system

Abstract

The system according to this embodiment aims to suggest the optimal route based on the driver's hobbies and preferences. [Solution] The system according to the embodiment comprises a collection unit, a generation unit, and a calculation unit. The collection unit collects driver profile information. The generation unit generates customized content based on hobbies and preferences based on the information collected by the collection unit. The calculation unit integrates real-time traffic information and weather data based on the customized content generated by the generation unit to calculate the optimal route.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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] In the conventional technology, route proposals based on the personal hobbies and preferences of drivers have not been sufficiently made, and there is room for improvement.

[0005] The system according to the embodiment aims to propose an optimal route based on the hobbies and preferences of the driver.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a generation unit, and a calculation unit. The collection unit collects driver profile information. The generation unit generates customized content based on hobbies and preferences based on the information collected by the collection unit. The calculation unit integrates real-time traffic information and weather data based on the customized content generated by the generation unit to calculate the optimal route. [Effects of the Invention]

[0007] The system according to this embodiment can suggest the optimal route based on the driver's hobbies and preferences. [Brief explanation of the drawing]

[0008] [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] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when three or more matters are connected and expressed with "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] 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.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is a system that recommends tourist spots and restaurants and proposes the optimal route based on the driver's personal hobbies and preferences. This AI agent system collects the driver's profile information and generates customized content based on hobbies and preferences. Next, it integrates real-time traffic information and weather data to calculate the optimal route. This is expected to reduce travel time and improve tourist satisfaction. This AI agent system utilizes LLM (Large-Scale Language Model) and multimodal AI to provide personalized recommendations based on the driver's profile. For example, if the driver is interested in historical tourist spots, it will prioritize recommending such spots. Furthermore, by taking real-time traffic information and weather data into consideration, it proposes the optimal route and improves the quality of the trip. In addition, this AI agent system has developed a dynamic routing algorithm to improve the efficiency of travel planning and the quality of the trip. This reduces the time spent on travel planning and solves the problem of being unable to make the best choice due to insufficient information. The target users of this AI agent system are individuals aged 20-50 who love to travel, are adventurous, and seek new experiences. The introduction of an AI agent system is expected to streamline travel planning, improve the quality of travel, increase tourist satisfaction, and boost repeat visitor rates. Specifically, the AI ​​agent system can enhance travel quality by generating customized content based on driver profile information and calculating optimal routes.

[0029] The AI ​​agent system according to the embodiment comprises a collection unit, a generation unit, and a calculation unit. The collection unit collects driver profile information. Driver profile information includes, but is not limited to, age, gender, and driving history. The collection unit provides, for example, a form for inputting the driver's age and gender. The collection unit can also collect past driving data to obtain the driver's driving history. For example, the collection unit analyzes the driver's driving history to understand their driving style and frequency. The generation unit generates customized content based on hobbies and preferences based on the information collected by the collection unit. For example, the generation unit generates customized routes and sightseeing spots based on the driver's music preferences and travel preferences. The generation unit provides, for example, a form for inputting the driver's favorite music genres. The generation unit can also recommend sightseeing spots and restaurants based on the driver's travel preferences. For example, the generation unit prioritizes recommending sightseeing spots that the driver is interested in. The calculation unit integrates real-time traffic information and weather data based on the customized content generated by the generation unit to calculate the optimal route. The calculation unit, for example, acquires real-time traffic information and calculates the optimal route. The calculation unit proposes the optimal route, for example, by considering traffic congestion and accident information. The calculation unit can also acquire real-time weather data and propose a route according to the weather. For example, the calculation unit prioritizes proposing a safe route in rainy weather. As a result, the AI ​​agent system according to the embodiment can improve the quality of travel by generating customized content based on the driver's profile information and calculating the optimal route.

[0030] The data collection unit collects driver profile information. This information includes, but is not limited to, age, gender, and driving history. The data collection unit provides, for example, a form for drivers to input their age and gender. Specifically, the data collection unit provides an interface for drivers to input their age and gender through a web form or mobile application. This allows drivers to easily input their basic information. The data collection unit can also collect past driving data to obtain the driver's driving history. For example, the data collection unit obtains driving data from the vehicle's onboard diagnostics (OBD) system or the driver's smartphone app. This includes detailed data such as mileage, driving time, speed, and the number of sudden braking incidents. The data collection unit analyzes this data to understand the driver's driving style and frequency. For example, the data collection unit can identify whether the driver frequently uses highways or mainly drives on congested urban roads. This allows the data collection unit to understand the driver's driving habits and preferences in detail and provide accurate information to subsequent generation and calculation units. Furthermore, the data collection unit can also implement surveys and evaluation systems to collect driver feedback. This allows for understanding driver satisfaction levels and areas for improvement, thereby enhancing the overall system performance.

[0031] The generation unit generates customized content based on the driver's hobbies and preferences, using information collected by the collection unit. For example, the generation unit generates customized routes and sightseeing spots based on the driver's music preferences and travel preferences. Specifically, the generation unit provides a form for the driver to input their favorite music genres. The driver can select genres such as rock, pop, and classical, and the generation unit creates a playlist tailored to the driver's preferences based on this. The generation unit can also recommend sightseeing spots and restaurants based on the driver's travel preferences. For example, if the driver prefers natural scenery, the generation unit will suggest a route that passes through national parks and beautiful lakes. On the other hand, for drivers who prefer city sightseeing, it will suggest a route through urban areas with historical buildings and famous restaurants. The generation unit uses AI to learn from the driver's past choices and feedback, generating more accurate customized content. For example, the generation unit analyzes data on places the driver has visited and sightseeing spots they have rated in the past, and recommends new spots that match the driver's preferences. Furthermore, the generation unit can utilize real-time updated information to provide customized content that includes the latest events and special promotions. This allows the generating unit to consistently offer fresh and appealing suggestions to drivers, thereby improving the quality of their travel experience.

[0032] The calculation unit integrates real-time traffic information and weather data based on the customizations generated by the generation unit to calculate the optimal route. For example, the calculation unit acquires real-time traffic information and calculates the optimal route. Specifically, the calculation unit acquires real-time traffic data from traffic information service providers to understand the current traffic situation. This includes information such as traffic congestion, accidents, and road construction. Based on this information, the calculation unit calculates the most efficient and safe route for the driver. For example, the calculation unit can suggest an alternative route to avoid traffic congestion. The calculation unit can also acquire real-time weather data and suggest a route appropriate to the weather. For example, the calculation unit acquires current weather data from weather information service providers and prioritizes suggesting safe routes on rainy or snowy days. This allows drivers to drive with peace of mind even in bad weather. Furthermore, the calculation unit considers the driver's profile information and the customizations generated by the generation unit to suggest a route that suits the driver's preferences. For example, if the driver prefers natural scenery, the calculation unit can suggest a scenic route while considering traffic conditions and weather. In this way, the calculation unit can provide the optimal route for the driver and improve the quality of their trip. Furthermore, the calculation unit can recalculate the route based on data updated in real time, always providing the optimal route based on the latest information.

[0033] The AI ​​department utilizes LLM and multimodal AI. LLM is a large-scale language model that can analyze text data and perform natural language processing. For example, LLM can analyze a driver's profile information and generate customized content based on their hobbies and preferences. Multimodal AI is an AI that integrates and analyzes multiple modals (e.g., text, images, audio). For example, multimodal AI can analyze image and audio data based on a driver's profile information and generate customized content. As a result, the AI ​​department can provide personalized recommendations based on the driver's profile by utilizing LLM and multimodal AI. For example, if a driver is interested in historical tourist spots, the AI ​​department will prioritize recommending such spots. The AI ​​department can also recommend appropriate music based on the driver's musical preferences. For example, the AI ​​department can analyze the driver's favorite music genres and recommend music related to those genres. This allows the AI ​​department to provide more appropriate customized content based on the driver's profile information.

[0034] The Algorithm Department develops dynamic routing algorithms. Dynamic routing algorithms calculate the optimal route by considering real-time traffic information and weather data. For example, the Algorithm Department acquires real-time traffic information and calculates the optimal route by considering traffic congestion and accident information. The Algorithm Department can also acquire real-time weather data and calculate routes according to the weather. For example, the Algorithm Department prioritizes calculating safe routes in rainy weather. By developing dynamic routing algorithms, the Algorithm Department aims to improve the efficiency of travel planning and the quality of travel. For example, the Algorithm Department can reduce the time spent on travel planning and solve the problem of being unable to make optimal choices due to insufficient information. As a result, the Algorithm Department can provide more appropriate routes based on driver profile information.

[0035] The data collection unit can analyze the driver's past travel history and select the optimal data collection method. For example, the data collection unit can prioritize collecting relevant information based on places the driver has visited in the past. The data collection unit can also identify categories of interest from the driver's past travel history and collect information related to those categories. For example, the data collection unit can analyze the driver's past travel history and determine the optimal timing for data collection. This allows the data collection unit to prioritize collecting relevant information by analyzing the driver's past travel history. Past travel history includes, but is not limited to, places visited and frequency of travel. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the driver's past travel history data into a generating AI and have the generating AI select the optimal data collection method.

[0036] The data collection unit can filter profile information based on the driver's current living situation and areas of interest. For example, the data collection unit can prioritize collecting relevant information based on the driver's current occupation and hobbies. The data collection unit can also filter appropriate information based on the driver's current living situation (e.g., family structure, presence of pets). The data collection unit can also collect relevant information based on the driver's areas of interest (e.g., sports, music). This allows the data collection unit to collect appropriate information by filtering information based on the driver's current living situation and areas of interest. Living situation includes, but is not limited to, occupation and family environment. Areas of interest include, but is not limited to, hobbies and topics of interest. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the driver's current living situation data into a generating AI and have the generating AI perform the information filtering.

[0037] The data collection unit can prioritize the collection of highly relevant information by considering the driver's geographical location when collecting profile information. For example, the data collection unit can prioritize the collection of information on tourist attractions and restaurants related to the area where the driver is currently located. For example, the data collection unit can also collect information on nearby events based on the driver's geographical location. For example, the data collection unit can also collect information related to the optimal route by considering the driver's geographical location. In this way, the data collection unit can prioritize the collection of highly relevant information by considering the driver's geographical location. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the driver's geographical location data into a generating AI and have the generating AI perform the collection of highly relevant information.

[0038] The collection unit can analyze the driver's social media activity and collect relevant information when collecting profile information. For example, the collection unit can analyze the driver's social media posts and collect information related to categories of interest. The collection unit can also collect relevant information based on the driver's social media following list. For example, the collection unit can analyze the driver's social media activity and collect information related to their current areas of interest. Thus, by analyzing the driver's social media activity, the collection unit can collect information related to their current areas of interest. Social media activity includes, but is not limited to, posts and the number of likes. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the driver's social media data into a generating AI and have the generating AI collect relevant information.

[0039] The generation unit can adjust the level of detail generated based on the importance of the driver's hobbies and preferences when generating customized content. For example, if the driver has a strong interest in a particular hobby, the generation unit will generate detailed information related to that hobby. The generation unit can also adjust the level of detail of the customized content according to the importance of the driver's preferences. The generation unit can also prioritize the generation of relevant information based on the driver's hobbies and preferences. This allows the generation unit to provide more appropriate customized content by adjusting the level of detail based on the importance of the driver's hobbies and preferences. The importance of hobbies and preferences includes, but is not limited to, survey results and behavioral history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on the driver's hobbies and preferences into a generation AI and have the generation AI adjust the level of detail of the generation.

[0040] The generation unit can apply different generation algorithms depending on the driver's category when generating customized content. For example, if the driver is interested in historical tourist spots, the generation unit can apply a generation algorithm that emphasizes historical information. For example, if the driver is interested in gourmet food, the generation unit can apply a generation algorithm that emphasizes restaurant information. For example, if the driver is interested in nature tourism, the generation unit can apply a generation algorithm that emphasizes natural scenery. In this way, the generation unit can provide more appropriate customized content by applying different generation algorithms depending on the driver's category. Driver categories include, but are not limited to, age group and driving style. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input driver category data into a generation AI and have the generation AI execute the application of different generation algorithms.

[0041] The generation unit can determine the generation priority based on the driver's past travel history when generating customized content. For example, the generation unit can prioritize generating relevant information based on places the driver has visited in the past. The generation unit can also, for example, identify categories of interest from the driver's past travel history and prioritize generating information related to those categories. The generation unit can also, for example, analyze the driver's past travel history to determine the optimal generation timing. This allows the generation unit to prioritize providing relevant information by determining the generation priority based on the driver's past travel history. Past travel history includes, but is not limited to, places visited and travel frequency. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the driver's past travel history data into a generation AI and have the generation AI perform the determination of generation priorities.

[0042] The generation unit can adjust the generation order based on the driver's relevance when generating customized content. For example, the generation unit can prioritize generating relevant information based on the driver's current areas of interest. The generation unit can also prioritize generating highly relevant information based on the driver's past travel history. The generation unit can also prioritize generating highly relevant information by analyzing the driver's profile information. This allows the generation unit to provide more appropriate information by adjusting the generation order based on the driver's relevance. Relevance includes, but is not limited to, past behavioral history and topics of interest. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input driver relevance data into a generation AI and have the generation AI adjust the generation order.

[0043] The calculation unit can improve the accuracy of its calculations by considering the driver's past travel history when calculating the optimal route. For example, the calculation unit calculates the optimal route based on routes the driver has used in the past. The calculation unit can also calculate routes that avoid congestion from the driver's past travel history. For example, the calculation unit can analyze the driver's past travel history and calculate the most efficient route. In this way, the calculation unit can improve the accuracy of its calculations by considering the driver's past travel history. Past travel history includes, but is not limited to, places visited and frequency of travel. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input the driver's past travel history data into a generating AI and have the generating AI perform the calculation accuracy improvement.

[0044] The calculation unit can perform calculations considering the driver's attribute information when calculating the optimal route. For example, the calculation unit can calculate the optimal route based on the driver's age and gender. The calculation unit can also calculate the optimal route based on the driver's driving experience. The calculation unit can also calculate the optimal route based on the driver's health condition. In this way, the calculation unit can provide a more appropriate route by considering the driver's attribute information. Attribute information includes, but is not limited to, age, gender, and occupation. Some or all of the above processing in the calculation unit may be performed using, for example, AI, or not using AI. For example, the calculation unit can input driver attribute information data into a generating AI and have the generating AI perform the calculations.

[0045] The calculation unit can perform calculations considering the geographical distribution of drivers when calculating the optimal route. For example, the calculation unit calculates the optimal route based on the area where the driver is currently located. The calculation unit can also prioritize the calculation of relevant information based on the geographical distribution of drivers. The calculation unit can also calculate the optimal route considering the geographical distribution of drivers. This allows the calculation unit to provide a more appropriate route by considering the geographical distribution of drivers. Geographical distribution includes, but is not limited to, place of residence and frequency of visits. Some or all of the above processing in the calculation unit may be performed using, for example, AI, or not using AI. For example, the calculation unit can input the geographical distribution data of drivers into a generating AI and have the generating AI perform the calculations.

[0046] The calculation unit can improve the accuracy of its calculations by referring to relevant literature for the driver when calculating the optimal route. For example, the calculation unit can refer to relevant literature and calculate the optimal route based on the driver's past travel history. The calculation unit can also refer to relevant literature and calculate the optimal route based on the driver's attribute information. The calculation unit can also refer to relevant literature and calculate the optimal route based on the driver's current situation. In this way, the calculation unit can improve the accuracy of its calculations by referring to relevant literature for the driver. Relevant literature includes, but is not limited to, academic papers and technical reports. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input the driver's relevant literature data into a generating AI and have the generating AI perform the calculation accuracy improvement.

[0047] The AI ​​unit can optimize the learning algorithm by referring to past learning data during AI training. For example, the AI ​​unit can analyze past learning data and select the optimal learning algorithm. The AI ​​unit can also adjust the parameters of the learning algorithm based on past learning data. The AI ​​unit can also improve the accuracy of the learning algorithm by referring to past learning data. Past learning data includes, but is not limited to, training datasets and evaluation data. Some or all of the above processing in the AI ​​unit may be performed using AI, for example, or without AI. For example, the AI ​​unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0048] The AI ​​unit can weight training data based on the timing of driver profile information submissions during AI training. For example, the AI ​​unit can prioritize weighting of recently submitted driver profile information as training data. The AI ​​unit can also adjust the weighting of training data based on the timing of driver profile information submissions. For example, the AI ​​unit can weight training data considering the timing of driver profile information submissions. This allows the AI ​​unit to perform more appropriate training by weighting training data based on the timing of driver profile information submissions. Submission timing includes, but is not limited to, submission date and submission frequency. Some or all of the above processing in the AI ​​unit may be performed using AI or not using AI. For example, the AI ​​unit can input driver profile information submission timing data into a generating AI and have the generating AI perform the training data weighting.

[0049] The algorithm unit can optimize routing algorithms by referring to past route data during algorithm development. For example, the algorithm unit can analyze past route data and select the optimal routing algorithm. The algorithm unit can also adjust the parameters of the routing algorithm based on past route data. The algorithm unit can also improve the accuracy of the routing algorithm by referring to past route data. Thus, the algorithm unit can improve the accuracy of the routing algorithm by referring to past route data. Past route data includes, but is not limited to, travel history and reasons for route selection. Some or all of the above processing in the algorithm unit may be performed using AI, for example, or without AI. For example, the algorithm unit can input past route data into a generating AI and have the generating AI perform algorithm optimization.

[0050] The algorithm unit can optimize the routing algorithm by considering the geographical distribution of drivers during its development. For example, the algorithm unit develops an optimal routing algorithm based on the area where the driver is currently located. The algorithm unit can also prioritize the incorporation of relevant information into the algorithm based on the geographical distribution of drivers. For example, the algorithm unit can develop an optimal routing algorithm by considering the geographical distribution of drivers. This allows the algorithm unit to provide more appropriate routes by considering the geographical distribution of drivers. Geographical distribution includes, but is not limited to, place of residence and frequency of visits. Some or all of the above processing in the algorithm unit may be performed using AI, for example, or without AI. For example, the algorithm unit can input driver geographical distribution data into a generating AI and have the generating AI perform algorithm optimization.

[0051] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0052] The data collection unit can monitor the driver's health status and adjust the method of collecting profile information based on that status. For example, the data collection unit can monitor the driver's heart rate and blood pressure and collect detailed profile information when the driver is in good health. The data collection unit can also simplify the collection method and collect only the minimum necessary information if the driver is fatigued, for example. The data collection unit can also adjust the timing of data collection to ensure the accuracy of the information if the driver is stressed, for example. In this way, the data collection unit can improve the accuracy and efficiency of the information by adjusting the method of collecting profile information according to the driver's health status.

[0053] The data collection unit can analyze drivers' social media activity and collect relevant information. For example, the data collection unit can analyze the content of drivers' social media posts and collect information related to categories of interest. The data collection unit can also collect relevant information based on drivers' social media following lists, for example. The data collection unit can also analyze drivers' social media activity and collect information related to their current areas of interest. In this way, the data collection unit can collect information related to drivers' current areas of interest by analyzing their social media activity.

[0054] The calculation unit can calculate the optimal route by considering the driver's past travel history. For example, the calculation unit calculates the optimal route based on routes the driver has used in the past. The calculation unit can also calculate routes that avoid congestion from the driver's past travel history. The calculation unit can also analyze the driver's past travel history and calculate the most efficient route. In this way, the calculation unit can improve the accuracy of its calculations by considering the driver's past travel history.

[0055] The generation unit can generate customized content based on the driver's past travel history. For example, the generation unit can prioritize generating relevant information based on places the driver has visited in the past. The generation unit can also identify categories of interest from the driver's past travel history and generate information related to those categories. The generation unit can also analyze the driver's past travel history to determine the optimal generation timing. This allows the generation unit to prioritize the provision of relevant information by determining generation priorities based on the driver's past travel history.

[0056] The data collection unit can prioritize collecting highly relevant information by considering the driver's geographical location. For example, the unit can prioritize collecting information on tourist attractions and restaurants related to the area where the driver is currently located. The unit can also collect information on nearby events based on the driver's geographical location. The unit can also collect information related to the optimal route by considering the driver's geographical location. In this way, the data collection unit can prioritize collecting highly relevant information by considering the driver's geographical location.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The collection unit collects driver profile information. Driver profile information includes, for example, age, gender, and driving history. The collection unit provides a form for drivers to input their age and gender, and collects past driving data to understand their driving style and frequency. Step 2: The generation unit generates customized content based on the driver's hobbies and preferences, using the information collected by the collection unit. The generation unit generates customized routes and sightseeing spots based on the driver's music preferences and travel preferences. For example, it provides a form for the driver to input their favorite music genres and recommends sightseeing spots and restaurants based on their travel preferences. Step 3: The calculation unit integrates real-time traffic information and weather data based on the customizations generated by the generation unit to calculate the optimal route. The calculation unit acquires real-time traffic information and weather data, and proposes the optimal route considering traffic congestion, accident information, and weather conditions. For example, in rainy weather, it prioritizes proposing a safe route.

[0059] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system that recommends tourist spots and restaurants and proposes the optimal route based on the driver's personal hobbies and preferences. This AI agent system collects the driver's profile information and generates customized content based on hobbies and preferences. Next, it integrates real-time traffic information and weather data to calculate the optimal route. This is expected to reduce travel time and improve tourist satisfaction. This AI agent system utilizes LLM (Large-Scale Language Model) and multimodal AI to provide personalized recommendations based on the driver's profile. For example, if the driver is interested in historical tourist spots, it will prioritize recommending such spots. Furthermore, by taking real-time traffic information and weather data into consideration, it proposes the optimal route and improves the quality of the trip. In addition, this AI agent system has developed a dynamic routing algorithm to improve the efficiency of travel planning and the quality of the trip. This reduces the time spent on travel planning and solves the problem of being unable to make the best choice due to insufficient information. The target users of this AI agent system are individuals aged 20-50 who love to travel, are adventurous, and seek new experiences. The introduction of an AI agent system is expected to streamline travel planning, improve the quality of travel, increase tourist satisfaction, and boost repeat visitor rates. Specifically, the AI ​​agent system can enhance travel quality by generating customized content based on driver profile information and calculating optimal routes.

[0060] The AI ​​agent system according to the embodiment comprises a collection unit, a generation unit, and a calculation unit. The collection unit collects driver profile information. Driver profile information includes, but is not limited to, age, gender, and driving history. The collection unit provides, for example, a form for inputting the driver's age and gender. The collection unit can also collect past driving data to obtain the driver's driving history. For example, the collection unit analyzes the driver's driving history to understand their driving style and frequency. The generation unit generates customized content based on hobbies and preferences based on the information collected by the collection unit. For example, the generation unit generates customized routes and sightseeing spots based on the driver's music preferences and travel preferences. The generation unit provides, for example, a form for inputting the driver's favorite music genres. The generation unit can also recommend sightseeing spots and restaurants based on the driver's travel preferences. For example, the generation unit prioritizes recommending sightseeing spots that the driver is interested in. The calculation unit integrates real-time traffic information and weather data based on the customized content generated by the generation unit to calculate the optimal route. The calculation unit, for example, acquires real-time traffic information and calculates the optimal route. The calculation unit proposes the optimal route, for example, by considering traffic congestion and accident information. The calculation unit can also acquire real-time weather data and propose a route according to the weather. For example, the calculation unit prioritizes proposing a safe route in rainy weather. As a result, the AI ​​agent system according to the embodiment can improve the quality of travel by generating customized content based on the driver's profile information and calculating the optimal route.

[0061] The data collection unit collects driver profile information. This information includes, but is not limited to, age, gender, and driving history. The data collection unit provides, for example, a form for drivers to input their age and gender. Specifically, the data collection unit provides an interface for drivers to input their age and gender through a web form or mobile application. This allows drivers to easily input their basic information. The data collection unit can also collect past driving data to obtain the driver's driving history. For example, the data collection unit obtains driving data from the vehicle's onboard diagnostics (OBD) system or the driver's smartphone app. This includes detailed data such as mileage, driving time, speed, and the number of sudden braking incidents. The data collection unit analyzes this data to understand the driver's driving style and frequency. For example, the data collection unit can identify whether the driver frequently uses highways or mainly drives on congested urban roads. This allows the data collection unit to understand the driver's driving habits and preferences in detail and provide accurate information to subsequent generation and calculation units. Furthermore, the data collection unit can also implement surveys and evaluation systems to collect driver feedback. This allows for understanding driver satisfaction levels and areas for improvement, thereby enhancing the overall system performance.

[0062] The generation unit generates customized content based on the driver's hobbies and preferences, using information collected by the collection unit. For example, the generation unit generates customized routes and sightseeing spots based on the driver's music preferences and travel preferences. Specifically, the generation unit provides a form for the driver to input their favorite music genres. The driver can select genres such as rock, pop, and classical, and the generation unit creates a playlist tailored to the driver's preferences based on this. The generation unit can also recommend sightseeing spots and restaurants based on the driver's travel preferences. For example, if the driver prefers natural scenery, the generation unit will suggest a route that passes through national parks and beautiful lakes. On the other hand, for drivers who prefer city sightseeing, it will suggest a route through urban areas with historical buildings and famous restaurants. The generation unit uses AI to learn from the driver's past choices and feedback, generating more accurate customized content. For example, the generation unit analyzes data on places the driver has visited and sightseeing spots they have rated in the past, and recommends new spots that match the driver's preferences. Furthermore, the generation unit can utilize real-time updated information to provide customized content that includes the latest events and special promotions. This allows the generating unit to consistently offer fresh and appealing suggestions to drivers, thereby improving the quality of their travel experience.

[0063] The calculation unit integrates real-time traffic information and weather data based on the customizations generated by the generation unit to calculate the optimal route. For example, the calculation unit acquires real-time traffic information and calculates the optimal route. Specifically, the calculation unit acquires real-time traffic data from traffic information service providers to understand the current traffic situation. This includes information such as traffic congestion, accidents, and road construction. Based on this information, the calculation unit calculates the most efficient and safe route for the driver. For example, the calculation unit can suggest an alternative route to avoid traffic congestion. The calculation unit can also acquire real-time weather data and suggest a route appropriate to the weather. For example, the calculation unit acquires current weather data from weather information service providers and prioritizes suggesting safe routes on rainy or snowy days. This allows drivers to drive with peace of mind even in bad weather. Furthermore, the calculation unit considers the driver's profile information and the customizations generated by the generation unit to suggest a route that suits the driver's preferences. For example, if the driver prefers natural scenery, the calculation unit can suggest a scenic route while considering traffic conditions and weather. In this way, the calculation unit can provide the optimal route for the driver and improve the quality of their trip. Furthermore, the calculation unit can recalculate the route based on data updated in real time, always providing the optimal route based on the latest information.

[0064] The AI ​​department utilizes LLM and multimodal AI. LLM is a large-scale language model that can analyze text data and perform natural language processing. For example, LLM can analyze a driver's profile information and generate customized content based on their hobbies and preferences. Multimodal AI is an AI that integrates and analyzes multiple modals (e.g., text, images, audio). For example, multimodal AI can analyze image and audio data based on a driver's profile information and generate customized content. As a result, the AI ​​department can provide personalized recommendations based on the driver's profile by utilizing LLM and multimodal AI. For example, if a driver is interested in historical tourist spots, the AI ​​department will prioritize recommending such spots. The AI ​​department can also recommend appropriate music based on the driver's musical preferences. For example, the AI ​​department can analyze the driver's favorite music genres and recommend music related to those genres. This allows the AI ​​department to provide more appropriate customized content based on the driver's profile information.

[0065] The Algorithm Department develops dynamic routing algorithms. Dynamic routing algorithms calculate the optimal route by considering real-time traffic information and weather data. For example, the Algorithm Department acquires real-time traffic information and calculates the optimal route by considering traffic congestion and accident information. The Algorithm Department can also acquire real-time weather data and calculate routes according to the weather. For example, the Algorithm Department prioritizes calculating safe routes in rainy weather. By developing dynamic routing algorithms, the Algorithm Department aims to improve the efficiency of travel planning and the quality of travel. For example, the Algorithm Department can reduce the time spent on travel planning and solve the problem of being unable to make optimal choices due to insufficient information. As a result, the Algorithm Department can provide more appropriate routes based on driver profile information.

[0066] The data collection unit can estimate the driver's emotions and adjust the timing of profile information collection based on the estimated emotions. For example, the data collection unit starts collecting profile information when the driver is relaxed. For example, the data collection unit can delay the collection timing when the driver is stressed. For example, the data collection unit can adjust the collection timing to ensure the accuracy of the information when the driver is excited. In this way, the data collection unit can ensure the accuracy of the information by adjusting the timing of profile information collection according to the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input the driver's facial expression data into a generative AI and have the generative AI perform the estimation of the driver's emotions.

[0067] The data collection unit can analyze the driver's past travel history and select the optimal data collection method. For example, the data collection unit can prioritize collecting relevant information based on places the driver has visited in the past. The data collection unit can also identify categories of interest from the driver's past travel history and collect information related to those categories. For example, the data collection unit can analyze the driver's past travel history and determine the optimal timing for data collection. This allows the data collection unit to prioritize collecting relevant information by analyzing the driver's past travel history. Past travel history includes, but is not limited to, places visited and frequency of travel. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the driver's past travel history data into a generating AI and have the generating AI select the optimal data collection method.

[0068] The data collection unit can filter profile information based on the driver's current living situation and areas of interest. For example, the data collection unit can prioritize collecting relevant information based on the driver's current occupation and hobbies. The data collection unit can also filter appropriate information based on the driver's current living situation (e.g., family structure, presence of pets). The data collection unit can also collect relevant information based on the driver's areas of interest (e.g., sports, music). This allows the data collection unit to collect appropriate information by filtering information based on the driver's current living situation and areas of interest. Living situation includes, but is not limited to, occupation and family environment. Areas of interest include, but is not limited to, hobbies and topics of interest. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the driver's current living situation data into a generating AI and have the generating AI perform the information filtering.

[0069] The data collection unit can estimate the driver's emotions and determine the priority of profile information to collect based on the estimated emotions. For example, if the driver is relaxed, the data collection unit may prioritize collecting detailed profile information. If the driver is stressed, the data collection unit may also prioritize collecting only basic profile information. If the driver is excited, the data collection unit may also prioritize collecting important profile information. This allows the data collection unit to prioritize the collection of important information by prioritizing profile information according to the driver's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input the driver's facial expression data into a generative AI and have the generative AI perform the estimation of the driver's emotions.

[0070] The data collection unit can prioritize the collection of highly relevant information by considering the driver's geographical location when collecting profile information. For example, the data collection unit can prioritize the collection of information on tourist attractions and restaurants related to the area where the driver is currently located. For example, the data collection unit can also collect information on nearby events based on the driver's geographical location. For example, the data collection unit can also collect information related to the optimal route by considering the driver's geographical location. In this way, the data collection unit can prioritize the collection of highly relevant information by considering the driver's geographical location. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the driver's geographical location data into a generating AI and have the generating AI perform the collection of highly relevant information.

[0071] The collection unit can analyze the driver's social media activity and collect relevant information when collecting profile information. For example, the collection unit can analyze the driver's social media posts and collect information related to categories of interest. The collection unit can also collect relevant information based on the driver's social media following list. For example, the collection unit can analyze the driver's social media activity and collect information related to their current areas of interest. Thus, by analyzing the driver's social media activity, the collection unit can collect information related to their current areas of interest. Social media activity includes, but is not limited to, posts and the number of likes. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the driver's social media data into a generating AI and have the generating AI collect relevant information.

[0072] The generation unit can estimate the driver's emotions and adjust the way the customized content is presented based on the estimated emotions. For example, if the driver is relaxed, the generation unit can generate customized content that includes detailed explanations. If the driver is in a hurry, for example, the generation unit can also generate concise and to-the-point customized content. If the driver is excited, for example, the generation unit can also generate visually appealing customized content. In this way, the generation unit can provide more appropriate content by adjusting the way the customized content is presented according to the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input the driver's facial expression data into the generation AI and have the generation AI perform the estimation of the driver's emotions.

[0073] The generation unit can adjust the level of detail generated based on the importance of the driver's hobbies and preferences when generating customized content. For example, if the driver has a strong interest in a particular hobby, the generation unit will generate detailed information related to that hobby. The generation unit can also adjust the level of detail of the customized content according to the importance of the driver's preferences. The generation unit can also prioritize the generation of relevant information based on the driver's hobbies and preferences. This allows the generation unit to provide more appropriate customized content by adjusting the level of detail based on the importance of the driver's hobbies and preferences. The importance of hobbies and preferences includes, but is not limited to, survey results and behavioral history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on the driver's hobbies and preferences into a generation AI and have the generation AI adjust the level of detail of the generation.

[0074] The generation unit can apply different generation algorithms depending on the driver's category when generating customized content. For example, if the driver is interested in historical tourist spots, the generation unit can apply a generation algorithm that emphasizes historical information. For example, if the driver is interested in gourmet food, the generation unit can apply a generation algorithm that emphasizes restaurant information. For example, if the driver is interested in nature tourism, the generation unit can apply a generation algorithm that emphasizes natural scenery. In this way, the generation unit can provide more appropriate customized content by applying different generation algorithms depending on the driver's category. Driver categories include, but are not limited to, age group and driving style. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input driver category data into a generation AI and have the generation AI execute the application of different generation algorithms.

[0075] The generation unit can estimate the driver's emotions and adjust the length of the customized content based on the estimated emotions. For example, if the driver is relaxed, the generation unit can generate detailed customized content. If the driver is in a hurry, the generation unit can also generate short, concise customized content. If the driver is excited, the generation unit can also generate visually appealing customized content. This allows the generation unit to provide more appropriate content by adjusting the length of the customized content according to the driver's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input the driver's facial expression data into the generation AI and have the generation AI perform the driver's emotion estimation.

[0076] The generation unit can determine the generation priority based on the driver's past travel history when generating customized content. For example, the generation unit can prioritize generating relevant information based on places the driver has visited in the past. The generation unit can also, for example, identify categories of interest from the driver's past travel history and prioritize generating information related to those categories. The generation unit can also, for example, analyze the driver's past travel history to determine the optimal generation timing. This allows the generation unit to prioritize providing relevant information by determining the generation priority based on the driver's past travel history. Past travel history includes, but is not limited to, places visited and travel frequency. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the driver's past travel history data into a generation AI and have the generation AI perform the determination of generation priorities.

[0077] The generation unit can adjust the generation order based on the driver's relevance when generating customized content. For example, the generation unit can prioritize generating relevant information based on the driver's current areas of interest. The generation unit can also prioritize generating highly relevant information based on the driver's past travel history. The generation unit can also prioritize generating highly relevant information by analyzing the driver's profile information. This allows the generation unit to provide more appropriate information by adjusting the generation order based on the driver's relevance. Relevance includes, but is not limited to, past behavioral history and topics of interest. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input driver relevance data into a generation AI and have the generation AI adjust the generation order.

[0078] The calculation unit can estimate the driver's emotions and adjust the calculation criteria for the optimal route based on the estimated emotions. For example, if the driver is relaxed, the calculation unit may prioritize a scenic route. If the driver is in a hurry, the calculation unit may also prioritize the shortest route. If the driver is excited, the calculation unit may also prioritize a visually appealing route. In this way, the calculation unit can provide a more appropriate route by adjusting the calculation criteria for the optimal route according to the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the calculation unit may be performed using AI or not using AI. For example, the calculation unit can input the driver's facial expression data into the generative AI and have the generative AI perform the estimation of the driver's emotions.

[0079] The calculation unit can improve the accuracy of its calculations by considering the driver's past travel history when calculating the optimal route. For example, the calculation unit calculates the optimal route based on routes the driver has used in the past. The calculation unit can also calculate routes that avoid congestion from the driver's past travel history. For example, the calculation unit can analyze the driver's past travel history and calculate the most efficient route. In this way, the calculation unit can improve the accuracy of its calculations by considering the driver's past travel history. Past travel history includes, but is not limited to, places visited and frequency of travel. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input the driver's past travel history data into a generating AI and have the generating AI perform the calculation accuracy improvement.

[0080] The calculation unit can perform calculations considering the driver's attribute information when calculating the optimal route. For example, the calculation unit can calculate the optimal route based on the driver's age and gender. The calculation unit can also calculate the optimal route based on the driver's driving experience. The calculation unit can also calculate the optimal route based on the driver's health condition. In this way, the calculation unit can provide a more appropriate route by considering the driver's attribute information. Attribute information includes, but is not limited to, age, gender, and occupation. Some or all of the above processing in the calculation unit may be performed using, for example, AI, or not using AI. For example, the calculation unit can input driver attribute information data into a generating AI and have the generating AI perform the calculations.

[0081] The calculation unit can estimate the driver's emotions and adjust the display order of the calculation results based on the estimated emotions. For example, if the driver is relaxed, the calculation unit may prioritize displaying detailed calculation results. For example, if the driver is in a hurry, the calculation unit may prioritize displaying concise calculation results. For example, if the driver is excited, the calculation unit may prioritize displaying visually appealing calculation results. In this way, the calculation unit can provide more appropriate information by adjusting the display order of calculation results according to the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input the driver's facial expression data into the generative AI and have the generative AI perform the estimation of the driver's emotions.

[0082] The calculation unit can perform calculations considering the geographical distribution of drivers when calculating the optimal route. For example, the calculation unit calculates the optimal route based on the area where the driver is currently located. The calculation unit can also prioritize the calculation of relevant information based on the geographical distribution of drivers. The calculation unit can also calculate the optimal route considering the geographical distribution of drivers. This allows the calculation unit to provide a more appropriate route by considering the geographical distribution of drivers. Geographical distribution includes, but is not limited to, place of residence and frequency of visits. Some or all of the above processing in the calculation unit may be performed using, for example, AI, or not using AI. For example, the calculation unit can input the geographical distribution data of drivers into a generating AI and have the generating AI perform the calculations.

[0083] The calculation unit can improve the accuracy of its calculations by referring to relevant literature for the driver when calculating the optimal route. For example, the calculation unit can refer to relevant literature and calculate the optimal route based on the driver's past travel history. The calculation unit can also refer to relevant literature and calculate the optimal route based on the driver's attribute information. The calculation unit can also refer to relevant literature and calculate the optimal route based on the driver's current situation. In this way, the calculation unit can improve the accuracy of its calculations by referring to relevant literature for the driver. Relevant literature includes, but is not limited to, academic papers and technical reports. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input the driver's relevant literature data into a generating AI and have the generating AI perform the calculation accuracy improvement.

[0084] The AI ​​unit can estimate the driver's emotions and select AI training data based on the estimated emotions. For example, if the driver is relaxed, the AI ​​unit will prioritize selecting data from past relaxed states as training data. For example, if the driver is stressed, the AI ​​unit can also prioritize selecting data from past stressed states as training data. For example, if the driver is excited, the AI ​​unit can also prioritize selecting data from past excited states as training data. This allows the AI ​​unit to perform more appropriate training by selecting training data based on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the AI ​​unit may be performed using AI, or not using AI. For example, the AI ​​unit can input the driver's facial expression data into a generative AI and have the generative AI perform the estimation of the driver's emotions.

[0085] The AI ​​unit can optimize the learning algorithm by referring to past learning data during AI training. For example, the AI ​​unit can analyze past learning data and select the optimal learning algorithm. The AI ​​unit can also adjust the parameters of the learning algorithm based on past learning data. The AI ​​unit can also improve the accuracy of the learning algorithm by referring to past learning data. Past learning data includes, but is not limited to, training datasets and evaluation data. Some or all of the above processing in the AI ​​unit may be performed using AI, for example, or without AI. For example, the AI ​​unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0086] The AI ​​unit can estimate the driver's emotions and adjust the frequency of AI learning based on the estimated emotions. For example, if the driver is relaxed, the AI ​​unit can set a lower learning frequency. For example, if the driver is stressed, the AI ​​unit can set a higher learning frequency. For example, if the driver is excited, the AI ​​unit can adjust the learning frequency to perform optimal learning. This allows the AI ​​unit to perform more appropriate learning by adjusting the frequency of AI learning based on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the AI ​​unit may be performed using AI or not using AI. For example, the AI ​​unit can input the driver's facial expression data into the generative AI and have the generative AI perform the estimation of the driver's emotions.

[0087] The AI ​​unit can weight training data based on the timing of driver profile information submissions during AI training. For example, the AI ​​unit can prioritize weighting of recently submitted driver profile information as training data. The AI ​​unit can also adjust the weighting of training data based on the timing of driver profile information submissions. For example, the AI ​​unit can weight training data considering the timing of driver profile information submissions. This allows the AI ​​unit to perform more appropriate training by weighting training data based on the timing of driver profile information submissions. Submission timing includes, but is not limited to, submission date and submission frequency. Some or all of the above processing in the AI ​​unit may be performed using AI or not using AI. For example, the AI ​​unit can input driver profile information submission timing data into a generating AI and have the generating AI perform the training data weighting.

[0088] The algorithm unit can estimate the driver's emotions and adjust the routing algorithm parameters based on the estimated emotions. For example, if the driver is relaxed, the algorithm unit may set parameters to prioritize scenic routes. If the driver is in a hurry, the algorithm unit may also set parameters to prioritize the shortest route. If the driver is excited, the algorithm unit may also set parameters to prioritize visually appealing routes. This allows the algorithm unit to provide a more appropriate route by adjusting the routing algorithm parameters based on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the algorithm unit may be performed using AI or not. For example, the algorithm unit can input driver facial expression data into a generative AI and have the generative AI perform the driver's emotion estimation.

[0089] The algorithm unit can optimize routing algorithms by referring to past route data during algorithm development. For example, the algorithm unit can analyze past route data and select the optimal routing algorithm. The algorithm unit can also adjust the parameters of the routing algorithm based on past route data. The algorithm unit can also improve the accuracy of the routing algorithm by referring to past route data. Thus, the algorithm unit can improve the accuracy of the routing algorithm by referring to past route data. Past route data includes, but is not limited to, travel history and reasons for route selection. Some or all of the above processing in the algorithm unit may be performed using AI, for example, or without AI. For example, the algorithm unit can input past route data into a generating AI and have the generating AI perform algorithm optimization.

[0090] The algorithm unit can estimate the driver's emotions and adjust the scope of the routing algorithm based on the estimated emotions. For example, if the driver is relaxed, the algorithm unit may apply a wide range of routes. If the driver is in a hurry, the algorithm unit may apply a narrower range of routes. If the driver is excited, the algorithm unit may apply a visually appealing route. In this way, the algorithm unit can provide a more appropriate route by adjusting the scope of the routing algorithm based on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the algorithm unit may be performed using AI or not using AI. For example, the algorithm unit can input the driver's facial expression data into the generative AI and have the generative AI perform the estimation of the driver's emotions.

[0091] The algorithm unit can optimize the routing algorithm by considering the geographical distribution of drivers during its development. For example, the algorithm unit develops an optimal routing algorithm based on the area where the driver is currently located. The algorithm unit can also prioritize the incorporation of relevant information into the algorithm based on the geographical distribution of drivers. For example, the algorithm unit can develop an optimal routing algorithm by considering the geographical distribution of drivers. This allows the algorithm unit to provide more appropriate routes by considering the geographical distribution of drivers. Geographical distribution includes, but is not limited to, place of residence and frequency of visits. Some or all of the above processing in the algorithm unit may be performed using AI, for example, or without AI. For example, the algorithm unit can input driver geographical distribution data into a generating AI and have the generating AI perform algorithm optimization.

[0092] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0093] The data collection unit can monitor the driver's health status and adjust the method of collecting profile information based on that status. For example, the data collection unit can monitor the driver's heart rate and blood pressure and collect detailed profile information when the driver is in good health. The data collection unit can also simplify the collection method and collect only the minimum necessary information if the driver is fatigued, for example. The data collection unit can also adjust the timing of data collection to ensure the accuracy of the information if the driver is stressed, for example. In this way, the data collection unit can improve the accuracy and efficiency of the information by adjusting the method of collecting profile information according to the driver's health status.

[0094] The AI ​​unit can estimate the driver's emotions and select training data for the AI ​​based on the estimated emotions. For example, if the driver is relaxed, the AI ​​unit will prioritize selecting data from past relaxed states as training data. If the driver is stressed, the AI ​​unit can also prioritize selecting data from past stressed states as training data. If the driver is excited, the AI ​​unit can also prioritize selecting data from past excited states as training data. This allows the AI ​​unit to perform more appropriate learning by selecting training data based on the driver's emotions.

[0095] The algorithm unit can estimate the driver's emotions and adjust the routing algorithm parameters based on the estimated emotions. For example, if the driver is relaxed, the algorithm unit can set parameters to prioritize scenic routes. If the driver is in a hurry, for example, the algorithm unit can set parameters to prioritize the shortest route. If the driver is excited, for example, the algorithm unit can set parameters to prioritize visually appealing routes. In this way, the algorithm unit can provide a more appropriate route by adjusting the routing algorithm parameters based on the driver's emotions.

[0096] The data collection unit can analyze drivers' social media activity and collect relevant information. For example, the data collection unit can analyze the content of drivers' social media posts and collect information related to categories of interest. The data collection unit can also collect relevant information based on drivers' social media following lists, for example. The data collection unit can also analyze drivers' social media activity and collect information related to their current areas of interest. In this way, the data collection unit can collect information related to drivers' current areas of interest by analyzing their social media activity.

[0097] The generation unit can estimate the driver's emotions and adjust how the customized content is presented based on those emotions. For example, if the driver is relaxed, the generation unit will generate customized content that includes detailed explanations. If the driver is in a hurry, for example, the generation unit can generate concise and to-the-point customized content. If the driver is excited, for example, the generation unit can generate visually appealing customized content. In this way, the generation unit can provide more appropriate content by adjusting how the customized content is presented according to the driver's emotions.

[0098] The calculation unit can calculate the optimal route by considering the driver's past travel history. For example, the calculation unit calculates the optimal route based on routes the driver has used in the past. The calculation unit can also calculate routes that avoid congestion from the driver's past travel history. The calculation unit can also analyze the driver's past travel history and calculate the most efficient route. In this way, the calculation unit can improve the accuracy of its calculations by considering the driver's past travel history.

[0099] The data collection unit can estimate the driver's emotions and determine the priority of profile information to collect based on the estimated emotions. For example, if the driver is relaxed, the data collection unit will prioritize collecting detailed profile information. If the driver is stressed, for example, the data collection unit may collect only basic profile information. If the driver is excited, for example, the data collection unit may prioritize collecting important profile information. In this way, the data collection unit can prioritize the collection of important information by determining the priority of profile information according to the driver's emotions.

[0100] The generation unit can generate customized content based on the driver's past travel history. For example, the generation unit can prioritize generating relevant information based on places the driver has visited in the past. The generation unit can also identify categories of interest from the driver's past travel history and generate information related to those categories. The generation unit can also analyze the driver's past travel history to determine the optimal generation timing. This allows the generation unit to prioritize the provision of relevant information by determining generation priorities based on the driver's past travel history.

[0101] The calculation unit can estimate the driver's emotions and adjust the optimal route calculation criteria based on the estimated emotions. For example, if the driver is relaxed, the calculation unit will prioritize a scenic route. If the driver is in a hurry, for example, the calculation unit may prioritize the shortest route. If the driver is excited, for example, the calculation unit may prioritize a visually appealing route. In this way, the calculation unit can provide a more appropriate route by adjusting the optimal route calculation criteria according to the driver's emotions.

[0102] The data collection unit can prioritize collecting highly relevant information by considering the driver's geographical location. For example, the unit can prioritize collecting information on tourist attractions and restaurants related to the area where the driver is currently located. The unit can also collect information on nearby events based on the driver's geographical location. The unit can also collect information related to the optimal route by considering the driver's geographical location. In this way, the data collection unit can prioritize collecting highly relevant information by considering the driver's geographical location.

[0103] The following briefly describes the processing flow for example form 2.

[0104] Step 1: The collection unit collects driver profile information. Driver profile information includes, for example, age, gender, and driving history. The collection unit provides a form for drivers to input their age and gender, and collects past driving data to understand their driving style and frequency. Step 2: The generation unit generates customized content based on the driver's hobbies and preferences, using the information collected by the collection unit. The generation unit generates customized routes and sightseeing spots based on the driver's music preferences and travel preferences. For example, it provides a form for the driver to input their favorite music genres and recommends sightseeing spots and restaurants based on their travel preferences. Step 3: The calculation unit integrates real-time traffic information and weather data based on the customizations generated by the generation unit to calculate the optimal route. The calculation unit acquires real-time traffic information and weather data, and proposes the optimal route considering traffic congestion, accident information, and weather conditions. For example, in rainy weather, it prioritizes proposing a safe route.

[0105] 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.

[0106] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0107] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] Each of the multiple elements described above, including the collection unit, generation unit, calculation unit, AI unit, and algorithm unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects driver profile information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates customized content based on the collected information. The calculation unit is implemented by the specific processing unit 290 of the data processing unit 12 and calculates the optimal route by integrating real-time traffic information and weather data. The AI ​​unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs personalized recommendations using LLM and multimodal AI. The algorithm unit is implemented by the specific processing unit 290 of the data processing unit 12 and develops a dynamic routing algorithm. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0109] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0110] 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.

[0111] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0112] 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.

[0113] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0114] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0115] 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.

[0116] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0117] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0118] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0119] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0120] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0121] 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.

[0122] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0123] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] Each of the multiple elements described above, including the collection unit, generation unit, calculation unit, AI unit, and algorithm unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects driver profile information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates customized content based on the collected information. The calculation unit is implemented by the specific processing unit 290 of the data processing unit 12 and calculates the optimal route by integrating real-time traffic information and weather data. The AI ​​unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs personalized recommendations using LLM and multimodal AI. The algorithm unit is implemented by the specific processing unit 290 of the data processing unit 12 and develops a dynamic routing algorithm. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0125] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0126] 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.

[0127] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0128] 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.

[0129] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0130] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0131] 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.

[0132] 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.

[0133] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0134] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0135] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0136] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0137] 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.

[0138] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0139] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the collection unit, generation unit, calculation unit, AI unit, and algorithm unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects driver profile information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates customized content based on the collected information. The calculation unit is implemented by the specific processing unit 290 of the data processing unit 12 and calculates the optimal route by integrating real-time traffic information and weather data. The AI ​​unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs personalized recommendations using LLM and multimodal AI. The algorithm unit is implemented by the specific processing unit 290 of the data processing unit 12 and develops a dynamic routing algorithm. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0141] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0144] 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.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0146] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] 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.

[0148] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0149] 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.

[0150] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0151] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0152] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0154] 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.

[0155] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0156] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements described above, including the collection unit, generation unit, calculation unit, AI unit, and algorithm unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects driver profile information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates customized content based on the collected information. The calculation unit is implemented by the specific processing unit 290 of the data processing unit 12 and calculates the optimal route by integrating real-time traffic information and weather data. The AI ​​unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs personalized recommendations using LLM and multimodal AI. The algorithm unit is implemented by the specific processing unit 290 of the data processing unit 12 and develops a dynamic routing algorithm. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0158] 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.

[0159] Figure 9 shows the 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.

[0160] 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.

[0161] 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.

[0162] 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, and motorcycles, 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 based, for example, 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.

[0163] 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."

[0164] 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.

[0165] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0174] 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 other things 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.

[0175] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0176] (Note 1) A collection unit that collects driver profile information, A generation unit generates customized content based on hobbies and preferences based on the information collected by the collection unit, A calculation unit that integrates real-time traffic information and weather data based on the customized content generated by the generation unit to calculate the optimal route, Equipped with A system characterized by the following features. (Note 2) It has an AI department that utilizes LLM and multimodal AI. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an algorithms unit for developing dynamic routing algorithms. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is The system estimates the driver's emotions and adjusts the timing of profile information collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is Analyze the driver's past travel history to select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting profile information, filtering is performed based on the driver's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates the driver's emotions and prioritizes the profile information to collect based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is When collecting profile information, the system prioritizes collecting highly relevant information by considering the driver's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting profile information, we analyze the driver's social media activity and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 10) The generating unit is It estimates the driver's emotions and adjusts how the customization is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The generating unit is When generating customization details, the level of detail is adjusted based on the importance of the driver's preferences and tastes. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is When generating customizations, different generation algorithms are applied depending on the driver category. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is It estimates the driver's emotions and adjusts the length of the customization based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating customization options, the priority of the generation process is determined based on the driver's past travel history. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating customizations, the generation order is adjusted based on the relevance of the drivers. The system described in Appendix 1, characterized by the features described herein. (Note 16) The calculation unit, It estimates the driver's emotions and adjusts the calculation criteria for the optimal route based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The calculation unit, When calculating the optimal route, the driver's past travel history is taken into account to improve the accuracy of the calculation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The calculation unit, When calculating the optimal route, the driver's attribute information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 19) The calculation unit, It estimates the driver's emotions and adjusts the display order of the calculation results based on the estimated driver's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The calculation unit, When calculating the optimal route, the calculation takes into account the geographical distribution of drivers. The system described in Appendix 1, characterized by the features described herein. (Note 21) The calculation unit, When calculating the optimal route, refer to relevant documentation for the driver to improve calculation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned AI unit, The system estimates the driver's emotions and selects AI training data based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 23) The aforementioned AI unit, During AI training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 24) The aforementioned AI unit, The system estimates the driver's emotions and adjusts the frequency of AI learning based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 25) The aforementioned AI unit, During AI training, the training data is weighted based on when the driver's profile information was submitted. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned algorithm unit is It estimates the driver's emotions and adjusts the routing algorithm parameters based on the estimated driver emotions. The system described in Appendix 3, characterized by the features described herein. (Note 27) The aforementioned algorithm unit is When developing routing algorithms, we optimize the algorithms by referring to past route data. The system described in Appendix 3, characterized by the features described herein. (Note 28) The aforementioned algorithm unit is The system estimates the driver's emotions and adjusts the scope of the routing algorithm based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 29) The aforementioned algorithm unit is When developing routing algorithms, optimize the algorithms by considering the geographical distribution of drivers. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection unit that collects driver profile information, A generation unit generates customized content based on hobbies and preferences based on the information collected by the collection unit, A calculation unit that integrates real-time traffic information and weather data based on the customized content generated by the generation unit to calculate the optimal route, Equipped with A system characterized by the following features.

2. It features an AI unit that utilizes LLM and multimodal AI. The system according to feature 1.

3. It includes an algorithms unit for developing dynamic routing algorithms. The system according to feature 1.

4. The aforementioned collection unit is The system estimates the driver's emotions and adjusts the timing of profile information collection based on the estimated emotions. The system according to feature 1.

5. The aforementioned collection unit is Analyze the driver's past travel history to select the optimal data collection method. The system according to feature 1.

6. The aforementioned collection unit is When collecting profile information, filtering is performed based on the driver's current lifestyle and areas of interest. The system according to feature 1.

7. The aforementioned collection unit is The system estimates the driver's emotions and prioritizes the profile information to collect based on the estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is When collecting profile information, the system prioritizes collecting highly relevant information by considering the driver's geographical location. The system according to feature 1.

9. The aforementioned collection unit is When collecting profile information, we analyze the driver's social media activity and collect relevant information. The system according to feature 1.

Images