system

Abstract

The system aims to reduce the complexity of route selection and support driver decision-making by presenting users with appropriate and easy-to-understand directions. [Solution] A system comprising: data collection means for acquiring driving behavior data; route analysis means for analyzing the characteristics of multiple routes using generation technology; route selection means for selecting the optimal route based on the user's past behavior patterns; explanation generation means for generating an easy-to-understand explanation based on the selected route; explanation presentation means for presenting the explanation to the user; and learning means for training the generation technology based on the user's route selection results.

Description

Technical Field

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

Background Art

[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 an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When driving an automobile, there is a problem that it is difficult to select a road that meets the user's wishes from a plurality of routes provided by an in-vehicle navigation system. In particular, it takes time to determine a route that the user usually uses or wants to select based on past experience, which may impair the driving efficiency and safety. The object of this invention is to reduce the complexity of route selection and support the driver's decision-making by presenting an appropriate and easy-to-understand driving route to the user.

Means for Solving the Problems

[0005] This invention provides a method for acquiring driving behavior data and analyzing the characteristics of multiple routes using generation technology. Furthermore, it selects the optimal route based on the user's past behavior patterns and generates an easy-to-understand explanation based on the selected route. This makes the route information presented to the user more familiar, including frequently seen landmarks, thereby optimizing the user's route selection. In addition, by training the generation technology based on the user's route selection results and further improving its accuracy, a system is built that continuously improves user satisfaction.

[0006] "Driving behavior" refers to a series of activities and patterns related to the actions and decision-making involved when a driver operates a vehicle.

[0007] "Data collection means" refers to a device or method for automatically acquiring, storing, or analyzing various types of information related to driving behavior.

[0008] "Generative technology" refers to technology that uses artificial intelligence to process data and generate results or information suitable for a specific purpose.

[0009] "Route analysis means" refers to a device or method for analyzing acquired route information and understanding its characteristics.

[0010] "Route selection means" refers to a device or method for selecting the optimal route based on the user's past behavioral patterns and preferences.

[0011] "Explanation generation means" refers to a device or method for creating an explanation that is easy for the user to understand for a selected route.

[0012] "Explanation presentation means" refers to a device or method for presenting a generated route explanation to the user.

[0013] "Learning means" refers to a device or method for improving the performance and accuracy of generation technology by utilizing feedback obtained from users. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The present invention provides a system to support drivers in selecting an appropriate route. The system comprises the following components: data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, and learning means.

[0036] First, the server collects data from the in-car navigation system and dashcam. This data includes the driver's current location, destination, and past driving routes, allowing the system to understand driving behavior trends. This information is used as foundational data for analyzing the user's preferences and behavioral patterns.

[0037] Next, the terminal uses generation technology to analyze the collected data and identify multiple routes. Here, route analysis is used to extract the characteristics of each route (e.g., distance, traffic volume, landmarks passed through, etc.). This route information is then used to select the optimal route by comparing it with the user's behavioral patterns, such as what routes the user has chosen in the past and which landmarks they recognize.

[0038] The server then generates a driver-friendly explanation based on the selected route. The explanation generation system uses generation technology to create a specific route, including frequently seen landmarks and intersections. For example, an explanation might be created that includes specific instructions such as, "After passing the park on your right, turn left at the next traffic light."

[0039] Users receive this explanation, which is presented in an easy-to-understand format, allowing them to choose the most suitable route from the available options. This enables more efficient and stress-free driving, while taking into account the user's preferences and familiar routes.

[0040] Finally, the terminal sends the route selected by the user and its results to the server, and the learning mechanism improves the accuracy of the generation technique with past feedback. This feedback loop allows the system to continuously evolve to better suit the user's needs.

[0041] This system allows drivers to receive optimal navigation tailored to their preferences, and the system's adaptive capabilities continuously improve through learning mechanisms.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server retrieves driver location information, destination information, and past driving route data from the in-car navigation system and dashcam. This data is used as basic information to analyze the user's past behavior patterns and preferences.

[0045] Step 2:

[0046] The terminal collects the acquired data and analyzes it using generation technology. This analysis identifies the characteristics of multiple routes, taking into account the driver's preferences, and extracts the distance, traffic conditions, and landmarks passed through each route.

[0047] Step 3:

[0048] Based on the route analysis results, the server selects the optimal route from multiple options, taking into account route patterns previously chosen by the driver and preferred landmarks.

[0049] Step 4:

[0050] The server generates easy-to-understand instructions for the driver based on the selected route. The generating AI creates specific directions that include frequently seen landmarks and facilities, providing clear instructions such as, "Turn right at the next corner where there is a convenience store on your right."

[0051] Step 5:

[0052] The user receives route instructions sent from the server via their device. Based on the instructions provided, the user can choose the most suitable route.

[0053] Step 6:

[0054] The terminal sends information about the route selected by the user to the server and also provides the route selection result as feedback.

[0055] Step 7:

[0056] The server utilizes the collected feedback and uses learning mechanisms to improve the accuracy of its generation technology. This process is carried out to improve the system so that future route suggestions better match the user's preferences.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] There is a problem in that drivers have difficulty selecting the optimal route based on their own preferences and behavioral patterns. Furthermore, in order to improve the accuracy of route selection, it is necessary to learn from the driver's past choices and effectively utilize feedback.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes an information gathering means for acquiring information related to driving, a route analysis means for analyzing the attributes of multiple routes using generative artificial intelligence technology, and a route selection means for selecting the optimal route based on the user's past behavior patterns. This enables the efficient and appropriate presentation of routes according to the driver's preferences and continuous improvement of the system's accuracy.

[0062] "Information gathering means" refers to means of acquiring information related to driving, and includes devices or systems that collect data from in-vehicle navigation systems, dashcams, etc.

[0063] "Generative artificial intelligence technology" is a technology that generates new information and options based on past data and learning, and is an algorithm used for optimizing routes and generating explanatory texts.

[0064] A "route analysis means" is a method for analyzing the attributes of multiple routes using generative artificial intelligence technology, and is a system that evaluates and analyzes the distance, traffic volume, and other attributes of the routes.

[0065] A "route selection method" is a means for selecting the optimal route based on the user's past behavior patterns, and is a process for selecting a route that takes into account the user's preferences and past choices.

[0066] An "information generation means" is a system that generates easy-to-understand explanations based on a selected route, and creates specific instructions including landmarks and intersections.

[0067] An "information presentation means" is a means of providing the generated explanation to the user, and is an interface for presenting information through screen display or sound.

[0068] "Educational tools" refer to methods for training generative artificial intelligence technology based on the user's choices and a mechanism for continuously improving the system using feedback.

[0069] This invention is an information processing device that provides drivers with efficient and personalized route selection. Specifically, it consists of three components: a server, a terminal, and a user.

[0070] The server collects driving-related data from the in-vehicle navigation system and dashcam. Through this data collection, the driver's current location, destination, past driving route data, and road conditions are obtained. This data is stored in the server's storage and used for subsequent route analysis.

[0071] The terminal performs route analysis and selection using data received from the server. This is where generative artificial intelligence technology is utilized. The generative AI model generates numerous route options based on the received data and analyzes their characteristics. This process considers factors such as the distance of each route, traffic conditions, and the location of landmarks. For example, a possible prompt to the generative AI model might be, "Consider the driver's past routes and generate an efficient route."

[0072] Next, the server generates a visually easy-to-understand explanation based on the optimal route analyzed and selected by the generating AI model. By using the information generation means, specific instructions including landmarks and intersections are created. For example, navigation such as "After passing landmark A on your right, turn left at the second traffic light" is possible.

[0073] The user receives instructions from the terminal and begins driving accordingly. Information is provided through screen displays and voice guidance, allowing for safe and quick access to information even while driving.

[0074] Finally, the user's selected route and its results are sent from the terminal to the server. This feedback is used to train the generative artificial intelligence technology through educational means, improving the accuracy of future route selections. Through this continuous learning process, the system continues to evolve to meet the driver's preferences and needs.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects driving-related data from the in-vehicle navigation system and dashcam. Inputs include the driver's location, destination, road conditions, and past driving records. This data is stored in the server's storage for analysis. Specifically, the server periodically inputs data via a communication module and stores it in a database.

[0078] Step 2:

[0079] The terminal uses data obtained from the server to apply a generative AI model and perform route analysis. The input is driving-related data received from the server, and the output is multiple route options tailored to the driver's preferences and past behavior patterns. Specifically, the terminal inputs prompt messages to the generative AI model, for example, "Consider the driver's past routes and generate an efficient route," and obtains the analysis results.

[0080] Step 3:

[0081] The server receives route analysis results from the terminal and selects the optimal route. The input is multiple route options, and the output is the selected optimal route. The server scores factors such as route distance, traffic volume, and landmarks passed through, and selects the most appropriate route based on these scores. Specifically, the server uses a selection algorithm to score routes and outputs the route with the highest score.

[0082] Step 4:

[0083] The server generates instructions for the driver based on the selected optimal route. The input is the selected route, and the output is an easy-to-understand explanation presented to the driver. Specifically, the server uses a generation AI to create detailed navigation, including visual landmarks such as intersections.

[0084] Step 5:

[0085] The user receives instructions from the server via a terminal and then begins driving. The input is the instructional text from the server, and the output is the result of the user's route selection. In terms of specific actions, the user checks the terminal's screen display and voice guidance and proceeds with driving according to the instructions.

[0086] Step 6:

[0087] The terminal sends the user's route selection results and feedback after the drive to the server. The input is the user's feedback data, and the output is the training data for the generated AI model. Specifically, the terminal analyzes the received feedback and sends it to the server to improve the model's accuracy.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In autonomous vehicles, there is a challenge in selecting the optimal route based on the individual behavior patterns of the user. In particular, there is a need to propose an effective route that takes into account the user's preferences and past choices, while also responding to real-time, fluctuating traffic conditions. Furthermore, efficiently reflecting this route information in the autonomous vehicle is also a challenge.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes information gathering means for acquiring information on driving behavior, route analysis means for analyzing the characteristics of multiple routes using generation technology, route selection means for selecting an optimal route based on the user's past behavioral tendencies, instruction generation means for generating clear instructions based on the selected route, instruction presentation means for presenting the instructions to the user, and communication means for providing route instructions to the automated vehicle. This makes it possible to select an optimal route that takes into account the user's preferences and real-time traffic conditions, and to quickly reflect that information in the automated vehicle.

[0093] "Information on driving behavior" refers to records of driving operations performed by the vehicle driver and their results.

[0094] "Information gathering means" refers to means that have the function of acquiring information on driving behavior and accumulating it as data.

[0095] "Generative technology" is a concept that refers to algorithms and methods for processing large amounts of data to generate new information.

[0096] A "route analysis means" is a means for analyzing the characteristics of acquired route data.

[0097] "Behavioral tendencies" refer to characteristics related to the driving patterns and preferences that the user has chosen in the past.

[0098] A "route selection method" is a means of identifying the optimal route based on the user's behavioral tendencies.

[0099] "Instruction generation means" refers to a means for presenting a clear route to the user based on the optimal path.

[0100] A "means for presenting instructions" is a means of communicating generated instructions to the driver or system.

[0101] "Communication means" refers to communication protocols and devices used to transmit generated route instructions to an automated mobile vehicle.

[0102] The term "autonomous mobile device" refers to a machine that moves while making its own decisions based on external instructions.

[0103] The system for realizing this invention aims to generate and present the optimal route based on driver behavior data. Here, the server plays a central role, integrating information gathering means, generation technology, instruction generation and presentation, and communication means.

[0104] The server first acquires information on driving behavior transmitted from on-board sensors through information gathering means. This information includes the driver's current location, destination, and past driving routes, and is used for trend analysis of driving patterns.

[0105] Next, the server uses generation technology to perform route analysis based on the data obtained by the information gathering means. The analyzed data reveals the characteristics of multiple routes (e.g., distance, average speed, reference points passed through, etc.) and is used for evaluation by the route selection means and for selecting the optimal route.

[0106] The optimal route selected by the route selection means is converted into specific travel instructions by the instruction generation means. In this process, reference points frequently seen by the user are included in the instructions, presenting them in a clear and easy-to-understand manner for the driver.

[0107] Instructions based on the selected route are transmitted in real time to the control system of the automated vehicle using communication means installed on the vehicle. This allows the automated vehicle to operate smoothly according to the proposed optimal route.

[0108] A specific example of the present invention is a situation in which, during commuting hours, an optimal route is proposed that avoids traffic congestion while utilizing scenic roads preferred by the driver. In this case, the generating AI model considers prompt statements such as, "For this week's commute, please tell me your usual route with minimal traffic congestion. I would like a route that also passes through parks and scenic spots," and generates individually optimized instructions.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server uses data collection tools to acquire information about driving behavior from on-board sensors. Inputs include the driver's location and destination, while output is an aggregation of this data. This information is used as foundational data for analyzing driving pattern trends.

[0112] Step 2:

[0113] The server analyzes the input driving data using generation technology. This analysis process evaluates the characteristics of multiple routes, including distance, speed, and reference points. Data calculations output an evaluation score for each route, revealing the driver's past behavioral tendencies.

[0114] Step 3:

[0115] The server uses a route selection mechanism to select the optimal route based on the analysis results. The input is data from multiple evaluated routes, and the output is information on the selected optimal route. This selection process takes into account past user preferences and traffic conditions.

[0116] Step 4:

[0117] The server generates specific travel instructions based on the selected optimal route using an instruction generation mechanism. The input is information about the optimal route, and the output includes detailed instructions, such as "Turn left at the next intersection." These instructions are easy for the driver to understand intuitively because they highlight reference points that the user frequently sees.

[0118] Step 5:

[0119] The server transmits the generated instructions to the driver and the control system of the automated vehicle through the instruction presentation means. The output is navigation information presented in visual and audible formats. This allows the driver to move safely and comfortably based on the received instructions.

[0120] Step 6:

[0121] The user returns the route selection results to the server as feedback. The feedback inputs include the results of the selected route and the driver's satisfaction level. The server uses this information as a learning tool to update the generative AI model. The output is an improved route selection algorithm, which improves the accuracy of future route suggestions.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention aims to realize a system that enables more accurate route selection and explanation provision by combining an emotion engine with a driver assistance system. The system comprises data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, learning means, and an emotion engine.

[0124] First, the server acquires the driver's location, destination information, and past driving route data from the in-car navigation system and dashcam. In addition, the emotion engine recognizes the driver's emotional state using facial expressions, tone of voice, and other biosensor data, and collects this information as foundational data used throughout the system.

[0125] Next, the terminal collects data and analyzes it using generation technology. Route analysis means support this, identifying the characteristics of each route and extracting the conditions for each route (distance, traffic volume, landmarks, etc.). Furthermore, using emotional information obtained from the emotion engine, route selection is performed to match the driver's stress level and mood.

[0126] Subsequently, the server uses the analysis results and route selection methods to determine the optimal route, taking into account patterns and preferences from previously selected routes. It adjusts the selection results according to the emotion engine data, selecting routes and landmarks to reduce stress.

[0127] Based on the selection results, the server uses an explanation generation mechanism to create a specific route. The generating AI produces an easy-to-understand route explanation that includes specific instructions, making it possible to provide explanations that take into account the driver's mental state, such as "Turn left at the next corner in front of the building with the humorous advertisement."

[0128] The user receives this route description on their device and can choose a safe and comfortable route without being influenced by their current emotional state. Even if a choice is made without emotional influence, feedback is provided as it occurs.

[0129] Finally, the terminal sends the user's selected route and its results to the server, where learning tools, including an emotion engine, use the data to improve accuracy. For subsequent system use, navigation that is more considerate of the user's psychological state is provided.

[0130] This system allows drivers to receive optimal navigation that takes into account their emotional state while driving, and the overall adaptive capability of the system continuously improves through the use of an emotion engine.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server works in conjunction with the in-car navigation system to acquire the driver's current location, destination information, and past driving history data. It also analyzes the driver's facial expressions and voice data through an emotion engine to determine their current emotional state.

[0134] Step 2:

[0135] The device integrates driving data and emotional data and performs analysis using generational technology. This analysis identifies the characteristics of multiple routes and processes the distance, traffic information, and landmark locations for each route. The data used helps select a less stressful route based on the user's emotional state.

[0136] Step 3:

[0137] Based on the analyzed data, the server selects the optimal route, taking into account the driver's past behavior patterns and preferences. It also references the output of the emotion engine and automatically incorporates stress-reducing content into its selections.

[0138] Step 4:

[0139] Based on the selected route, the server uses an explanation generation system to create a driver-friendly route. In this process, the generating AI creates explanatory text that includes landmarks and specific instructions, providing easy-to-understand guidance that responds to the user's emotional state.

[0140] Step 5:

[0141] The user receives a generated route description through their device. This description, which reflects the analysis results of the emotion engine, allows them to select the most comfortable route that best suits their current emotional state.

[0142] Step 6:

[0143] The terminal sends the user's final route selection to the server, and feedback data is collected in conjunction with the driver's selection. This data is used to improve the system's performance in the future.

[0144] Step 7:

[0145] The server utilizes feedback data and output from the emotion engine, employing learning methods to improve the accuracy of its generation techniques, and ultimately leading to improvements that allow the system to provide more user-friendly navigation.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] In driver assistance systems, route selection does not take into account the driver's psychological state, making it difficult to avoid situations that are easily affected by stress and emotions. A challenge with conventional systems is that they do not provide navigation that adequately reflects the user's current emotions or past travel patterns.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes information gathering means for acquiring information on driving behavior, route analysis means for analyzing the characteristics of multiple routes using generation technology, and route selection means for selecting the optimal route based on the user's past travel patterns and emotional data. This enables route guidance that takes into account the user's emotional state.

[0151] "Information gathering means" refers to functions for acquiring data on the driver's behavior, and includes information such as location, destination, and driving route.

[0152] "Generative technology" refers to techniques that analyze large amounts of data and synthesize or generate information tailored to specific purposes. For example, it is used for optimizing routes and generating instructions.

[0153] A "route analysis tool" is a function that identifies the characteristics of multiple routes and analyzes the conditions of each route, specifically evaluating elements such as distance, traffic volume, and landmarks.

[0154] A "route selection method" is a function that takes into account the user's past behavior and emotional data to select the optimal route, enabling a less stressful travel experience for the user.

[0155] "Emotional data" refers to information that indicates the user's psychological state, and is measured based on facial expressions, tone of voice, and other biosensor data.

[0156] The "explanation generation means" is a function that generates clear and specific route explanations for the user based on selected route information, and provides instructions that take into account the user's emotional state.

[0157] "Explanation presentation means" refers to a function that presents the generated route explanation to the user visually or audibly, and is intended to support safe and comfortable travel.

[0158] "Learning methods" refer to functions that collect and analyze user feedback data to improve the accuracy and adaptability of the system, and in particular, include learning based on emotional data.

[0159] The present invention provides optimal route guidance in a driver assistance system while taking into account the user's emotional state. This system includes information gathering means, route analysis means, route selection means, emotional data processing means, explanation generation means, explanation presentation means, and learning means.

[0160] The server acquires information about driving behavior, such as GPS data, driving routes, and destinations, from devices within the vehicle, such as in-car navigation systems and dashcams. This information, which also includes traffic conditions and congestion predictions, is updated in real time. The server further uses an emotion engine to understand the driver's emotional state based on their facial expressions, voice, and data obtained from biosensor devices.

[0161] The terminal uses a generated AI model based on the collected data to analyze it. This analysis employs machine learning techniques to evaluate the characteristics of various routes. For example, it includes analyzing congestion levels and landmark locations to select routes that minimize the psychological burden on the driver.

[0162] Based on the analyzed data, the server selects a route. It takes into account the user's past travel patterns, preferences, and emotional data to provide the optimal route that minimizes stress. In this process, the aforementioned emotional data plays a crucial role, with a generative AI model selecting distances and scenery that alleviate specific emotions.

[0163] The generated instructions are provided to the driver by the server as specific directions. The instructions displayed on the terminal via visual and auditory means will take into account the user's mental state, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right."

[0164] Users can travel safely and comfortably by following the guidance provided through their device. For example, when heading to a picnic with family, the system suggests a route that avoids crowded areas in frequently visited parks and provides guidance tailored to the driver's needs.

[0165] As feedback, the device sends the driving results to the server, where learning tools, including emotional data, analyze them to improve the overall system accuracy. This process enables more personalized navigation when the system is reused.

[0166] An example of a prompt message is, "Please tell me the best time and least stressful route for a picnic." This allows the user to choose the optimal route based on the situation at the time.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server acquires location information, destination information, and driving route data from the in-car navigation system and dashcam. The input data includes GPS data, speed information, and route history, which are used to determine the driver's current location and destination. The output generates geographical context information for the driver. Specifically, the system periodically collects data using the navigation system's API.

[0170] Step 2:

[0171] The server uses an emotion engine to understand the driver's emotional state using data from facial expressions, voice, and other biosensors. Inputs include camera footage, audio recordings, and biometric data from sensors, which are then analyzed by an emotion recognition algorithm. Outputs include evaluation data of the driver's stress level and emotional state. Specifically, emotions are quantified in real time using facial recognition software and voice analysis technology.

[0172] Step 3:

[0173] The terminal receives data provided by the server and performs analysis using a generated AI model. The input includes characteristic information, traffic information, and landmark information for each route. Based on this data, machine learning techniques are used to extract route features suitable for the driver and generate analysis results. The output is an evaluation report that includes detailed convenience and psychological impact for each route. Specifically, the AI ​​model performs route prediction and calculates a convenience score.

[0174] Step 4:

[0175] The server combines analysis results and emotional data to select the optimal route. Route analysis results and driver emotional assessments are used as input. The output is a selected route that reduces user stress and is suitable for the purpose. Adjustments are made based on past behavioral history and emotional data to determine the most appropriate route. Specifically, it uses AI-driven data mining and pattern recognition.

[0176] Step 5:

[0177] Based on the selection results, the server generates specific and emotionally sensitive route descriptions using a generative AI model. Selected route information and landmark information are provided as input. The generated route descriptions are in sentence format and focus on instructions. The output is an emotionally sensitive guide, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right." For specific actions, natural language generation technology is used to create the descriptions.

[0178] Step 6:

[0179] The user receives the generated route description on their terminal and drives based on the guidance. The input is the route description sent from the server, and the output is a safe and comfortable driving experience. Specifically, the terminal also provides voice guidance as needed, allowing the driver to obtain information through both sight and sound.

[0180] Step 7:

[0181] After completing a drive, the terminal sends the selected route and its results to the server. Inputs include stored travel data and driver feedback, while outputs are learning data that contributes to overall system improvement. Furthermore, including emotional data optimizes future route suggestions to reflect the user experience. Specific actions include sending collected data to the cloud and updating the learning algorithm.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] One challenge in autonomous vehicles is the difficulty in selecting the optimal route while considering the emotional state of passengers. Conventional navigation systems select routes without considering the physiological and psychological state of passengers, which can cause stress for some passengers.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes a device for acquiring driving behavior data, a device for analyzing the characteristics of multiple routes using generation technology, a device for selecting the optimal route based on the user's past behavior patterns, a device for generating an easy-to-understand explanation based on the selected route, a device for presenting the explanation to the user, a device for acquiring and analyzing biometric data for recognizing emotional states, a device for selecting a route based on the analyzed emotional data, and a device for ensuring that the selected route explanation takes into account the user's psychological state. This enables route selection and navigation that takes into account the emotional state of passengers.

[0187] "Driving behavior data" refers to information about the driver and vehicle operation, specifically including speed, acceleration, and brake usage.

[0188] "Generative technology" refers to methods of analyzing and generating information using artificial intelligence and machine learning algorithms, and is a technology that understands the characteristics of data and creates new value.

[0189] "Route analysis" refers to the process of analyzing the characteristics of multiple routes to derive the optimal route, and it evaluates based on factors such as traffic volume and distance.

[0190] "Selecting the optimal route" is the procedure for choosing the route that best suits the user's purpose and conditions, taking into account past behavioral patterns and current circumstances.

[0191] "Easy-to-understand explanations" refer to information provided in a way that users can intuitively comprehend, including specific instructions and landmarks.

[0192] "Emotional state" refers to the user's physiological and psychological state, particularly stress levels and mood.

[0193] "Biometric data" refers to information obtained from an individual's body, including data such as facial expressions, voice tone, and heart rate.

[0194] "Route selection based on analyzed emotional data" is a process for selecting the most optimized route, taking into account the user's emotional information.

[0195] "Path explanation that takes psychological state into consideration" refers to providing route instructions that are adjusted to provide reassurance and satisfaction based on the user's mental state.

[0196] The system implementing this invention consists of three elements: a server, a terminal, and a user. The server uses multiple sensors installed in the vehicle to collect data on driving behavior and biometric data. This includes hardware such as cameras and microphones, which are connected to small computing devices such as Raspberry Pi. A platform on the server with real-time data processing capabilities is used for data transmission and processing. For example, facial recognition using OpenCV, speech analysis using PyAudio, and machine learning libraries such as TENSORFLOW® are applied to biometric data analysis.

[0197] The terminal functions as a central control unit within the autonomous vehicle, performing route selection and explanation generation based on analysis results received from the server. While utilizing external services such as the Google® Maps API for route selection, it generates detailed explanations to inform the user about the selected route. The generated explanations are provided in a format appropriate to the user's emotional state, utilizing generative AI models such as OpenAI®'s GPT series.

[0198] Users receive route information displayed on their devices, enabling them to travel safely and comfortably. During this process, user feedback and biometric data are sent back to the server as feedback, contributing to the learning and optimization of the entire system.

[0199] For example, if a passenger wishes to relax during their journey, the system can analyze the situation to determine that the passenger is calm and suggest a route with plenty of natural scenery. An example of a prompt to the AI ​​model in this case would be, "Please generate instructions to select a route that will allow the passenger to relax and guide them along a road with beautiful scenery."

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The server collects biometric data through cameras and microphones installed inside the vehicle. Inputs include image and audio data from the biosensors. This data is analyzed using OpenCV and PyAudio to determine facial expressions and voice tone. Outputs data indicating the user's emotional state.

[0203] Step 2:

[0204] The server integrates collected driving behavior data and user emotional state data, and performs analysis using generative techniques. The input consists of information about past driving routes and destinations. The data is processed using algorithms such as TensorFlow to generate route suggestions optimized for the user's emotional state. The output is the recommended route.

[0205] Step 3:

[0206] The terminal selects a route based on route suggestions sent from the server. Inputs include route suggestions from the server and current traffic conditions. The terminal uses the Google Maps API to retrieve traffic data and select the optimal route. The output is this optimal route.

[0207] Step 4:

[0208] The terminal generates a unique and easy-to-understand route description using a generation AI model based on the selected route. The input is the route selection result by the terminal. The terminal uses automatically generated prompt sentences to instruct OpenAI's GPT series to generate a route description that takes the user's psychological state into consideration. The output is the route description presented to the user.

[0209] Step 5:

[0210] The user reviews the route description displayed on the terminal and begins moving according to the instructions. The input is the route and instructions provided by the terminal. The route selection result based on the user's choices is returned to the server as feedback. The output is the actual route traveled and the feedback data.

[0211] Step 6:

[0212] The server receives feedback data from the user and initiates the system's learning process. The input consists of user feedback data and biometric data. The server uses this data to improve its generation techniques and optimize for more accurate emotional responses on subsequent uses. The output is the updated algorithm and database.

[0213] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0214] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0215] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0219] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0220] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0221] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0223] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0224] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0225] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0226] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0227] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0228] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0229] The present invention provides a system to support drivers in selecting an appropriate route. The system comprises the following components: data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, and learning means.

[0230] First, the server collects data from the in-car navigation system and dashcam. This data includes the driver's current location, destination, and past driving routes, allowing the system to understand driving behavior trends. This information is used as foundational data for analyzing the user's preferences and behavioral patterns.

[0231] Next, the terminal uses generation technology to analyze the collected data and identify multiple routes. Here, route analysis is used to extract the characteristics of each route (e.g., distance, traffic volume, landmarks passed through, etc.). This route information is then used to select the optimal route by comparing it with the user's behavioral patterns, such as what routes the user has chosen in the past and which landmarks they recognize.

[0232] The server then generates a driver-friendly explanation based on the selected route. The explanation generation system uses generation technology to create a specific route, including frequently seen landmarks and intersections. For example, an explanation might be created that includes specific instructions such as, "After passing the park on your right, turn left at the next traffic light."

[0233] Users receive this explanation, which is presented in an easy-to-understand format, allowing them to choose the most suitable route from the available options. This enables more efficient and stress-free driving, while taking into account the user's preferences and familiar routes.

[0234] Finally, the terminal sends the route selected by the user and its results to the server, and the learning mechanism improves the accuracy of the generation technique with past feedback. This feedback loop allows the system to continuously evolve to better suit the user's needs.

[0235] This system allows drivers to receive optimal navigation tailored to their preferences, and the system's adaptive capabilities continuously improve through learning mechanisms.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server retrieves driver location information, destination information, and past driving route data from the in-car navigation system and dashcam. This data is used as basic information to analyze the user's past behavior patterns and preferences.

[0239] Step 2:

[0240] The terminal collects the acquired data and analyzes it using generation technology. This analysis identifies the characteristics of multiple routes, taking into account the driver's preferences, and extracts the distance, traffic conditions, and landmarks passed through each route.

[0241] Step 3:

[0242] Based on the route analysis results, the server selects the optimal route from multiple options, taking into account route patterns previously chosen by the driver and preferred landmarks.

[0243] Step 4:

[0244] The server generates easy-to-understand instructions for the driver based on the selected route. The generating AI creates specific directions that include frequently seen landmarks and facilities, providing clear instructions such as, "Turn right at the next corner where there is a convenience store on your right."

[0245] Step 5:

[0246] The user receives route instructions sent from the server via their device. Based on the instructions provided, the user can choose the most suitable route.

[0247] Step 6:

[0248] The terminal sends information about the route selected by the user to the server and also provides the route selection result as feedback.

[0249] Step 7:

[0250] The server utilizes the collected feedback and uses learning mechanisms to improve the accuracy of its generation technology. This process is carried out to improve the system so that future route suggestions better match the user's preferences.

[0251] (Example 1)

[0252] Next, we will describe Example 1. 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."

[0253] There is a problem in that drivers have difficulty selecting the optimal route based on their own preferences and behavioral patterns. Furthermore, in order to improve the accuracy of route selection, it is necessary to learn from the driver's past choices and effectively utilize feedback.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes an information gathering means for acquiring information related to driving, a route analysis means for analyzing the attributes of multiple routes using generative artificial intelligence technology, and a route selection means for selecting the optimal route based on the user's past behavior patterns. This enables the efficient and appropriate presentation of routes according to the driver's preferences and continuous improvement of the system's accuracy.

[0256] "Information gathering means" refers to means of acquiring information related to driving, and is a device or mechanism that collects data from in-vehicle navigation systems, dashcams, etc.

[0257] "Generative artificial intelligence technology" is a technology that generates new information and options based on past data and learning, and is an algorithm used for optimizing routes and generating explanatory texts.

[0258] A "route analysis means" is a method for analyzing the attributes of multiple routes using generative artificial intelligence technology, and is a system that evaluates and analyzes the distance, traffic volume, and other attributes of the routes.

[0259] A "route selection method" is a means for selecting the optimal route based on the user's past behavior patterns, and is a process for selecting a route that takes into account the user's preferences and past choices.

[0260] An "information generation means" is a system that generates easy-to-understand explanations based on a selected route, and creates specific instructions including landmarks and intersections.

[0261] An "information presentation means" is a means of providing the generated explanation to the user, and is an interface for presenting information through screen display or sound.

[0262] "Educational tools" refer to methods for training generative artificial intelligence technology based on the user's choices and a mechanism for continuously improving the system using feedback.

[0263] This invention is an information processing device that provides drivers with efficient and personalized route selection. Specifically, it consists of three components: a server, a terminal, and a user.

[0264] The server collects driving-related data from the in-vehicle navigation system and dashcam. Through this data collection, the driver's current location, destination, past driving route data, and road conditions are obtained. This data is stored in the server's storage and used for subsequent route analysis.

[0265] The terminal performs route analysis and selection using data received from the server. This is where generative artificial intelligence technology is utilized. The generative AI model generates numerous route options based on the received data and analyzes their characteristics. This process considers factors such as the distance of each route, traffic conditions, and the location of landmarks. For example, a possible prompt to the generative AI model might be, "Consider the driver's past routes and generate an efficient route."

[0266] Next, the server generates a visually easy-to-understand explanation based on the optimal route analyzed and selected by the generating AI model. By using the information generation means, specific instructions including landmarks and intersections are created. For example, navigation such as "After passing landmark A on your right, turn left at the second traffic light" is possible.

[0267] The user receives instructions from the terminal and begins driving accordingly. Information is provided through screen displays and voice guidance, allowing for safe and quick access to information even while driving.

[0268] Finally, the user's selected route and its results are sent from the terminal to the server. This feedback is used to train the generative artificial intelligence technology through educational means, improving the accuracy of future route selections. Through this continuous learning process, the system continues to evolve to meet the driver's preferences and needs.

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] The server collects driving-related data from the in-vehicle navigation system and dashcam. Inputs include the driver's location, destination, road conditions, and past driving records. This data is stored in the server's storage for analysis. Specifically, the server periodically inputs data via a communication module and stores it in a database.

[0272] Step 2:

[0273] The terminal uses data obtained from the server to apply a generative AI model and perform route analysis. The input is driving-related data received from the server, and the output is multiple route options tailored to the driver's preferences and past behavior patterns. Specifically, the terminal inputs prompt messages to the generative AI model, for example, "Consider the driver's past routes and generate an efficient route," and obtains the analysis results.

[0274] Step 3:

[0275] The server receives route analysis results from the terminal and selects the optimal route. The input is multiple route options, and the output is the selected optimal route. The server scores factors such as route distance, traffic volume, and landmarks passed through, and selects the most appropriate route based on these scores. Specifically, the server uses a selection algorithm to score routes and outputs the route with the highest score.

[0276] Step 4:

[0277] The server generates instructions for the driver based on the selected optimal route. The input is the selected route, and the output is an easy-to-understand explanation presented to the driver. Specifically, the server uses a generation AI to create detailed navigation, including visual landmarks such as intersections.

[0278] Step 5:

[0279] The user receives the instructions provided by the server via the terminal and starts driving. The input is the explanatory text from the server, and the output is the result of the route selection by the user. As a specific operation, the user checks the screen display and voice guidance of the terminal and proceeds with driving according to the instructions.

[0280] Step 6:

[0281] The terminal sends the user's route selection result and feedback after driving to the server. The input is the user's feedback data, and the output is the training data of the generative AI model. As a specific operation, the terminal analyzes the obtained feedback and improves the model's accuracy by sending it to the server.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] In an autonomous mobile device, there is a problem that it is difficult to select an optimal route based on the individual behavior patterns of users. In particular, there is a demand to propose an effective route that takes into account the user's preferences and past selections while responding to real-time changing traffic conditions. Furthermore, it is also a problem to efficiently reflect the route information on the autonomous mobile device.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes: an information collection means for acquiring information on driving behavior; a route analysis means for analyzing the characteristics of multiple routes using generation techniques; a route selection means for selecting an optimal route based on the past behavior tendencies of the user; an instruction generation means for generating clear instructions based on the selected route; an instruction presentation means for presenting the instructions to the user; and a communication means for performing route instructions in an autonomous vehicle. This enables the selection of an optimal route considering the user's preferences and real-time traffic conditions, and enables the rapid reflection of this information in the autonomous vehicle.

[0287] The "information on driving behavior" refers to the driving operations performed by the driver of the vehicle and the records of the results thereof.

[0288] The "information collection means" is a means having a function for acquiring information on driving behavior and accumulating it as data.

[0289] The "generation technique" is a concept referring to algorithms and methods for processing a large amount of data to generate new information.

[0290] The "route analysis means" is a means for analyzing the characteristics based on the acquired route data.

[0291] The "behavior tendency" indicates characteristics regarding the driving patterns and preferences selected by the user in the past.

[0292] The "route selection means" is a means for identifying an optimal route based on the behavior tendencies of the user.

[0293] The "instruction generation means" is a means for presenting a clear driving sequence to the user based on the optimal route.

[0294] The "instruction presentation means" is a means for transmitting the generated instructions to the driver or the system.

[0295] The "communication means" refers to the communication protocol and device for transmitting the generated route instructions to the autonomous vehicle.

[0296] The term "autonomous mobile device" refers to a machine that moves while making its own decisions based on external instructions.

[0297] The system for realizing this invention aims to generate and present the optimal route based on driver behavior data. Here, the server plays a central role, integrating information gathering means, generation technology, instruction generation and presentation, and communication means.

[0298] The server first acquires information on driving behavior transmitted from on-board sensors through information gathering means. This information includes the driver's current location, destination, and past driving routes, and is used for trend analysis of driving patterns.

[0299] Next, the server uses generation technology to perform route analysis based on the data obtained by the information gathering means. The analyzed data reveals the characteristics of multiple routes (e.g., distance, average speed, reference points passed through, etc.) and is used for evaluation by the route selection means and for selecting the optimal route.

[0300] The optimal route selected by the route selection means is converted into specific travel instructions by the instruction generation means. In this process, reference points frequently seen by the user are included in the instructions, presenting them in a clear and easy-to-understand manner for the driver.

[0301] Instructions based on the selected route are transmitted in real time to the control system of the automated vehicle using communication means installed on the vehicle. This allows the automated vehicle to operate smoothly according to the proposed optimal route.

[0302] As a specific example in the present invention, a situation is presented where, during the commuting hours, an optimal route that avoids traffic jams while using a scenic road preferred by the driver is proposed. In this case, the generative AI model generates individually optimized instructions in consideration of a prompt sentence such as "Please tell me the route with less traffic jams that I usually use for commuting this week. I hope for a route that also passes through a park or a scenic place on the way."

[0303] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0304] Step 1:

[0305] The server uses information collection means to obtain information on driving behavior from in-vehicle sensors. The input here is the driver's position information, destination, etc., and the output is the aggregation of these data. This information is used as basic data for trend analysis of driving patterns.

[0306] Step 2:

[0307] The server analyzes the input driving data using generative technology. In this analysis process, the characteristics of multiple routes are evaluated, and the characteristics include distance, speed, reference points, etc. Through data calculation, the evaluation score of each route is output. Thereby, the past behavior tendency of the driver becomes clear.

[0308] Step 3:

[0309] The server uses route selection means to select an optimal route based on the analysis results. The input is the data of multiple evaluated routes, and the output is the information of the selected optimal route. In this selection process, the preferences of past users and traffic conditions are considered.

[0310] Step 4:

[0311] The server generates specific travel instructions based on the selected optimal route using an instruction generation mechanism. The input is information about the optimal route, and the output includes detailed instructions, such as "Turn left at the next intersection." These instructions are easy for the driver to understand intuitively because they highlight reference points that the user frequently sees.

[0312] Step 5:

[0313] The server transmits the generated instructions to the driver and the control system of the automated vehicle through the instruction presentation means. The output is navigation information presented in visual and audible formats. This allows the driver to move safely and comfortably based on the received instructions.

[0314] Step 6:

[0315] The user returns the route selection results to the server as feedback. The feedback inputs include the results of the selected route and the driver's satisfaction level. The server uses this information as a learning tool to update the generative AI model. The output is an improved route selection algorithm, which improves the accuracy of future route suggestions.

[0316] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0317] This invention aims to realize a system that enables more accurate route selection and explanation provision by combining an emotion engine with a driver assistance system. The system comprises data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, learning means, and an emotion engine.

[0318] First, the server acquires the driver's location, destination information, and past driving route data from the in-car navigation system and dashcam. In addition, the emotion engine recognizes the driver's emotional state using facial expressions, tone of voice, and other biosensor data, and collects this information as foundational data used throughout the system.

[0319] Next, the terminal collects data and analyzes it using generation technology. Route analysis means support this, identifying the characteristics of each route and extracting the conditions for each route (distance, traffic volume, landmarks, etc.). Furthermore, using emotional information obtained from the emotion engine, route selection is performed to match the driver's stress level and mood.

[0320] Subsequently, the server uses the analysis results and route selection methods to determine the optimal route, taking into account patterns and preferences from previously selected routes. It adjusts the selection results according to the emotion engine data, selecting routes and landmarks to reduce stress.

[0321] Based on the selection results, the server uses an explanation generation mechanism to create a specific route. The generating AI produces an easy-to-understand route explanation that includes specific instructions, making it possible to provide explanations that take into account the driver's mental state, such as "Turn left at the next corner in front of the building with the humorous advertisement."

[0322] The user receives this route description on their device and can choose a safe and comfortable route without being influenced by their current emotional state. Even if a choice is made without emotional influence, feedback is provided as it occurs.

[0323] Finally, the terminal sends the user's selected route and its results to the server, where learning tools, including an emotion engine, use the data to improve accuracy. For subsequent system use, navigation that is more considerate of the user's psychological state is provided.

[0324] This system allows drivers to receive optimal navigation that takes into account their emotional state while driving, and the overall adaptive capability of the system continuously improves through the use of an emotion engine.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The server works in conjunction with the in-car navigation system to acquire the driver's current location, destination information, and past driving history data. It also analyzes the driver's facial expressions and voice data through an emotion engine to determine their current emotional state.

[0328] Step 2:

[0329] The device integrates driving data and emotional data and performs analysis using generational technology. This analysis identifies the characteristics of multiple routes and processes the distance, traffic information, and landmark locations for each route. The data used helps select a less stressful route based on the user's emotional state.

[0330] Step 3:

[0331] Based on the analyzed data, the server selects the optimal route, taking into account the driver's past behavior patterns and preferences. It also references the output of the emotion engine and automatically incorporates stress-reducing content into its selections.

[0332] Step 4:

[0333] Based on the selected route, the server uses an explanation generation system to create a driver-friendly route. In this process, the generating AI creates explanatory text that includes landmarks and specific instructions, providing easy-to-understand guidance that responds to the user's emotional state.

[0334] Step 5:

[0335] The user receives a generated route description through their device. This description, which reflects the analysis results of the emotion engine, allows them to select the most comfortable route that best suits their current emotional state.

[0336] Step 6:

[0337] The terminal sends the user's final route selection to the server, and feedback data is collected in conjunction with the driver's selection. This data is used to improve the system's performance in the future.

[0338] Step 7:

[0339] The server utilizes feedback data and output from the emotion engine, employing learning methods to improve the accuracy of its generation techniques, and ultimately leading to improvements that allow the system to provide more user-friendly navigation.

[0340] (Example 2)

[0341] Next, we will describe Example 2. 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".

[0342] In driver assistance systems, route selection does not take into account the driver's psychological state, making it difficult to avoid situations that are easily affected by stress and emotions. A challenge with conventional systems is that they do not provide navigation that adequately reflects the user's current emotions or past travel patterns.

[0343] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0344] In this invention, the server includes information gathering means for acquiring information on driving behavior, route analysis means for analyzing the characteristics of multiple routes using generation technology, and route selection means for selecting the optimal route based on the user's past travel patterns and emotional data. This enables route guidance that takes into account the user's emotional state.

[0345] "Information gathering means" refers to functions for acquiring data on the driver's behavior, and includes information such as location, destination, and driving route.

[0346] "Generative technology" refers to techniques that analyze large amounts of data and synthesize or generate information tailored to specific purposes. For example, it is used for optimizing routes and generating instructions.

[0347] A "route analysis tool" is a function that identifies the characteristics of multiple routes and analyzes the conditions of each route, specifically evaluating elements such as distance, traffic volume, and landmarks.

[0348] A "route selection method" is a function that takes into account the user's past behavior and emotional data to select the optimal route, enabling a less stressful travel experience for the user.

[0349] "Emotional data" refers to information that indicates the user's psychological state, and is measured based on facial expressions, tone of voice, and other biosensor data.

[0350] The "explanation generation means" is a function that generates clear and specific route explanations for the user based on selected route information, and provides instructions that take into account the user's emotional state.

[0351] "Explanation presentation means" refers to a function that presents the generated route explanation to the user visually or audibly, and is intended to support safe and comfortable travel.

[0352] "Learning methods" refer to functions that collect and analyze user feedback data to improve the accuracy and adaptability of the system, and in particular, include learning based on emotional data.

[0353] The present invention provides optimal route guidance in a driver assistance system while taking into account the user's emotional state. This system includes information gathering means, route analysis means, route selection means, emotional data processing means, explanation generation means, explanation presentation means, and learning means.

[0354] The server acquires information about driving behavior, such as GPS data, driving routes, and destinations, from devices within the vehicle, such as in-car navigation systems and dashcams. This information, which also includes traffic conditions and congestion predictions, is updated in real time. The server further uses an emotion engine to understand the driver's emotional state based on their facial expressions, voice, and data obtained from biosensor devices.

[0355] The terminal uses a generated AI model based on the collected data to analyze it. This analysis employs machine learning techniques to evaluate the characteristics of various routes. For example, it includes analyzing congestion levels and landmark locations to select routes that minimize the psychological burden on the driver.

[0356] Based on the analyzed data, the server selects a route. It takes into account the user's past travel patterns, preferences, and emotional data to provide the optimal route that minimizes stress. In this process, the aforementioned emotional data plays a crucial role, with a generative AI model selecting distances and scenery that alleviate specific emotions.

[0357] The generated instructions are provided to the driver by the server as specific directions. The instructions displayed on the terminal via visual and auditory means will take into account the user's mental state, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right."

[0358] Users can travel safely and comfortably by following the guidance provided through their device. For example, when heading to a picnic with family, the system suggests a route that avoids crowded areas in frequently visited parks and provides guidance tailored to the driver's needs.

[0359] As feedback, the device sends the driving results to the server, where learning tools, including emotional data, analyze them to improve the overall system accuracy. This process enables more personalized navigation when the device is reused.

[0360] An example of a prompt message is, "Please tell me the best time and least stressful route for a picnic." This allows the user to choose the optimal route based on the situation at the time.

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] The server acquires location information, destination information, and driving route data from the in-car navigation system and dashcam. The input data includes GPS data, speed information, and route history, which are used to determine the driver's current location and destination. The output generates geographical context information for the driver. Specifically, the system periodically collects data using the navigation system's API.

[0364] Step 2:

[0365] The server uses an emotion engine to understand the driver's emotional state using data from facial expressions, voice, and other biosensors. Inputs include camera footage, audio recordings, and biometric data from sensors, which are then analyzed by an emotion recognition algorithm. Outputs include evaluation data of the driver's stress level and emotional state. Specifically, emotions are quantified in real time using facial recognition software and voice analysis technology.

[0366] Step 3:

[0367] The terminal receives data provided by the server and performs analysis using a generated AI model. The input includes characteristic information, traffic information, and landmark information for each route. Based on this data, machine learning techniques are used to extract route features suitable for the driver and generate analysis results. The output is an evaluation report that includes detailed convenience and psychological impact for each route. Specifically, the AI ​​model performs route prediction and calculates a convenience score.

[0368] Step 4:

[0369] The server combines analysis results and emotional data to select the optimal route. Route analysis results and driver emotional assessments are used as input. The output is a selected route that reduces user stress and is suitable for the purpose. Adjustments are made based on past behavioral history and emotional data to determine the most appropriate route. Specifically, it uses AI-driven data mining and pattern recognition.

[0370] Step 5:

[0371] Based on the selection results, the server generates specific and emotionally sensitive route descriptions using a generative AI model. Selected route information and landmark information are provided as input. The generated route descriptions are in sentence format and focus on instructions. The output is an emotionally sensitive guide, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right." For specific actions, natural language generation technology is used to create the descriptions.

[0372] Step 6:

[0373] The user receives the generated route description on their terminal and drives based on the guidance. The input is the route description sent from the server, and the output is a safe and comfortable driving experience. Specifically, the terminal also provides voice guidance as needed, allowing the driver to obtain information through both sight and sound.

[0374] Step 7:

[0375] After completing a drive, the terminal sends the selected route and its results to the server. Inputs include stored travel data and driver feedback, while outputs are learning data that contributes to overall system improvement. Furthermore, including emotional data optimizes future route suggestions to reflect the user experience. Specific actions include sending collected data to the cloud and updating the learning algorithm.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] One challenge in autonomous vehicles is the difficulty in selecting the optimal route while considering the emotional state of passengers. Conventional navigation systems select routes without considering the physiological and psychological state of passengers, which can cause stress for some passengers.

[0379] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0380] In this invention, the server includes a device for acquiring driving behavior data, a device for analyzing the characteristics of multiple routes using generation technology, a device for selecting the optimal route based on the user's past behavior patterns, a device for generating an easy-to-understand explanation based on the selected route, a device for presenting the explanation to the user, a device for acquiring and analyzing biometric data for recognizing emotional states, a device for selecting a route based on the analyzed emotional data, and a device for ensuring that the selected route explanation takes into account the user's psychological state. This enables route selection and navigation that takes into account the emotional state of passengers.

[0381] "Driving behavior data" refers to information about the driver and vehicle operation, specifically including speed, acceleration, and brake usage.

[0382] "Generative technology" refers to methods of analyzing and generating information using artificial intelligence and machine learning algorithms, and is a technology that understands the characteristics of data and creates new value.

[0383] "Route analysis" refers to the process of analyzing the characteristics of multiple routes to derive the optimal route, and it evaluates based on factors such as traffic volume and distance.

[0384] "Selecting the optimal route" is the procedure for choosing the route that best suits the user's purpose and conditions, taking into account past behavioral patterns and current circumstances.

[0385] "Easy-to-understand explanations" refer to information provided in a way that users can intuitively comprehend, including specific instructions and landmarks.

[0386] "Emotional state" refers to the user's physiological and psychological state, particularly stress levels and mood.

[0387] "Biometric data" refers to information obtained from an individual's body, including data such as facial expressions, voice tone, and heart rate.

[0388] "Route selection based on analyzed emotional data" is a process for selecting the most optimized route, taking into account the user's emotional information.

[0389] "Path explanation that takes psychological state into consideration" refers to providing route instructions that are adjusted to provide reassurance and satisfaction based on the user's mental state.

[0390] The system implementing this invention consists of three elements: a server, a terminal, and a user. The server uses multiple sensors installed in the vehicle to collect data on driving behavior and biometric data. This includes hardware such as cameras and microphones, which are connected to small computing devices such as Raspberry Pi. A platform on the server with real-time data processing capabilities is used for data transmission and processing. For example, facial recognition using OpenCV, speech analysis using PyAudio, and machine learning libraries such as TensorFlow are applied for biometric data analysis.

[0391] The terminal functions as a central control unit within the autonomous vehicle, performing route selection and explanation generation based on analysis results received from the server. While utilizing external services such as the Google Maps API for route selection, it generates detailed explanations to communicate the selected route to the user. The generated explanations are provided in a format appropriate to the user's emotional state, utilizing generative AI models such as OpenAI's GPT series.

[0392] Users receive route information displayed on their devices, enabling them to travel safely and comfortably. During this process, user feedback and biometric data are sent back to the server as feedback, contributing to the learning and optimization of the entire system.

[0393] For example, if a passenger wishes to relax during their journey, the system can analyze the situation to determine that the passenger is calm and suggest a route with plenty of natural scenery. An example of a prompt to the AI ​​model in this case would be, "Please generate instructions to select a route that will allow the passenger to relax and guide them along a road with beautiful scenery."

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The server collects biometric data through cameras and microphones installed inside the vehicle. Inputs include image and audio data from the biosensors. This data is analyzed using OpenCV and PyAudio to determine facial expressions and voice tone. Outputs data indicating the user's emotional state.

[0397] Step 2:

[0398] The server integrates collected driving behavior data and user emotional state data, and performs analysis using generative techniques. The input consists of information about past driving routes and destinations. The data is processed using algorithms such as TensorFlow to generate route suggestions optimized for the user's emotional state. The output is the recommended route.

[0399] Step 3:

[0400] The terminal selects a route based on route suggestions sent from the server. Inputs include route suggestions from the server and current traffic conditions. The terminal uses the Google Maps API to retrieve traffic data and select the optimal route. The output is this optimal route.

[0401] Step 4:

[0402] The terminal generates a unique and easy-to-understand route description using a generation AI model based on the selected route. The input is the route selection result by the terminal. The terminal uses automatically generated prompt sentences to instruct OpenAI's GPT series to generate a route description that takes the user's psychological state into consideration. The output is the route description presented to the user.

[0403] Step 5:

[0404] The user reviews the route description displayed on the terminal and begins moving according to the instructions. The input is the route and instructions provided by the terminal. The route selection result based on the user's choices is returned to the server as feedback. The output is the actual route traveled and the feedback data.

[0405] Step 6:

[0406] The server receives feedback data from the user and initiates the system's learning process. The input consists of user feedback data and biometric data. The server uses this data to improve its generation techniques and optimize for more accurate emotional responses in subsequent uses. The output is the updated algorithm and database.

[0407] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0408] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0410] [Third Embodiment]

[0411] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0412] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0413] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0415] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0417] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0418] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0419] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0420] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0422] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0423] The present invention provides a system to support drivers in selecting an appropriate route. The system comprises the following components: data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, and learning means.

[0424] First, the server collects data from the in-car navigation system and dashcam. This data includes the driver's current location, destination, and past driving routes, allowing the system to understand driving behavior trends. This information is used as foundational data for analyzing the user's preferences and behavioral patterns.

[0425] Next, the terminal uses generation technology to analyze the collected data and identify multiple routes. Here, route analysis is used to extract the characteristics of each route (e.g., distance, traffic volume, landmarks passed through, etc.). This route information is then used to select the optimal route by comparing it with the user's behavioral patterns, such as what routes the user has chosen in the past and which landmarks they recognize.

[0426] The server then generates a driver-friendly explanation based on the selected route. The explanation generation system uses generation technology to create a specific route, including frequently seen landmarks and intersections. For example, an explanation might be created that includes specific instructions such as, "After passing the park on your right, turn left at the next traffic light."

[0427] Users receive this explanation, which is presented in an easy-to-understand format, allowing them to choose the most suitable route from the available options. This enables more efficient and stress-free driving, while taking into account the user's preferences and familiar routes.

[0428] Finally, the terminal sends the route selected by the user and its results to the server, and the learning mechanism improves the accuracy of the generation technique with past feedback. This feedback loop allows the system to continuously evolve to better suit the user's needs.

[0429] This system allows drivers to receive optimal navigation tailored to their preferences, and the system's adaptive capabilities continuously improve through learning mechanisms.

[0430] The following describes the processing flow.

[0431] Step 1:

[0432] The server retrieves driver location information, destination information, and past driving route data from the in-car navigation system and dashcam. This data is used as basic information to analyze the user's past behavior patterns and preferences.

[0433] Step 2:

[0434] The terminal collects the acquired data and analyzes it using generation technology. This analysis identifies the characteristics of multiple routes, taking into account the driver's preferences, and extracts the distance, traffic conditions, and landmarks passed through each route.

[0435] Step 3:

[0436] Based on the route analysis results, the server selects the optimal route from multiple options, taking into account route patterns previously chosen by the driver and preferred landmarks.

[0437] Step 4:

[0438] The server generates easy-to-understand instructions for the driver based on the selected route. The generating AI creates specific directions that include frequently seen landmarks and facilities, providing clear instructions such as, "Turn right at the next corner where there is a convenience store on your right."

[0439] Step 5:

[0440] The user receives route instructions sent from the server via their device. Based on the instructions provided, the user can choose the most suitable route.

[0441] Step 6:

[0442] The terminal sends information about the route selected by the user to the server and also provides the route selection result as feedback.

[0443] Step 7:

[0444] The server utilizes the collected feedback and uses learning mechanisms to improve the accuracy of its generation technology. This process is carried out to improve the system so that future route suggestions better match the user's preferences.

[0445] (Example 1)

[0446] Next, we will describe Example 1. 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."

[0447] There is a problem in that drivers have difficulty selecting the optimal route based on their own preferences and behavioral patterns. Furthermore, in order to improve the accuracy of route selection, it is necessary to learn from the driver's past choices and effectively utilize feedback.

[0448] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0449] In this invention, the server includes an information gathering means for acquiring information related to driving, a route analysis means for analyzing the attributes of multiple routes using generative artificial intelligence technology, and a route selection means for selecting the optimal route based on the user's past behavior patterns. This enables the efficient and appropriate presentation of routes according to the driver's preferences and continuous improvement of the system's accuracy.

[0450] "Information gathering means" refers to means of acquiring information related to driving, and is a device or mechanism that collects data from in-vehicle navigation systems, dashcams, etc.

[0451] "Generative artificial intelligence technology" is a technology that generates new information and options based on past data and learning, and is an algorithm used for optimizing routes and generating explanatory texts.

[0452] A "route analysis means" is a method for analyzing the attributes of multiple routes using generative artificial intelligence technology, and is a system that evaluates and analyzes the distance, traffic volume, and other attributes of the routes.

[0453] A "route selection method" is a means for selecting the optimal route based on the user's past behavior patterns, and is a process for selecting a route that takes into account the user's preferences and past choices.

[0454] An "information generation means" is a system that generates easy-to-understand explanations based on a selected route, and creates specific instructions including landmarks and intersections.

[0455] An "information presentation means" is a means of providing the generated explanation to the user, and is an interface for presenting information through screen display or sound.

[0456] "Educational tools" refer to methods for training generative artificial intelligence technology based on the user's choices and a mechanism for continuously improving the system using feedback.

[0457] This invention is an information processing device that provides drivers with efficient and personalized route selection. Specifically, it consists of three components: a server, a terminal, and a user.

[0458] The server collects driving-related data from the in-vehicle navigation system and dashcam. Through this data collection, the driver's current location, destination, past driving route data, and road conditions are obtained. This data is stored in the server's storage and used for subsequent route analysis.

[0459] The terminal performs route analysis and selection using data received from the server. This is where generative artificial intelligence technology is utilized. The generative AI model generates numerous route options based on the received data and analyzes their characteristics. This process considers factors such as the distance of each route, traffic conditions, and the location of landmarks. For example, a possible prompt to the generative AI model might be, "Consider the driver's past routes and generate an efficient route."

[0460] Next, the server generates a visually easy-to-understand explanation based on the optimal route analyzed and selected by the generating AI model. By using the information generation means, specific instructions including landmarks and intersections are created. For example, navigation such as "After passing landmark A on your right, turn left at the second traffic light" is possible.

[0461] The user receives instructions from the terminal and begins driving accordingly. Information is provided through screen displays and voice guidance, allowing for safe and quick access to information even while driving.

[0462] Finally, the user's selected route and its results are sent from the terminal to the server. This feedback is used to train the generative artificial intelligence technology through educational means, improving the accuracy of future route selections. Through this continuous learning process, the system continues to evolve to meet the driver's preferences and needs.

[0463] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0464] Step 1:

[0465] The server collects driving-related data from the in-vehicle navigation system and dashcam. Inputs include the driver's location, destination, road conditions, and past driving records. This data is stored in the server's storage for analysis. Specifically, the server periodically inputs data via a communication module and stores it in a database.

[0466] Step 2:

[0467] The terminal uses data obtained from the server to apply a generative AI model and perform route analysis. The input is driving-related data received from the server, and the output is multiple route options tailored to the driver's preferences and past behavior patterns. Specifically, the terminal inputs prompt messages to the generative AI model, for example, "Consider the driver's past routes and generate an efficient route," and obtains the analysis results.

[0468] Step 3:

[0469] The server receives route analysis results from the terminal and selects the optimal route. The input is multiple route options, and the output is the selected optimal route. The server scores factors such as route distance, traffic volume, and landmarks passed through, and selects the most appropriate route based on these scores. Specifically, the server uses a selection algorithm to score routes and outputs the route with the highest score.

[0470] Step 4:

[0471] The server generates instructions for the driver based on the selected optimal route. The input is the selected route, and the output is an easy-to-understand explanation presented to the driver. Specifically, the server uses a generation AI to create detailed navigation, including visual landmarks such as intersections.

[0472] Step 5:

[0473] The user receives instructions from the server via a terminal and then begins driving. The input is the instructional text from the server, and the output is the result of the user's route selection. In terms of specific actions, the user checks the terminal's screen display and voice guidance and proceeds with driving according to the instructions.

[0474] Step 6:

[0475] The terminal sends the user's route selection results and feedback after the drive to the server. The input is the user's feedback data, and the output is the training data for the generated AI model. Specifically, the terminal analyzes the received feedback and sends it to the server to improve the model's accuracy.

[0476] (Application Example 1)

[0477] Next, we will explain Application Example 1. In the following explanation, 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."

[0478] In autonomous vehicles, there is a challenge in selecting the optimal route based on the individual behavior patterns of the user. In particular, there is a need to propose an effective route that takes into account the user's preferences and past choices, while also responding to real-time changes in traffic conditions. Furthermore, efficiently reflecting this route information in the autonomous vehicle is also a challenge.

[0479] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0480] In this invention, the server includes information gathering means for acquiring information on driving behavior, route analysis means for analyzing the characteristics of multiple routes using generation technology, route selection means for selecting an optimal route based on the user's past behavioral tendencies, instruction generation means for generating clear instructions based on the selected route, instruction presentation means for presenting the instructions to the user, and communication means for providing route instructions to the automated vehicle. This makes it possible to select an optimal route that takes into account the user's preferences and real-time traffic conditions, and to quickly reflect that information in the automated vehicle.

[0481] "Information on driving behavior" refers to records of driving operations performed by the vehicle driver and their results.

[0482] "Information gathering means" refers to means that have the function of acquiring information on driving behavior and accumulating it as data.

[0483] "Generative technology" is a concept that refers to algorithms and methods for processing large amounts of data to generate new information.

[0484] A "route analysis means" is a means for analyzing the characteristics of acquired route data.

[0485] "Behavioral tendencies" refer to characteristics related to the driving patterns and preferences that the user has chosen in the past.

[0486] A "route selection method" is a means of identifying the optimal route based on the user's behavioral tendencies.

[0487] "Instruction generation means" refers to a means for presenting a clear route to the user based on the optimal path.

[0488] A "means for presenting instructions" is a means of communicating generated instructions to the driver or system.

[0489] "Communication means" refers to communication protocols and devices used to transmit generated route instructions to an automated mobile vehicle.

[0490] The term "autonomous mobile device" refers to a machine that moves while making its own decisions based on external instructions.

[0491] The system for realizing this invention aims to generate and present the optimal route based on driver behavior data. Here, the server plays a central role, integrating information gathering means, generation technology, instruction generation and presentation, and communication means.

[0492] The server first acquires information on driving behavior transmitted from on-board sensors through information gathering means. This information includes the driver's current location, destination, and past driving routes, and is used for trend analysis of driving patterns.

[0493] Next, the server uses generation technology to perform route analysis based on the data obtained by the information gathering means. The analyzed data reveals the characteristics of multiple routes (e.g., distance, average speed, reference points passed through, etc.) and is used for evaluation by the route selection means and for selecting the optimal route.

[0494] The optimal route selected by the route selection means is converted into specific travel instructions by the instruction generation means. In this process, reference points frequently seen by the user are included in the instructions, presenting them in a clear and easy-to-understand manner for the driver.

[0495] Instructions based on the selected route are transmitted in real time to the control system of the automated vehicle using communication means installed on the vehicle. This allows the automated vehicle to operate smoothly according to the proposed optimal route.

[0496] A specific example of the present invention is a situation in which an optimal route is proposed that avoids traffic congestion while utilizing scenic roads preferred by the driver during commuting hours. In this case, the generating AI model considers prompt statements such as, "For my commute this week, please tell me the least congested route I usually use. I would like a route that also passes through parks and scenic spots," and generates individually optimized instructions.

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] The server uses data collection tools to acquire information about driving behavior from on-board sensors. Inputs include the driver's location and destination, while output is an aggregation of this data. This information is used as foundational data for analyzing driving pattern trends.

[0500] Step 2:

[0501] The server analyzes the input driving data using generation technology. This analysis process evaluates the characteristics of multiple routes, including distance, speed, and reference points. Data calculations output an evaluation score for each route, revealing the driver's past behavioral tendencies.

[0502] Step 3:

[0503] The server uses a route selection mechanism to select the optimal route based on the analysis results. The input is data from multiple evaluated routes, and the output is information on the selected optimal route. This selection process takes into account past user preferences and traffic conditions.

[0504] Step 4:

[0505] The server generates specific travel instructions based on the selected optimal route using an instruction generation mechanism. The input is information about the optimal route, and the output includes detailed instructions, such as "Turn left at the next intersection." These instructions are easy for the driver to understand intuitively because they highlight reference points that the user frequently sees.

[0506] Step 5:

[0507] The server transmits the generated instructions to the driver and the control system of the automated vehicle through the instruction presentation means. The output is navigation information presented in visual and audible formats. This allows the driver to move safely and comfortably based on the received instructions.

[0508] Step 6:

[0509] The user returns the route selection results to the server as feedback. The feedback inputs include the results of the selected route and the driver's satisfaction level. The server uses this information as a learning tool to update the generative AI model. The output is an improved route selection algorithm, which improves the accuracy of future route suggestions.

[0510] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0511] This invention aims to realize a system that enables more accurate route selection and explanation provision by combining an emotion engine with a driver assistance system. The system comprises data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, learning means, and an emotion engine.

[0512] First, the server acquires the driver's location, destination information, and past driving route data from the in-car navigation system and dashcam. In addition, the emotion engine recognizes the driver's emotional state using facial expressions, tone of voice, and other biosensor data, and collects this information as foundational data used throughout the system.

[0513] Next, the terminal collects data and analyzes it using generation technology. Route analysis means support this, identifying the characteristics of each route and extracting the conditions for each route (distance, traffic volume, landmarks, etc.). Furthermore, using emotional information obtained from the emotion engine, route selection is performed to match the driver's stress level and mood.

[0514] Subsequently, the server uses the analysis results and route selection methods to determine the optimal route, taking into account patterns and preferences from previously selected routes. It adjusts the selection results according to the emotion engine data, selecting routes and landmarks to reduce stress.

[0515] Based on the selection results, the server uses an explanation generation mechanism to create a specific route. The generating AI produces an easy-to-understand route explanation that includes specific instructions, making it possible to provide explanations that take into account the driver's mental state, such as "Turn left at the next corner in front of the building with the humorous advertisement."

[0516] The user receives this route description on their device and can choose a safe and comfortable route without being influenced by their current emotional state. Even if a choice is made without emotional influence, feedback is provided as it occurs.

[0517] Finally, the terminal sends the user's selected route and its results to the server, where learning tools, including an emotion engine, use the data to improve accuracy. For subsequent system use, navigation that is more considerate of the user's psychological state is provided.

[0518] This system allows drivers to receive optimal navigation that takes into account their emotional state while driving, and the overall adaptive capability of the system continuously improves through the use of an emotion engine.

[0519] The following describes the processing flow.

[0520] Step 1:

[0521] The server works in conjunction with the in-car navigation system to acquire the driver's current location, destination information, and past driving history data. It also analyzes the driver's facial expressions and voice data through an emotion engine to determine their current emotional state.

[0522] Step 2:

[0523] The device integrates driving data and emotional data and performs analysis using generational technology. This analysis identifies the characteristics of multiple routes and processes the distance, traffic information, and landmark locations for each route. The data used helps select a less stressful route based on the user's emotional state.

[0524] Step 3:

[0525] Based on the analyzed data, the server selects the optimal route, taking into account the driver's past behavior patterns and preferences. It also references the output of the emotion engine and automatically incorporates stress-reducing content into its selections.

[0526] Step 4:

[0527] Based on the selected route, the server uses an explanation generation system to create a driver-friendly route. In this process, the generating AI creates explanatory text that includes landmarks and specific instructions, providing easy-to-understand guidance that responds to the user's emotional state.

[0528] Step 5:

[0529] The user receives a generated route description through their device. This description, which reflects the analysis results of the emotion engine, allows them to select the most comfortable route that best suits their current emotional state.

[0530] Step 6:

[0531] The terminal sends the user's final route selection to the server, and feedback data is collected in conjunction with the driver's selection. This data is used to improve the system's performance in the future.

[0532] Step 7:

[0533] The server utilizes feedback data and output from the emotion engine, employing learning methods to improve the accuracy of its generation techniques, and ultimately leading to improvements in the system to provide more user-friendly navigation.

[0534] (Example 2)

[0535] Next, we will describe Example 2. 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."

[0536] In driver assistance systems, route selection does not take into account the driver's psychological state, making it difficult to avoid situations that are easily affected by stress and emotions. A challenge with conventional systems is that they do not provide navigation that adequately reflects the user's current emotions or past travel patterns.

[0537] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0538] In this invention, the server includes information gathering means for acquiring information on driving behavior, route analysis means for analyzing the characteristics of multiple routes using generation technology, and route selection means for selecting the optimal route based on the user's past travel patterns and emotional data. This enables route guidance that takes into account the user's emotional state.

[0539] "Information gathering means" refers to functions for acquiring data on the driver's behavior, and includes information such as location, destination, and driving route.

[0540] "Generative technology" refers to techniques that analyze large amounts of data and synthesize or generate information tailored to specific purposes. For example, it is used for optimizing routes and generating instructions.

[0541] A "route analysis tool" is a function that identifies the characteristics of multiple routes and analyzes the conditions of each route, specifically evaluating elements such as distance, traffic volume, and landmarks.

[0542] A "route selection method" is a function that takes into account the user's past behavior and emotional data to select the optimal route, enabling a less stressful travel experience for the user.

[0543] "Emotional data" refers to information that indicates the user's psychological state, and is measured based on facial expressions, tone of voice, and other biosensor data.

[0544] The "explanation generation means" is a function that generates clear and specific route explanations for the user based on selected route information, and provides instructions that take into account the user's emotional state.

[0545] "Explanation presentation means" refers to a function that presents the generated route explanation to the user visually or audibly, and is intended to support safe and comfortable travel.

[0546] "Learning methods" refer to functions that collect and analyze user feedback data to improve the accuracy and adaptability of the system, and in particular, include learning based on emotional data.

[0547] The present invention provides optimal route guidance in a driver assistance system while taking into account the user's emotional state. This system includes information gathering means, route analysis means, route selection means, emotional data processing means, explanation generation means, explanation presentation means, and learning means.

[0548] The server acquires information about driving behavior, such as GPS data, driving routes, and destinations, from devices within the vehicle, such as in-car navigation systems and dashcams. This information, which also includes traffic conditions and congestion predictions, is updated in real time. The server further uses an emotion engine to understand the driver's emotional state based on their facial expressions, voice, and data obtained from biosensor devices.

[0549] The terminal uses a generated AI model based on the collected data to analyze it. This analysis employs machine learning techniques to evaluate the characteristics of various routes. For example, it includes analyzing congestion levels and landmark locations to select routes that minimize the psychological burden on the driver.

[0550] Based on the analyzed data, the server selects a route. It takes into account the user's past travel patterns, preferences, and emotional data to provide the optimal route that minimizes stress. In this process, the aforementioned emotional data plays a crucial role, with a generative AI model selecting distances and scenery that alleviate specific emotions.

[0551] The generated instructions are provided to the driver by the server as specific directions. The instructions displayed on the terminal via visual and auditory means will take into account the user's mental state, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right."

[0552] Users can travel safely and comfortably by following the guidance provided through their device. For example, when heading to a picnic with family, the system suggests a route that avoids crowded areas in frequently visited parks and provides guidance tailored to the driver's needs.

[0553] As feedback, the device sends the driving results to the server, where learning tools, including emotional data, analyze them to improve the overall system accuracy. This process enables more personalized navigation when the system is reused.

[0554] An example of a prompt message is, "Please tell me the best time and least stressful route for a picnic." This allows the user to choose the optimal route based on the situation at the time.

[0555] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0556] Step 1:

[0557] The server acquires location information, destination information, and driving route data from the in-car navigation system and dashcam. The input data includes GPS data, speed information, and route history, which are used to determine the driver's current location and destination. The output generates geographical context information for the driver. Specifically, the system periodically collects data using the navigation system's API.

[0558] Step 2:

[0559] The server uses an emotion engine to understand the driver's emotional state using data from facial expressions, voice, and other biosensors. Inputs include camera footage, audio recordings, and biometric data from sensors, which are then analyzed by an emotion recognition algorithm. Outputs include evaluation data of the driver's stress level and emotional state. Specifically, emotions are quantified in real time using facial recognition software and voice analysis technology.

[0560] Step 3:

[0561] The terminal receives data provided by the server and performs analysis using a generated AI model. The input includes characteristic information, traffic information, and landmark information for each route. Based on this data, machine learning techniques are used to extract route features suitable for the driver and generate analysis results. The output is an evaluation report that includes detailed convenience and psychological impact for each route. Specifically, the AI ​​model performs route prediction and calculates a convenience score.

[0562] Step 4:

[0563] The server combines analysis results and emotional data to select the optimal route. Route analysis results and driver emotional assessments are used as input. The output is a selected route that reduces user stress and is suitable for the purpose. Adjustments are made based on past behavioral history and emotional data to determine the most appropriate route. Specifically, it uses AI-driven data mining and pattern recognition.

[0564] Step 5:

[0565] Based on the selection results, the server generates specific and emotionally sensitive route descriptions using a generative AI model. Selected route information and landmark information are provided as input. The generated route descriptions are in sentence format and focus on instructions. The output is an emotionally sensitive guide, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right." For specific actions, natural language generation technology is used to create the descriptions.

[0566] Step 6:

[0567] The user receives the generated route description on their terminal and drives based on the guidance. The input is the route description sent from the server, and the output is a safe and comfortable driving experience. Specifically, the terminal also provides voice guidance as needed, allowing the driver to obtain information through both sight and sound.

[0568] Step 7:

[0569] After completing a drive, the terminal sends the selected route and its results to the server. Inputs include stored travel data and driver feedback, while outputs are learning data that contributes to overall system improvement. Furthermore, including emotional data optimizes future route suggestions to reflect the user experience. Specific actions include sending collected data to the cloud and updating the learning algorithm.

[0570] (Application Example 2)

[0571] Next, we will explain Application Example 2. In the following explanation, 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."

[0572] One challenge in autonomous vehicles is the difficulty in selecting the optimal route while considering the emotional state of passengers. Conventional navigation systems select routes without considering the physiological and psychological state of passengers, which can cause stress for some passengers.

[0573] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0574] In this invention, the server includes a device for acquiring driving behavior data, a device for analyzing the characteristics of multiple routes using generation technology, a device for selecting the optimal route based on the user's past behavior patterns, a device for generating an easy-to-understand explanation based on the selected route, a device for presenting the explanation to the user, a device for acquiring and analyzing biometric data for recognizing emotional states, a device for selecting a route based on the analyzed emotional data, and a device for ensuring that the selected route explanation takes into account the user's psychological state. This enables route selection and navigation that takes into account the emotional state of passengers.

[0575] "Driving behavior data" refers to information about the driver and vehicle operation, specifically including speed, acceleration, and brake usage.

[0576] "Generative technology" refers to methods of analyzing and generating information using artificial intelligence and machine learning algorithms, and is a technology that understands the characteristics of data and creates new value.

[0577] "Route analysis" refers to the process of analyzing the characteristics of multiple routes to derive the optimal route, and it evaluates based on factors such as traffic volume and distance.

[0578] "Selecting the optimal route" is the procedure for choosing the route that best suits the user's purpose and conditions, taking into account past behavioral patterns and current circumstances.

[0579] "Easy-to-understand explanations" refer to information provided in a way that users can intuitively comprehend, including specific instructions and landmarks.

[0580] "Emotional state" refers to the user's physiological and psychological state, particularly stress levels and mood.

[0581] "Biometric data" refers to information obtained from an individual's body, including data such as facial expressions, voice tone, and heart rate.

[0582] "Route selection based on analyzed emotional data" is a process for selecting the most optimized route, taking into account the user's emotional information.

[0583] "Path explanation that takes psychological state into consideration" refers to providing route instructions that are adjusted to provide reassurance and satisfaction based on the user's mental state.

[0584] The system implementing this invention consists of three elements: a server, a terminal, and a user. The server uses multiple sensors installed in the vehicle to collect data on driving behavior and biometric data. This includes hardware such as cameras and microphones, which are connected to small computing devices such as Raspberry Pi. A platform on the server with real-time data processing capabilities is used for data transmission and processing. For example, facial recognition using OpenCV, speech analysis using PyAudio, and machine learning libraries such as TensorFlow are applied for biometric data analysis.

[0585] The terminal functions as a central control unit within the autonomous vehicle, performing route selection and explanation generation based on analysis results received from the server. While utilizing external services such as the Google Maps API for route selection, it generates detailed explanations to communicate the selected route to the user. The generated explanations are provided in a format appropriate to the user's emotional state, utilizing generative AI models such as OpenAI's GPT series.

[0586] Users receive route information displayed on their devices, enabling them to travel safely and comfortably. During this process, user feedback and biometric data are sent back to the server as feedback, contributing to the learning and optimization of the entire system.

[0587] For example, if a passenger wishes to relax during their journey, the system can analyze the situation to determine that the passenger is calm and suggest a route with plenty of natural scenery. An example of a prompt to the AI ​​model in this case would be, "Please generate instructions to select a route that will allow the passenger to relax and guide them along a road with beautiful scenery."

[0588] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0589] Step 1:

[0590] The server collects biometric data through cameras and microphones installed inside the vehicle. Inputs include image and audio data from the biosensors. This data is analyzed using OpenCV and PyAudio to determine facial expressions and voice tone. Outputs data indicating the user's emotional state.

[0591] Step 2:

[0592] The server integrates collected driving behavior data and user emotional state data, and performs analysis using generative techniques. The input consists of information about past driving routes and destinations. The data is processed using algorithms such as TensorFlow to generate route suggestions optimized for the user's emotional state. The output is the recommended route.

[0593] Step 3:

[0594] The terminal selects a route based on route suggestions sent from the server. Inputs include route suggestions from the server and current traffic conditions. The terminal uses the Google Maps API to retrieve traffic data and select the optimal route. The output is this optimal route.

[0595] Step 4:

[0596] The terminal generates a unique and easy-to-understand route description using a generation AI model based on the selected route. The input is the route selection result by the terminal. The terminal uses automatically generated prompt sentences to instruct OpenAI's GPT series to generate a route description that takes the user's psychological state into consideration. The output is the route description presented to the user.

[0597] Step 5:

[0598] The user reviews the route description displayed on the terminal and begins moving according to the instructions. The input is the route and instructions provided by the terminal. The route selection result based on the user's choices is returned to the server as feedback. The output is the actual route traveled and the feedback data.

[0599] Step 6:

[0600] The server receives feedback data from the user and initiates the system's learning process. The input consists of user feedback data and biometric data. The server uses this data to improve its generation techniques and optimize for more accurate emotional responses in subsequent uses. The output is the updated algorithm and database.

[0601] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0602] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0603] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0604] [Fourth Embodiment]

[0605] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0606] As shown in Figure 7, the 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.

[0607] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0608] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0609] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0610] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0611] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0612] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0613] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0614] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0615] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0616] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0617] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0618] The present invention provides a system to support drivers in selecting an appropriate route. The system comprises the following components: data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, and learning means.

[0619] First, the server collects data from the in-car navigation system and dashcam. This data includes the driver's current location, destination, and past driving routes, allowing the system to understand driving behavior trends. This information is used as foundational data for analyzing the user's preferences and behavioral patterns.

[0620] Next, the terminal uses generation technology to analyze the collected data and identify multiple routes. Here, route analysis is used to extract the characteristics of each route (e.g., distance, traffic volume, landmarks passed through, etc.). This route information is then used to select the optimal route by comparing it with the user's behavioral patterns, such as what routes the user has chosen in the past and which landmarks they recognize.

[0621] The server then generates a driver-friendly explanation based on the selected route. The explanation generation system uses generation technology to create a specific route, including frequently seen landmarks and intersections. For example, an explanation might be created that includes specific instructions such as, "After passing the park on your right, turn left at the next traffic light."

[0622] Users receive this explanation, which is presented in an easy-to-understand format, allowing them to choose the most suitable route from the available options. This enables more efficient and stress-free driving, while taking into account the user's preferences and familiar routes.

[0623] Finally, the terminal sends the route selected by the user and its results to the server, and the learning mechanism improves the accuracy of the generation technique with past feedback. This feedback loop allows the system to continuously evolve to better suit the user's needs.

[0624] This system allows drivers to receive optimal navigation tailored to their preferences, and the system's adaptive capabilities continuously improve through learning mechanisms.

[0625] The following describes the processing flow.

[0626] Step 1:

[0627] The server retrieves driver location information, destination information, and past driving route data from the in-car navigation system and dashcam. This data is used as basic information to analyze the user's past behavior patterns and preferences.

[0628] Step 2:

[0629] The terminal collects the acquired data and analyzes it using generation technology. This analysis identifies the characteristics of multiple routes, taking into account the driver's preferences, and extracts the distance, traffic conditions, and landmarks passed through each route.

[0630] Step 3:

[0631] Based on the route analysis results, the server selects the optimal route from multiple options, taking into account route patterns previously chosen by the driver and preferred landmarks.

[0632] Step 4:

[0633] The server generates easy-to-understand instructions for the driver based on the selected route. The generating AI creates specific directions that include frequently seen landmarks and facilities, providing clear instructions such as, "Turn right at the next corner where there is a convenience store on your right."

[0634] Step 5:

[0635] The user receives route instructions sent from the server via their device. Based on the instructions provided, the user can choose the most suitable route.

[0636] Step 6:

[0637] The terminal sends information about the route selected by the user to the server and also provides the route selection result as feedback.

[0638] Step 7:

[0639] The server utilizes the collected feedback and uses learning mechanisms to improve the accuracy of its generation technology. This process is carried out to improve the system so that future route suggestions better match the user's preferences.

[0640] (Example 1)

[0641] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] There is a problem in that drivers have difficulty selecting the optimal route based on their own preferences and behavioral patterns. Furthermore, in order to improve the accuracy of route selection, it is necessary to learn from the driver's past choices and effectively utilize feedback.

[0643] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0644] In this invention, the server includes an information gathering means for acquiring information related to driving, a route analysis means for analyzing the attributes of multiple routes using generative artificial intelligence technology, and a route selection means for selecting the optimal route based on the user's past behavior patterns. This enables the efficient and appropriate presentation of routes according to the driver's preferences and continuous improvement of the system's accuracy.

[0645] "Information gathering means" refers to means of acquiring information related to driving, and includes devices or systems that collect data from in-vehicle navigation systems, dashcams, etc.

[0646] "Generative artificial intelligence technology" is a technology that generates new information and options based on past data and learning, and is an algorithm used for optimizing routes and generating explanatory texts.

[0647] A "route analysis means" is a method for analyzing the attributes of multiple routes using generative artificial intelligence technology, and is a system that evaluates and analyzes the distance, traffic volume, and other attributes of the routes.

[0648] A "route selection method" is a means for selecting the optimal route based on the user's past behavior patterns, and is a process for selecting a route that takes into account the user's preferences and past choices.

[0649] An "information generation means" is a system that generates easy-to-understand explanations based on a selected route, and creates specific instructions including landmarks and intersections.

[0650] An "information presentation means" is a means of providing the generated explanation to the user, and is an interface for presenting information through screen display or sound.

[0651] "Educational tools" refer to methods for training generative artificial intelligence technology based on the user's choices and a mechanism for continuously improving the system using feedback.

[0652] This invention is an information processing device that provides drivers with efficient and personalized route selection. Specifically, it consists of three components: a server, a terminal, and a user.

[0653] The server collects driving-related data from the in-vehicle navigation system and dashcam. Through this data collection, the driver's current location, destination, past driving route data, and road conditions are obtained. This data is stored in the server's storage and used for subsequent route analysis.

[0654] The terminal performs route analysis and selection using data received from the server. This is where generative artificial intelligence technology is utilized. The generative AI model generates numerous route options based on the received data and analyzes their characteristics. This process considers factors such as the distance of each route, traffic conditions, and the location of landmarks. For example, a possible prompt to the generative AI model might be, "Consider the driver's past routes and generate an efficient route."

[0655] Next, the server generates a visually easy-to-understand explanation based on the optimal route analyzed and selected by the generating AI model. By using the information generation means, specific instructions including landmarks and intersections are created. For example, navigation such as "After passing landmark A on your right, turn left at the second traffic light" is possible.

[0656] The user receives instructions from the terminal and begins driving accordingly. Information is provided through screen displays and voice guidance, allowing for safe and quick access to information even while driving.

[0657] Finally, the user's selected route and its results are sent from the terminal to the server. This feedback is used to train the generative artificial intelligence technology through educational means, improving the accuracy of future route selections. Through this continuous learning process, the system continues to evolve to meet the driver's preferences and needs.

[0658] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0659] Step 1:

[0660] The server collects driving-related data from the in-vehicle navigation system and dashcam. Inputs include the driver's location, destination, road conditions, and past driving records. This data is stored in the server's storage for analysis. Specifically, the server periodically inputs data via a communication module and stores it in a database.

[0661] Step 2:

[0662] The terminal uses data obtained from the server to apply a generative AI model and perform route analysis. The input is driving-related data received from the server, and the output is multiple route options tailored to the driver's preferences and past behavior patterns. Specifically, the terminal inputs prompt messages to the generative AI model, for example, "Consider the driver's past routes and generate an efficient route," and obtains the analysis results.

[0663] Step 3:

[0664] The server receives route analysis results from the terminal and selects the optimal route. The input is multiple route options, and the output is the selected optimal route. The server scores factors such as route distance, traffic volume, and landmarks passed through, and selects the most appropriate route based on these scores. Specifically, the server uses a selection algorithm to score routes and outputs the route with the highest score.

[0665] Step 4:

[0666] The server generates instructions for the driver based on the selected optimal route. The input is the selected route, and the output is an easy-to-understand explanation presented to the driver. Specifically, the server uses a generation AI to create detailed navigation, including visual landmarks such as intersections.

[0667] Step 5:

[0668] The user receives instructions from the server via a terminal and then begins driving. The input is the instructional text from the server, and the output is the result of the user's route selection. In terms of specific actions, the user checks the terminal's screen display and voice guidance and proceeds with driving according to the instructions.

[0669] Step 6:

[0670] The terminal sends the user's route selection results and feedback after the drive to the server. The input is the user's feedback data, and the output is the training data for the generated AI model. Specifically, the terminal analyzes the received feedback and sends it to the server to improve the model's accuracy.

[0671] (Application Example 1)

[0672] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0673] In autonomous vehicles, there is a challenge in selecting the optimal route based on the individual behavior patterns of the user. In particular, there is a need to propose an effective route that takes into account the user's preferences and past choices, while also responding to real-time changes in traffic conditions. Furthermore, efficiently reflecting this route information in the autonomous vehicle is also a challenge.

[0674] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0675] In this invention, the server includes information gathering means for acquiring information on driving behavior, route analysis means for analyzing the characteristics of multiple routes using generation technology, route selection means for selecting an optimal route based on the user's past behavioral tendencies, instruction generation means for generating clear instructions based on the selected route, instruction presentation means for presenting the instructions to the user, and communication means for providing route instructions to the automated vehicle. This makes it possible to select an optimal route that takes into account the user's preferences and real-time traffic conditions, and to quickly reflect that information in the automated vehicle.

[0676] "Information on driving behavior" refers to records of driving operations performed by the vehicle driver and their results.

[0677] "Information gathering means" refers to means that have the function of acquiring information on driving behavior and accumulating it as data.

[0678] "Generative technology" is a concept that refers to algorithms and methods for processing large amounts of data to generate new information.

[0679] A "route analysis means" is a means for analyzing the characteristics of acquired route data.

[0680] "Behavioral tendencies" refer to characteristics related to the driving patterns and preferences that the user has chosen in the past.

[0681] A "route selection method" is a means of identifying the optimal route based on the user's behavioral tendencies.

[0682] "Instruction generation means" refers to a means for presenting a clear route to the user based on the optimal path.

[0683] A "means for presenting instructions" is a means of communicating generated instructions to the driver or system.

[0684] "Communication means" refers to communication protocols and devices used to transmit generated route instructions to an automated mobile vehicle.

[0685] The term "autonomous mobile device" refers to a machine that moves while making its own decisions based on external instructions.

[0686] The system for realizing this invention aims to generate and present the optimal route based on driver behavior data. Here, the server plays a central role, integrating information gathering means, generation technology, instruction generation and presentation, and communication means.

[0687] The server first acquires information on driving behavior transmitted from on-board sensors through information gathering means. This information includes the driver's current location, destination, and past driving routes, and is used for trend analysis of driving patterns.

[0688] Next, the server uses generation technology to perform route analysis based on the data obtained by the information gathering means. The analyzed data reveals the characteristics of multiple routes (e.g., distance, average speed, reference points passed through, etc.) and is used for evaluation by the route selection means and for selecting the optimal route.

[0689] The optimal route selected by the route selection means is converted into specific travel instructions by the instruction generation means. In this process, reference points frequently seen by the user are included in the instructions, presenting them in a clear and easy-to-understand manner for the driver.

[0690] Instructions based on the selected route are transmitted in real time to the control system of the automated vehicle using communication means installed on the vehicle. This allows the automated vehicle to operate smoothly according to the proposed optimal route.

[0691] A specific example of the present invention is a situation in which, during commuting hours, an optimal route is proposed that avoids traffic congestion while utilizing scenic roads preferred by the driver. In this case, the generating AI model considers prompt statements such as, "For this week's commute, please tell me your usual route with minimal traffic congestion. I would like a route that also passes through parks and scenic spots," and generates individually optimized instructions.

[0692] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0693] Step 1:

[0694] The server uses data collection tools to acquire information about driving behavior from on-board sensors. Inputs include the driver's location and destination, while output is an aggregation of this data. This information is used as foundational data for analyzing driving pattern trends.

[0695] Step 2:

[0696] The server analyzes the input driving data using generation technology. This analysis process evaluates the characteristics of multiple routes, including distance, speed, and reference points. Data calculations output an evaluation score for each route, revealing the driver's past behavioral tendencies.

[0697] Step 3:

[0698] The server uses a route selection mechanism to select the optimal route based on the analysis results. The input is data from multiple evaluated routes, and the output is information on the selected optimal route. This selection process takes into account past user preferences and traffic conditions.

[0699] Step 4:

[0700] The server generates specific travel instructions based on the selected optimal route using an instruction generation mechanism. The input is information about the optimal route, and the output includes detailed instructions, such as "Turn left at the next intersection." These instructions are easy for the driver to understand intuitively because they highlight reference points that the user frequently sees.

[0701] Step 5:

[0702] The server transmits the generated instructions to the driver and the control system of the automated vehicle through the instruction presentation means. The output is navigation information presented in visual and audible formats. This allows the driver to move safely and comfortably based on the received instructions.

[0703] Step 6:

[0704] The user returns the route selection results to the server as feedback. The feedback inputs include the results of the selected route and the driver's satisfaction level. The server uses this information as a learning tool to update the generative AI model. The output is an improved route selection algorithm, which improves the accuracy of future route suggestions.

[0705] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0706] This invention aims to realize a system that enables more accurate route selection and explanation provision by combining an emotion engine with a driver assistance system. The system comprises data collection means, route analysis means, route selection means, explanation generation means, explanation presentation means, learning means, and an emotion engine.

[0707] First, the server acquires the driver's location, destination information, and past driving route data from the in-car navigation system and dashcam. In addition, the emotion engine recognizes the driver's emotional state using facial expressions, tone of voice, and other biosensor data, and collects this information as foundational data used throughout the system.

[0708] Next, the terminal collects data and analyzes it using generation technology. Route analysis means support this, identifying the characteristics of each route and extracting the conditions for each route (distance, traffic volume, landmarks, etc.). Furthermore, using emotional information obtained from the emotion engine, route selection is performed to match the driver's stress level and mood.

[0709] Subsequently, the server uses the analysis results and route selection methods to determine the optimal route, taking into account patterns and preferences from previously selected routes. It adjusts the selection results according to the emotion engine data, selecting routes and landmarks to reduce stress.

[0710] Based on the selection results, the server uses an explanation generation mechanism to create a specific route. The generating AI produces an easy-to-understand route explanation that includes specific instructions, making it possible to provide explanations that take into account the driver's mental state, such as "Turn left at the next corner in front of the building with the humorous advertisement."

[0711] The user receives this route description on their device and can choose a safe and comfortable route without being influenced by their current emotional state. Even if a choice is made without emotional influence, feedback is provided as it occurs.

[0712] Finally, the terminal sends the user's selected route and its results to the server, where learning tools, including an emotion engine, use the data to improve accuracy. For subsequent system use, navigation that is more considerate of the user's psychological state is provided.

[0713] This system allows drivers to receive optimal navigation that takes into account their emotional state while driving, and the overall adaptive capability of the system continuously improves through the use of an emotion engine.

[0714] The following describes the processing flow.

[0715] Step 1:

[0716] The server works in conjunction with the in-car navigation system to acquire the driver's current location, destination information, and past driving history data. It also analyzes the driver's facial expressions and voice data through an emotion engine to determine their current emotional state.

[0717] Step 2:

[0718] The device integrates driving data and emotional data and performs analysis using generational technology. This analysis identifies the characteristics of multiple routes and processes the distance, traffic information, and landmark locations for each route. The data used helps select a less stressful route based on the user's emotional state.

[0719] Step 3:

[0720] Based on the analyzed data, the server selects the optimal route, taking into account the driver's past behavior patterns and preferences. It also references the output of the emotion engine and automatically incorporates stress-reducing content into its selections.

[0721] Step 4:

[0722] Based on the selected route, the server uses an explanation generation system to create a driver-friendly route. In this process, the generating AI creates explanatory text that includes landmarks and specific instructions, providing easy-to-understand guidance that responds to the user's emotional state.

[0723] Step 5:

[0724] The user receives a generated route description through their device. This description, which reflects the analysis results of the emotion engine, allows them to select the most comfortable route that best suits their current emotional state.

[0725] Step 6:

[0726] The terminal sends the user's final route selection to the server, and feedback data is collected in conjunction with the driver's selection. This data is used to improve the system's performance in the future.

[0727] Step 7:

[0728] The server utilizes feedback data and output from the emotion engine, employing learning methods to improve the accuracy of its generation techniques, and ultimately leading to improvements in the system to provide more user-friendly navigation.

[0729] (Example 2)

[0730] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0731] In driver assistance systems, route selection does not take into account the driver's psychological state, making it difficult to avoid situations that are easily affected by stress and emotions. A challenge with conventional systems is that they do not provide navigation that adequately reflects the user's current emotions or past travel patterns.

[0732] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0733] In this invention, the server includes information gathering means for acquiring information on driving behavior, route analysis means for analyzing the characteristics of multiple routes using generation technology, and route selection means for selecting the optimal route based on the user's past travel patterns and emotional data. This enables route guidance that takes into account the user's emotional state.

[0734] "Information gathering means" refers to functions for acquiring data on the driver's behavior, and includes information such as location, destination, and driving route.

[0735] "Generative technology" refers to techniques that analyze large amounts of data and synthesize or generate information tailored to specific purposes. For example, it is used for optimizing routes and generating instructions.

[0736] A "route analysis tool" is a function that identifies the characteristics of multiple routes and analyzes the conditions of each route, specifically evaluating elements such as distance, traffic volume, and landmarks.

[0737] A "route selection method" is a function that takes into account the user's past behavior and emotional data to select the optimal route, enabling a less stressful travel experience for the user.

[0738] "Emotional data" refers to information that indicates the user's psychological state, and is measured based on facial expressions, tone of voice, and other biosensor data.

[0739] The "explanation generation means" is a function that generates clear and specific route explanations for the user based on selected route information, and provides instructions that take into account the user's emotional state.

[0740] "Explanation presentation means" refers to a function that presents the generated route explanation to the user visually or audibly, and is intended to support safe and comfortable travel.

[0741] "Learning methods" refer to functions that collect and analyze user feedback data to improve the accuracy and adaptability of the system, and in particular, include learning based on emotional data.

[0742] The present invention provides optimal route guidance in a driver assistance system while taking into account the user's emotional state. This system includes information gathering means, route analysis means, route selection means, emotional data processing means, explanation generation means, explanation presentation means, and learning means.

[0743] The server acquires information about driving behavior, such as GPS data, driving routes, and destinations, from devices within the vehicle, such as in-car navigation systems and dashcams. This information, which also includes traffic conditions and congestion predictions, is updated in real time. The server further uses an emotion engine to understand the driver's emotional state based on their facial expressions, voice, and data obtained from biosensor devices.

[0744] The terminal uses a generated AI model based on the collected data to analyze it. This analysis employs machine learning techniques to evaluate the characteristics of various routes. For example, it includes analyzing congestion levels and landmark locations to select routes that minimize the psychological burden on the driver.

[0745] Based on the analyzed data, the server selects a route. It takes into account the user's past travel patterns, preferences, and emotional data to provide the optimal route that minimizes stress. In this process, the aforementioned emotional data plays a crucial role, with a generative AI model selecting distances and scenery that alleviate specific emotions.

[0746] The generated instructions are provided to the driver by the server as specific directions. The instructions displayed on the terminal via visual and auditory means will take into account the user's mental state, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right."

[0747] Users can travel safely and comfortably by following the guidance provided through their device. For example, when heading to a picnic with family, the system suggests a route that avoids crowded areas in frequently visited parks and provides guidance tailored to the driver's needs.

[0748] As feedback, the device sends the driving results to the server, where learning tools, including emotional data, analyze them to improve the overall system accuracy. This process enables more personalized navigation when the system is reused.

[0749] An example of a prompt message is, "Please tell me the best time and least stressful route for a picnic." This allows the user to choose the optimal route based on the situation at the time.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1:

[0752] The server acquires location information, destination information, and driving route data from the in-car navigation system and dashcam. The input data includes GPS data, speed information, and route history, which are used to determine the driver's current location and destination. The output generates geographical context information for the driver. Specifically, the system periodically collects data using the navigation system's API.

[0753] Step 2:

[0754] The server uses an emotion engine to understand the driver's emotional state using data from facial expressions, voice, and other biosensors. Inputs include camera footage, audio recordings, and biometric data from sensors, which are then analyzed by an emotion recognition algorithm. Outputs include evaluation data of the driver's stress level and emotional state. Specifically, emotions are quantified in real time using facial recognition software and voice analysis technology.

[0755] Step 3:

[0756] The terminal receives data provided by the server and performs analysis using a generated AI model. The input includes characteristic information, traffic information, and landmark information for each route. Based on this data, machine learning techniques are used to extract route features suitable for the driver and generate analysis results. The output is an evaluation report that includes detailed convenience and psychological impact for each route. Specifically, the AI ​​model performs route prediction and calculates a convenience score.

[0757] Step 4:

[0758] The server combines analysis results and emotional data to select the optimal route. Route analysis results and driver emotional assessments are used as input. The output is a selected route that reduces user stress and is suitable for the purpose. Adjustments are made based on past behavioral history and emotional data to determine the most appropriate route. Specifically, it uses AI-driven data mining and pattern recognition.

[0759] Step 5:

[0760] Based on the selection results, the server generates specific and emotionally sensitive route descriptions using a generative AI model. Selected route information and landmark information are provided as input. The generated route descriptions are in sentence format and focus on instructions. The output is an emotionally sensitive guide, such as, "Turn right at the next traffic light, and you will see a beautiful park on your right." For specific actions, natural language generation technology is used to create the descriptions.

[0761] Step 6:

[0762] The user receives the generated route description on their terminal and drives based on the guidance. The input is the route description sent from the server, and the output is a safe and comfortable driving experience. Specifically, the terminal also provides voice guidance as needed, allowing the driver to obtain information through both sight and sound.

[0763] Step 7:

[0764] After completing a drive, the terminal sends the selected route and its results to the server. Inputs include stored travel data and driver feedback, while outputs are learning data that contributes to overall system improvement. Furthermore, including emotional data optimizes future route suggestions to reflect the user experience. Specific actions include sending collected data to the cloud and updating the learning algorithm.

[0765] (Application Example 2)

[0766] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0767] One challenge in autonomous vehicles is the difficulty in selecting the optimal route while considering the emotional state of passengers. Conventional navigation systems select routes without considering the physiological and psychological state of passengers, which can cause stress for some passengers.

[0768] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0769] In this invention, the server includes a device for acquiring driving behavior data, a device for analyzing the characteristics of multiple routes using generation technology, a device for selecting the optimal route based on the user's past behavior patterns, a device for generating an easy-to-understand explanation based on the selected route, a device for presenting the explanation to the user, a device for acquiring and analyzing biometric data for recognizing emotional states, a device for selecting a route based on the analyzed emotional data, and a device for ensuring that the selected route explanation takes into account the user's psychological state. This enables route selection and navigation that takes into account the emotional state of passengers.

[0770] "Driving behavior data" refers to information about the driver and vehicle operation, specifically including speed, acceleration, and brake usage.

[0771] "Generative technology" refers to methods of analyzing and generating information using artificial intelligence and machine learning algorithms, and is a technology that understands the characteristics of data and creates new value.

[0772] "Route analysis" refers to the process of analyzing the characteristics of multiple routes to derive the optimal route, and it evaluates based on factors such as traffic volume and distance.

[0773] "Selecting the optimal route" is the procedure for choosing the route that best suits the user's purpose and conditions, taking into account past behavioral patterns and current circumstances.

[0774] "Easy-to-understand explanations" refer to information provided in a way that users can intuitively comprehend, including specific instructions and landmarks.

[0775] "Emotional state" refers to the user's physiological and psychological state, particularly stress levels and mood.

[0776] "Biometric data" refers to information obtained from an individual's body, including data such as facial expressions, voice tone, and heart rate.

[0777] "Route selection based on analyzed emotional data" is a process for selecting the most optimized route, taking into account the user's emotional information.

[0778] "Path explanation that takes psychological state into consideration" refers to providing route instructions that are adjusted to provide reassurance and satisfaction based on the user's mental state.

[0779] The system implementing this invention consists of three elements: a server, a terminal, and a user. The server uses multiple sensors installed in the vehicle to collect data on driving behavior and biometric data. This includes hardware such as cameras and microphones, which are connected to small computing devices such as Raspberry Pi. A platform on the server with real-time data processing capabilities is used for data transmission and processing. For example, facial recognition using OpenCV, speech analysis using PyAudio, and machine learning libraries such as TensorFlow are applied for biometric data analysis.

[0780] The terminal functions as a central control unit within the autonomous vehicle, performing route selection and explanation generation based on analysis results received from the server. While utilizing external services such as the Google Maps API for route selection, it generates detailed explanations to communicate the selected route to the user. The generated explanations are provided in a format appropriate to the user's emotional state, utilizing generative AI models such as OpenAI's GPT series.

[0781] Users receive route information displayed on their devices, enabling them to travel safely and comfortably. During this process, user feedback and biometric data are sent back to the server as feedback, contributing to the learning and optimization of the entire system.

[0782] For example, if a passenger wishes to relax during their journey, the system can analyze the situation to determine that the passenger is calm and suggest a route with plenty of natural scenery. An example of a prompt to the AI ​​model in this case would be, "Please generate instructions to select a route that will allow the passenger to relax and guide them along a road with beautiful scenery."

[0783] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0784] Step 1:

[0785] The server collects biometric data through cameras and microphones installed inside the vehicle. Inputs include image and audio data from the biosensors. This data is analyzed using OpenCV and PyAudio to determine facial expressions and voice tone. Outputs data indicating the user's emotional state.

[0786] Step 2:

[0787] The server integrates collected driving behavior data and user emotional state data, and performs analysis using generative techniques. The input consists of information about past driving routes and destinations. The data is processed using algorithms such as TensorFlow to generate route suggestions optimized for the user's emotional state. The output is the recommended route.

[0788] Step 3:

[0789] The terminal selects a route based on route suggestions sent from the server. Inputs include route suggestions from the server and current traffic conditions. The terminal uses the Google Maps API to retrieve traffic data and select the optimal route. The output is this optimal route.

[0790] Step 4:

[0791] The terminal generates a unique and easy-to-understand route description using a generation AI model based on the selected route. The input is the route selection result by the terminal. The terminal uses automatically generated prompt sentences to instruct OpenAI's GPT series to generate a route description that takes the user's psychological state into consideration. The output is the route description presented to the user.

[0792] Step 5:

[0793] The user reviews the route description displayed on the terminal and begins moving according to the instructions. The input is the route and instructions provided by the terminal. The route selection result based on the user's choices is returned to the server as feedback. The output is the actual route traveled and the feedback data.

[0794] Step 6:

[0795] The server receives feedback data from the user and initiates the system's learning process. The input consists of user feedback data and biometric data. The server uses this data to improve its generation techniques and optimize for more accurate emotional responses in subsequent uses. The output is the updated algorithm and database.

[0796] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0797] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0798] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0799] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0800] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0801] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0802] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0803] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0804] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0805] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0806] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0807] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0808] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0809] 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.

[0810] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0811] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0812] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0813] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0814] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0815] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0816] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0817] The following is further disclosed regarding the embodiments described above.

[0818] (Claim 1)

[0819] A data collection method for acquiring data on driving behavior,

[0820] A path analysis means that analyzes the characteristics of multiple paths using generation technology,

[0821] A route selection means that selects the optimal route based on the user's past behavior patterns,

[0822] Explanation generation means for generating an easy-to-understand explanation based on the selected route,

[0823] An explanation presentation means for presenting the aforementioned explanation to the user,

[0824] A learning method for training generation technology based on the user's route selection results,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the description generation means generates a description that includes landmarks that the user frequently sees.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the learning means collects user feedback data and improves the accuracy of the generation technology.

[0830] "Example 1"

[0831] (Claim 1)

[0832] Information gathering means for obtaining information related to driving,

[0833] A path analysis means that analyzes the attributes of multiple paths using generative artificial intelligence technology,

[0834] A route selection means that selects the optimal route based on the user's past behavior patterns,

[0835] Information generation means that generates an easy-to-understand explanation based on the selected route,

[0836] Information presentation means for presenting the above explanation to the user,

[0837] An educational tool that trains generative artificial intelligence technology based on the user's path selection results,

[0838] Information processing device including

[0839] (Claim 2)

[0840] The information processing apparatus according to claim 1, wherein the information generation means generates a description that includes features frequently viewed by the user.

[0841] (Claim 3)

[0842] The information processing apparatus according to claim 1, wherein the educational means collects user evaluation data and improves the accuracy of generative artificial intelligence technology.

[0843] "Application Example 1"

[0844] (Claim 1)

[0845] Information gathering means for acquiring information on driving behavior,

[0846] A path analysis means that analyzes the characteristics of multiple paths using generation technology,

[0847] A route selection method that selects the optimal route based on the user's past behavioral trends,

[0848] Instruction generation means for generating clear instructions based on the selected route,

[0849] An instruction presentation means for presenting the aforementioned instructions to the user,

[0850] A learning method for training generation technology based on the user's route selection results,

[0851] A communication means for providing route instructions in an automated mobile vehicle,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, wherein the instruction generating means generates instructions that include reference points that the user frequently sees.

[0855] (Claim 3)

[0856] The system according to claim 1, wherein the learning means collects user feedback information and improves the accuracy of the generation technology.

[0857] "Example 2 of combining an emotion engine"

[0858] (Claim 1)

[0859] Information gathering means for acquiring information on driving behavior,

[0860] A path analysis means that analyzes the characteristics of multiple paths using generation technology,

[0861] A route selection means that selects the optimal route based on the user's past travel patterns and emotional data,

[0862] An explanation generation means that uses a generated AI model based on the selected route to generate an explanation that takes into account the user's mental state,

[0863] An explanatory presentation means for presenting the aforementioned explanation to the user visually and audibly,

[0864] A learning method that trains generation technology based on user feedback results including emotional data,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, wherein the explanation generating means generates an explanation that includes instructions corresponding to the user's emotional state and takes into account landmarks that reduce stress.

[0868] (Claim 3)

[0869] The system according to claim 1, wherein the learning means uses emotional information collected by the emotion engine as feedback data to improve the accuracy of the generation technology.

[0870] "Application example 2 when combining with an emotional engine"

[0871] (Claim 1)

[0872] A device for acquiring data on driving behavior,

[0873] A device that analyzes the characteristics of multiple paths using generation technology,

[0874] A device that selects the optimal route based on the user's past behavior patterns,

[0875] A device that generates easy-to-understand explanations based on the selected route,

[0876] A device that presents the above explanation to the user,

[0877] A device that acquires and analyzes biometric data to recognize emotional states,

[0878] A device that selects a route based on analyzed emotional data,

[0879] A device that guarantees that the selected route description takes into account the user's psychological state,

[0880] A device that learns generation technology based on the user's route selection results,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, wherein the explanation generation device generates explanations tailored to the user's frequently seen landmarks and emotional state.

[0884] (Claim 3)

[0885] The system according to claim 1, wherein the learning device collects user feedback data and emotion change data to improve the accuracy of the generation technology. [Explanation of symbols]

[0886] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method for acquiring data on driving behavior, A path analysis means that analyzes the characteristics of multiple paths using generation technology, A route selection means that selects the optimal route based on the user's past behavior patterns, Explanation generation means for generating an easy-to-understand explanation based on the selected route, An explanation presentation means for presenting the aforementioned explanation to the user, A learning method for training generation technology based on the user's route selection results, A system that includes this.

2. The system according to claim 1, wherein the description generation means generates a description that includes landmarks that the user frequently sees.

3. The system according to claim 1, wherein the learning means collects user feedback data and improves the accuracy of the generation technology.

Images