system

Abstract

We provide the system. [Solution] A means for analyzing speech or text input using a generative model to identify destinations and waypoints, A means of acquiring traffic information and calculating the optimal route, A means of presenting proposed routes and candidate locations to the user and adjusting the route based on the user's instructions and responses, A means of monitoring traffic conditions in real time and recalculating routes, A system that includes this.

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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional navigation systems have required pre-setting destinations and waypoints, which were difficult to change during driving and often involved risks. Furthermore, they were unable to flexibly respond to changes in traffic conditions, increasing the burden and risk on drivers. As a result, there was a problem that safe and efficient movement was difficult.

Means for Solving the Problems

[0005] This invention provides a means for analyzing voice or text input using a generative model to identify destinations and waypoints. Furthermore, it includes means for acquiring real-time traffic information to calculate the optimal route, and means for presenting routes and candidate locations to the user and modifying the route based on feedback. In addition, it achieves safe and efficient navigation by recalculating the route in response to changes in traffic conditions and presenting alternative options to the user.

[0006] A "generative model" is a type of artificial intelligence that analyzes speech and text to identify destinations and directions based on their content.

[0007] "Traffic information" refers to real-time data such as road congestion, accidents, and road closures due to construction, and is an important factor when calculating routes.

[0008] "Route calculation" is the process of determining the optimal route to a destination or intermediate points based on traffic information.

[0009] "Candidate locations" refer to suggested locations that users can select as waypoints or rest stops, and are presented by a generative model.

[0010] "Real-time" means being able to instantly reflect the current situation and respond immediately without missing an opportunity.

[0011] An "alternative" is a new option proposed to the user when the original plan or route is undesirable.

[0012] "Navigation" is the process of guiding users on the route to their specified destination and providing support to ensure they follow the directions. [Brief explanation of the drawing]

[0013] [Figure 1] This 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 device 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 device 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 device 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 device 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

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

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

[0016] In the following embodiments, the processor with reference numerals (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.

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

[0018] In the following embodiments, the storage with reference numerals 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.

[0019] [[ID=**16**]]In the following embodiments, the communication I / F (Interface) with reference numerals is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc. [[ID=**17**]] [[ID=**18**]]

[0020] [[ID=**19**]] It should be noted that in the original text, there are some consecutive tags without content between lines 11 and 16. I have translated the text as accurately as possible while maintaining the original format and tags. If there are any specific requirements or corrections regarding this, please let me know. Also, in the translation, I have made sure to follow the rules you provided strictly. For the line 16 translation, I have adjusted the format to make it more in line with the overall structure while keeping the content intact as per the rules. If this is not acceptable, please clarify the requirements.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."

[0021] [First Embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This system is a navigation system that analyzes user voice or text input to efficiently set destinations and waypoints. When the user communicates their travel preferences to the terminal in natural language, the terminal analyzes the content using speech recognition and natural language processing technologies and sends the converted data to a generative model. Based on this data, the generative model identifies the destination and possible waypoints.

[0035] The server collects real-time traffic information based on the specified destination and waypoints, and calculates the optimal route. This traffic information includes road congestion, accident information, and construction status, and the server uses this data to present the user with the best possible route.

[0036] Furthermore, the device can use a generative model to suggest potential rest stops and tourist attractions along the way. This makes it easy for users to add waypoints and adjust their rest plans.

[0037] While driving, the server continuously monitors changes in traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server can generate an alternative route and present it to the user via the terminal. The user can then efficiently correct the route in real time by approving the proposed alternative.

[0038] As a concrete example, suppose a user wants to travel from Tokyo to Nagoya and wants to stop in Yokohama along the way. The user instructs the device, "I want to go to Nagoya via Yokohama." Upon receiving this instruction, the device uses a generative model to convert the speech into text and analyzes the content of the instruction.

[0039] The server calculates the optimal route from Tokyo to Yokohama and then to Nagoya, taking traffic information into account. If traffic congestion occurs on the way to Yokohama after departure, the server calculates an alternative optimal route and suggests it to the user via the terminal, saying, "There is traffic congestion. Please try the new route." In this way, users can reach their destination via the optimal route without stress.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user enters instructions into the device via voice or text, specifying the destination and waypoints.

[0043] Step 2:

[0044] The terminal receives the user's voice input and converts it into text using speech recognition technology. The resulting text data is then analyzed using natural language processing technology to identify the destination and waypoints.

[0045] Step 3:

[0046] The device sends the analysis results to a generative model, which accurately understands the user's intent. The information obtained by the generative model is then converted into detailed instructions for the next action.

[0047] Step 4:

[0048] The server obtains real-time traffic information based on the specified destination and waypoint information and calculates the optimal route. The server collects current road conditions, accident information, construction information, etc. from the internet and traffic databases.

[0049] Step 5:

[0050] The server sends the route calculation results to the terminal, which then presents the calculated optimal route to the user. The user reviews the presented optimal route and makes adjustments or additional instructions as needed.

[0051] Step 6:

[0052] The device uses a generative model to suggest potential rest stops and tourist spots along the route, presenting them to the user as options.

[0053] Step 7:

[0054] During operation, the server periodically monitors traffic conditions and recalculates the route as needed. For example, if congestion or an accident occurs, the server generates an alternative route and resends it.

[0055] Step 8:

[0056] The device presents the user with a recalculated alternative route, and if the user approves the new route, it updates the navigation and continues providing directions.

[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] Modern navigation systems lack the ability to provide optimal routes that reflect real-time traffic conditions, and they also struggle to suggest waypoints based on user preferences and dynamically adjust routes. Furthermore, their suggestions for rest stops and tourist attractions are limited, highlighting the need for improved user experience.

[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 means for analyzing the user's voice or text input using speech recognition technology and natural language processing technology to identify destinations and intermediate points based on a generative model; means for acquiring traffic conditions, calculating and proposing an optimal route; and means for monitoring traffic conditions in real time while driving and recalculating the route as needed. This enables flexible and optimal navigation that efficiently and accurately reflects the user's wishes.

[0062] "User" refers to the entity that operates the system and specifies destinations and intermediate stops.

[0063] "Speech recognition technology" refers to the technology that analyzes voice input and converts it into corresponding text data.

[0064] "Natural language processing technology" refers to techniques for analyzing text written in natural language and understanding its meaning and intent.

[0065] A "generative model" refers to an algorithm or system that generates a specific output based on input data.

[0066] "Destination" refers to the place that the user ultimately wishes to reach.

[0067] A "stopover point" refers to a designated location where you are to stop on your way to your destination.

[0068] "Traffic conditions" refers to information that includes all factors affecting travel, such as road congestion, accident information, and whether or not there is construction work.

[0069] "Optimal route" refers to the shortest or most efficient path to the destination under specified conditions.

[0070] "Real-time monitoring" refers to constantly observing the ongoing traffic situation and updating the information as needed.

[0071] "Recalculating the route" refers to recalculating the path to the destination based on predicted changes and new information.

[0072] This invention is a system in which users input their travel preferences into a terminal via voice or text, and the system provides optimal navigation via a server.

[0073] First, the user communicates their travel preferences to the device in natural language. The device uses speech recognition technology (e.g., a common speech recognition API) to receive the voice input. The speech recognition technology converts the voice into text, and then natural language processing technology (e.g., a natural language processing library or model) is used to analyze the text for destination and waypoint information.

[0074] The analyzed information is sent to a generative AI model and input as a specific prompt, such as "Calculate the route to the next destination. The starting point is Tokyo, the intermediate point is Yokohama, and the final destination is Nagoya." This generative AI model is designed to identify the destination and intermediate points based on the input prompt.

[0075] Next, the server receives destination information and collects traffic information in real time. This traffic information is obtained from a dedicated API and includes road congestion, accidents, and construction information. Based on this information, the server calculates the optimal route and sends the calculation result to the terminal.

[0076] The device presents the user with a calculated optimal route. Furthermore, it can use a generative AI model to suggest rest stops and sightseeing spots along the way. This allows users to create more personalized travel plans in addition to standard navigation.

[0077] While driving, the server continuously monitors traffic conditions. For example, if unexpected congestion occurs along the way, the server recalculates the route and proposes a new route to the user via the terminal. In this way, users can always reach their destination efficiently based on the latest information.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user enters their travel preferences into the device via voice or text.

[0081] As a concrete example, the user speaks into their smartphone saying, "I want to go to Nagoya via Yokohama." This input data is converted into text data through speech recognition technology. Once the voice input is converted into text information via speech recognition, it is ready to proceed to the next analysis step.

[0082] Step 2:

[0083] The device analyzes the text converted by speech recognition.

[0084] Using natural language processing technology, the converted text data is analyzed to extract the destination "Nagoya" and the waypoint "Yokohama". At this stage, analysis is performed to understand the user's intent, and the destination and waypoint information is output as a result of the analysis.

[0085] Step 3:

[0086] The device sends the analysis results to an AI model that generates them.

[0087] Specifically, a prompt message such as "Calculate the route to the next destination. The starting point is Tokyo, the intermediate point is Yokohama, and the final destination is Nagoya" is created and passed to the generating AI model. Based on this prompt, the AI ​​model checks the destination and intermediate points and outputs a corresponding list.

[0088] Step 4:

[0089] The server receives data from the generated AI model and collects traffic information.

[0090] The server obtains real-time road and traffic conditions through a traffic information API. This data includes road congestion and construction information, and is used to calculate the optimal route. The calculated route information is then generated from the server.

[0091] Step 5:

[0092] The terminal presents the user with the optimal route received from the server.

[0093] The terminal displays route information retrieved from the server on its screen and suggests rest stops and sightseeing spots along the way as needed. Users can review the presented information and adjust their travel plan accordingly. The output includes detailed map displays and route guidance.

[0094] Step 6:

[0095] The server monitors traffic conditions while driving and recalculates the route if necessary.

[0096] When new traffic conditions, such as congestion or accident information, are received, the server recalculates the route and calculates a new optimal route. The result is sent to the terminal, and the user receives a notification such as "A new route is available." Based on this information, the user can continue to efficiently adjust their route in real time.

[0097] (Application Example 1)

[0098] 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."

[0099] Autonomous vehicles require systems that can efficiently set routes to destinations and respond quickly to real-time changes. However, current navigation systems do not adequately provide intuitive route setting via voice input or information display using visual devices. Furthermore, they lack sufficient flexibility in rerouting in response to changes in traffic conditions, resulting in reduced convenience for users.

[0100] 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.

[0101] In this invention, the server includes means for analyzing voice or text input using a generative model to identify the destination and waypoints, means for acquiring traffic information and calculating the optimal route, and means for presenting the proposed route to a visual device and adjusting the route based on the user's instructions and responses. This makes it possible for users to obtain the optimal route to their destination with simple voice input and to provide a means that can flexibly respond to real-time changing traffic conditions.

[0102] A "generative model" is an artificial intelligence technology that analyzes speech and text data to identify destinations, waypoints, and other points of reference.

[0103] "Means for analyzing voice or text input" refers to means that have the function of understanding voice or text instructions from the user and extracting necessary information.

[0104] A "means for calculating the optimal route" refers to a means that has the function of deriving the shortest or most efficient route to a destination while taking into account traffic information acquired in real time.

[0105] A "means for adjusting routes based on instructions and responses" refers to a means that has the function of modifying and optimizing the proposed route in accordance with user approval or instructions.

[0106] A "means of monitoring traffic conditions in real time" refers to a means of continuously acquiring updated traffic data and evaluating the current route based on that information.

[0107] A "visual device" is a device used by a user to view information, and includes display devices such as smart glasses and displays.

[0108] The system for carrying out this invention begins with the user entering their destination by voice or text. The terminal analyzes the user's input using a combination of speech recognition and natural language processing technologies and transmits the content to a generative AI model in text format. This generative AI model uses prompt sentences to identify destinations and waypoints and generates data for further suggestions. One example of such a prompt sentence is "Please suggest destinations and waypoints: [Example of user input]".

[0109] The server receives the analyzed data and collects the latest traffic information in real time. This traffic information includes road congestion, accident information, and construction. Based on this information, the server calculates the optimal route to the destination and selected waypoints. The calculated route is displayed on a visual device so that the user can check it while traveling. Visual devices include display devices such as smart glasses.

[0110] While driving, the server constantly monitors traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server calculates an alternative route and displays a message on the visual device saying, "There is congestion. Please try the new route." This feature allows users to reach their destination via the optimal route without stress.

[0111] The main hardware used for this system includes microphones, smartphones, and smart glasses, while the software includes Python, the SpeechRecognition library, and the OpenAI® API. This system provides users with intuitive and efficient route planning, improving the travel experience.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The device receives the user's voice input via a microphone and converts that voice data into text data using the SpeechRecognition library. The input is voice data, and the output is the converted text data. In this step, data conversion is performed to extract the necessary information from the voice.

[0115] Step 2:

[0116] The device generates a prompt message for the generative AI model and sends it as text data. Specifically, it generates a prompt message such as "Suggest a destination and waypoints: [User input text]". The input is text data, and the output is a prompt message that the generative model can interpret.

[0117] Step 3:

[0118] The server receives responses from the generative AI model and analyzes the proposed destinations and waypoints. The input is the response data from the generative model, and the output is a list of the analyzed destinations and waypoints. Here, natural language processing techniques are used to interpret and organize the proposed data.

[0119] Step 4:

[0120] The server collects real-time traffic information based on the destination and waypoints, and calculates the optimal route based on that information. The input is destination and waypoint information, as well as traffic data, and the output is the calculated optimal route. Efficient route calculation is performed using traffic information from the database.

[0121] Step 5:

[0122] The server sends the calculated optimal route to the visual device, allowing the user to verify the information. The input is optimized route data, and the output is route information displayed on the visual device. The user can visually confirm the presented route and proceed with their journey.

[0123] Step 6:

[0124] During transit, the server monitors changes in traffic conditions and recalculates the route as needed. The input is constantly updated traffic information data, and the output is the new route calculated as required. The server generates alternative routes when unexpected congestion or changes occur and provides that information to the user's visual device.

[0125] 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.

[0126] This invention provides a navigation system that analyzes user-inputted voice and text to identify destinations and waypoints, as well as a function to recognize the user's emotions and provide an optimal route based on those emotions. The aim of this system is to provide a more comfortable and satisfying travel experience by understanding the user's emotional state in real time and optimizing routes and rest stops accordingly.

[0127] The user uses the device to specify destinations and waypoints in natural language. The device analyzes this using speech recognition technology and identifies the destination using a generative model based on the obtained data. The device also has an emotion engine that analyzes the user's voice tone and facial expression data to evaluate the user's emotional state.

[0128] The server calculates the optimal route based on destination information and real-time traffic information, and also considers the user's emotional state when sending suggested routes and rest stops to the terminal. This allows the server to suggest relaxing routes with scenic views or rest stops such as cafes if the user is feeling stressed.

[0129] While driving, the server continues to monitor traffic conditions and re-evaluates the route as needed, taking into account the user's state as determined by the emotion engine. If the user indicates discomfort due to congestion, for example, an alternative route is generated and its advantages are presented to the user through the device. If the user approves the alternative, the device immediately updates the navigation and guides the user along the new route.

[0130] As a concrete example, suppose a user requests a route from Tokyo to Osaka and wishes to take a break along the way. After departure, if the system determines that the user's stress level is high while driving, it will suggest a suitable rest stop early and present a relaxing scenic route as an alternative. In this way, the system supports a safe and comfortable journey while taking into consideration the user's emotional state.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user specifies the destination and waypoints to the device via voice or text input. The device receives the input, converts the speech to text using speech recognition technology, and analyzes it using natural language processing.

[0134] Step 2:

[0135] The terminal sends the obtained analysis data to a generative model to identify the destination and waypoints. The generative model then generates detailed instructions for the destination.

[0136] Step 3:

[0137] The emotion engine built into the device analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state.

[0138] Step 4:

[0139] Based on the destination and waypoint information received by the server, it calculates the optimal route while considering real-time traffic information. The server also considers data from the emotion engine at the same time.

[0140] Step 5:

[0141] The server sends the terminal a suggested route, along with suggestions including rest stops and potential destinations based on the user's emotional state. The terminal then presents the suggestions to the user and prompts them to make the best choice according to their preferences.

[0142] Step 6:

[0143] While driving, the terminal continuously uses the emotion engine to monitor the user's emotional state. The server also continuously checks traffic conditions and re-evaluates the route as needed.

[0144] Step 7:

[0145] If a user expresses discomfort or experiences stress due to unexpected traffic congestion, the server quickly calculates an alternative route and presents it to the user via their terminal.

[0146] Step 8:

[0147] Once the user accepts the suggested alternative, the device updates the navigation and begins guiding the user along the new route. To ensure a satisfying journey, the guidance takes into account the user's emotions and traffic information.

[0148] (Example 2)

[0149] 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".

[0150] Conventional navigation systems, while providing optimal routes based on traffic information, fail to consider the user's emotional state. This results in a decline in the quality of the driving experience, as they cannot alleviate stress and discomfort during driving. Furthermore, simply selecting the shortest route is insufficient to reduce fatigue and psychological stress from long-distance driving.

[0151] 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.

[0152] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for analyzing the user's emotional state and considering it in route selection. This makes it possible to select the optimal route according to the user's emotional state, thereby reducing stress and providing a more comfortable travel experience.

[0153] A "generative model" is a type of artificial intelligence technology that analyzes speech and text data to extract specific information.

[0154] "Voice or text input" refers to an information format that indicates a destination or instructions given by the user through their device.

[0155] "Identifying destinations and waypoints" is the process of extracting and identifying travel targets and intermediate locations from the input data provided by the user.

[0156] "Traffic information" refers to real-time environmental data related to travel routes, such as road conditions and traffic congestion.

[0157] "Calculating the optimal route" is the process of determining an efficient and beneficial travel route based on a given destination and traffic information.

[0158] "Emotional state" refers to state information that represents a user's psychological and physiological responses and tendencies.

[0159] "Route selection optimization" is the process of selecting a route that prioritizes comfort and efficiency, taking into account the user's emotional state and traffic information.

[0160] The present invention will now be described in terms of embodiments. This system provides advanced navigation technology using a generative AI model to realize a comfortable travel experience for the user. It efficiently processes data between the user, terminal, and server, and provides an optimal route that takes into account the user's emotional state.

[0161] First, the user inputs their destination and intermediate points using voice or text via the device. For example, the user might say, "I want to go to Tokyo Station." This input data is then converted into text data through the speech recognition technology built into the device.

[0162] The device uses a generative AI model to analyze the obtained text data and identify destinations and waypoints. The generative AI model has advanced data processing and analysis capabilities and can quickly understand instructions written in natural language.

[0163] Furthermore, the device is equipped with an emotion engine that analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state. This emotional state data is an important element for use in navigation.

[0164] The server receives destination information and emotional state data transmitted from the terminal and calculates the optimal route by combining it with real-time traffic information. This calculation includes not only the shortest route but also routes with beautiful scenery that reduce the user's mental stress.

[0165] For example, if the emotion engine detects that the user is experiencing stress while driving for an extended period, the server sends alternative routes and rest stops to the device that are expected to have a relaxing effect. The device then proposes these to the user, and if the user approves, the navigation system is immediately updated and begins guiding the user along the new route.

[0166] As a concrete example of a prompt, it can be input into a generative AI model in the format of, "My current destination is Tokyo Station. Please provide the optimal route based on my emotional state."

[0167] This system allows users to enjoy a travel experience that takes their emotional state into consideration, while also reducing stress while driving.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1: Obtain user input information

[0170] Users input their destination and intermediate points via voice or text through their device. This input is specific, such as "I want to go to Tokyo Station" when using voice.

[0171] Input: User's voice or text data

[0172] Output: Audio and text data provided to the terminal.

[0173] Step 2: Speech Recognition and Text Analysis

[0174] The device uses speech recognition technology to convert the user's voice input into text data.

[0175] Input: User's voice data

[0176] Output: Data converted from audio to text

[0177] Specific operation: The voice input "I want to go to Tokyo Station" is recognized as the text "I want to go to Tokyo Station".

[0178] Step 3: Identify your destination and emotional state.

[0179] The device uses a generative AI model to analyze text data to identify destinations and waypoints, and an emotion engine to analyze the user's voice tone and facial expression data to evaluate their emotional state.

[0180] Input: Text data converted by speech recognition, as well as voice tone and facial expression data.

[0181] Output: Identified destination information and user emotional state data

[0182] Specific operation: The generative AI model identifies "Tokyo Station" as the destination, and the emotion engine evaluates the stress level.

[0183] Step 4: Calculating the optimal path

[0184] The server calculates the optimal route based on destination information, emotional state data, and real-time traffic information received from the terminal.

[0185] Input: Destination information, emotional state data, traffic information

[0186] Output: Optimal route information

[0187] Specific operation: A scenic route that avoids traffic congestion and allows for relaxation is calculated.

[0188] Step 5: Route Suggestion and Selection

[0189] The server sends the calculated route to the terminal, which then proposes it to the user and prompts them to make a choice.

[0190] Input: Optimal route information

[0191] Output: Route suggestion to the user

[0192] Specific operation: Options are displayed on the terminal screen, and the user selects a route.

[0193] Step 6: Update Navigation

[0194] If the user selects an alternative route, the device updates its navigation system and generates data to guide the user along the new route.

[0195] Input: User route selection

[0196] Output: Updated navigation information

[0197] Specific action: Navigation voice based on the selected route is updated instantly.

[0198] Step 7: Re-evaluate the route

[0199] During operation, the server monitors changes in traffic conditions and the user's emotional state, recalculates the route as needed, and suggests alternative routes.

[0200] Input: Real-time traffic information, user's emotional state

[0201] Output: Alternative route information (if necessary)

[0202] Specific action: An alternative route to avoid new traffic congestion is generated and suggested to the user.

[0203] (Application Example 2)

[0204] 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 device 14 will be referred to as the "terminal."

[0205] Conventional navigation systems only provide routes based on traffic information, making it impossible to optimize routes while considering the user's emotional state. As a result, users are often exposed to stressful environments, making it difficult to obtain a comfortable travel experience. The objective of this invention is to solve this problem and improve the travel experience based on emotions.

[0206] 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.

[0207] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for evaluating the user's emotional state in real time and optimizing the route and rest stops based on that evaluation. This makes it possible to provide the optimal route according to the user's instructions and emotional state.

[0208] A "generative model" is an artificial intelligence technology that learns from collected data and generates output based on a given input.

[0209] "Voice or text input" refers to voice or text information used by a user to communicate a destination or instructions.

[0210] "Destination and intermediate points" refer to the final place a user intends to reach during their journey, as well as any points they will visit along the way.

[0211] "Traffic information" refers to real-time, ever-changing data related to travel, such as road congestion, accidents, and road closures.

[0212] "Means for calculating the optimal route" refers to a method or device for calculating the most efficient travel route based on acquired traffic information and destination information.

[0213] "Emotional state" refers to the psychological and emotional state of the user, analyzed from their voice and facial expressions.

[0214] "Real-time monitoring" refers to continuously tracking and analyzing the situation as it unfolds.

[0215] "Recalculating the route" means recalculating the initially set travel route in accordance with changing conditions.

[0216] The system implementing this invention is intended to be installed in autonomous vehicles and to provide users with a comfortable travel experience. The system mainly consists of a server and an in-vehicle terminal, and realizes the following functions.

[0217] The server uses a generative AI model to analyze voice or text input from the user to identify destinations and waypoints. During this process, the user's voice data is converted to text via the Google® Speech-to-Text API. The device's built-in microphone and camera are used to collect user voice and facial expression data. Microsoft® Azure® Face API is used to assess the user's emotional state in real time based on their facial expressions, measuring stress levels and comfort levels.

[0218] The server also collects traffic information in real time and calculates the optimal route using the Mapbox Directions API. Based on the user's emotional state, it suggests scenic routes and relaxing rest stops. If the user is feeling stressed, it selects rest stops or alternative routes and presents them to the user while driving.

[0219] As a concrete example, when a user sets off on a weekend trip with their family, they can instruct the system to "take the route to Nagoya" while in the car. The system will then calculate the optimal route and depart. If the user appears tired while driving, the system will suggest a nearby rest stop with a nice view. If the user accepts this suggestion, the system will immediately present a new route and guide them to that location.

[0220] Examples of prompts for a generative AI model are as follows:

[0221] User instruction: "Tell me the route to Nagoya."

[0222] Requirements for the interpretive model: "Identify the destination in Nagoya and generate suggestions based on the emotional state."

[0223] Predicted outcome: "We offer the following suggested route: Use the expressway to Nagoya. You can visit scenic rest stops along the way."

[0224] In this way, the server and terminal can understand the user's voice commands and emotional state, enabling appropriate navigation and emotion-based route optimization.

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The user enters their destination in the car by giving voice instructions. The device captures the user's voice via the microphone and converts the voice data to text using the Google Speech-to-Text API. This entered text data is then used in the next step.

[0228] Step 2:

[0229] The server inputs the text data obtained in Step 1 into the generating AI model to identify the destination and waypoints. Based on the given prompt sentence, the model infers the destination and outputs relevant location information. This output is then used to calculate the route.

[0230] Step 3:

[0231] The server obtains traffic information via the Mapbox Directions API. Using the obtained traffic information and the location information obtained in step 2, the server calculates the optimal route. As a result of this calculation, efficient route information is obtained.

[0232] Step 4:

[0233] The terminal presents the user with the route calculated in step 3. Based on the user's response, it receives final approval for the route and adjusts it accordingly. Suggestions for rest stops and scenic routes to reduce user stress are also presented.

[0234] Step 5:

[0235] The device uses a camera and an emotion recognition API to acquire the user's facial expression data and evaluate their emotional state in real time. This data is sent to a server to monitor changes in the user's psychological state.

[0236] Step 6:

[0237] The server integrates the emotional state information obtained in step 5 with real-time traffic conditions and re-evaluates alternative routes as needed. As a result of the re-evaluation, new candidate routes are generated and presented to the user via the terminal. If the user approves the suggestion, the terminal immediately updates the navigation.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] [Second Embodiment]

[0242] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0243] 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.

[0244] 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).

[0245] 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.

[0246] 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.

[0247] 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).

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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".

[0254] This system is a navigation system that analyzes user voice or text input to efficiently set destinations and waypoints. When the user communicates their travel preferences to the terminal in natural language, the terminal analyzes the content using speech recognition and natural language processing technologies and sends the converted data to a generative model. Based on this data, the generative model identifies the destination and possible waypoints.

[0255] The server collects real-time traffic information based on the specified destination and waypoints, and calculates the optimal route. This traffic information includes road congestion, accident information, and construction status, and the server uses this data to present the user with the best possible route.

[0256] Furthermore, the device can use a generative model to suggest potential rest stops and tourist attractions along the way. This makes it easy for users to add waypoints and adjust their rest plans.

[0257] While driving, the server continuously monitors changes in traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server can generate an alternative route and present it to the user via the terminal. The user can then efficiently correct the route in real time by approving the proposed alternative.

[0258] As a concrete example, suppose a user wants to travel from Tokyo to Nagoya and wants to stop in Yokohama along the way. The user instructs the device, "I want to go to Nagoya via Yokohama." Upon receiving this instruction, the device uses a generative model to convert the speech into text and analyzes the content of the instruction.

[0259] The server calculates the optimal route from Tokyo to Yokohama and then to Nagoya, taking traffic information into account. If traffic congestion occurs on the way to Yokohama after departure, the server calculates an alternative optimal route and suggests it to the user via the terminal, saying, "There is traffic congestion. Please try the new route." In this way, users can reach their destination via the optimal route without stress.

[0260] The following describes the processing flow.

[0261] Step 1:

[0262] The user enters instructions into the device via voice or text, specifying the destination and waypoints.

[0263] Step 2:

[0264] The terminal receives the user's voice input and converts it into text using speech recognition technology. The resulting text data is then analyzed using natural language processing technology to identify the destination and waypoints.

[0265] Step 3:

[0266] The device sends the analysis results to a generative model, which accurately understands the user's intent. The information obtained by the generative model is then converted into detailed instructions for the next action.

[0267] Step 4:

[0268] The server obtains real-time traffic information based on the specified destination and waypoint information and calculates the optimal route. The server collects current road conditions, accident information, construction information, etc. from the internet and traffic databases.

[0269] Step 5:

[0270] The server sends the route calculation results to the terminal, which then presents the calculated optimal route to the user. The user reviews the presented optimal route and makes adjustments or additional instructions as needed.

[0271] Step 6:

[0272] The device uses a generative model to suggest potential rest stops and tourist spots along the route, presenting them to the user as options.

[0273] Step 7:

[0274] During operation, the server periodically monitors traffic conditions and recalculates the route as needed. For example, if congestion or an accident occurs, the server generates an alternative route and resends it.

[0275] Step 8:

[0276] When presenting the user with an alternative where the terminal has been recalculated, if the user approves the new route, update the navigation and continue the guidance.

[0277] (Example 1)

[0278] Next, 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".

[0279] Modern navigation systems not only lack the ability to present an optimal route that reflects the traffic situation in real time, but also have problems such as difficulty in proposing via points based on the user's wishes and dynamic route adjustment. In addition, since the proposal of rest points and tourist spots during the journey is also limited, an improvement in the user experience is required.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0281] In this invention, the server includes means for analyzing the user's voice or text input by voice recognition technology and natural language processing technology to identify the destination and via positions based on a generation model, means for obtaining the traffic state, calculating and proposing an optimal route, and means for monitoring the traffic situation during driving in real time and performing route recalculation as necessary. As a result, flexible and optimal navigation that efficiently and accurately reflects the user's wishes becomes possible.

[0282] The "user" refers to the entity that operates the system and designates the destination and via points.

[0283] The "voice recognition technology" refers to the technology for analyzing voice input and converting it into corresponding text data.

[0284] The "natural language processing technology" refers to the technology for analyzing text written in natural language and understanding its meaning and intention.

[0285] A "generative model" refers to an algorithm or system for generating a specific output based on input data.

[0286] A "destination" refers to the place where the user ultimately wishes to arrive.

[0287] A "stopover location" refers to a place designated to make a stop on the way to the destination.

[0288] "Traffic conditions" refer to information that includes all elements affecting movement, such as road congestion, accident information, and the presence of construction.

[0289] The "optimal route" refers to the shortest or most efficient route to the destination under the specified conditions.

[0290] "Real-time monitoring" refers to constantly observing the current traffic conditions and updating information as needed.

[0291] "Route recalculation" refers to recalculating the route to the destination based on predicted changes or new information.

[0292] The present invention is a system in which a user inputs travel wishes in voice or text to a terminal, and provides optimal navigation via a server.

[0293] First, the user conveys travel wishes to the terminal in natural language. At this time, the terminal uses speech recognition technology (e.g., a general speech recognition API) to receive voice input. The voice is converted into text by the speech recognition technology, and then destination and stopover location information is analyzed from the text using natural language processing technology (e.g., a natural language processing library or model).

[0294] The analyzed information is sent to a generative AI model and input as a specific prompt, such as "Calculate the route to the next destination. The starting point is Tokyo, the intermediate point is Yokohama, and the final destination is Nagoya." This generative AI model is designed to identify the destination and intermediate points based on the input prompt.

[0295] Next, the server receives destination information and collects traffic information in real time. This traffic information is obtained from a dedicated API and includes road congestion, accidents, and construction information. Based on this information, the server calculates the optimal route and sends the calculation result to the terminal.

[0296] The device presents the user with a calculated optimal route. Furthermore, it can use a generative AI model to suggest rest stops and sightseeing spots along the way. This allows users to create more personalized travel plans in addition to standard navigation.

[0297] While driving, the server continuously monitors traffic conditions. For example, if unexpected congestion occurs along the way, the server recalculates the route and proposes a new route to the user via the terminal. In this way, users can always reach their destination efficiently based on the latest information.

[0298] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0299] Step 1:

[0300] The user enters their travel preferences into the device via voice or text.

[0301] As a concrete example, the user speaks into their smartphone saying, "I want to go to Nagoya via Yokohama." This input data is converted into text data through speech recognition technology. Once the voice input is converted into text information via speech recognition, it is ready to proceed to the next analysis step.

[0302] Step 2:

[0303] The terminal analyzes the text converted by voice recognition.

[0304] Using natural language processing technology, the converted text data is analyzed to extract the destination "Nagoya" and the transit point "Yokohama". At this stage, the analysis is performed to understand the user's intention, and information on the destination and transit point is output as the analysis result.

[0305] Step 3:

[0306] The terminal sends the analysis result to the generation AI model.

[0307] Specifically, a prompt sentence such as "Calculate the next destination route. The departure place is Tokyo, the transit point is Yokohama, and the final destination is Nagoya." is created and passed to the generation AI model. Based on this prompt, the AI model confirms the destination and transit point and outputs the corresponding list.

[0308] Step 4:

[0309] The server receives the data from the generation AI model and collects traffic information.

[0310] The server obtains real-time road and traffic conditions through the traffic information API. The data includes road congestion conditions and construction information and is used to calculate the optimal route. The calculated route information is generated by the server.

[0311] Step 5:

[0312] The terminal presents the optimal route received from the server to the user.

[0313] The terminal displays the route information obtained from the server on the screen and also proposes intermediate rest points and tourist spots if necessary. The user can check the presented information and adjust the travel plan. The output information includes specific map displays and route guidance.

[0314] Step 6:

[0315] The server monitors traffic conditions while driving and recalculates the route if necessary.

[0316] When new traffic conditions, such as congestion or accident information, are received, the server recalculates the route and calculates a new optimal route. The result is sent to the terminal, and the user receives a notification such as "A new route is available." Based on this information, the user can continue to efficiently adjust their route in real time.

[0317] (Application Example 1)

[0318] 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 glasses 214 will be referred to as the "terminal."

[0319] Autonomous vehicles require systems that can efficiently set routes to destinations and respond quickly to real-time changes. However, current navigation systems do not adequately provide intuitive route setting via voice input or information display using visual devices. Furthermore, they lack sufficient flexibility in rerouting in response to changes in traffic conditions, resulting in reduced convenience for users.

[0320] 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.

[0321] In this invention, the server includes means for analyzing voice or text input using a generative model to identify the destination and waypoints, means for acquiring traffic information and calculating the optimal route, and means for presenting the proposed route to a visual device and adjusting the route based on the user's instructions and responses. This makes it possible for users to obtain the optimal route to their destination with simple voice input and to provide a means that can flexibly respond to real-time changing traffic conditions.

[0322] A "generative model" is an artificial intelligence technology that analyzes speech and text data to identify destinations, waypoints, and other points of reference.

[0323] "Means for analyzing voice or text input" refers to means that have the function of understanding voice or text instructions from the user and extracting necessary information.

[0324] A "means for calculating the optimal route" refers to a means that has the function of deriving the shortest or most efficient route to a destination while taking into account traffic information acquired in real time.

[0325] A "means for adjusting routes based on instructions and responses" refers to a means that has the function of modifying and optimizing the proposed route in accordance with user approval or instructions.

[0326] A "means of monitoring traffic conditions in real time" refers to a means of continuously acquiring updated traffic data and evaluating the current route based on that information.

[0327] A "visual device" is a device used by a user to view information, and includes display devices such as smart glasses and displays.

[0328] The system for carrying out this invention begins with the user entering their destination by voice or text. The terminal analyzes the user's input using a combination of speech recognition and natural language processing technologies and transmits the content to a generative AI model in text format. This generative AI model uses prompt sentences to identify destinations and waypoints and generates data for further suggestions. One example of such a prompt sentence is "Please suggest destinations and waypoints: [Example of user input]".

[0329] The server receives the analyzed data and collects the latest traffic information in real time. This traffic information includes road congestion, accident information, and construction. Based on this information, the server calculates the optimal route to the destination and selected waypoints. The calculated route is displayed on a visual device so that the user can check it while traveling. Visual devices include display devices such as smart glasses.

[0330] While driving, the server constantly monitors traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server calculates an alternative route and displays a message on the visual device saying, "There is congestion. Please try the new route." This feature allows users to reach their destination via the optimal route without stress.

[0331] The main hardware used for this system includes microphones, smartphones, and smart glasses, while the software includes Python, the SpeechRecognition library, and the OpenAI API. This system provides users with intuitive and efficient route planning, improving the travel experience.

[0332] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0333] Step 1:

[0334] The device receives the user's voice input via a microphone and converts that voice data into text data using the SpeechRecognition library. The input is voice data, and the output is the converted text data. In this step, data conversion is performed to extract the necessary information from the voice.

[0335] Step 2:

[0336] The device generates a prompt message for the generative AI model and sends it as text data. Specifically, it generates a prompt message such as "Suggest a destination and waypoints: [User input text]". The input is text data, and the output is a prompt message that the generative model can interpret.

[0337] Step 3:

[0338] The server receives responses from the generative AI model and analyzes the proposed destinations and waypoints. The input is the response data from the generative model, and the output is a list of the analyzed destinations and waypoints. Here, natural language processing techniques are used to interpret and organize the proposed data.

[0339] Step 4:

[0340] The server collects real-time traffic information based on the destination and waypoints, and calculates the optimal route based on that information. The input is destination and waypoint information, as well as traffic data, and the output is the calculated optimal route. Efficient route calculation is performed using traffic information from the database.

[0341] Step 5:

[0342] The server sends the calculated optimal route to the visual device, allowing the user to verify the information. The input is optimized route data, and the output is route information displayed on the visual device. The user can visually confirm the presented route and proceed with their journey.

[0343] Step 6:

[0344] During transit, the server monitors changes in traffic conditions and recalculates the route as needed. The input is constantly updated traffic information data, and the output is the new route calculated as required. The server generates alternative routes when unexpected congestion or changes occur and provides that information to the user's visual device.

[0345] 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.

[0346] This invention provides a navigation system that analyzes user-inputted voice and text to identify destinations and waypoints, as well as a function to recognize the user's emotions and provide an optimal route based on those emotions. The aim of this system is to provide a more comfortable and satisfying travel experience by understanding the user's emotional state in real time and optimizing routes and rest stops accordingly.

[0347] The user uses the device to specify destinations and waypoints in natural language. The device analyzes this using speech recognition technology and identifies the destination using a generative model based on the obtained data. The device also has an emotion engine that analyzes the user's voice tone and facial expression data to evaluate the user's emotional state.

[0348] The server calculates the optimal route based on destination information and real-time traffic information, and also considers the user's emotional state when sending suggested routes and rest stops to the terminal. This allows the server to suggest relaxing routes with scenic views or rest stops such as cafes if the user is feeling stressed.

[0349] While driving, the server continues to monitor traffic conditions and re-evaluates the route as needed, taking into account the user's state as determined by the emotion engine. If the user indicates discomfort due to congestion, for example, an alternative route is generated and its advantages are presented to the user through the device. If the user approves the alternative, the device immediately updates the navigation and guides the user along the new route.

[0350] As a concrete example, suppose a user requests a route from Tokyo to Osaka and wishes to take a break along the way. After departure, if the system determines that the user's stress level is high while driving, it will suggest a suitable rest stop early and present a relaxing scenic route as an alternative. In this way, the system supports a safe and comfortable journey while taking into consideration the user's emotional state.

[0351] The following describes the processing flow.

[0352] Step 1:

[0353] The user specifies the destination and waypoints to the device via voice or text input. The device receives the input, converts the speech to text using speech recognition technology, and analyzes it using natural language processing.

[0354] Step 2:

[0355] The terminal sends the obtained analysis data to a generative model to identify the destination and waypoints. The generative model then generates detailed instructions for the destination.

[0356] Step 3:

[0357] The emotion engine built into the device analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state.

[0358] Step 4:

[0359] Based on the destination and waypoint information received by the server, it calculates the optimal route while considering real-time traffic information. The server also considers data from the emotion engine at the same time.

[0360] Step 5:

[0361] The server sends the terminal a suggested route, along with suggestions including rest stops and potential destinations based on the user's emotional state. The terminal then presents the suggestions to the user and prompts them to make the best choice according to their preferences.

[0362] Step 6:

[0363] While driving, the terminal continuously uses the emotion engine to monitor the user's emotional state. The server also continuously checks traffic conditions and re-evaluates the route as needed.

[0364] Step 7:

[0365] If a user expresses discomfort or experiences stress due to unexpected traffic congestion, the server quickly calculates an alternative route and presents it to the user via their terminal.

[0366] Step 8:

[0367] Once the user accepts the suggested alternative, the device updates the navigation and begins guiding the user along the new route. To ensure a satisfying journey, the guidance takes into account the user's emotions and traffic information.

[0368] (Example 2)

[0369] 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".

[0370] Conventional navigation systems, while providing optimal routes based on traffic information, fail to consider the user's emotional state. This results in a decline in the quality of the driving experience, as they cannot alleviate stress and discomfort during driving. Furthermore, simply selecting the shortest route is insufficient to reduce fatigue and psychological stress from long-distance driving.

[0371] 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.

[0372] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for analyzing the user's emotional state and considering it in route selection. This makes it possible to select the optimal route according to the user's emotional state, thereby reducing stress and providing a more comfortable travel experience.

[0373] A "generative model" is a type of artificial intelligence technology that analyzes speech and text data to extract specific information.

[0374] "Voice or text input" refers to an information format that indicates a destination or instructions given by the user through their device.

[0375] "Identifying destinations and waypoints" is the process of extracting and identifying travel targets and intermediate locations from the input data provided by the user.

[0376] "Traffic information" refers to real-time environmental data related to travel routes, such as road conditions and traffic congestion.

[0377] "Calculating the optimal route" is the process of determining an efficient and beneficial travel route based on a given destination and traffic information.

[0378] "Emotional state" refers to state information that represents a user's psychological and physiological responses and tendencies.

[0379] "Route selection optimization" is the process of selecting a route that prioritizes comfort and efficiency, taking into account the user's emotional state and traffic information.

[0380] The present invention will now be described in terms of embodiments. This system provides advanced navigation technology using a generative AI model to realize a comfortable travel experience for the user. It efficiently processes data between the user, terminal, and server, and provides an optimal route that takes into account the user's emotional state.

[0381] First, the user inputs their destination and intermediate points using voice or text via the device. For example, the user might say, "I want to go to Tokyo Station." This input data is then converted into text data through the speech recognition technology built into the device.

[0382] The device uses a generative AI model to analyze the obtained text data and identify destinations and waypoints. The generative AI model has advanced data processing and analysis capabilities and can quickly understand instructions written in natural language.

[0383] Furthermore, the device is equipped with an emotion engine that analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state. This emotional state data is an important element for use in navigation.

[0384] The server receives destination information and emotional state data transmitted from the terminal and calculates the optimal route by combining it with real-time traffic information. This calculation includes not only the shortest route but also routes with beautiful scenery that reduce the user's mental stress.

[0385] For example, if the emotion engine detects that the user is experiencing stress while driving for an extended period, the server sends alternative routes and rest stops to the device that are expected to have a relaxing effect. The device then proposes these to the user, and if the user approves, the navigation system is immediately updated and begins guiding the user along the new route.

[0386] As a concrete example of a prompt, it can be input into a generative AI model in the format of, "My current destination is Tokyo Station. Please provide the optimal route based on my emotional state."

[0387] This system allows users to enjoy a travel experience that takes their emotional state into consideration, while also reducing stress while driving.

[0388] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0389] Step 1: Obtain user input information

[0390] Users input their destination and intermediate points via voice or text through their device. This input is specific, such as "I want to go to Tokyo Station" when using voice.

[0391] Input: User's voice or text data

[0392] Output: Audio and text data provided to the terminal.

[0393] Step 2: Speech Recognition and Text Analysis

[0394] The device uses speech recognition technology to convert the user's voice input into text data.

[0395] Input: User's voice data

[0396] Output: Data converted from audio to text

[0397] Specific operation: The voice input "I want to go to Tokyo Station" is recognized as the text "I want to go to Tokyo Station".

[0398] Step 3: Identify your destination and emotional state.

[0399] The device uses a generative AI model to analyze text data to identify destinations and waypoints, and an emotion engine to analyze the user's voice tone and facial expression data to evaluate their emotional state.

[0400] Input: Text data converted by speech recognition, as well as voice tone and facial expression data.

[0401] Output: Identified destination information and user emotional state data

[0402] Specific operation: The generative AI model identifies "Tokyo Station" as the destination, and the emotion engine evaluates the stress level.

[0403] Step 4: Calculating the optimal path

[0404] The server calculates the optimal route based on destination information, emotional state data, and real-time traffic information received from the terminal.

[0405] Input: Destination information, emotional state data, traffic information

[0406] Output: Optimal route information

[0407] Specific operation: A scenic route that avoids traffic congestion and allows for relaxation is calculated.

[0408] Step 5: Route Suggestion and Selection

[0409] The server sends the calculated route to the terminal, which then proposes it to the user and prompts them to make a choice.

[0410] Input: Optimal route information

[0411] Output: Route suggestion to the user

[0412] Specific operation: Options are displayed on the terminal screen, and the user selects a route.

[0413] Step 6: Update Navigation

[0414] If the user selects an alternative route, the device updates its navigation system and generates data to guide the user along the new route.

[0415] Input: User route selection

[0416] Output: Updated navigation information

[0417] Specific action: Navigation voice based on the selected route is updated instantly.

[0418] Step 7: Re-evaluate the route

[0419] During operation, the server monitors changes in traffic conditions and the user's emotional state, recalculates the route as needed, and suggests alternative routes.

[0420] Input: Real-time traffic information, user's emotional state

[0421] Output: Alternative route information (if necessary)

[0422] Specific action: An alternative route to avoid new traffic congestion is generated and suggested to the user.

[0423] (Application Example 2)

[0424] 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 as the "terminal".

[0425] Conventional navigation systems only provide routes based on traffic information, making it impossible to optimize routes while considering the user's emotional state. As a result, users are often exposed to stressful environments, making it difficult to obtain a comfortable travel experience. The objective of this invention is to solve this problem and improve the travel experience based on emotions.

[0426] 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.

[0427] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for evaluating the user's emotional state in real time and optimizing the route and rest stops based on that evaluation. This makes it possible to provide the optimal route according to the user's instructions and emotional state.

[0428] A "generative model" is an artificial intelligence technology that learns from collected data and generates output based on a given input.

[0429] "Voice or text input" refers to voice or text information used by a user to communicate a destination or instructions.

[0430] "Destination and intermediate points" refer to the final place a user intends to reach during their journey, as well as any points they will visit along the way.

[0431] "Traffic information" refers to real-time, ever-changing data related to travel, such as road congestion, accidents, and road closures.

[0432] "Means for calculating the optimal route" refers to a method or device for calculating the most efficient travel route based on acquired traffic information and destination information.

[0433] "Emotional state" refers to the psychological and emotional state of the user, analyzed from their voice and facial expressions.

[0434] "Real-time monitoring" refers to continuously tracking and analyzing the situation as it unfolds.

[0435] "Recalculating the route" means recalculating the initially set travel route in accordance with changing conditions.

[0436] The system implementing this invention is intended to be installed in autonomous vehicles and to provide users with a comfortable travel experience. The system mainly consists of a server and an in-vehicle terminal, and realizes the following functions.

[0437] The server uses a generative AI model to analyze voice or text input from the user to identify destinations and waypoints. During this process, the user's voice data is converted to text via the Google Speech-to-Text API. The device's built-in microphone and camera are used to collect user voice and facial expression data. Microsoft Azure's Face API is used to assess the user's emotional state in real time based on their facial expressions, measuring stress levels and comfort levels.

[0438] The server also collects traffic information in real time and calculates the optimal route using the Mapbox Directions API. Based on the user's emotional state, it suggests scenic routes and relaxing rest stops. If the user is feeling stressed, it selects rest stops or alternative routes and presents them to the user while driving.

[0439] As a concrete example, when a user sets off on a weekend trip with their family, they can instruct the system to "take the route to Nagoya" while in the car. The system will then calculate the optimal route and depart. If the user appears tired while driving, the system will suggest a nearby rest stop with a nice view. If the user accepts this suggestion, the system will immediately present a new route and guide them to that location.

[0440] Examples of prompts for a generative AI model are as follows:

[0441] User instruction: "Tell me the route to Nagoya."

[0442] Requirements for the interpretive model: "Identify the destination in Nagoya and generate suggestions based on the emotional state."

[0443] Predicted outcome: "We offer the following suggested route: Use the expressway to Nagoya. You can visit scenic rest stops along the way."

[0444] In this way, the server and terminal can understand the user's voice commands and emotional state, enabling appropriate navigation and emotion-based route optimization.

[0445] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0446] Step 1:

[0447] The user enters their destination in the car by giving voice instructions. The device captures the user's voice via the microphone and converts the voice data to text using the Google Speech-to-Text API. This entered text data is then used in the next step.

[0448] Step 2:

[0449] The server inputs the text data obtained in Step 1 into the generating AI model to identify the destination and waypoints. Based on the given prompt sentence, the model infers the destination and outputs relevant location information. This output is then used to calculate the route.

[0450] Step 3:

[0451] The server obtains traffic information via the Mapbox Directions API. Using the obtained traffic information and the location information obtained in step 2, the server calculates the optimal route. As a result of this calculation, efficient route information is obtained.

[0452] Step 4:

[0453] The terminal presents the user with the route calculated in step 3. Based on the user's response, it receives final approval for the route and adjusts it accordingly. Suggestions for rest stops and scenic routes to reduce user stress are also presented.

[0454] Step 5:

[0455] The device uses a camera and an emotion recognition API to acquire the user's facial expression data and evaluate their emotional state in real time. This data is sent to a server to monitor changes in the user's psychological state.

[0456] Step 6:

[0457] The server integrates the emotional state information obtained in step 5 with real-time traffic conditions and re-evaluates alternative routes as needed. As a result of the re-evaluation, new candidate routes are generated and presented to the user via the terminal. If the user approves the suggestion, the terminal immediately updates the navigation.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Third Embodiment]

[0462] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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".

[0474] This system is a navigation system that analyzes user voice or text input to efficiently set destinations and waypoints. When the user communicates their travel preferences to the terminal in natural language, the terminal analyzes the content using speech recognition and natural language processing technologies and sends the converted data to a generative model. Based on this data, the generative model identifies the destination and possible waypoints.

[0475] The server collects real-time traffic information based on the specified destination and waypoints, and calculates the optimal route. This traffic information includes road congestion, accident information, and construction status, and the server uses this data to present the user with the best possible route.

[0476] Furthermore, the device can use a generative model to suggest potential rest stops and tourist attractions along the way. This makes it easy for users to add waypoints and adjust their rest plans.

[0477] While driving, the server continuously monitors changes in traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server can generate an alternative route and present it to the user via the terminal. The user can then efficiently correct the route in real time by approving the proposed alternative.

[0478] As a concrete example, suppose a user wants to travel from Tokyo to Nagoya and wants to stop in Yokohama along the way. The user instructs the device, "I want to go to Nagoya via Yokohama." Upon receiving this instruction, the device uses a generative model to convert the speech into text and analyzes the content of the instruction.

[0479] The server calculates the optimal route from Tokyo to Yokohama and then to Nagoya, taking traffic information into account. If traffic congestion occurs on the way to Yokohama after departure, the server calculates an alternative optimal route and suggests it to the user via the terminal, saying, "There is traffic congestion. Please try the new route." In this way, users can reach their destination via the optimal route without stress.

[0480] The following describes the processing flow.

[0481] Step 1:

[0482] The user enters instructions into the device via voice or text, specifying the destination and waypoints.

[0483] Step 2:

[0484] The terminal receives the user's voice input and converts it into text using speech recognition technology. The resulting text data is then analyzed using natural language processing technology to identify the destination and waypoints.

[0485] Step 3:

[0486] The device sends the analysis results to a generative model, which accurately understands the user's intent. The information obtained by the generative model is then converted into detailed instructions for the next action.

[0487] Step 4:

[0488] The server obtains real-time traffic information based on the specified destination and waypoint information and calculates the optimal route. The server collects current road conditions, accident information, construction information, etc. from the internet and traffic databases.

[0489] Step 5:

[0490] The server sends the route calculation results to the terminal, which then presents the calculated optimal route to the user. The user reviews the presented optimal route and makes adjustments or additional instructions as needed.

[0491] Step 6:

[0492] The device uses a generative model to suggest potential rest stops and tourist spots along the route, presenting them to the user as options.

[0493] Step 7:

[0494] During operation, the server periodically monitors traffic conditions and recalculates the route as needed. For example, if congestion or an accident occurs, the server generates an alternative route and resends it.

[0495] Step 8:

[0496] The device presents the user with a recalculated alternative route, and if the user approves the new route, it updates the navigation and continues providing directions.

[0497] (Example 1)

[0498] 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."

[0499] Modern navigation systems lack the ability to provide optimal routes that reflect real-time traffic conditions, and they also struggle to suggest waypoints based on user preferences and dynamically adjust routes. Furthermore, their suggestions for rest stops and tourist attractions are limited, highlighting the need for improved user experience.

[0500] 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.

[0501] In this invention, the server includes means for analyzing the user's voice or text input using speech recognition technology and natural language processing technology to identify destinations and intermediate points based on a generative model; means for acquiring traffic conditions, calculating and proposing an optimal route; and means for monitoring traffic conditions in real time while driving and recalculating the route as needed. This enables flexible and optimal navigation that efficiently and accurately reflects the user's wishes.

[0502] "User" refers to the entity that operates the system and specifies destinations and intermediate stops.

[0503] "Speech recognition technology" refers to the technology that analyzes voice input and converts it into corresponding text data.

[0504] "Natural language processing technology" refers to techniques for analyzing text written in natural language and understanding its meaning and intent.

[0505] A "generative model" refers to an algorithm or system that generates a specific output based on input data.

[0506] "Destination" refers to the place that the user ultimately wishes to reach.

[0507] A "stopover point" refers to a designated location where you are to stop on your way to your destination.

[0508] "Traffic conditions" refers to information that includes all factors affecting travel, such as road congestion, accident information, and whether or not there is construction work.

[0509] "Optimal route" refers to the shortest or most efficient path to the destination under specified conditions.

[0510] "Real-time monitoring" refers to constantly observing the ongoing traffic situation and updating the information as needed.

[0511] "Recalculating the route" refers to recalculating the path to the destination based on predicted changes and new information.

[0512] This invention is a system in which users input their travel preferences into a terminal via voice or text, and the system provides optimal navigation via a server.

[0513] First, the user communicates their travel preferences to the device in natural language. The device uses speech recognition technology (e.g., a common speech recognition API) to receive the voice input. The speech recognition technology converts the voice into text, and then natural language processing technology (e.g., a natural language processing library or model) is used to analyze the text for destination and waypoint information.

[0514] The analyzed information is sent to a generative AI model and input as a specific prompt, such as "Calculate the route to the next destination. The starting point is Tokyo, the intermediate point is Yokohama, and the final destination is Nagoya." This generative AI model is designed to identify the destination and intermediate points based on the input prompt.

[0515] Next, the server receives destination information and collects traffic information in real time. This traffic information is obtained from a dedicated API and includes road congestion, accidents, and construction information. Based on this information, the server calculates the optimal route and sends the calculation result to the terminal.

[0516] The device presents the user with a calculated optimal route. Furthermore, it can use a generative AI model to suggest rest stops and sightseeing spots along the way. This allows users to create more personalized travel plans in addition to standard navigation.

[0517] While driving, the server continuously monitors traffic conditions. For example, if unexpected congestion occurs along the way, the server recalculates the route and proposes a new route to the user via the terminal. In this way, users can always reach their destination efficiently based on the latest information.

[0518] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0519] Step 1:

[0520] The user enters their travel preferences into the device via voice or text.

[0521] As a concrete example, the user speaks into their smartphone saying, "I want to go to Nagoya via Yokohama." This input data is converted into text data through speech recognition technology. Once the voice input is converted into text information via speech recognition, it is ready to proceed to the next analysis step.

[0522] Step 2:

[0523] The device analyzes the text converted by speech recognition.

[0524] Using natural language processing technology, the converted text data is analyzed to extract the destination "Nagoya" and the waypoint "Yokohama". At this stage, analysis is performed to understand the user's intent, and the destination and waypoint information is output as a result of the analysis.

[0525] Step 3:

[0526] The device sends the analysis results to an AI model that generates them.

[0527] Specifically, a prompt message such as "Calculate the route to the next destination. The starting point is Tokyo, the intermediate point is Yokohama, and the final destination is Nagoya" is created and passed to the generating AI model. Based on this prompt, the AI ​​model checks the destination and intermediate points and outputs a corresponding list.

[0528] Step 4:

[0529] The server receives data from the generated AI model and collects traffic information.

[0530] The server obtains real-time road and traffic conditions through a traffic information API. This data includes road congestion and construction information, and is used to calculate the optimal route. The calculated route information is then generated from the server.

[0531] Step 5:

[0532] The terminal presents the user with the optimal route received from the server.

[0533] The terminal displays route information retrieved from the server on its screen and suggests rest stops and sightseeing spots along the way as needed. Users can review the presented information and adjust their travel plan accordingly. The output includes detailed map displays and route guidance.

[0534] Step 6:

[0535] The server monitors traffic conditions while driving and recalculates the route if necessary.

[0536] When new traffic conditions, such as congestion or accident information, are received, the server recalculates the route and calculates a new optimal route. The result is sent to the terminal, and the user receives a notification such as "A new route is available." Based on this information, the user can continue to efficiently adjust their route in real time.

[0537] (Application Example 1)

[0538] 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."

[0539] Autonomous vehicles require systems that can efficiently set routes to destinations and respond quickly to real-time changes. However, current navigation systems do not adequately provide intuitive route setting via voice input or information display using visual devices. Furthermore, they lack sufficient flexibility in rerouting in response to changes in traffic conditions, resulting in reduced convenience for users.

[0540] 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.

[0541] In this invention, the server includes means for analyzing voice or text input using a generative model to identify the destination and waypoints, means for acquiring traffic information and calculating the optimal route, and means for presenting the proposed route to a visual device and adjusting the route based on the user's instructions and responses. This makes it possible for users to obtain the optimal route to their destination with simple voice input and to provide a means that can flexibly respond to real-time changing traffic conditions.

[0542] A "generative model" is an artificial intelligence technology that analyzes speech and text data to identify destinations, waypoints, and other points of reference.

[0543] "Means for analyzing voice or text input" refers to means that have the function of understanding voice or text instructions from the user and extracting necessary information.

[0544] A "means for calculating the optimal route" refers to a means that has the function of deriving the shortest or most efficient route to a destination while taking into account traffic information acquired in real time.

[0545] A "means for adjusting routes based on instructions and responses" refers to a means that has the function of modifying and optimizing the proposed route in accordance with user approval or instructions.

[0546] A "means of monitoring traffic conditions in real time" refers to a means of continuously acquiring updated traffic data and evaluating the current route based on that information.

[0547] A "visual device" is a device used by a user to view information, and includes display devices such as smart glasses and displays.

[0548] The system for carrying out this invention begins with the user entering their destination by voice or text. The terminal analyzes the user's input using a combination of speech recognition and natural language processing technologies and transmits the content to a generative AI model in text format. This generative AI model uses prompt sentences to identify destinations and waypoints and generates data for further suggestions. One example of such a prompt sentence is "Please suggest destinations and waypoints: [Example of user input]".

[0549] The server receives the analyzed data and collects the latest traffic information in real time. This traffic information includes road congestion, accident information, and construction. Based on this information, the server calculates the optimal route to the destination and selected waypoints. The calculated route is displayed on a visual device so that the user can check it while traveling. Visual devices include display devices such as smart glasses.

[0550] While driving, the server constantly monitors traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server calculates an alternative route and displays a message on the visual device saying, "There is congestion. Please try the new route." This feature allows users to reach their destination via the optimal route without stress.

[0551] The main hardware used for this system includes microphones, smartphones, and smart glasses, while the software includes Python, the SpeechRecognition library, and the OpenAI API. This system provides users with intuitive and efficient route planning, improving the travel experience.

[0552] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0553] Step 1:

[0554] The device receives the user's voice input via a microphone and converts that voice data into text data using the SpeechRecognition library. The input is voice data, and the output is the converted text data. In this step, data conversion is performed to extract the necessary information from the voice.

[0555] Step 2:

[0556] The device generates a prompt message for the generative AI model and sends it as text data. Specifically, it generates a prompt message such as "Suggest a destination and waypoints: [User input text]". The input is text data, and the output is a prompt message that the generative model can interpret.

[0557] Step 3:

[0558] The server receives responses from the generative AI model and analyzes the proposed destinations and waypoints. The input is the response data from the generative model, and the output is a list of the analyzed destinations and waypoints. Here, natural language processing techniques are used to interpret and organize the proposed data.

[0559] Step 4:

[0560] The server collects real-time traffic information based on the destination and waypoints, and calculates the optimal route based on that information. The input is destination and waypoint information, as well as traffic data, and the output is the calculated optimal route. Efficient route calculation is performed using traffic information from the database.

[0561] Step 5:

[0562] The server sends the calculated optimal route to the visual device, allowing the user to verify the information. The input is optimized route data, and the output is route information displayed on the visual device. The user can visually confirm the presented route and proceed with their journey.

[0563] Step 6:

[0564] During transit, the server monitors changes in traffic conditions and recalculates the route as needed. The input is constantly updated traffic information data, and the output is the new route calculated as required. The server generates alternative routes when unexpected congestion or changes occur and provides that information to the user's visual device.

[0565] 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.

[0566] This invention provides a navigation system that analyzes user-inputted voice and text to identify destinations and waypoints, as well as a function to recognize the user's emotions and provide an optimal route based on those emotions. The aim of this system is to provide a more comfortable and satisfying travel experience by understanding the user's emotional state in real time and optimizing routes and rest stops accordingly.

[0567] The user uses the device to specify destinations and waypoints in natural language. The device analyzes this using speech recognition technology and identifies the destination using a generative model based on the obtained data. The device also has an emotion engine that analyzes the user's voice tone and facial expression data to evaluate the user's emotional state.

[0568] The server calculates the optimal route based on destination information and real-time traffic information, and also considers the user's emotional state when sending suggested routes and rest stops to the terminal. This allows the server to suggest relaxing routes with scenic views or rest stops such as cafes if the user is feeling stressed.

[0569] While driving, the server continues to monitor traffic conditions and re-evaluates the route as needed, taking into account the user's state as determined by the emotion engine. If the user indicates discomfort due to congestion, for example, an alternative route is generated and its advantages are presented to the user through the device. If the user approves the alternative, the device immediately updates the navigation and guides the user along the new route.

[0570] As a concrete example, suppose a user requests a route from Tokyo to Osaka and wishes to take a break along the way. After departure, if the system determines that the user's stress level is high while driving, it will suggest a suitable rest stop early and present a relaxing scenic route as an alternative. In this way, the system supports a safe and comfortable journey while taking into consideration the user's emotional state.

[0571] The following describes the processing flow.

[0572] Step 1:

[0573] The user specifies the destination and waypoints to the device via voice or text input. The device receives the input, converts the speech to text using speech recognition technology, and analyzes it using natural language processing.

[0574] Step 2:

[0575] The terminal sends the obtained analysis data to a generative model to identify the destination and waypoints. The generative model then generates detailed instructions for the destination.

[0576] Step 3:

[0577] The emotion engine built into the device analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state.

[0578] Step 4:

[0579] Based on the destination and waypoint information received by the server, it calculates the optimal route while considering real-time traffic information. The server also considers data from the emotion engine at the same time.

[0580] Step 5:

[0581] The server sends the terminal a suggested route, along with suggestions including rest stops and potential destinations based on the user's emotional state. The terminal then presents the suggestions to the user and prompts them to make the best choice according to their preferences.

[0582] Step 6:

[0583] While driving, the terminal continuously uses the emotion engine to monitor the user's emotional state. The server also continuously checks traffic conditions and re-evaluates the route as needed.

[0584] Step 7:

[0585] If a user expresses discomfort or experiences stress due to unexpected traffic congestion, the server quickly calculates an alternative route and presents it to the user via their terminal.

[0586] Step 8:

[0587] Once the user accepts the suggested alternative, the device updates the navigation and begins guiding the user along the new route. To ensure a satisfying journey, the guidance takes into account the user's emotions and traffic information.

[0588] (Example 2)

[0589] 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."

[0590] Conventional navigation systems, while providing optimal routes based on traffic information, fail to consider the user's emotional state. This results in a decline in the quality of the driving experience, as they cannot alleviate stress and discomfort during driving. Furthermore, simply selecting the shortest route is insufficient to reduce fatigue and psychological stress from long-distance driving.

[0591] 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.

[0592] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for analyzing the user's emotional state and considering it in route selection. This makes it possible to select the optimal route according to the user's emotional state, thereby reducing stress and providing a more comfortable travel experience.

[0593] A "generative model" is a type of artificial intelligence technology that analyzes speech and text data to extract specific information.

[0594] "Voice or text input" refers to an information format that indicates a destination or instructions given by the user through their device.

[0595] "Identifying destinations and waypoints" is the process of extracting and identifying travel targets and intermediate locations from the input data provided by the user.

[0596] "Traffic information" refers to real-time environmental data related to travel routes, such as road conditions and traffic congestion.

[0597] "Calculating the optimal route" is the process of determining an efficient and beneficial travel route based on a given destination and traffic information.

[0598] "Emotional state" refers to state information that represents a user's psychological and physiological responses and tendencies.

[0599] "Route selection optimization" is the process of selecting a route that prioritizes comfort and efficiency, taking into account the user's emotional state and traffic information.

[0600] The present invention will now be described in terms of embodiments. This system provides advanced navigation technology using a generative AI model to realize a comfortable travel experience for the user. It efficiently processes data between the user, terminal, and server, and provides an optimal route that takes into account the user's emotional state.

[0601] First, the user inputs their destination and intermediate points using voice or text via the device. For example, the user might say, "I want to go to Tokyo Station." This input data is then converted into text data through the speech recognition technology built into the device.

[0602] The device uses a generative AI model to analyze the obtained text data and identify destinations and waypoints. The generative AI model has advanced data processing and analysis capabilities and can quickly understand instructions written in natural language.

[0603] Furthermore, the device is equipped with an emotion engine that analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state. This emotional state data is an important element for use in navigation.

[0604] The server receives destination information and emotional state data transmitted from the terminal and calculates the optimal route by combining it with real-time traffic information. This calculation includes not only the shortest route but also routes with beautiful scenery that reduce the user's mental stress.

[0605] For example, if the emotion engine detects that the user is experiencing stress while driving for an extended period, the server sends alternative routes and rest stops to the device that are expected to have a relaxing effect. The device then proposes these to the user, and if the user approves, the navigation system is immediately updated and begins guiding the user along the new route.

[0606] As a concrete example of a prompt, it can be input into a generative AI model in the format of, "My current destination is Tokyo Station. Please provide the optimal route based on my emotional state."

[0607] This system allows users to enjoy a travel experience that takes their emotional state into consideration, while also reducing stress while driving.

[0608] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0609] Step 1: Obtain user input information

[0610] Users input their destination and intermediate points via voice or text through their device. This input is specific, such as "I want to go to Tokyo Station" when using voice.

[0611] Input: User's voice or text data

[0612] Output: Audio and text data provided to the terminal.

[0613] Step 2: Speech Recognition and Text Analysis

[0614] The device uses speech recognition technology to convert the user's voice input into text data.

[0615] Input: User's voice data

[0616] Output: Data converted from audio to text

[0617] Specific operation: The voice input "I want to go to Tokyo Station" is recognized as the text "I want to go to Tokyo Station".

[0618] Step 3: Identify your destination and emotional state.

[0619] The device uses a generative AI model to analyze text data to identify destinations and waypoints, and an emotion engine to analyze the user's voice tone and facial expression data to evaluate their emotional state.

[0620] Input: Text data converted by speech recognition, as well as voice tone and facial expression data.

[0621] Output: Identified destination information and user emotional state data

[0622] Specific operation: The generative AI model identifies "Tokyo Station" as the destination, and the emotion engine evaluates the stress level.

[0623] Step 4: Calculating the optimal path

[0624] The server calculates the optimal route based on destination information, emotional state data, and real-time traffic information received from the terminal.

[0625] Input: Destination information, emotional state data, traffic information

[0626] Output: Optimal route information

[0627] Specific operation: A scenic route that avoids traffic congestion and allows for relaxation is calculated.

[0628] Step 5: Route Suggestion and Selection

[0629] The server sends the calculated route to the terminal, which then proposes it to the user and prompts them to make a choice.

[0630] Input: Optimal route information

[0631] Output: Route suggestion to the user

[0632] Specific operation: Options are displayed on the terminal screen, and the user selects a route.

[0633] Step 6: Update Navigation

[0634] If the user selects an alternative route, the device updates its navigation system and generates data to guide the user along the new route.

[0635] Input: User route selection

[0636] Output: Updated navigation information

[0637] Specific action: Navigation voice based on the selected route is updated instantly.

[0638] Step 7: Re-evaluate the route

[0639] During operation, the server monitors changes in traffic conditions and the user's emotional state, recalculates the route as needed, and suggests alternative routes.

[0640] Input: Real-time traffic information, user's emotional state

[0641] Output: Alternative route information (if necessary)

[0642] Specific action: An alternative route to avoid new traffic congestion is generated and suggested to the user.

[0643] (Application Example 2)

[0644] 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."

[0645] Conventional navigation systems only provide routes based on traffic information, making it impossible to optimize routes while considering the user's emotional state. As a result, users are often exposed to stressful environments, making it difficult to obtain a comfortable travel experience. The objective of this invention is to solve this problem and improve the travel experience based on emotions.

[0646] 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.

[0647] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for evaluating the user's emotional state in real time and optimizing the route and rest stops based on that evaluation. This makes it possible to provide the optimal route according to the user's instructions and emotional state.

[0648] A "generative model" is an artificial intelligence technology that learns from collected data and generates output based on a given input.

[0649] "Voice or text input" refers to voice or text information used by a user to communicate a destination or instructions.

[0650] "Destination and intermediate points" refer to the final place a user intends to reach during their journey, as well as any points they will visit along the way.

[0651] "Traffic information" refers to real-time, ever-changing data related to travel, such as road congestion, accidents, and road closures.

[0652] "Means for calculating the optimal route" refers to a method or device for calculating the most efficient travel route based on acquired traffic information and destination information.

[0653] "Emotional state" refers to the psychological and emotional state of the user, analyzed from their voice and facial expressions.

[0654] "Real-time monitoring" refers to continuously tracking and analyzing the situation as it unfolds.

[0655] "Recalculating the route" means recalculating the initially set travel route in accordance with changing conditions.

[0656] The system implementing this invention is intended to be installed in autonomous vehicles and to provide users with a comfortable travel experience. The system mainly consists of a server and an in-vehicle terminal, and realizes the following functions.

[0657] The server uses a generative AI model to analyze voice or text input from the user to identify destinations and waypoints. During this process, the user's voice data is converted to text via the Google Speech-to-Text API. The device's built-in microphone and camera are used to collect user voice and facial expression data. Microsoft Azure's Face API is used to assess the user's emotional state in real time based on their facial expressions, measuring stress levels and comfort levels.

[0658] The server also collects traffic information in real time and calculates the optimal route using the Mapbox Directions API. Based on the user's emotional state, it suggests scenic routes and relaxing rest stops. If the user is feeling stressed, it selects rest stops or alternative routes and presents them to the user while driving.

[0659] As a concrete example, when a user sets off on a weekend trip with their family, they can instruct the system to "take the route to Nagoya" while in the car. The system will then calculate the optimal route and depart. If the user appears tired while driving, the system will suggest a nearby rest stop with a nice view. If the user accepts this suggestion, the system will immediately present a new route and guide them to that location.

[0660] Examples of prompts for a generative AI model are as follows:

[0661] User instruction: "Tell me the route to Nagoya."

[0662] Requirements for the interpretive model: "Identify the destination in Nagoya and generate suggestions based on the emotional state."

[0663] Predicted outcome: "We offer the following suggested route: Use the expressway to Nagoya. You can visit scenic rest stops along the way."

[0664] In this way, the server and terminal can understand the user's voice commands and emotional state, enabling appropriate navigation and emotion-based route optimization.

[0665] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0666] Step 1:

[0667] The user enters their destination in the car by giving voice instructions. The device captures the user's voice via the microphone and converts the voice data to text using the Google Speech-to-Text API. This entered text data is then used in the next step.

[0668] Step 2:

[0669] The server inputs the text data obtained in Step 1 into the generating AI model to identify the destination and waypoints. Based on the given prompt sentence, the model infers the destination and outputs relevant location information. This output is then used to calculate the route.

[0670] Step 3:

[0671] The server obtains traffic information via the Mapbox Directions API. Using the obtained traffic information and the location information obtained in step 2, the server calculates the optimal route. As a result of this calculation, efficient route information is obtained.

[0672] Step 4:

[0673] The terminal presents the user with the route calculated in step 3. Based on the user's response, it receives final approval for the route and adjusts it accordingly. Suggestions for rest stops and scenic routes to reduce user stress are also presented.

[0674] Step 5:

[0675] The device uses a camera and an emotion recognition API to acquire the user's facial expression data and evaluate their emotional state in real time. This data is sent to a server to monitor changes in the user's psychological state.

[0676] Step 6:

[0677] The server integrates the emotional state information obtained in step 5 with real-time traffic conditions and re-evaluates alternative routes as needed. As a result of the re-evaluation, new candidate routes are generated and presented to the user via the terminal. If the user approves the suggestion, the terminal immediately updates the navigation.

[0678] 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.

[0679] 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.

[0680] 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.

[0681] [Fourth Embodiment]

[0682] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0683] 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.

[0684] 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).

[0685] 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.

[0686] 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.

[0687] 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).

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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".

[0695] This system is a navigation system that analyzes user voice or text input to efficiently set destinations and waypoints. When the user communicates their travel preferences to the terminal in natural language, the terminal analyzes the content using speech recognition and natural language processing technologies and sends the converted data to a generative model. Based on this data, the generative model identifies the destination and possible waypoints.

[0696] The server collects real-time traffic information based on the specified destination and waypoints, and calculates the optimal route. This traffic information includes road congestion, accident information, and construction status, and the server uses this data to present the user with the best possible route.

[0697] Furthermore, the device can use a generative model to suggest potential rest stops and tourist attractions along the way. This makes it easy for users to add waypoints and adjust their rest plans.

[0698] While driving, the server continuously monitors changes in traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server can generate an alternative route and present it to the user via the terminal. The user can then efficiently correct the route in real time by approving the proposed alternative.

[0699] As a concrete example, suppose a user wants to travel from Tokyo to Nagoya and wants to stop in Yokohama along the way. The user instructs the device, "I want to go to Nagoya via Yokohama." Upon receiving this instruction, the device uses a generative model to convert the speech into text and analyzes the content of the instruction.

[0700] The server calculates the optimal route from Tokyo to Yokohama and then to Nagoya, taking traffic information into account. If traffic congestion occurs on the way to Yokohama after departure, the server calculates an alternative optimal route and suggests it to the user via the terminal, saying, "There is traffic congestion. Please try the new route." In this way, users can reach their destination via the optimal route without stress.

[0701] The following describes the processing flow.

[0702] Step 1:

[0703] The user enters instructions into the device via voice or text, specifying the destination and waypoints.

[0704] Step 2:

[0705] The terminal receives the user's voice input and converts it into text using speech recognition technology. The resulting text data is then analyzed using natural language processing technology to identify the destination and waypoints.

[0706] Step 3:

[0707] The device sends the analysis results to a generative model, which accurately understands the user's intent. The information obtained by the generative model is then converted into detailed instructions for the next action.

[0708] Step 4:

[0709] The server obtains real-time traffic information based on the specified destination and waypoint information and calculates the optimal route. The server collects current road conditions, accident information, construction information, etc. from the internet and traffic databases.

[0710] Step 5:

[0711] The server sends the route calculation results to the terminal, which then presents the calculated optimal route to the user. The user reviews the presented optimal route and makes adjustments or additional instructions as needed.

[0712] Step 6:

[0713] The device uses a generative model to suggest potential rest stops and tourist spots along the route, presenting them to the user as options.

[0714] Step 7:

[0715] During operation, the server periodically monitors traffic conditions and recalculates the route as needed. For example, if congestion or an accident occurs, the server generates an alternative route and resends it.

[0716] Step 8:

[0717] The device presents the user with a recalculated alternative route, and if the user approves the new route, it updates the navigation and continues providing directions.

[0718] (Example 1)

[0719] 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".

[0720] Modern navigation systems lack the ability to provide optimal routes that reflect real-time traffic conditions, and they also struggle to suggest waypoints based on user preferences and dynamically adjust routes. Furthermore, their suggestions for rest stops and tourist attractions are limited, highlighting the need for improved user experience.

[0721] 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.

[0722] In this invention, the server includes means for analyzing the user's voice or text input using speech recognition technology and natural language processing technology to identify destinations and intermediate points based on a generative model; means for acquiring traffic conditions, calculating and proposing an optimal route; and means for monitoring traffic conditions in real time while driving and recalculating the route as needed. This enables flexible and optimal navigation that efficiently and accurately reflects the user's wishes.

[0723] "User" refers to the entity that operates the system and specifies destinations and intermediate stops.

[0724] "Speech recognition technology" refers to the technology that analyzes voice input and converts it into corresponding text data.

[0725] "Natural language processing technology" refers to techniques for analyzing text written in natural language and understanding its meaning and intent.

[0726] A "generative model" refers to an algorithm or system that generates a specific output based on input data.

[0727] "Destination" refers to the place that the user ultimately wishes to reach.

[0728] A "stopover point" refers to a designated location where you are to stop on your way to your destination.

[0729] "Traffic conditions" refers to information that includes all factors affecting travel, such as road congestion, accident information, and whether or not there is construction work.

[0730] "Optimal route" refers to the shortest or most efficient path to the destination under specified conditions.

[0731] "Real-time monitoring" refers to constantly observing the ongoing traffic situation and updating the information as needed.

[0732] "Recalculating the route" refers to recalculating the path to the destination based on predicted changes and new information.

[0733] This invention is a system in which users input their travel preferences into a terminal via voice or text, and the system provides optimal navigation via a server.

[0734] First, the user communicates their travel preferences to the device in natural language. The device uses speech recognition technology (e.g., a common speech recognition API) to receive the voice input. The speech recognition technology converts the voice into text, and then natural language processing technology (e.g., a natural language processing library or model) is used to analyze the text for destination and waypoint information.

[0735] The analyzed information is sent to a generative AI model and input as a specific prompt, such as "Calculate the route to the next destination. The starting point is Tokyo, the intermediate point is Yokohama, and the final destination is Nagoya." This generative AI model is designed to identify the destination and intermediate points based on the input prompt.

[0736] Next, the server receives destination information and collects traffic information in real time. This traffic information is obtained from a dedicated API and includes road congestion, accidents, and construction information. Based on this information, the server calculates the optimal route and sends the calculation result to the terminal.

[0737] The device presents the user with a calculated optimal route. Furthermore, it can use a generative AI model to suggest rest stops and sightseeing spots along the way. This allows users to create more personalized travel plans in addition to standard navigation.

[0738] While driving, the server continuously monitors traffic conditions. For example, if unexpected congestion occurs along the way, the server recalculates the route and proposes a new route to the user via the terminal. In this way, users can always reach their destination efficiently based on the latest information.

[0739] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0740] Step 1:

[0741] The user enters their travel preferences into the device via voice or text.

[0742] As a concrete example, the user speaks into their smartphone saying, "I want to go to Nagoya via Yokohama." This input data is converted into text data through speech recognition technology. Once the voice input is converted into text information via speech recognition, it is ready to proceed to the next analysis step.

[0743] Step 2:

[0744] The device analyzes the text converted by speech recognition.

[0745] Using natural language processing technology, the converted text data is analyzed to extract the destination "Nagoya" and the waypoint "Yokohama". At this stage, analysis is performed to understand the user's intent, and the destination and waypoint information is output as a result of the analysis.

[0746] Step 3:

[0747] The device sends the analysis results to an AI model that generates them.

[0748] Specifically, a prompt message such as "Calculate the route to the next destination. The starting point is Tokyo, the intermediate point is Yokohama, and the final destination is Nagoya" is created and passed to the generating AI model. Based on this prompt, the AI ​​model checks the destination and intermediate points and outputs a corresponding list.

[0749] Step 4:

[0750] The server receives data from the generated AI model and collects traffic information.

[0751] The server obtains real-time road and traffic conditions through a traffic information API. This data includes road congestion and construction information, and is used to calculate the optimal route. The calculated route information is then generated from the server.

[0752] Step 5:

[0753] The terminal presents the user with the optimal route received from the server.

[0754] The terminal displays route information retrieved from the server on its screen and suggests rest stops and sightseeing spots along the way as needed. Users can review the presented information and adjust their travel plan accordingly. The output includes detailed map displays and route guidance.

[0755] Step 6:

[0756] The server monitors traffic conditions while driving and recalculates the route if necessary.

[0757] When new traffic conditions, such as congestion or accident information, are received, the server recalculates the route and calculates a new optimal route. The result is sent to the terminal, and the user receives a notification such as "A new route is available." Based on this information, the user can continue to efficiently adjust their route in real time.

[0758] (Application Example 1)

[0759] 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".

[0760] Autonomous vehicles require systems that can efficiently set routes to destinations and respond quickly to real-time changes. However, current navigation systems do not adequately provide intuitive route setting via voice input or information display using visual devices. Furthermore, they lack sufficient flexibility in rerouting in response to changes in traffic conditions, resulting in reduced convenience for users.

[0761] 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.

[0762] In this invention, the server includes means for analyzing voice or text input using a generative model to identify the destination and waypoints, means for acquiring traffic information and calculating the optimal route, and means for presenting the proposed route to a visual device and adjusting the route based on the user's instructions and responses. This makes it possible for users to obtain the optimal route to their destination with simple voice input and to provide a means that can flexibly respond to real-time changing traffic conditions.

[0763] A "generative model" is an artificial intelligence technology that analyzes speech and text data to identify destinations, waypoints, and other points of reference.

[0764] "Means for analyzing voice or text input" refers to means that have the function of understanding voice or text instructions from the user and extracting necessary information.

[0765] A "means for calculating the optimal route" refers to a means that has the function of deriving the shortest or most efficient route to a destination while taking into account traffic information acquired in real time.

[0766] A "means for adjusting routes based on instructions and responses" refers to a means that has the function of modifying and optimizing the proposed route in accordance with user approval or instructions.

[0767] A "means of monitoring traffic conditions in real time" refers to a means of continuously acquiring updated traffic data and evaluating the current route based on that information.

[0768] A "visual device" is a device used by a user to view information, and includes display devices such as smart glasses and displays.

[0769] The system for carrying out this invention begins with the user entering their destination by voice or text. The terminal analyzes the user's input using a combination of speech recognition and natural language processing technologies and transmits the content to a generative AI model in text format. This generative AI model uses prompt sentences to identify destinations and waypoints and generates data for further suggestions. One example of such a prompt sentence is "Please suggest destinations and waypoints: [Example of user input]".

[0770] The server receives the analyzed data and collects the latest traffic information in real time. This traffic information includes road congestion, accident information, and construction. Based on this information, the server calculates the optimal route to the destination and selected waypoints. The calculated route is displayed on a visual device so that the user can check it while traveling. Visual devices include display devices such as smart glasses.

[0771] While driving, the server constantly monitors traffic conditions and recalculates the route as needed. For example, if unexpected congestion occurs, the server calculates an alternative route and displays a message on the visual device saying, "There is congestion. Please try the new route." This feature allows users to reach their destination via the optimal route without stress.

[0772] The main hardware used for this system includes microphones, smartphones, and smart glasses, while the software includes Python, the SpeechRecognition library, and the OpenAI API. This system provides users with intuitive and efficient route planning, improving the travel experience.

[0773] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0774] Step 1:

[0775] The device receives the user's voice input via a microphone and converts that voice data into text data using the SpeechRecognition library. The input is voice data, and the output is the converted text data. In this step, data conversion is performed to extract the necessary information from the voice.

[0776] Step 2:

[0777] The device generates a prompt message for the generative AI model and sends it as text data. Specifically, it generates a prompt message such as "Suggest a destination and waypoints: [User input text]". The input is text data, and the output is a prompt message that the generative model can interpret.

[0778] Step 3:

[0779] The server receives responses from the generative AI model and analyzes the proposed destinations and waypoints. The input is the response data from the generative model, and the output is a list of the analyzed destinations and waypoints. Here, natural language processing techniques are used to interpret and organize the proposed data.

[0780] Step 4:

[0781] The server collects real-time traffic information based on the destination and waypoints, and calculates the optimal route based on that information. The input is destination and waypoint information, as well as traffic data, and the output is the calculated optimal route. Efficient route calculation is performed using traffic information from the database.

[0782] Step 5:

[0783] The server sends the calculated optimal route to the visual device, allowing the user to verify the information. The input is optimized route data, and the output is route information displayed on the visual device. The user can visually confirm the presented route and proceed with their journey.

[0784] Step 6:

[0785] During transit, the server monitors changes in traffic conditions and recalculates the route as needed. The input is constantly updated traffic information data, and the output is the new route calculated as required. The server generates alternative routes when unexpected congestion or changes occur and provides that information to the user's visual device.

[0786] 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.

[0787] This invention provides a navigation system that analyzes user-inputted voice and text to identify destinations and waypoints, as well as a function to recognize the user's emotions and provide an optimal route based on those emotions. The aim of this system is to provide a more comfortable and satisfying travel experience by understanding the user's emotional state in real time and optimizing routes and rest stops accordingly.

[0788] The user uses the device to specify destinations and waypoints in natural language. The device analyzes this using speech recognition technology and identifies the destination using a generative model based on the obtained data. The device also has an emotion engine that analyzes the user's voice tone and facial expression data to evaluate the user's emotional state.

[0789] The server calculates the optimal route based on destination information and real-time traffic information, and also considers the user's emotional state when sending suggested routes and rest stops to the terminal. This allows the server to suggest relaxing routes with scenic views or rest stops such as cafes if the user is feeling stressed.

[0790] While driving, the server continues to monitor traffic conditions and re-evaluates the route as needed, taking into account the user's state as determined by the emotion engine. If the user indicates discomfort due to congestion, for example, an alternative route is generated and its advantages are presented to the user through the device. If the user approves the alternative, the device immediately updates the navigation and guides the user along the new route.

[0791] As a concrete example, suppose a user requests a route from Tokyo to Osaka and wishes to take a break along the way. After departure, if the system determines that the user's stress level is high while driving, it will suggest a suitable rest stop early and present a relaxing scenic route as an alternative. In this way, the system supports a safe and comfortable journey while taking into consideration the user's emotional state.

[0792] The following describes the processing flow.

[0793] Step 1:

[0794] The user specifies the destination and waypoints to the device via voice or text input. The device receives the input, converts the speech to text using speech recognition technology, and analyzes it using natural language processing.

[0795] Step 2:

[0796] The terminal sends the obtained analysis data to a generative model to identify the destination and waypoints. The generative model then generates detailed instructions for the destination.

[0797] Step 3:

[0798] The emotion engine built into the device analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state.

[0799] Step 4:

[0800] Based on the destination and waypoint information received by the server, it calculates the optimal route while considering real-time traffic information. The server also considers data from the emotion engine at the same time.

[0801] Step 5:

[0802] The server sends the terminal a suggested route, along with suggestions including rest stops and potential destinations based on the user's emotional state. The terminal then presents the suggestions to the user and prompts them to make the best choice according to their preferences.

[0803] Step 6:

[0804] While driving, the terminal continuously uses the emotion engine to monitor the user's emotional state. The server also continuously checks traffic conditions and re-evaluates the route as needed.

[0805] Step 7:

[0806] If a user expresses discomfort or experiences stress due to unexpected traffic congestion, the server quickly calculates an alternative route and presents it to the user via their terminal.

[0807] Step 8:

[0808] Once the user accepts the suggested alternative, the device updates the navigation and begins guiding the user along the new route. To ensure a satisfying journey, the guidance takes into account the user's emotions and traffic information.

[0809] (Example 2)

[0810] 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".

[0811] Conventional navigation systems, while providing optimal routes based on traffic information, fail to consider the user's emotional state. This results in a decline in the quality of the driving experience, as they cannot alleviate stress and discomfort during driving. Furthermore, simply selecting the shortest route is insufficient to reduce fatigue and psychological stress from long-distance driving.

[0812] 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.

[0813] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for analyzing the user's emotional state and considering it in route selection. This makes it possible to select the optimal route according to the user's emotional state, thereby reducing stress and providing a more comfortable travel experience.

[0814] A "generative model" is a type of artificial intelligence technology that analyzes speech and text data to extract specific information.

[0815] "Voice or text input" refers to an information format that indicates a destination or instructions given by the user through their device.

[0816] "Identifying destinations and waypoints" is the process of extracting and identifying travel targets and intermediate locations from the input data provided by the user.

[0817] "Traffic information" refers to real-time environmental data related to travel routes, such as road conditions and traffic congestion.

[0818] "Calculating the optimal route" is the process of determining an efficient and beneficial travel route based on a given destination and traffic information.

[0819] "Emotional state" refers to state information that represents a user's psychological and physiological responses and tendencies.

[0820] "Route selection optimization" is the process of selecting a route that prioritizes comfort and efficiency, taking into account the user's emotional state and traffic information.

[0821] The present invention will now be described in terms of embodiments. This system provides advanced navigation technology using a generative AI model to realize a comfortable travel experience for the user. It efficiently processes data between the user, terminal, and server, and provides an optimal route that takes into account the user's emotional state.

[0822] First, the user inputs their destination and intermediate points using voice or text via the device. For example, the user might say, "I want to go to Tokyo Station." This input data is then converted into text data through the speech recognition technology built into the device.

[0823] The device uses a generative AI model to analyze the obtained text data and identify destinations and waypoints. The generative AI model has advanced data processing and analysis capabilities and can quickly understand instructions written in natural language.

[0824] Furthermore, the device is equipped with an emotion engine that analyzes the user's voice tone and facial expression data in real time to evaluate the user's emotional state. This emotional state data is an important element for use in navigation.

[0825] The server receives destination information and emotional state data transmitted from the terminal and calculates the optimal route by combining it with real-time traffic information. This calculation includes not only the shortest route but also routes with beautiful scenery that reduce the user's mental stress.

[0826] For example, if the emotion engine detects that the user is experiencing stress while driving for an extended period, the server sends alternative routes and rest stops to the device that are expected to have a relaxing effect. The device then proposes these to the user, and if the user approves, the navigation system is immediately updated and begins guiding the user along the new route.

[0827] As a concrete example of a prompt, it can be input into a generative AI model in the format of, "My current destination is Tokyo Station. Please provide the optimal route based on my emotional state."

[0828] This system allows users to enjoy a travel experience that takes their emotional state into consideration, while also reducing stress while driving.

[0829] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0830] Step 1: Obtain user input information

[0831] Users input their destination and intermediate points via voice or text through their device. This input is specific, such as "I want to go to Tokyo Station" when using voice.

[0832] Input: User's voice or text data

[0833] Output: Audio and text data provided to the terminal.

[0834] Step 2: Speech Recognition and Text Analysis

[0835] The device uses speech recognition technology to convert the user's voice input into text data.

[0836] Input: User's voice data

[0837] Output: Data converted from audio to text

[0838] Specific operation: The voice input "I want to go to Tokyo Station" is recognized as the text "I want to go to Tokyo Station".

[0839] Step 3: Identify your destination and emotional state.

[0840] The device uses a generative AI model to analyze text data to identify destinations and waypoints, and an emotion engine to analyze the user's voice tone and facial expression data to evaluate their emotional state.

[0841] Input: Text data converted by speech recognition, as well as voice tone and facial expression data.

[0842] Output: Identified destination information and user emotional state data

[0843] Specific operation: The generative AI model identifies "Tokyo Station" as the destination, and the emotion engine evaluates the stress level.

[0844] Step 4: Calculating the optimal path

[0845] The server calculates the optimal route based on destination information, emotional state data, and real-time traffic information received from the terminal.

[0846] Input: Destination information, emotional state data, traffic information

[0847] Output: Optimal route information

[0848] Specific operation: A scenic route that avoids traffic congestion and allows for relaxation is calculated.

[0849] Step 5: Route Suggestion and Selection

[0850] The server sends the calculated route to the terminal, which then proposes it to the user and prompts them to make a choice.

[0851] Input: Optimal route information

[0852] Output: Route suggestion to the user

[0853] Specific operation: Options are displayed on the terminal screen, and the user selects a route.

[0854] Step 6: Update Navigation

[0855] If the user selects an alternative route, the device updates its navigation system and generates data to guide the user along the new route.

[0856] Input: User route selection

[0857] Output: Updated navigation information

[0858] Specific action: Navigation voice based on the selected route is updated instantly.

[0859] Step 7: Re-evaluate the route

[0860] During operation, the server monitors changes in traffic conditions and the user's emotional state, recalculates the route as needed, and suggests alternative routes.

[0861] Input: Real-time traffic information, user's emotional state

[0862] Output: Alternative route information (if necessary)

[0863] Specific action: An alternative route to avoid new traffic congestion is generated and suggested to the user.

[0864] (Application Example 2)

[0865] 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".

[0866] Conventional navigation systems only provide routes based on traffic information, making it impossible to optimize routes while considering the user's emotional state. As a result, users are often exposed to stressful environments, making it difficult to obtain a comfortable travel experience. The objective of this invention is to solve this problem and improve the travel experience based on emotions.

[0867] 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.

[0868] In this invention, the server includes means for analyzing voice or text input using a generative model to identify destinations and waypoints, means for acquiring traffic information and calculating the optimal route, and means for evaluating the user's emotional state in real time and optimizing the route and rest stops based on that evaluation. This makes it possible to provide the optimal route according to the user's instructions and emotional state.

[0869] A "generative model" is an artificial intelligence technology that learns from collected data and generates output based on a given input.

[0870] "Voice or text input" refers to voice or text information used by a user to communicate a destination or instructions.

[0871] "Destination and intermediate points" refer to the final place a user intends to reach during their journey, as well as any points they will visit along the way.

[0872] "Traffic information" refers to real-time, ever-changing data related to travel, such as road congestion, accidents, and road closures.

[0873] "Means for calculating the optimal route" refers to a method or device for calculating the most efficient travel route based on acquired traffic information and destination information.

[0874] "Emotional state" refers to the psychological and emotional state of the user, analyzed from their voice and facial expressions.

[0875] "Real-time monitoring" refers to continuously tracking and analyzing the situation as it unfolds.

[0876] "Recalculating the route" means recalculating the initially set travel route in accordance with changing conditions.

[0877] The system implementing this invention is intended to be installed in autonomous vehicles and to provide users with a comfortable travel experience. The system mainly consists of a server and an in-vehicle terminal, and realizes the following functions.

[0878] The server uses a generative AI model to analyze voice or text input from the user to identify destinations and waypoints. During this process, the user's voice data is converted to text via the Google Speech-to-Text API. The device's built-in microphone and camera are used to collect user voice and facial expression data. Microsoft Azure's Face API is used to assess the user's emotional state in real time based on their facial expressions, measuring stress levels and comfort levels.

[0879] The server also collects traffic information in real time and calculates the optimal route using the Mapbox Directions API. Based on the user's emotional state, it suggests scenic routes and relaxing rest stops. If the user is feeling stressed, it selects rest stops or alternative routes and presents them to the user while driving.

[0880] As a concrete example, when a user sets off on a weekend trip with their family, they can instruct the system to "take the route to Nagoya" while in the car. The system will then calculate the optimal route and depart. If the user appears tired while driving, the system will suggest a nearby rest stop with a nice view. If the user accepts this suggestion, the system will immediately present a new route and guide them to that location.

[0881] Examples of prompts for a generative AI model are as follows:

[0882] User instruction: "Tell me the route to Nagoya."

[0883] Requirements for the interpretive model: "Identify the destination in Nagoya and generate suggestions based on the emotional state."

[0884] Predicted outcome: "We offer the following suggested route: Use the expressway to Nagoya. You can visit scenic rest stops along the way."

[0885] In this way, the server and terminal can understand the user's voice commands and emotional state, enabling appropriate navigation and emotion-based route optimization.

[0886] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0887] Step 1:

[0888] The user enters their destination in the car by giving voice instructions. The device captures the user's voice via the microphone and converts the voice data to text using the Google Speech-to-Text API. This entered text data is then used in the next step.

[0889] Step 2:

[0890] The server inputs the text data obtained in Step 1 into the generating AI model to identify the destination and waypoints. Based on the given prompt sentence, the model infers the destination and outputs relevant location information. This output is then used to calculate the route.

[0891] Step 3:

[0892] The server obtains traffic information via the Mapbox Directions API. Using the obtained traffic information and the location information obtained in step 2, the server calculates the optimal route. As a result of this calculation, efficient route information is obtained.

[0893] Step 4:

[0894] The terminal presents the user with the route calculated in step 3. Based on the user's response, it receives final approval for the route and adjusts it accordingly. Suggestions for rest stops and scenic routes to reduce user stress are also presented.

[0895] Step 5:

[0896] The device uses a camera and an emotion recognition API to acquire the user's facial expression data and evaluate their emotional state in real time. This data is sent to a server to monitor changes in the user's psychological state.

[0897] Step 6:

[0898] The server integrates the emotional state information obtained in step 5 with real-time traffic conditions and re-evaluates alternative routes as needed. As a result of the re-evaluation, new candidate routes are generated and presented to the user via the terminal. If the user approves the suggestion, the terminal immediately updates the navigation.

[0899] 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.

[0900] 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.

[0901] 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 robot 414.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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."

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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 as being incorporated by reference.

[0920] The following is further disclosed regarding the embodiments described above.

[0921] (Claim 1)

[0922] A means for analyzing speech or text input using a generative model to identify destinations and waypoints,

[0923] A means of acquiring traffic information and calculating the optimal route,

[0924] A means of presenting proposed routes and candidate locations to the user and adjusting the route based on the user's instructions and responses,

[0925] A means of monitoring traffic conditions in real time and recalculating routes,

[0926] A system that includes this.

[0927] (Claim 2)

[0928] The system according to claim 1, which uses a generative model to suggest rest stops and intermediate destinations to the user.

[0929] (Claim 3)

[0930] The system according to claim 1, which presents an alternative route to the user based on changes in traffic conditions and navigates the user along that route if approved.

[0931] "Example 1"

[0932] (Claim 1)

[0933] A means for analyzing the user's voice or text input using speech recognition technology and natural language processing technology, and identifying the destination and intermediate points based on a generative model,

[0934] A means of acquiring traffic conditions, calculating and proposing the optimal route,

[0935] A means of presenting candidate routes and locations and adjusting the route through instructions and responses,

[0936] A means of monitoring traffic conditions in real time while driving and recalculating the route as needed,

[0937] A system that includes this.

[0938] (Claim 2)

[0939] The system according to claim 1, which applies a generative model to suggest intermediate rest stops and intermediate destinations.

[0940] (Claim 3)

[0941] The system according to claim 1, which, in response to changes in traffic conditions, presents alternative routes to the user and guides them along those routes if approved.

[0942] "Application Example 1"

[0943] (Claim 1)

[0944] A means for analyzing speech or text input using a generative model to identify destinations and waypoints,

[0945] A means of acquiring traffic information and calculating the optimal route,

[0946] A means of presenting proposed routes and candidate locations to the user and adjusting the route based on the user's instructions and responses,

[0947] A means of monitoring traffic conditions in real time and recalculating routes,

[0948] A method in which the user inputs instructions by voice, and based on that, the optimal route to the destination and intermediate points is suggested in real time,

[0949] A means of presenting route information to passengers so that they can check it on their visual devices,

[0950] A system that includes this.

[0951] (Claim 2)

[0952] The system according to claim 1, which uses a generative model to suggest rest stops and intermediate destinations to the user and displays them on a visual device.

[0953] (Claim 3)

[0954] The system according to claim 1, which, based on changes in traffic conditions, presents an alternative route to the user and, if approved, navigates the user to the new route on a visual device.

[0955] "Example 2 of combining an emotion engine"

[0956] (Claim 1)

[0957] A means for analyzing speech or text input using a generative model to identify destinations and waypoints,

[0958] A means of acquiring traffic information and calculating the optimal route,

[0959] A means of presenting proposed routes and candidate locations to the user and adjusting the route based on the user's instructions and responses,

[0960] A means of monitoring traffic conditions in real time and recalculating routes,

[0961] A means of analyzing the user's emotional state and considering it in route selection,

[0962] A means for optimizing routes and rest stops based on the user's emotional state,

[0963] A system that includes this.

[0964] (Claim 2)

[0965] The system according to claim 1, which uses a generative model to suggest rest stops and intermediate destinations to the user and optimizes them according to the user's emotional state.

[0966] (Claim 3)

[0967] The system according to claim 1, which, based on traffic conditions and changes in the user's emotional state, presents an alternative route to the user and navigates them along that route if approved.

[0968] "Application example 2 of combining emotional engines"

[0969] (Claim 1)

[0970] A means for analyzing speech or text input using a generative model to identify destinations and waypoints,

[0971] A means of acquiring traffic information and calculating the optimal route,

[0972] A means of presenting proposed routes and candidate locations to the user and adjusting the route based on the user's instructions and responses,

[0973] A means for evaluating the user's emotional state in real time and optimizing routes and rest stops based on that evaluation,

[0974] A means of monitoring traffic conditions in real time and recalculating routes,

[0975] A system that includes this.

[0976] (Claim 2)

[0977] The system according to claim 1, which uses a generative model to suggest rest stops and intermediate destinations to the user while taking into account their emotional state.

[0978] (Claim 3)

[0979] The system according to claim 1, which, based on changes in traffic conditions and the user's emotional state, presents an alternative route to the user and navigates them along that route if approved. [Explanation of Symbols]

[0980] 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 means for analyzing speech or text input using a generative model to identify destinations and waypoints, A means of acquiring traffic information and calculating the optimal route, A means of presenting proposed routes and candidate locations to the user and adjusting the route based on the user's instructions and responses, A means of monitoring traffic conditions in real time and recalculating routes, A system that includes this.

2. The system according to claim 1, which uses a generative model to suggest rest stops and intermediate destinations to the user.

3. The system according to claim 1, which presents an alternative route to the user based on changes in traffic conditions and navigates the user along that route if approved.

Images