means for generating prompt sentences to optimize candidate routes using a generative AI model.

[1735] System Configuration

[1736] The system consists of the following main components:

[1737] 1. Speech recognition means: Analyzes the user's speech and converts it into text data.

[1738] 2. Data collection methods: collect geographical information, traffic information, visual information and user emotional information.

[1739] 3. Route generation method: Analyze the collected data and generate candidate routes that are scenic and comfortable to drive.

[1740] 4. Navigation method: Select the best route for the user from the candidate routes and navigate.

[1741] 5. Feedback collection method: Collect evaluation feedback from users and reflect it in the next route generation.

[1742] 6. Route provision and guidance for autonomous vehicles: Provides generated routes to autonomous vehicles and provides visual and audio guidance.

[1743] 7. Generative AI model and prompt sentence generation means: The generative AI model is used to optimize the candidate routes, and the prompt sentence is input to generate the optimal route.

[1744] Hardware and software used

[1745] Hardware: Smartphone (including microphone, speaker, and GPS function), cloud server

[1746] software:

[1747] Google Cloud Speech-to-Text API (voice recognition)

[1748] OpenAI GPT-4 (Natural Language Analysis and Route Generation)

[1749] Node.js (server-side scripting)

[1750] Map API (geography and navigation)

[1751] Program processing

[1752] 1. Voice input and recognition:

[1753] The user speaks a request into their smartphone, such as "I want to take a scenic route to my destination."

[1754] The smartphone's microphone captures this audio and converts it into text data using the Google Cloud Speech-to-Text API.

[1755] 2. Send to server:

[1756] The text data is sent to a cloud server in real time, and the request content is analyzed.

[1757] 3. Data Collection and Analysis:

[1758] The cloud server collects geographic information, traffic information, visual information, and user emotional information using data collection means.

[1759] Based on this data, the route generation means generates a plurality of candidate routes that are scenic and comfortable to drive.

[1760] 4. Route generation and provisioning:

[1761] Based on the collected data, prompts are input into the OpenAI GPT-4 model to generate the optimal route.

[1762] For example, enter the following prompt:

[1763] The user wants to reach their destination by a scenic route. Generate a scenic route.

[1764] The generated route is provided to the autonomous vehicle from a cloud server.

[1765] 5. Navigation and Feedback:

[1766] The route is displayed on the smartphone and navigation is provided visually and audibly.

[1767] After a drive is completed, user ratings and feedback are collected and reflected in the next route generation.

[1768] Specific examples

[1769] If a user requests a drive to Hakone with a route that gives a view of Mt. Fuji, the system will:

[1770] 1. The smartphone converts the voice data into text and sends it to a cloud server.

[1771] 2. The cloud server analyzes the request and generates multiple candidates, including routes from which Mount Fuji can be seen.

[1772] 3. Select the best route based on geographic, visual, traffic, and past feedback.

[1773] 4. The optimal route will be displayed on your smartphone and navigation will begin.

[1774] In this way, the system of the present invention allows the user to easily enjoy a scenic and comfortable drive.

[1775] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1776] Step 1:

[1777] Voice Input and Recognition

[1778] Input: A user speaks a request into their smartphone: "I want to take a scenic route to my destination."

[1779] Processing: The device's microphone captures this audio data and converts it to text using the Google Cloud Speech-to-Text API.

[1780] Output: The text data generated is "I want to take a scenic road to my destination."

[1781] Step 2:

[1782] Sending to the server

[1783] Input: Text data generated by a speech recognition means.

[1784] Processing: The device sends this text data to the cloud server in real time.

[1785] Output: Text data is sent to the server.

[1786] Step 3:

[1787] Request content analysis

[1788] Input: The text data sent to the server.

[1789] Processing: The server analyzes the text data and identifies the user's request, for example, extracting keywords such as "scenic" and "destination."

[1790] Output: The analysis results clarify the user's request.

[1791] Step 4:

[1792] Data collection

[1793] Input: Search criteria based on the request content.

[1794] Processing: The server collects geographical information, traffic information, visual information, and user emotional information. Specifically, it uses map APIs, social media posts, and weather information services to collect the necessary data.

[1795] Output: Various data collected.

[1796] Step 5:

[1797] Route Generation

[1798] Input: The data collected and what you request.

[1799] Processing: The server generates an optimal route by inputting the following prompt into the OpenAI GPT-4 model: "The user wants to reach their destination by a scenic route. Please generate a route with beautiful scenery." The generative AI model outputs candidate routes.

[1800] Output: Multiple candidate routes with good scenery and comfortable driving.

[1801] Step 6:

[1802] Route Selection

[1803] Input: Multiple generated candidate routes and past user ratings and feedback.

[1804] Processing: The server compares the candidate routes with the rating data and selects the optimal route.

[1805] Output: The route that is determined to be optimal.

[1806] Step 7:

[1807] Navigation provided

[1808] Input: The selected optimal route.

[1809] Processing: The device receives this route information and provides visual and audio guidance to the user, using a map API to display the route and a text-to-speech API to provide guidance.

[1810] Output: Visual and audio guidance to the user.

[1811] Step 8:

[1812] Feedback collection

[1813] Input: User post-drive ratings and feedback.

[1814] Processing: The server collects this feedback data and stores it in a database to be used in the next route generation.

[1815] Output: Collected feedback data.

[1816] 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.

[1817] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[1818] System Configuration

[1819] The system consists of the following main components:

[1820] 1. Voice Recognition Method

[1821] 2. Data Collection Methods

[1822] 3. Route Generation Method

[1823] 4. Navigation Methods

[1824] 5. Feedback Collection Methods

[1825] 6. Emotion Engine

[1826] Program processing

[1827] Receiving a user's speech request

[1828] The user speaks to the car navigation device, saying, "Tell me about a scenic driving route." This speech is captured by the device's microphone.

[1829] Voice recognition and data transmission

[1830] The terminal converts the captured voice data into text data using a voice recognition means, and transmits the converted text data to the server.

[1831] Request content analysis

[1832] The server analyzes the received text data and identifies the user's request. For example, it extracts and recognizes keywords such as "a scenic driving route."

[1833] Data collection

[1834] The server then collects the following information using data collection means:

[1835] Map information: Location information of roads and tourist spots around the destination

[1836] Surrounding area information: specific road width, traffic conditions, weather

[1837] GPS movement information: All users' movement data, including speed and number of stops

[1838] Landscape information on social media: Information on places with beautiful scenery based on positive posts and images

[1839] User rating feedback and emotional information: Obtaining feedback and emotional expressions from past users.

[1840] emotion recognition

[1841] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. For example, it can determine whether the user is relaxed or tense from voice data. It can also infer the user's emotional state from the frequency of sudden braking and acceleration.

[1842] Route Generation

[1843] The server analyzes the collected data and emotional information to generate multiple candidate routes. This route generation method selects roads with beautiful scenery and a great driving experience, and also considers the user's past preferences, ratings, and emotional information to select the optimal route. The final route is determined using a route generation AI model.

[1844] Route provision and navigation

[1845] The device receives the determined route sent from the server, displays it to the user, and provides audio and visual guidance along the generated route to navigate the user.

[1846] Specific examples

[1847] For example, if a user requests a car navigation system to "drive to Hakone on a route that allows for a view of Mt. Fuji," the system will operate as follows:

[1848] 1. The device converts the voice data into text data and sends it to the server.

[1849] 2. The server analyzes the request and generates multiple options, including routes that allow you to see Mount Fuji.

[1850] 3. The server selects the optimal route based on map information, landscape information, surrounding environment information, emotional information, and past user feedback.

[1851] 4. The device displays the final selected route to the user and provides audio and visual navigation along the route.

[1852] In addition, the emotion engine recognizes the user's emotions during the drive and when making a request. For example, if the driver's desire to relax is recognized, the system will prioritize quieter and more scenic roads. Emotional information from previous driving experiences is also taken into account, providing the user with the most comfortable route.

[1853] This system allows users to enjoy a hassle-free, comfortable, and scenic drive.In this way, the present invention provides a fulfilling driving experience by generating an advanced route based on the user's requests, ratings, and emotional information.

[1854] The processing flow will be explained below.

[1855] Step 1:

[1856] The user speaks to the car navigation terminal, "Tell me a driving route with good scenery."

[1857] Step 2:

[1858] The device uses a microphone to capture the user's speech as audio data.

[1859] Step 3:

[1860] The terminal converts the voice data into text data using a voice recognition means. Here, the voice is analyzed using voice recognition technology to generate text data such as "Tell me about a scenic driving route."

[1861] Step 4:

[1862] The terminal sends the converted text data to the server via an HTTP request.

[1863] Step 5:

[1864] The server analyzes the received text data and identifies the user's request. For example, it extracts keywords such as "scenic driving routes" and prepares to collect appropriate information.

[1865] Step 6:

[1866] The server accesses a map information database to obtain road information around the destination and location information for tourist spots, including road width, traffic conditions, and weather information.

[1867] Step 7:

[1868] The server analyzes positive posts and images from social media and collects information on places with beautiful views, based on hashtags and location information.

[1869] Step 8:

[1870] The server analyzes the GPS movement information of all users and collects information on roads where users can comfortably drive (speed, number of stops, etc.).

[1871] Step 9:

[1872] Based on the user evaluation feedback and emotional information collected so far, the server identifies routes that have been rated as having good scenery and a good driving experience.

[1873] Step 10:

[1874] The emotion engine recognizes the user's emotional state from their speech data and driving behavior data. For example, it can determine whether the user is relaxed or tense from their voice data, and infer their emotional state from the frequency of sudden braking and acceleration.

[1875] Step 11:

[1876] The server integrates all this information and generates multiple candidate routes using a route generation method. The candidate routes are evaluated based on factors such as scenic beauty, road width, safety, and driving comfort.

[1877] Step 12:

[1878] The server selects the optimal route from the generated candidate routes based on the user's emotional state and past preferences and ratings.

[1879] Step 13:

[1880] The server uses the route generation AI model to make final adjustments and send the finalized route to the device.

[1881] Step 14:

[1882] The device then displays the received route information to the user, displaying a map and route on the screen to provide visual guidance to the user.

[1883] Step 15:

[1884] The device will then begin voice guidance and guide the user along the generated driving route, providing specific instructions such as "Turn left at the next intersection."

[1885] Step 16:

[1886] After the drive is complete, the device prompts the user for feedback, for example, asking, "How did you like the route?"

[1887] Step 17:

[1888] The user inputs feedback, such as "It felt really good" or "I'd like to pass through places with better scenery."

[1889] Step 18:

[1890] The device sends the input feedback to the server via an HTTP request.

[1891] Step 19:

[1892] The server analyzes the received feedback and stores it in a database as new data, which is then used for subsequent route generation.

[1893] This way, users can enjoy a hassle-free, comfortable and scenic drive, and the system will continue to evolve based on their feedback.

[1894] Example 2

[1895] 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."

[1896] Conventional car navigation systems have difficulty proposing routes based on the user's emotions and preferences, and often simply provide the shortest or fastest route. Furthermore, data collection and analysis to find scenic routes are insufficient, making it difficult to provide users with a satisfying driving experience. Furthermore, previous systems lacked a mechanism for utilizing user feedback and emotional information when generating the next route.

[1897] 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.

[1898] In this invention, the server includes: a speech recognition means for analyzing a user's speech and proposing a route suitable for driving; a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information; a route generation means for analyzing the collected data and generating candidate routes with beautiful landscapes and a good driving experience; a navigation means for selecting an optimal route for the user from the candidate routes and navigating the route; a feedback collection means for collecting evaluation feedback from the user and reflecting this in the next route generation; an emotion recognition means for analyzing the user's speech and driving behavior data to recognize the user's emotional state and reflecting this in route selection; and a route generation AI model that includes an artificial intelligence model used for route generation and uses prompt sentences as input to generate the optimal route. This enables advanced route suggestions based on the user's emotions and preferences, providing a fulfilling driving experience.

[1899] A "voice recognition means" is a device or system that analyzes a user's speech and converts it into text data.

[1900] The "data collection means" is a device or system that collects map information, surrounding environment information, landscape information, and user emotion information.

[1901] The "route generation means" is a device or system that analyzes collected data and generates candidate routes that offer beautiful scenery and a pleasant driving experience.

[1902] A "navigation means" is a device or system that selects the most suitable route for a user from among candidate routes and navigates the user.

[1903] The "feedback collection means" is a device or system that collects evaluation feedback from users and reflects it in the next route generation.

[1904] An "emotion recognition means" is a device or system that analyzes the user's speech and driving behavior data to recognize their emotional state and reflects this in route selection.

[1905] A "route generation AI model" is an artificial intelligence model used for route generation, which uses prompt sentences as input to generate the optimal route.

[1906] The car navigation system of the present invention is a system that provides a driving route to a destination that has beautiful scenery and a pleasant driving experience based on the user's verbal request. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and proposes the optimal route accordingly.

[1907] System Configuration

[1908] The system consists of the following main components:

[1909] 1. Voice Recognition Method

[1910] 2. Data Collection Methods

[1911] 3. Route Generation Method

[1912] 4. Navigation Methods

[1913] 5. Feedback Collection Methods

[1914] 6. Emotion recognition means

[1915] 7. Route Generation AI Model

[1916] Voice recognition means

[1917] The device is equipped with a microphone to capture the user's speech. The captured voice data is converted into text data by speech recognition software (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text), and the converted text data is sent to a server.

[1918] Data collection methods

[1919] The server uses various APIs (e.g., Google Maps API for map information, Increment P's traffic information API for traffic information, Weather Underground's weather API for weather information, Twitter API and Instagram Graph API for social media information) to collect map information around the destination, road width, traffic conditions, weather, GPS movement information, SNS landscape information, and past user evaluation feedback and sentiment information.

[1920] Route Generation Method

[1921] Based on the information collected by the data collection method, the server uses Dijkstra's algorithm, A-search algorithm, and a personalized model using deep learning to generate multiple candidate routes that offer beautiful scenery and a comfortable ride. It then uses a route generation AI model to select the optimal route, taking into account the user's past preferences, ratings, and emotional information. Finally, it determines the optimal route for the user.

[1922] Navigation methods

[1923] The device receives the confirmed route sent from the server. The route information is displayed on the screen and voice guidance is provided to navigate the user. Specifically, an interface similar to the navigation function of Google Maps is used to display the next intersection and the distance to the destination on the screen. Voice guidance is also provided to give instructions such as "Turn left at the next intersection."

[1924] Feedback collection methods

[1925] The device collects user feedback and sends it to the server, which uses this feedback information to generate the next route.

[1926] emotion recognition means

[1927] The emotion engine analyzes the user's speech and driving behavior data to recognize the user's emotional state. Specifically, it uses the Microsoft Azure Emotion API and Face++ emotion recognition API to analyze the tone and rhythm of the user's voice to determine whether they are relaxed or tense. It also estimates their stress level based on the frequency of sudden braking and acceleration while driving.

[1928] Route generation AI model

[1929] The route generation AI model uses prompts based on collected data to generate optimal routes, allowing for advanced route suggestions based on user sentiment and preferences.

[1930] Specific examples

[1931] For example, if a user requests a drive to Hakone with a route that allows for a view of Mt. Fuji, the system operates as follows:

[1932] 1. The device converts the voice data into text data using the Google Cloud Speech-to-Text API and sends it to the server.

[1933] 2. The server analyzes the received text data using the BERT model and extracts "Routes to see Mt. Fuji" and "To Hakone."

[1934] 3. The server obtains road information around Mount Fuji from the Google Maps API and also collects landscape and traffic information from social media.

[1935] 4. The emotion engine recognizes from the user's tone of voice that they want to relax and prioritizes quieter, more scenic routes.

[1936] 5. The route generation AI model inputs emotional and landscape information into Dijkstra's algorithm to generate the optimal route.

[1937] 6. The device displays the determined route to the user and provides voice navigation.

[1938] Prompt Sentence Examples

[1939] Example prompts fed to a generative AI model:

[1940] "A user has requested a drive to Hakone with a route that allows for a view of Mt. Fuji. Generate the optimal route using the following information:

[1941] Map information: Roads around Mt. Fuji and Hakone location information

[1942] Landscape information on social media: Posts of places where Mount Fuji is said to be visible

[1943] Surrounding environment information: traffic conditions, weather, road width

[1944] User feedback: Evaluation information on routes that have been moderately relaxing in the past

[1945] Emotional information: the user's current level of relaxation

[1946] In this way, the system generates an advanced route that combines the user's voice request and emotional state, providing a scenic and comfortable driving experience.

[1947] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1948] Step 1:

[1949] The user issues a voice request to the car navigation device, such as "Tell me about a scenic driving route." This request is captured by the device's microphone. The input is the user's voice data, and the output is the captured voice data. Specifically, the user speaks into the microphone of the head unit or smartphone app.

[1950] Step 2:

[1951] The device converts the captured voice data into text data in real time using the Google Cloud Speech-to-Text API. The input is the captured voice data, and the output is text data generated by speech recognition. Specifically, the device sends the voice data to the API and stores the returned text data in an internal buffer.

[1952] Step 3:

[1953] The terminal sends text data to the server. The input is the text data, and the output is the status of completion of transmission. In concrete terms, the terminal sends data to the server via the network.

[1954] Step 4:

[1955] The server analyzes the received text data using the BERT model to identify the user's request. The input is text data, and the output is the analyzed request information (e.g., "Scenic driving route"). Specifically, the server runs an NLP (natural language processing) algorithm to extract keywords and the intent of the request from the text data.

[1956] Step 5:

[1957] The server uses data collection methods to collect the following information: map information from the Google Maps API, surrounding environment information from a traffic information service, weather information from Weather Underground's weather API, and social media information from the Twitter API and Instagram Graph API. The input is the request information, and the output is the various collected information data. Specifically, the server calls the various APIs, obtains the necessary information from each data source, and stores it.

[1958] Step 6:

[1959] The server uses an emotion engine to analyze the user's speech and driving behavior data to recognize the user's emotional state. The input is the user's text data and behavioral data, and the output is the user's emotional state data. Specifically, the server sends the acquired data to the Microsoft Azure Emotion API or Face++ emotion recognition API to determine the emotional state.

[1960] Step 7:

[1961] The server integrates the collected data and emotional information to generate multiple candidate routes using a route generation AI model. The input is the aggregated data and emotional information, and the output is multiple candidate routes. Specifically, the server inputs the data into Dijkstra's algorithm and A-search algorithm to generate candidate routes.

[1962] Step 8:

[1963] The server selects the optimal route from the candidate routes and provides it to the user. The input is multiple candidate routes, and the output is the optimal route. Specifically, the server calculates the optimal route by taking into account the user's past feedback, evaluation, and emotional state.

[1964] Step 9:

[1965] The terminal receives the optimal route sent from the server and displays it to the user. The input is the optimal route, and the output is the display on the user interface and voice guidance. In concrete terms, the terminal displays the route on the screen and provides voice navigation instructions.

[1966] Step 10:

[1967] After the trip, the device receives user feedback and sends it to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. Specifically, the device allows the user to input the evaluation through the user interface and sends it to the server via the network.

[1968] Step 11:

[1969] The server analyzes the received feedback and reflects it in the next route generation. The input is the feedback data, and the output is an updated evaluation database. Specifically, the server analyzes the feedback information and stores it in the database for use in the next route generation algorithm.

[1970] (Application example 2)

[1971] 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."

[1972] Conventional car navigation systems primarily focus on suggesting the shortest or fastest route, making it difficult to propose routes that take into account the user's emotions and scenic preferences. In particular, autonomous vehicles are required to provide routes that not only transport users to their destination but also adapt to the user's comfort and emotional state. To meet these requirements, it is necessary to collect and analyze user emotional information and generate an optimal route based on this information. However, there is still a lack of technology that utilizes user utterances and feedback in real time to propose routes that correspond to the user's emotional state. Therefore, there is a need for the development of a system that allows users to enjoy a comfortable and scenic drive without hassle.

[1973] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1974] In this invention, the server includes a speech recognition means for analyzing a user's speech and proposing a route suitable for driving, a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information, a route generation means for analyzing the collected data and generating candidate routes with good scenery and a good driving experience, a navigation means for selecting an optimal route for the user from the candidate routes and controlling the autonomous vehicle, a feedback collection means for collecting evaluation feedback from the user and reflecting it in the next route generation, and an emotion engine for analyzing the user's emotions and optimizing navigation based on the analysis results. This makes it possible to provide a comfortable and scenic driving route that takes the user's emotional state into consideration.

[1975] "Speech recognition means" refers to a device or software that analyzes a user's speech, converts it into text data, and understands its content.

[1976] "Data collection means" refers to a device or software for collecting map information, surrounding environment information, landscape information, and user emotion information.

[1977] The "route generation means" is a device or software that analyzes collected data and generates candidate routes that offer good scenery and a pleasant driving experience.

[1978] "Navigation means" refers to a device or software that selects the optimal route for the user from among candidate routes and controls the autonomous vehicle.

[1979] The "feedback collection means" is a device or software that collects evaluation feedback from users and reflects it in the next route generation.

[1980] An "emotion engine" is a device or software that analyzes a user's emotions and optimizes navigation based on the analysis results.

[1981] This invention is a system for proposing an optimal driving route for an autonomous vehicle based on the user's speech and emotional information. The configuration and operation of this system are described in detail below.

[1982] System configuration

[1983] The system consists of the following main components:

[1984] 1. Voice Recognition Method

[1985] 2. Data Collection Methods

[1986] 3. Route Generation Method

[1987] 4. Navigation Methods

[1988] 5. Feedback Collection Methods

[1989] 6. Emotion Engine

[1990] Hardware and software used

[1991] 1. Voice Recognition Method

[1992] Hardware: Microphones in autonomous vehicles

[1993] Software: speech_recognition package, speech recognition API

[1994] 2. Data Collection Methods

[1995] Hardware: Vehicle sensors (GPS, camera)

[1996] Software: Map information API, surrounding environment information API, SNS analysis software

[1997] 3. Route Generation Method

[1998] Software: Route generation AI model

[1999] 4. Navigation Methods

[2000] Hardware: Vehicle control system

[2001] Software: Navigation software

[2002] 5. Feedback Collection Methods

[2003] Software: Feedback Management Software

[2004] 6. Emotion Engine

[2005] Software: Sentiment analysis software

[2006] How it works

[2007] First, the user speaks from inside the vehicle, saying, "Tell me about a driving route along the Shonan coast." This speech is converted into text data by a speech recognition means. Next, a data collection means collects map information, surrounding environment information, landscape information, and user emotion information. For example, the scenery of a specific coastline and traffic conditions are acquired in conjunction with GPS.

[2008] The route generator analyzes the collected data and generates multiple candidate routes based on the user's request. The emotion engine analyzes the user's speech and past feedback to recommend the most suitable route. For example, if the emotion of wanting to relax is recognized, a quiet and scenic route will be prioritized.

[2009] The generated route is sent to the autonomous vehicle's control system by the navigation means. The vehicle drives according to the navigation and is provided with audio and visual guidance. At the same time, after the drive is completed, the feedback collection means collects evaluation feedback from the user and reflects it in the next route generation.

[2010] Examples of concrete examples and prompts

[2011] For example, if a user requests a smartphone app to "tell me about a driving route along the Shonan coast," the request is converted into text data using voice recognition. If the app then recognizes that the user is feeling relaxed, it will recommend a quiet route along the coast.

[2012] Examples of prompt sentences include:

[2013] User utterance: "Tell me about a driving route along the Shonan coast."

[2014] Emotional state: "Relaxed"

[2015] Recommended route: "Prefer quiet coastal roads"

[2016] In this way, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[2017] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2018] Step 1:

[2019] The user speaks to the system, "Tell me about a driving course along the Shonan coast."

[2020] Input: User utterance

[2021] Output: Audio data

[2022] Step 2:

[2023] The terminal captures the user's voice data through a microphone and converts it into text data using a voice recognition means.

[2024] Input: Audio data

[2025] Output: Text data

[2026] How it works: The device's microphone captures audio, and a speech recognition API (e.g., speech_recognition package) converts the audio data into text data.

[2027] Step 3:

[2028] The server receives the text data and analyzes the request. For example, it extracts keywords such as "Driving courses along the Shonan coast."

[2029] Input: Text data

[2030] Output: Request content (keywords)

[2031] How it works: The server analyzes the text data and uses natural language processing to determine the user's intent.

[2032] Step 4:

[2033] The server uses the data collection means to collect map information, surrounding environment information, landscape information, and user emotion information.

[2034] Input: Request content (keywords)

[2035] Output: Map information, surrounding environment information, landscape information, emotion information

[2036] How it works: The server collects relevant data using multiple APIs (e.g., map information API, environmental information API, SNS analysis software).

[2037] Step 5:

[2038] The server uses an emotion engine to analyze the user's emotions, for example, by using voice data and past feedback to determine whether the user is relaxed.

[2039] Input: Voice data, past feedback

[2040] Output: User's emotional state

[2041] How it works: Emotion analysis software analyzes the user's voice tone and past driving behavior data to identify their emotional state.

[2042] Step 6:

[2043] The server uses a route generation means to analyze the collected data and the user's emotion information and generate a plurality of candidate routes.

[2044] Input: Map information, surrounding environment information, landscape information, emotional information

[2045] Output: candidate routes

[2046] How it works: A route generation AI model combines each piece of data and generates multiple candidate routes.

[2047] Step 7:

[2048] The server selects the route that best suits the user's emotional state and request content from the candidate routes.

[2049] Input: candidate routes, user's emotional state, request content

[2050] Output: Optimal route

[2051] Operation: The server evaluates the generated routes based on their scenery and driving experience, and selects the optimal route.

[2052] Step 8:

[2053] The terminal receives the optimal route and transmits it to the autonomous vehicle's control system.

[2054] Input: Optimal Route

[2055] Output: Vehicle control signal

[2056] How it works: Navigation software sends the optimal route to the autonomous vehicle's control system, which then controls the vehicle.

[2057] Step 9:

[2058] The terminal navigates while providing audio and visual guidance to the user.

[2059] Input: control signal, optimal route

[2060] Output: Audio guidance, visual guidance

[2061] How it works: The device uses the vehicle's display and speaker to provide navigation instructions to the user.

[2062] Step 10:

[2063] The server collects user evaluation feedback after each trip and reflects it in the next route generation.

[2064] Input: User rating feedback

[2065] Output: Updated feedback data

[2066] How it works: The feedback collection tool stores user ratings in a database and uses them for analysis.

[2067] Through the above steps, it is possible to provide a comfortable and scenic driving route that takes into account the user's emotional state.

[2068] 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.

[2069] 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.

[2070] 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.

[2071] 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.

[2072] 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.

[2073] 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.

[2074] 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).

[2075] 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.

[2076] 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."

[2077] 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.

[2078] 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).

[2079] 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.

[2080] 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.

[2081] 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.

[2082] 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.

[2083] 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.

[2084] 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.

[2085] 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.

[2086] 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.

[2087] 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.

[2088] 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.

[2089] The following is further disclosed regarding the above embodiment.

[2090] (Claim 1)

[2091] A voice recognition system that analyzes the user's speech and suggests suitable routes for driving.

[2092] a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information;

[2093] a route generation means for analyzing the collected data and generating candidate routes that have beautiful scenery and a good driving experience;

[2094] A navigation means for selecting the optimal route for the user from among candidate routes and navigating the route;

[2095] A feedback collection means for collecting evaluation feedback from users and reflecting it in the next route generation;

[2096] A system including:

[2097] (Claim 2)

[2098] 10. The system of claim 1, further comprising means for optimizing the candidate routes based on user preferences and past rating feedback.

[2099] (Claim 3)

[2100] 10. The system of claim 1, wherein the navigation means includes means for providing audio and visual directions.

[2101] "Example 1"

[2102] (Claim 1)

[2103] A voice recognition system that analyzes the user's speech and suggests suitable routes for driving.

[2104] a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information;

[2105] a route generation means for analyzing the collected data and generating candidate routes that have beautiful scenery and a good driving experience;

[2106] A navigation means for selecting the optimal route for the user from among candidate routes and navigating the route;

[2107] A feedback collection means for collecting evaluation feedback from users and reflecting it in the next route generation;

[2108] A means of generating multiple candidate routes based on the analysis results and determining the optimal route using a generative AI model;

[2109] A system including:

[2110] (Claim 2)

[2111] 10. The system of claim 1, further comprising means for optimizing the candidate routes based on user preferences and past rating feedback.

[2112] (Claim 3)

[2113] 10. The system of claim 1, wherein the navigation means includes means for providing audio and visual directions.

[2114] "Application Example 1"

[2115] (Claim 1)

[2116] A voice recognition system that analyzes the user's speech and suggests suitable routes for driving.

[2117] a data collection means for collecting geographic information, traffic information, visual information, and user emotion information;

[2118] a route generation means for analyzing the collected data and generating candidate routes that are scenic and comfortable to drive;

[2119] A navigation means for selecting the optimal route for the user from among candidate routes and navigating the route;

[2120] A feedback collection means for collecting evaluation feedback from users and reflecting it in the next route generation;

[2121] means for providing generated routes and visual and audio guidance for the automated vehicle;

[2122] a means for optimizing candidate routes using a generative AI model; and

[2123] A means for inputting the prompt sentence into a generative AI model to generate an optimal route;

[2124] A system including:

[2125] (Claim 2)

[2126] 10. The system of claim 1, further comprising means for optimizing the candidate routes based on user preferences and past rating feedback.

[2127] (Claim 3)

[2128] The system of claim 1 , wherein the navigation means includes means for providing visual and audio directions.

[2129] "Example 2: Combining Emotion Engines"

[2130] (Claim 1)

[2131] A voice recognition system that analyzes the user's speech and suggests suitable routes for driving.

[2132] a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information;

[2133] a route generation means for analyzing the collected data and generating candidate routes that have beautiful scenery and a good driving experience;

[2134] A navigation means for selecting the optimal route for the user from among candidate routes and navigating the route;

[2135] A feedback collection means for collecting evaluation feedback from users and reflecting it in the next route generation;

[2136] An emotion recognition means that analyzes the user's speech and driving behavior data to recognize their emotional state and reflects this in route selection;

[2137] a route generation AI model including an artificial intelligence model used for route generation, the route generation AI model using a prompt sentence as input to generate an optimal route;

[2138] A system including:

[2139] (Claim 2)

[2140] 10. The system of claim 1, further comprising means for optimizing the candidate routes based on user preferences and past rating feedback.

[2141] (Claim 3)

[2142] 10. The system of claim 1, wherein the navigation means includes means for providing audio and visual directions.

[2143] "Application example 2 when combining emotion engines"

[2144] (Claim 1)

[2145] A voice recognition system that analyzes the user's speech and suggests suitable routes for driving.

[2146] a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information;

[2147] a route generation means for analyzing the collected data and generating candidate routes that have beautiful scenery and a good driving experience;

[2148] a navigation means for selecting an optimal route for a user from among candidate routes and controlling the autonomous vehicle;

[2149] A feedback collection means for collecting evaluation feedback from users and reflecting it in the next route generation;

[2150] An emotion engine that analyzes user emotions and optimizes navigation based on the analysis results;

[2151] A system including:

[2152] (Claim 2)

[2153] 10. The system of claim 1, further comprising means for optimizing the candidate routes based on user preferences and past rating feedback.

[2154] (Claim 3)

[2155] 10. The system of claim 1, wherein the navigation means includes means for providing audio and visual directions. [Explanation of symbols]

[2156] 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 voice recognition system that analyzes the user's speech and suggests suitable routes for driving. a data collection means for collecting map information, surrounding environment information, landscape information, and user emotion information; a route generation means for analyzing the collected data and generating candidate routes that have beautiful scenery and a good driving experience; A navigation means for selecting the optimal route for the user from among candidate routes and navigating the route; A feedback collection means for collecting evaluation feedback from users and reflecting it in the next route generation; A system including:

2. The system of claim 1 , further comprising means for optimizing the candidate routes based on user preferences and past rating feedback.

3. The system of claim 1 , wherein the navigation means includes means for providing audio and visual directions.

Images