system

Abstract

Provide a system. A means for a user to input a departure point, a destination, and a desired departure time; means for transmitting the input information to a server; means for analyzing the received information by the server; A means for connecting to a real-time database of a transportation agency to obtain current congestion status, delay information, and availability information; A means of utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; and A means of suggesting the best departure time and vehicle; means for transmitting the proposal results to a user terminal; means for displaying the recommendation results to the user; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional transportation search systems primarily display transportation options available to users during a specified time period, making it difficult for them to avoid crowded trains and traffic jams. This causes excessive stress for users and makes it difficult for service providers to use their resources efficiently. Furthermore, since congestion conditions cannot be reflected in real time, it is difficult to provide a service that satisfies users. The present invention solves these problems. [Means for solving the problem]

[0005] This invention provides a system in which users input their departure point, destination, and desired departure time and send this information to a server, which then connects to a real-time database of transportation services to obtain congestion status, delay information, and availability information, and then uses generative AI to predict congestion for multiple time periods.The server then proposes the optimal departure time and vehicle based on the prediction results, and sends the proposal to the user's terminal and displays it to the user.In this way, users can select a more comfortable means of transportation, and service providers can use their resources more efficiently.

[0006] A "user" is an individual or group that uses the system to search for transportation options and act on the information suggested.

[0007] "Start point" refers to the point where the user starts their journey.

[0008] "Destination" refers to the point where the user completes their journey.

[0009] "Desired departure time" refers to the time at which the user desires to start traveling from the departure point.

[0010] "User terminal" refers to a device (e.g., a smartphone or PC) used by a user to input and receive information.

[0011] "Server" refers to a computer system that receives requests from users, acquires real-time data, makes predictions using generative AI, and generates and transmits optimal proposals.

[0012] "Real-time database" refers to a database that provides real-time information about current transportation conditions.

[0013] "Generative AI" refers to artificial intelligence technology used to predict things like public transport congestion.

[0014] "Crowding forecast" refers to the analysis results that predict the degree of passenger congestion on transportation routes at each time slot.

[0015] "Suggestion" refers to the optimal departure time and vehicle selection results generated by the server to enable the user to travel comfortably.

[0016] "Transportation" refers to public transportation such as trains and buses and services related to their operation status.

[0017] "Delay information" refers to information about delays in transportation operations.

[0018] "Vacancy information" refers to information regarding the availability of seats and spaces in each vehicle of a transportation facility. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, the server connects to a real-time database of transportation companies based on that data, uses generative AI to predict congestion, and suggests the optimal departure time and vehicle.

[0041] The user submits a request

[0042] A user uses a transportation search app to input their departure point, destination, and desired departure time. For example, the user inputs "Tokyo Station" as the departure point, "Shinjuku Station" as the destination, and "6:00 PM" as the desired departure time. This information is sent from the user's device to the server.

[0043] The server receives and processes the request

[0044] The server receives the request sent by the user, analyzes the received information, and accesses the transportation company's real-time database to obtain current congestion status, delay information, and availability information.

[0045] Congestion prediction and optimal proposal generation

[0046] The server uses generative AI to predict congestion for multiple time periods, including the desired departure time specified by the user. The generative AI uses past and real-time data to predict the level of congestion, the possibility of delays, and availability for each time period. Based on these predictions, the server proposes the optimal departure time and vehicle to the user. For example, if the user's desired time of 18:00 is very crowded, the server generates a proposal to change the departure time to 18:30 and use an available car on the Chuo Line Rapid (e.g., car 8).

[0047] Sending and displaying proposal results

[0048] The server sends the generated proposal results to the user's terminal. The user's terminal receives the proposal results and displays the optimal departure time and vehicle information for the user. For example, the user receives a proposal to "depart at 6:30 PM and use car 8 of the Chuo Line Rapid."

[0049] Implementation by concrete example

[0050] For example, consider a user traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00" (user device operation). This information is sent to the server. The server connects to a real-time database to obtain congestion information, delay information, and car availability for the Chuo Line Rapid (server operation). It then uses generative AI to predict the congestion level for each time period and suggests the optimal departure time and car (server operation). Finally, the server generates a suggestion to "depart at 18:30 and use car 8" and sends it to the user's device (server operation). The user's device displays this suggestion to the user, allowing them to travel in a way that avoids crowds.

[0051] This system is extremely useful, not only because it allows users to avoid crowded trains and traffic jams, but also because it allows service providers to manage their resources more efficiently.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), etc.

[0055] Step 2:

[0056] The user inputs the departure point, destination, and desired departure time, and clicks the search button. This input information is sent to the server by the user terminal.

[0057] Step 3:

[0058] The server analyzes the request data received from the user terminal, including the origin, destination, and desired departure time.

[0059] Step 4:

[0060] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[0061] Step 5:

[0062] The server inputs the acquired real-time data into a generative AI to predict congestion levels for the next few hours, including the desired departure time. The generative AI then predicts congestion levels, possible delays, and availability for each time period.

[0063] Step 6:

[0064] Based on the predictions made by the generative AI, the server generates data to suggest optimal departure times and train cars to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and use car 8 of the Chuo Line Rapid."

[0065] Step 7:

[0066] The server transmits the generated proposal data to the user terminal.

[0067] Step 8:

[0068] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0069] In this way, users can choose the most suitable means of transportation that avoids congestion.

[0070] Example 1

[0071] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0072] In modern transportation, congestion often makes it difficult for users to travel efficiently and comfortably. Congestion is particularly severe during certain times of the day, such as rush hour and tourist season, and users face overcrowded trains and road congestion. Such congestion can be stressful for users, causing travel delays and forcing them to change their plans. Furthermore, congestion poses challenges for transportation agencies and road operators, as it can lead to reduced service quality and make operation management more difficult. Therefore, there is a need for a system that can predict congestion in real time and suggest optimal travel methods and times for users.

[0073] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0074] In this invention, the server includes means for a user to input a departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities and obtaining current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative artificial intelligence, means for proposing optimal departure times and vehicles based on the prediction results, means for transmitting the proposal results to a user terminal, means for displaying the proposal results to the user, and means for using past data and real-time data to predict congestion levels for multiple time periods, thereby enabling a user to select the optimal transportation means and time to avoid congestion in real time.

[0075] "User" refers to an individual user who uses the system to search for transportation travel information and receive suggestions on the best travel method and time.

[0076] "Start point" refers to the location where the user begins their journey.

[0077] "Destination" refers to the location where the user completes their journey.

[0078] "Desired departure time" refers to the time at which the user wishes to begin their journey.

[0079] "Server" refers to the central computing system that analyzes information submitted by users, obtains real-time data, performs congestion predictions, and generates and transmits proposal results.

[0080] "User terminal" refers to the device that a user uses to operate a transportation search app, and is typically a mobile device such as a smartphone or tablet.

[0081] A "real-time transportation database" refers to a database that holds the latest information about transportation, such as current congestion status, delay information, and availability information.

[0082] "Generative AI" refers to an AI model that has the ability to predict future congestion situations using past and real-time data.

[0083] "Congestion prediction" refers to the process in which generative artificial intelligence analyzes past and real-time data to predict future congestion conditions on public transport at specific times of the day.

[0084] "Proposal Report" refers to a document of proposals including the optimal departure time and vehicle for the user, created by the server based on the results of congestion predictions made by the generative artificial intelligence.

[0085] "Multiple modes of transportation" refers to multiple different modes of public transportation, such as trains and buses, that a user may use for travel.

[0086] "Data integration" refers to the process of centrally managing and comprehensively analyzing information obtained from multiple data sources.

[0087] System Overview

[0088] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, a server connects to a real-time database of transportation services based on that data, uses generative artificial intelligence to predict congestion, and suggests the optimal departure time and vehicle. In the description of the embodiment of the invention, specific program processing, and the hardware and software used will be described.

[0089] User Operation

[0090] A user opens a transportation search application on a user device such as a smartphone or tablet and inputs the origin, destination, and desired departure time. For example, consider the following information:

[0091] Departure point: Tokyo Station

[0092] Destination: Shinjuku Station

[0093] Desired departure time: 6:00 PM

[0094] This information is sent to the server in JSON format when the user taps the "Search" button.

[0095] Server Processing

[0096] Receiving and parsing the request

[0097] The server receives the data sent by the user through an HTTP POST request. Then, the server parses the received JSON data and extracts the origin, destination, and desired departure time. This process is handled by the data analysis module in the server.

[0098] Real-time data acquisition

[0099] The server sends an API request to the transit agency's real-time database. In this particular operation, the server invokes an API endpoint such as:

[0100] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[0101] This API request allows the server to obtain real-time data including current congestion status, delay information, and availability information.

[0102] Implementing congestion predictions

[0103] Next, the server uses generative artificial intelligence (e.g., GPT-3 (registered trademark)).5) to predict congestion. The server provides the collected historical and real-time data as input to the AI ​​model, which predicts congestion over multiple time periods. The following is an example of a prompt for making a congestion prediction:

[0104] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[0105] The generative AI returns congestion prediction results based on this prompt, and the server analyzes these results. For example, it predicts the level of congestion for each time slot between 6:00 PM and 7:00 PM.

[0106] Generating optimal proposals

[0107] The server then proposes the optimal departure time and vehicle to the user based on the predictions made by the generative AI. This proposal is reported in the form of a report with information such as the following:

[0108] Recommended departure time: 6:30 PM

[0109] Route and vehicle: Chuo Line Rapid No. 8

[0110] Sending and displaying proposal results

[0111] The server sends the generated proposal report to the user's device. The secure protocol HTTPS is used for communication, and the data is encrypted before transmission. The user's device analyzes the proposal report received from the server and displays it to the user in an intuitive interface.

[0112] Specific examples

[0113] For example, if a user wants to travel from Tokyo Station to Shinjuku Station at 6:00 PM, they open the app on their device and enter the information above. The server receives this information, acquires real-time data, predicts congestion using generative artificial intelligence, and suggests the optimal means of transportation to the user. Finally, the server displays the suggestion to the user: "Depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0114] This system allows users to avoid crowds and provides an efficient and comfortable travel experience.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1:

[0117] The user inputs the starting point, destination, and desired departure time. Specifically, the user opens a transportation search app on a user device such as a smartphone or tablet. In the input form that appears, the user enters the following information:

[0118] Departure point: Tokyo Station

[0119] Destination: Shinjuku Station

[0120] Desired departure time: 6:00 PM

[0121] When the user taps the "Search" button, this information is sent to the server in JSON format (input).

[0122] Step 2:

[0123] The server receives the request sent by the user. The server receives the data via an HTTP POST request and parses the received JSON data. For example, the following data is extracted:

[0124] Departure point: Tokyo Station

[0125] Destination: Shinjuku Station

[0126] Desired departure time: 6:00 PM

[0127] Based on this information, the server proceeds to the next step in the process (output).

[0128] Step 3:

[0129] The server sends an API request to the transport agency's real-time database to get the current congestion, delay, and availability information. For example, it calls the following API endpoint:

[0130] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[0131] The server analyzes the information obtained from this API request and obtains the following data (input):

[0132] Current congestion: High

[0133] Delay Information: None

[0134] Vehicle availability: Limited

[0135] This information is used in the next step (output).

[0136] Step 4:

[0137] The server inputs the collected real-time and past data into a generative AI model to predict congestion. The prompt is constructed as follows:

[0138] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[0139] The congestion prediction results returned by the generative AI are in the following format (input):

[0140] 18:00: Very high

[0141] 18:15: High

[0142] 18:30: Medium

[0143] 18:45: Low

[0144] 19:00: Very low

[0145] Based on this prediction result, the optimal proposal is generated (output) in the next step.

[0146] Step 5:

[0147] The server generates optimal departure time and vehicle recommendations for the user based on the predictions of the generative AI. For example, the following recommendations are generated:

[0148] Recommended departure time: 6:30 PM

[0149] Route and vehicle: Chuo Line Rapid No. 8

[0150] This proposal report will be generated in JSON format and will look something like this (input):

[0151] json

[0152] {

[0153] "recommended_departure_time": "18:30",

[0154] "recommended_vehicle": "Chuo Line Rapid Car No. 8"

[0155] }

[0156] The generated report is sent to the user terminal (output).

[0157] Step 6:

[0158] The server sends the generated proposal report to the user terminal. The secure protocol HTTPS is used for communication, and encrypted data is sent. The user terminal receives the proposal report from the server (input).

[0159] Step 7:

[0160] The user device analyzes the received proposal report and displays it in an intuitive interface for the user. Specifically, the following information is displayed on the screen:

[0161] Recommended departure time: 6:30 PM

[0162] Route and vehicle: Chuo Line Rapid No. 8

[0163] This allows the user to select a means of transportation that avoids congestion (output).

[0164] (Application example 1)

[0165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0166] In recent years, congestion and traffic jams on public transport have become increasingly serious, causing significant stress for users during travel. As a result, users are seeking more efficient and comfortable means of transportation. However, current systems do not adequately provide real-time congestion predictions or avoidance strategies. Furthermore, with the increasing number of autonomous vehicles, dynamic operation according to traffic conditions is required. With current technology, even if users input their departure point, destination, and desired departure time, optimal suggestions are not provided that take into account real-time congestion and traffic conditions, resulting in reduced user convenience. This issue needs to be resolved.

[0167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0168] In this invention, the server includes: a means for a user to input their departure point, destination, and desired departure time; a means for transmitting the input information to the server; a means for analyzing the information received by the server; a means for connecting to a real-time database of transportation facilities and acquiring current congestion status, delay information, and availability information; a means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; a means for proposing an optimal departure time and vehicle; a means for transmitting the proposal results to a user terminal; a means for displaying the proposal results to the user; and a means for an autonomous vehicle to pick up the user based on the proposed optimal departure time and route. This allows users to avoid congestion and traffic jams and travel to their destination efficiently and comfortably. Furthermore, autonomous vehicles dynamically selecting optimal routes and efficiently picking up users improves traffic flow and convenience.

[0169] "Means for the user to input the departure point, destination, and desired departure time" refers to means for providing an interface for the user to input their current location, destination, and desired departure time.

[0170] The "means for transmitting input information to a server" refers to a communication means for transmitting data input by a user to a server via a network.

[0171] The "means for analyzing the information received by the server" refers to the means by which the server analyzes the information sent by the user and understands details such as the destination and departure time.

[0172] "Means for connecting to a real-time database of a transportation facility and obtaining current congestion status, delay information, and availability information" refers to a means for a server to connect to a transportation facility's database in real time and obtain the latest congestion status, delay information, and availability information.

[0173] "Means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period" refers to means for using generative AI to predict congestion conditions for multiple time periods, including the user's desired time period.

[0174] The "means of suggesting the optimal departure time and vehicle" is a means of suggesting the optimal departure time and vehicle to be used for the user based on the acquired data and the prediction results of the generative AI.

[0175] The "means for transmitting the proposal results to the user terminal" is a communication means for transmitting the proposal results generated by the server to the terminal used by the user.

[0176] The "means for displaying the proposal results to the user" refers to the means for displaying the received proposal results on the user's terminal so that the user can confirm and use the information.

[0177] "Means for an autonomous vehicle to pick you up based on the proposed optimal departure time and route" refers to means for an autonomous vehicle to pick you up at a specified location based on the optimal departure time and route predicted by the server.

[0178] This invention provides a system that allows users to travel to their destinations efficiently and comfortably by optimizing an autonomous vehicle. How this system is implemented will be described below in detail.

[0179] System Overview

[0180] The user inputs their departure point, destination, and desired departure time via a smartphone app or in-car display. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. The server then suggests the optimal departure time and route, and sends this information to the autonomous vehicle. The autonomous vehicle then picks up the user based on this suggestion. This entire process is achieved using high-precision data analysis and AI technology.

[0181] Hardware and software used

[0182] Smartphones and in-car displays: Interfaces for users to input information.

[0183] Server: A central system for receiving, analyzing, and generating AI-based predictions.

[0184] Real-time traffic database: A database that provides congestion, delay, and availability information.

[0185] Generative AI model: A custom AI model using PyTorch or TENSORFLOW (registered trademark).

[0186] Communication module: A network communication function for transmitting data between the user terminal and the server, and between the server and the autonomous vehicle.

[0187] Data processing flow

[0188] 1. User input: The user enters the departure point, destination, and desired departure time using a smartphone app or the in-car display.

[0189] 2. Data transmission: The data entered by the user is transmitted from the interface to the server.

[0190] 3. Obtaining real-time data: The server connects to the real-time traffic database and obtains current congestion, delay, and availability information.

[0191] 4. Generative AI prediction: The server uses generative AI models to predict congestion levels, potential delays, and availability across multiple time periods.

[0192] 5. Generating optimal proposals: Based on the prediction results, the server proposes the optimal departure time and vehicle route to be used.

[0193] 6. Notification of proposed results: The proposed departure time and route are sent to the user's terminal and displayed for the user to review.

[0194] 7. Dispatch of autonomous vehicles: Based on the proposed route, an autonomous vehicle is dynamically dispatched to pick up the user.

[0195] Specific examples

[0196] For example, if a user wants to travel from Station A to Station B around 6:00 PM, they would enter Station A, Station B, and the desired time of 6:00 PM into the smartphone app. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. As a result, it predicts that 6:15 PM is the best time to travel, and that car 8 of the Chuo Line Rapid train is available. The server then sends the proposal to the user's smartphone, where the user can review it. If they agree, an autonomous vehicle will come to pick them up based on the prediction.

[0197] Example prompt sentences to use

[0198] Prompt: "Predict the optimal departure time and route given the following conditions: departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data."

[0199] As described above, in order to put this invention into practice, it is necessary to build a series of systems that utilize advanced data analysis and AI technology to optimize user mobility.

[0200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0201] Step 1:

[0202] The user inputs the departure point, destination, and desired departure time on a smartphone app or on the in-car display. The information the user inputs is the departure point, destination, and desired departure time.

[0203] Step 2:

[0204] The device sends the entered information to the server. In this step, the data entered by the user is sent to the server via the internet via a smartphone app or in-car display. Here, the user's intention is conveyed to the server as input.

[0205] Step 3:

[0206] The server analyzes the received information. In this step, the server analyzes the information submitted by the user, such as origin, destination, and desired departure time. The analysis results in an output that allows the server to understand the user's travel requirements.

[0207] Step 4:

[0208] The server connects to the real-time database of the transport agency to get the current congestion status, delay information, and availability information. Here, the server uses the API of the real-time database to collect the latest data related to the transport agency. This data is sent as input to the server, and the latest traffic information is obtained as output.

[0209] Step 5:

[0210] The server uses a generative AI model to predict congestion levels for multiple time periods, including the user's desired time period. Specifically, it combines past data and real-time data to predict congestion levels, potential delays, and availability. In this process, the server uses AI frameworks such as PyTorch and TensorFlow to make predictions using prompt statements as input. An example prompt statement is, "Predict the optimal departure time and route under the following conditions: Conditions: Departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data." The predicted results are then output.

[0211] Step 6:

[0212] The server proposes the optimal departure time and vehicle. Based on the prediction results, the server calculates the optimal departure time and vehicle to use to avoid congestion and generates a proposal. This proposal is obtained as the output.

[0213] Step 7:

[0214] The server sends the proposal results to the user's terminal. The generated proposal results are then sent via the network to the user's smartphone or in-car display, where they are input into the user's terminal and displayed.

[0215] Step 8:

[0216] The user's device displays the proposed results. The optimal departure time and vehicle are displayed on the user's device, and the user can confirm and select the information.

[0217] Step 9:

[0218] The server sends instructions to the autonomous vehicle to pick up the user based on the optimal departure time and route. After the optimal route and time are determined, the autonomous vehicle receives instructions to dynamically pick up the user based on the optimal route and time. This initiates the operation of the autonomous vehicle to pick up the user.

[0219] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0220] This invention is a system in which a user inputs their departure point, destination, and desired departure time, and the server connects to a real-time database of transportation companies to obtain information based on this information, and then uses generative AI to predict congestion and suggest the optimal departure time and vehicle.Furthermore, by combining this system with an emotion engine, the system recognizes the user's emotions and makes optimal suggestions taking into account that emotional information.

[0221] The user submits a request

[0222] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine that acquires emotional information from the user's facial expressions and voice.

[0223] The server receives and processes the request

[0224] The server receives and analyzes the request data sent from the user terminal, which includes the departure point, destination, desired departure time, and emotion information.

[0225] Real-time data acquisition and congestion prediction

[0226] The server connects to the transportation company's real-time database to retrieve current congestion, delay, and availability information related to the specified departure and destination. Generative AI then predicts congestion within the next few hours, including the desired departure time. Based on past and real-time data, the generative AI predicts congestion levels, potential delays, and availability for each time period.

[0227] Generating suggestions based on user's emotional information

[0228] The server provides the generative AI with the user's emotional information obtained by the emotion engine. The generative AI then makes adjustments based on the emotional information and suggests the optimal departure time and vehicle that takes the user's emotions into consideration. For example, if the user is stressed, it will prioritize suggestions that further avoid congestion.

[0229] Sending and displaying proposal results

[0230] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal might be displayed that says, "Depart at 6:30 PM and use car 8 of the Chuo Line Rapid." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[0231] Implementation by concrete example

[0232] For example, consider a case where a user travels from Tokyo Station to Shinjuku Station. The user inputs "Tokyo Station" and "Shinjuku Station" into the app, as well as the desired departure time of "18:00." Furthermore, the emotion engine detects that the user is feeling stressed from their facial expression (operation of the user's device). This information is then sent to the server (operation of the user's device).

[0233] The server connects to a real-time database and obtains information on congestion and delays on Chuo Line rapid trains, as well as car availability (server operation). Furthermore, it uses generative AI to predict the level of congestion for each time period and makes optimal suggestions based on emotional information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8" (server operation).

[0234] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user (operation of the user terminal). The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[0235] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[0236] The processing flow will be explained below.

[0237] Step 1:

[0238] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), and the emotion engine begins to acquire emotion information from the user's facial expressions and voice.

[0239] Step 2:

[0240] The user inputs the departure point, destination, and desired departure time and clicks the search button. At this time, the emotion engine recognizes the user's emotion and acquires emotion information. This input information and emotion information are sent from the user terminal to the server.

[0241] Step 3:

[0242] The server analyzes the request data received from the user terminal, including the departure point, destination, desired departure time, and emotion information.

[0243] Step 4:

[0244] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[0245] Step 5:

[0246] The server inputs the acquired real-time data into a generative AI to predict congestion for the next few hours, including the desired departure time. The generative AI uses past and real-time data to predict the level of congestion, potential delays, and availability for each time period.

[0247] Step 6:

[0248] The server provides the emotion information obtained from the emotion engine to the generative AI, which then adjusts the optimal suggestions based on the user's emotions. For example, if the user is stressed, the generative AI will select a less stressful time slot to generate suggestions.

[0249] Step 7:

[0250] The server generates data based on generative AI and emotion information to suggest optimal departure times and vehicles to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and take car 8 of the Chuo Line Rapid."

[0251] Step 8:

[0252] The server transmits the generated proposal data to the user terminal.

[0253] Step 9:

[0254] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0255] In this way, users can choose more comfortable means of transportation that take emotional information into account.

[0256] Example 2

[0257] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0258] When using conventional public transport, it is difficult for users to know the congestion situation or delay information in advance, and as a result, they cannot avoid stressful situations such as crowded trains and traffic jams.In addition, personalized travel suggestions that take into account the user's emotional information are not provided, so solutions that fully consider the user's comfort have not been provided.

[0259] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for adjusting the optimal departure time and vehicle taking into account the user's emotional information, a means for connecting to a real-time database of transportation means and acquiring current congestion status, delay information, and availability information, and a means for predicting congestion for multiple time periods including the user's desired time period by utilizing generative artificial intelligence. This enables the user to receive suggestions for avoiding congestion and realizing a more comfortable and less stressful trip.

[0260] A "user" is an individual or group that uses the system to input a departure point, destination, and desired departure time and view transportation information.

[0261] The "starting point" is the point from which the user starts traveling.

[0262] A "destination" is a point where a user completes their journey.

[0263] The "desired departure time" is the specific time at which the user wishes to start traveling.

[0264] "User terminal" refers to an electronic device (e.g., smartphone, personal computer) used by a user to input data into the system and view results.

[0265] "Server" means a centralized computer system that receives and analyzes information sent by users and performs appropriate processing.

[0266] "Transportation" refers to public or private means of transportation such as trains, buses, and taxis.

[0267] A "real-time database" is a database that provides real-time information on current congestion, delays, and availability related to transportation means.

[0268] "Generative artificial intelligence" is a machine learning model that uses past and current data to make predictions and suggestions.

[0269] "Crowd prediction" refers to the process in which generative artificial intelligence predicts future congestion situations based on past and real-time data.

[0270] "Emotion information" is data indicating the emotional state of the user, such as stress or satisfaction, obtained from the user's facial expression, voice, etc.

[0271] "Proposal results" are information about optimal departure times and vehicles provided to users based on data analyzed and predicted by generative artificial intelligence.

[0272] "Crowding status" is information that indicates the current number of people using a means of transportation and how available it is.

[0273] "Delay information" is information that indicates the degree to which transportation means are not operating according to the scheduled time.

[0274] "Vacancy information" refers to information about the availability of each vehicle and seat of a means of transportation.

[0275] "Parsing" refers to the act of the server understanding the information sent by the user and converting it into the form required for the next processing step.

[0276] "Adjusting" refers to the act of the generative AI optimizing the suggestions based on the user's wishes and emotional state.

[0277] This system allows users to input their departure point, destination, and desired departure time, and then the server connects to a real-time database of transportation modes to obtain information based on this information, uses generative artificial intelligence to predict congestion, and suggests optimal departure times and vehicles. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and makes optimal suggestions based on that emotional information.

[0278] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine, which can obtain emotional information from the user's facial expressions and voice.

[0279] The server receives and analyzes the request data sent from the user device. The sent data includes the origin, destination, desired departure time, and emotion information. The server connects to a real-time database of transportation modes to obtain current congestion, delay information, and availability information related to the specified origin and destination. It then uses generative artificial intelligence (e.g., a general deep learning model) to predict congestion within the next few hours, including the desired departure time.

[0280] The generative AI predicts congestion levels, potential delays, and availability for each time period based on past and real-time data. Furthermore, the server provides the user's emotional information obtained by the emotion engine to the generative AI, which then makes adjustments based on the emotional information and suggests optimal departure times and vehicles that take the user's emotions into consideration. For example, if the user is stressed, the AI ​​will prioritize suggestions that further avoid congestion.

[0281] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal may be presented such as "Depart at 6:30 PM and take car 8 on the Chuo Line." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[0282] As a concrete example, consider the case where a user is traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00." The emotion engine then detects stress from the user's facial expression. This information is sent to the server. The server connects to a real-time database to obtain information on congestion and delays on the Chuo Line, as well as the availability of train cars. It then uses generative artificial intelligence to predict the level of congestion for each time period and makes optimal suggestions based on the emotion information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8."

[0283] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user. The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[0284] (Example prompt)

[0285] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[0286] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[0287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0288] Step 1: User submits request

[0289] The user opens a transportation search app on their device, such as a smartphone or PC. They enter their departure point (e.g., Tokyo Station), destination (e.g., Shinjuku Station), and desired departure time (e.g., 6:00 p.m.), and click the search button. The app, which is equipped with an emotion engine, analyzes the user's facial expressions and voice in real time through the device's camera and microphone to obtain emotional information.

[0290] Specific behavior:

[0291] 1. The user enters their departure point, destination, and desired departure time into the app's input fields.

[0292] 2. The emotion engine uses the device's camera and microphone to obtain the user's emotional information.

[0293] 3. The input information and emotional information are sent to the server.

[0294] Input: departure point, destination, desired departure time, emotional information

[0295] Output: Request data sent to the server

[0296] Step 2: The server receives and processes the request

[0297] The server receives a request sent from the user terminal. The received data includes the origin, destination, desired departure time, and emotion information. This information is analyzed and converted into the form required for the next processing step.

[0298] Specific behavior:

[0299] 1. The server receives and analyzes the request data.

[0300] 2. Store the parsed data in variables (origin, destination, desired departure time, emotion information).

[0301] Input: Request data (origin, destination, desired departure time, emotional information)

[0302] Output: Parsed data (stored in a variable)

[0303] Step 3: Acquire and analyze real-time data

[0304] The server connects to a real-time database of transportation modes, retrieving current congestion, delay, and availability information related to the specified origin and destination, and then analyzing and organizing the retrieved data.

[0305] Specific behavior:

[0306] 1. The server connects to the specified API endpoint.

[0307] 2. Obtain real-time data (crowding, delay information, availability information) for the specified departure and destination.

[0308] 3. Analyze the acquired data and extract and organize the necessary information.

[0309] Input: Departure point, Destination

[0310] Output: Real-time data (congestion status, delay information, availability information)

[0311] Step 4: Congestion prediction using generative AI

[0312] The server uses generative artificial intelligence to predict congestion within the next few hours, including the desired departure time, based on past and real-time data. It also predicts the level of congestion, potential delays, and availability for each time slot.

[0313] Specific behavior:

[0314] 1. The server inputs past data and acquired real-time data into the generative artificial intelligence.

[0315] 2. Generative AI analyzes the data and predicts congestion during a specific time period (for example, between 6:00 PM and 9:00 PM).

[0316] Input: Historical data, real-time data

[0317] Output: Congestion forecast data (congestion level for each time period, possibility of delay, availability)

[0318] Step 5: Generate suggestions taking into account user's emotional information

[0319] The server provides the user's emotional information obtained from the emotion engine to the generative artificial intelligence, which takes the emotional information into consideration and selects the optimal departure time and vehicle to reduce the user's stress.

[0320] Specific behavior:

[0321] 1. The server inputs the user's emotional information into the generative AI.

[0322] 2. Generative AI takes emotional information into account and generates optimal suggestions based on congestion prediction data.

[0323] Input: Emotional information, congestion prediction data

[0324] Output: Optimal departure time and vehicle suggestions

[0325] Step 6: Submit and view the proposal results

[0326] The server sends the generated proposal results to the user terminal, which analyzes the proposal results and displays the optimal departure time and vehicle information to the user.

[0327] Specific behavior:

[0328] 1. The server sends the proposal results in JSON format to the user device.

[0329] 2. The user device analyzes the suggestion results and displays on the screen, "Please use car 8 on the Chuo Line at 6:30 p.m."

[0330] Input: Proposal results (optimal departure time and vehicle)

[0331] Output: Suggestion results displayed on the user's device

[0332] Example prompt:

[0333] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[0334] This system suggests optimal transportation methods that avoid crowds to users, enabling them to travel more comfortably and with less stress.

[0335] (Application example 2)

[0336] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0337] In modern transportation, users often experience stress due to congestion and delays. Conventional navigation systems and transportation suggestion systems provide optimal suggestions based on real-time congestion and delay information, but do not take into account the user's emotional state. As a result, users may travel without feeling fully comfortable. Furthermore, it is difficult to integrate and analyze data from multiple transportation modes, making it difficult to propose efficient transportation options. Therefore, there is a need for a system that takes into account the user's emotional state and suggests more comfortable and efficient transportation options.

[0338] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities to obtain current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative AI, means for proposing optimal departure times and transportation modes, means for acquiring the user's emotional information using an emotion recognition engine, means for adjusting the proposal results based on the acquired emotional information, means for transmitting the adjusted proposal results to the user terminal, and means for displaying the proposal results to the user. This not only enables the user to avoid congestion and delays, but also enables the user to receive suggestions for comfortable transportation modes that take into account their current emotional state.

[0339] "User" refers to a person who uses the system to input a departure point, destination, and desired departure time.

[0340] "Start point" refers to the point where the user starts their journey.

[0341] "Destination" refers to the point where the user ends their journey.

[0342] "Desired departure time" refers to the time at which the user wishes to start traveling.

[0343] "Server" refers to a computer system that receives and analyzes information sent by users.

[0344] "Real-time transportation database" refers to a database that provides current congestion, delay, and availability information.

[0345] "Generative AI" refers to artificial intelligence that predicts congestion based on past and current data.

[0346] "Congestion prediction" refers to the prediction made by generative AI of the level of congestion, possibility of delays, and availability at each time slot.

[0347] The "optimal departure time" refers to the most suitable time for the user to start traveling, determined in consideration of congestion forecasts and the user's emotional information.

[0348] "Means of transportation" refers to the means of transportation used by the user, such as public transport or automobiles.

[0349] An "emotion recognition engine" refers to a system that acquires emotional information from a user's facial expressions and voice.

[0350] "Emotion information" refers to the user's emotional state (stress, relaxation, etc.) acquired by the emotion recognition engine.

[0351] "Proposal result" refers to information about the optimal departure time and transportation means provided to the user by the server.

[0352] "User terminal" refers to a device used by a user, such as a smartphone or an in-vehicle display.

[0353] To implement this invention, the following system configuration is required: The system is configured using a server, a user terminal, a real-time database of transportation, a generative AI model, and an emotion recognition engine.

[0354] Hardware and software used

[0355] Hardware:

[0356] Smartphones and in-car displays (devices where users input their departure point, destination, and desired departure time)

[0357] Camera and microphone (used by the emotion recognition engine to capture the user's facial expressions and voice information)

[0358] Server (the central system that processes all data)

[0359] software:

[0360] Navigation applications (where users enter information and receive suggested results)

[0361] Emotion recognition engine (a system that acquires user emotional information)

[0362] Real-time transport data API (obtaining congestion status, delay information, and availability information)

[0363] Generative AI model (artificial intelligence model for congestion prediction)

[0364] Data processing and calculation

[0365] 1. Processing on the user terminal side

[0366] Users input their departure point, destination, and desired departure time using a smartphone or in-car display, and the emotion recognition engine then captures the user's emotional information through the camera and microphone.

[0367] The user terminal transmits this information to the server.

[0368] 2. Server-side processing

[0369] The server receives and analyzes the data sent from the user's device. The server connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[0370] Generative AI models are used to predict congestion levels, potential delays, and availability at each time of day.

[0371] Based on the user's emotional information obtained from the emotion recognition engine, the system proposes the optimal departure time and transportation method, adjusted by a generative AI model.

[0372] The adjusted proposal results are sent back to the user terminal.

[0373] 3. Processing on the user terminal side

[0374] The user device receives the proposed results sent from the server and displays them to the user, who can then select the optimal means of transportation that takes into account their current emotional state.

[0375] Specific examples

[0376] For example, consider the case where User A travels from Tokyo Station to Shinjuku Station in an autonomous vehicle. User A enters "Tokyo Station" and "Shinjuku Station" as well as the desired arrival time of "19:00" into his smartphone and sets it to automatically determine the departure time. From information acquired through the camera and microphone, the system detects that User A is feeling stressed. The server uses a generative AI model to propose an optimal route and departure time (17:45) based on congestion predictions and emotional information, and sends the results to User A's smartphone. User A can then review the proposal and choose a more comfortable and efficient mode of transportation.

[0377] Prompt Sentence Examples

[0378] To help a user travel from Tokyo Station to Shinjuku Station, please consider their emotional information and suggest the optimal route and departure time. The user is currently in a stressful state and their desired arrival time is 7:00 PM. Please use past and current traffic data to predict congestion, and then generate suggestions by integrating the prediction results with the user's emotional information.

[0379] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0380] Program processing flow

[0381] Step 1:

[0382] The user inputs the departure point, destination, and desired departure time into a smartphone or in-car display. At this time, the camera and microphone are used to capture the user's emotional information (e.g., stress, relaxation). This input information is sent from the user's device to the server.

[0383] Input: departure point, destination, desired departure time, user emotion information

[0384] Output: Request data sent to the server

[0385] Specific operation: Information is entered into an input form on a smartphone or in-car display, and the emotion recognition engine uses the camera and microphone to capture emotional information. Press the send button to send the information to the server.

[0386] Step 2:

[0387] The server receives and analyzes the request data sent from the user terminal, and also connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[0388] Input: Request data, data from transit agency real-time database

[0389] Output: Current congestion status, delay information, availability information

[0390] Specific operation: The server analyzes the request data and extracts the necessary information. It connects to the transportation company's real-time database API to retrieve the data. The retrieved data is then classified into congestion status, delay information, and availability information.

[0391] Step 3:

[0392] The server uses a generative AI model to predict congestion for multiple time periods, including the desired time slot, based on past and current traffic data, while also taking into account emotional information obtained from an emotion recognition engine.

[0393] Input: congestion status, delay information, availability information, past traffic data, user emotion information

[0394] Output: Congestion forecast results for each time period

[0395] How it works: The generative AI model uses past and current data to predict congestion levels at each time of day, adjusting the predictions based on emotional information obtained from the emotion recognition engine.

[0396] Step 4:

[0397] The server then proposes optimal departure times and modes of transportation to the user based on the congestion prediction results and emotion information. These proposals are then sent back to the user's device.

[0398] Input: Congestion prediction results, emotion information

[0399] Output: Recommendations for optimal departure time and transportation

[0400] Specific operation: Based on the adjusted prediction results, the generative AI model calculates the optimal departure time and transportation method, generates the proposed results as data, and sends it to the user's device.

[0401] Step 5:

[0402] The user terminal receives the proposed results sent from the server and displays them to the user, who can then select the most comfortable and efficient means of transportation based on the proposed results.

[0403] Input: Suggestion results from the server

[0404] Output: The suggested results that are displayed to the user

[0405] Specific operation: The user device receives the proposed results and displays them on the screen. The user checks the results and selects the most suitable transportation method for them.

[0406] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0407] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0408] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0409] [Second embodiment]

[0410] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0411] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0412] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0413] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0414] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0415] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0416] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0417] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0418] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0419] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0420] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0421] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0422] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, the server connects to a real-time database of transportation companies based on that data, uses generative AI to predict congestion, and suggests the optimal departure time and vehicle.

[0423] The user submits a request

[0424] A user uses a transportation search app to input their departure point, destination, and desired departure time. For example, the user inputs "Tokyo Station" as the departure point, "Shinjuku Station" as the destination, and "6:00 PM" as the desired departure time. This information is sent from the user's device to the server.

[0425] The server receives and processes the request

[0426] The server receives the request sent by the user, analyzes the received information, and accesses the transportation company's real-time database to obtain current congestion status, delay information, and availability information.

[0427] Congestion prediction and optimal proposal generation

[0428] The server uses generative AI to predict congestion for multiple time periods, including the desired departure time specified by the user. The generative AI uses past and real-time data to predict the level of congestion, the possibility of delays, and availability for each time period. Based on these predictions, the server proposes the optimal departure time and vehicle to the user. For example, if the user's desired time of 18:00 is very crowded, the server generates a proposal to change the departure time to 18:30 and use an available car on the Chuo Line Rapid (e.g., car 8).

[0429] Sending and displaying proposal results

[0430] The server sends the generated proposal results to the user's terminal. The user's terminal receives the proposal results and displays the optimal departure time and vehicle information for the user. For example, the user receives a proposal to "depart at 6:30 PM and use car 8 of the Chuo Line Rapid."

[0431] Implementation by concrete example

[0432] For example, consider a user traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00" (user device operation). This information is sent to the server. The server connects to a real-time database to obtain congestion information, delay information, and car availability for the Chuo Line Rapid (server operation). It then uses generative AI to predict the congestion level for each time period and suggests the optimal departure time and car (server operation). Finally, the server generates a suggestion to "depart at 18:30 and use car 8" and sends it to the user's device (server operation). The user's device displays this suggestion to the user, allowing them to travel in a way that avoids crowds.

[0433] This system is extremely useful, not only because it allows users to avoid crowded trains and traffic jams, but also because it allows service providers to manage their resources more efficiently.

[0434] The processing flow will be explained below.

[0435] Step 1:

[0436] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), etc.

[0437] Step 2:

[0438] The user inputs the departure point, destination, and desired departure time, and clicks the search button. This input information is sent to the server by the user terminal.

[0439] Step 3:

[0440] The server analyzes the request data received from the user terminal, including the origin, destination, and desired departure time.

[0441] Step 4:

[0442] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[0443] Step 5:

[0444] The server inputs the acquired real-time data into a generative AI to predict congestion levels for the next few hours, including the desired departure time. The generative AI then predicts congestion levels, possible delays, and availability for each time period.

[0445] Step 6:

[0446] Based on the predictions made by the generative AI, the server generates data to suggest optimal departure times and train cars to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and use car 8 of the Chuo Line Rapid."

[0447] Step 7:

[0448] The server transmits the generated proposal data to the user terminal.

[0449] Step 8:

[0450] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0451] In this way, users can choose the most suitable means of transportation that avoids congestion.

[0452] Example 1

[0453] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0454] In modern transportation, congestion often makes it difficult for users to travel efficiently and comfortably. Congestion is particularly severe during certain times of the day, such as rush hour and tourist season, and users face overcrowded trains and road congestion. Such congestion can be stressful for users, causing travel delays and forcing them to change their plans. Furthermore, congestion poses challenges for transportation agencies and road operators, as it can lead to reduced service quality and make operation management more difficult. Therefore, there is a need for a system that can predict congestion in real time and suggest optimal travel methods and times for users.

[0455] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0456] In this invention, the server includes means for a user to input a departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities and obtaining current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative artificial intelligence, means for proposing optimal departure times and vehicles based on the prediction results, means for transmitting the proposal results to a user terminal, means for displaying the proposal results to the user, and means for using past data and real-time data to predict congestion levels for multiple time periods, thereby enabling a user to select the optimal transportation means and time to avoid congestion in real time.

[0457] "User" refers to an individual user who uses the system to search for transportation travel information and receive suggestions on the best travel method and time.

[0458] "Start point" refers to the location where the user begins their journey.

[0459] "Destination" refers to the location where the user completes their journey.

[0460] "Desired departure time" refers to the time at which the user wishes to begin their journey.

[0461] "Server" refers to the central computing system that analyzes information submitted by users, obtains real-time data, performs congestion predictions, and generates and transmits proposal results.

[0462] "User terminal" refers to the device that a user uses to operate a transportation search app, and is typically a mobile device such as a smartphone or tablet.

[0463] A "real-time transportation database" refers to a database that holds the latest information about transportation, such as current congestion status, delay information, and availability information.

[0464] "Generative AI" refers to an AI model that has the ability to predict future congestion situations using past and real-time data.

[0465] "Congestion prediction" refers to the process in which generative artificial intelligence analyzes past and real-time data to predict future congestion conditions on public transport at specific times of the day.

[0466] "Proposal Report" refers to a document of proposals including the optimal departure time and vehicle for the user, created by the server based on the results of congestion predictions made by the generative artificial intelligence.

[0467] "Multiple modes of transportation" refers to multiple different modes of public transportation, such as trains and buses, that a user may use for travel.

[0468] "Data integration" refers to the process of centrally managing and comprehensively analyzing information obtained from multiple data sources.

[0469] System Overview

[0470] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, a server connects to a real-time database of transportation services based on that data, uses generative artificial intelligence to predict congestion, and suggests the optimal departure time and vehicle. In the description of the embodiment of the invention, specific program processing, and the hardware and software used will be described.

[0471] User Operation

[0472] A user opens a transportation search application on a user device such as a smartphone or tablet and inputs the origin, destination, and desired departure time. For example, consider the following information:

[0473] Departure point: Tokyo Station

[0474] Destination: Shinjuku Station

[0475] Desired departure time: 6:00 PM

[0476] This information is sent to the server in JSON format when the user taps the "Search" button.

[0477] Server Processing

[0478] Receiving and parsing the request

[0479] The server receives the data sent by the user through an HTTP POST request. Then, the server parses the received JSON data and extracts the origin, destination, and desired departure time. This process is handled by the data analysis module in the server.

[0480] Real-time data acquisition

[0481] The server sends an API request to the transit agency's real-time database. In this particular operation, the server invokes an API endpoint such as:

[0482] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[0483] This API request allows the server to obtain real-time data including current congestion status, delay information, and availability information.

[0484] Implementing congestion predictions

[0485] Next, the server uses generative artificial intelligence (e.g., GPT-3.5) to predict congestion. The server provides the collected historical and real-time data as input to the AI ​​model, which predicts congestion over multiple time periods. Below is an example of a prompt for congestion prediction:

[0486] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[0487] The generative AI returns congestion prediction results based on this prompt, and the server analyzes these results. For example, it predicts the level of congestion for each time slot between 6:00 PM and 7:00 PM.

[0488] Generating optimal proposals

[0489] The server then proposes the optimal departure time and vehicle to the user based on the predictions made by the generative AI. This proposal is reported in the form of a report with information such as the following:

[0490] Recommended departure time: 6:30 PM

[0491] Route and vehicle: Chuo Line Rapid No. 8

[0492] Sending and displaying proposal results

[0493] The server sends the generated proposal report to the user's device. The secure protocol HTTPS is used for communication, and the data is encrypted before transmission. The user's device analyzes the proposal report received from the server and displays it to the user in an intuitive interface.

[0494] Specific examples

[0495] For example, if a user wants to travel from Tokyo Station to Shinjuku Station at 6:00 PM, they open the app on their device and enter the information above. The server receives this information, acquires real-time data, predicts congestion using generative artificial intelligence, and suggests the optimal means of transportation to the user. Finally, the server displays the suggestion to the user: "Depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0496] This system allows users to avoid crowds and provides an efficient and comfortable travel experience.

[0497] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0498] Step 1:

[0499] The user inputs the starting point, destination, and desired departure time. Specifically, the user opens a transportation search app on a user device such as a smartphone or tablet. In the input form that appears, the user enters the following information:

[0500] Departure point: Tokyo Station

[0501] Destination: Shinjuku Station

[0502] Desired departure time: 6:00 PM

[0503] When the user taps the "Search" button, this information is sent to the server in JSON format (input).

[0504] Step 2:

[0505] The server receives the request sent by the user. The server receives the data via an HTTP POST request and parses the received JSON data. For example, the following data is extracted:

[0506] Departure point: Tokyo Station

[0507] Destination: Shinjuku Station

[0508] Desired departure time: 6:00 PM

[0509] Based on this information, the server proceeds to the next step in the process (output).

[0510] Step 3:

[0511] The server sends an API request to the transport agency's real-time database to get the current congestion, delay, and availability information. For example, it calls the following API endpoint:

[0512] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[0513] The server analyzes the information obtained from this API request and obtains the following data (input):

[0514] Current congestion: High

[0515] Delay Information: None

[0516] Vehicle availability: Limited

[0517] This information is used in the next step (output).

[0518] Step 4:

[0519] The server inputs the collected real-time and past data into a generative AI model to predict congestion. The prompt is constructed as follows:

[0520] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[0521] The congestion prediction results returned by the generative AI are in the following format (input):

[0522] 18:00: Very high

[0523] 18:15: High

[0524] 18:30: Medium

[0525] 18:45: Low

[0526] 19:00: Very low

[0527] Based on this prediction result, the optimal proposal is generated (output) in the next step.

[0528] Step 5:

[0529] The server generates optimal departure time and vehicle recommendations for the user based on the predictions of the generative AI. For example, the following recommendations are generated:

[0530] Recommended departure time: 6:30 PM

[0531] Route and vehicle: Chuo Line Rapid No. 8

[0532] This proposal report will be generated in JSON format and will look something like this (input):

[0533] json

[0534] {

[0535] "recommended_departure_time": "18:30",

[0536] "recommended_vehicle": "Chuo Line Rapid Car No. 8"

[0537] }

[0538] The generated report is sent to the user terminal (output).

[0539] Step 6:

[0540] The server sends the generated proposal report to the user terminal. The secure protocol HTTPS is used for communication, and encrypted data is sent. The user terminal receives the proposal report from the server (input).

[0541] Step 7:

[0542] The user device analyzes the received proposal report and displays it in an intuitive interface for the user. Specifically, the following information is displayed on the screen:

[0543] Recommended departure time: 6:30 PM

[0544] Route and vehicle: Chuo Line Rapid No. 8

[0545] This allows the user to select a means of transportation that avoids congestion (output).

[0546] (Application example 1)

[0547] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0548] In recent years, congestion and traffic jams on public transport have become increasingly serious, causing significant stress for users during travel. As a result, users are seeking more efficient and comfortable means of transportation. However, current systems do not adequately provide real-time congestion predictions or avoidance strategies. Furthermore, with the increasing number of autonomous vehicles, dynamic operation according to traffic conditions is required. With current technology, even if users input their departure point, destination, and desired departure time, optimal suggestions are not provided that take into account real-time congestion and traffic conditions, resulting in reduced user convenience. This issue needs to be resolved.

[0549] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0550] In this invention, the server includes: a means for a user to input their departure point, destination, and desired departure time; a means for transmitting the input information to the server; a means for analyzing the information received by the server; a means for connecting to a real-time database of transportation facilities and acquiring current congestion status, delay information, and availability information; a means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; a means for proposing an optimal departure time and vehicle; a means for transmitting the proposal results to a user terminal; a means for displaying the proposal results to the user; and a means for an autonomous vehicle to pick up the user based on the proposed optimal departure time and route. This allows users to avoid congestion and traffic jams and travel to their destination efficiently and comfortably. Furthermore, autonomous vehicles dynamically selecting optimal routes and efficiently picking up users improves traffic flow and convenience.

[0551] "Means for the user to input the departure point, destination, and desired departure time" refers to means for providing an interface for the user to input their current location, destination, and desired departure time.

[0552] The "means for transmitting input information to a server" refers to a communication means for transmitting data input by a user to a server via a network.

[0553] The "means for analyzing the information received by the server" refers to the means by which the server analyzes the information sent by the user and understands details such as the destination and departure time.

[0554] "Means for connecting to a real-time database of a transportation facility and obtaining current congestion status, delay information, and availability information" refers to a means for a server to connect to a transportation facility's database in real time and obtain the latest congestion status, delay information, and availability information.

[0555] "Means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period" refers to means for using generative AI to predict congestion conditions for multiple time periods, including the user's desired time period.

[0556] The "means of suggesting the optimal departure time and vehicle" is a means of suggesting the optimal departure time and vehicle to be used for the user based on the acquired data and the prediction results of the generative AI.

[0557] The "means for transmitting the proposal results to the user terminal" is a communication means for transmitting the proposal results generated by the server to the terminal used by the user.

[0558] The "means for displaying the proposal results to the user" refers to the means for displaying the received proposal results on the user's terminal so that the user can confirm and use the information.

[0559] "Means for an autonomous vehicle to pick you up based on the proposed optimal departure time and route" refers to means for an autonomous vehicle to pick you up at a specified location based on the optimal departure time and route predicted by the server.

[0560] This invention provides a system that allows users to travel to their destinations efficiently and comfortably by optimizing an autonomous vehicle. How this system is implemented will be described below in detail.

[0561] System Overview

[0562] The user inputs their departure point, destination, and desired departure time via a smartphone app or in-car display. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. The server then suggests the optimal departure time and route, and sends this information to the autonomous vehicle. The autonomous vehicle then picks up the user based on this suggestion. This entire process is achieved using high-precision data analysis and AI technology.

[0563] Hardware and software used

[0564] Smartphones and in-car displays: Interfaces for users to input information.

[0565] Server: A central system for receiving, analyzing, and generating AI-based predictions.

[0566] Real-time traffic database: A database that provides congestion, delay, and availability information.

[0567] Generative AI models: Custom AI models using PyTorch or TensorFlow.

[0568] Communication module: A network communication function for transmitting data between the user terminal and the server, and between the server and the autonomous vehicle.

[0569] Data processing flow

[0570] 1. User input: The user enters the departure point, destination, and desired departure time using a smartphone app or the in-car display.

[0571] 2. Data transmission: The data entered by the user is transmitted from the interface to the server.

[0572] 3. Obtaining real-time data: The server connects to the real-time traffic database and obtains current congestion, delay, and availability information.

[0573] 4. Generative AI prediction: The server uses generative AI models to predict congestion levels, potential delays, and availability across multiple time periods.

[0574] 5. Generating optimal proposals: Based on the prediction results, the server proposes the optimal departure time and vehicle route to be used.

[0575] 6. Notification of proposed results: The proposed departure time and route are sent to the user's terminal and displayed for the user to review.

[0576] 7. Dispatch of autonomous vehicles: Based on the proposed route, an autonomous vehicle is dynamically dispatched to pick up the user.

[0577] Specific examples

[0578] For example, if a user wants to travel from Station A to Station B around 6:00 PM, they would enter Station A, Station B, and the desired time of 6:00 PM into the smartphone app. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. As a result, it predicts that 6:15 PM is the best time to travel, and that car 8 of the Chuo Line Rapid train is available. The server then sends the proposal to the user's smartphone, where the user can review it. If they agree, an autonomous vehicle will come to pick them up based on the prediction.

[0579] Example prompt sentences to use

[0580] Prompt: "Predict the optimal departure time and route given the following conditions: departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data."

[0581] As described above, in order to put this invention into practice, it is necessary to build a series of systems that utilize advanced data analysis and AI technology to optimize user mobility.

[0582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0583] Step 1:

[0584] The user inputs the departure point, destination, and desired departure time on a smartphone app or on the in-car display. The information the user inputs is the departure point, destination, and desired departure time.

[0585] Step 2:

[0586] The device sends the entered information to the server. In this step, the data entered by the user is sent to the server via the internet via a smartphone app or in-car display. Here, the user's intention is conveyed to the server as input.

[0587] Step 3:

[0588] The server analyzes the received information. In this step, the server analyzes the information submitted by the user, such as origin, destination, and desired departure time. The analysis results in an output that allows the server to understand the user's travel requirements.

[0589] Step 4:

[0590] The server connects to the real-time database of the transport agency to get the current congestion status, delay information, and availability information. Here, the server uses the API of the real-time database to collect the latest data related to the transport agency. This data is sent as input to the server, and the latest traffic information is obtained as output.

[0591] Step 5:

[0592] The server uses a generative AI model to predict congestion levels for multiple time periods, including the user's desired time period. Specifically, it combines past data and real-time data to predict congestion levels, potential delays, and availability. In this process, the server uses AI frameworks such as PyTorch and TensorFlow to make predictions using prompt statements as input. An example prompt statement is, "Predict the optimal departure time and route under the following conditions: Conditions: Departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data." The predicted results are then output.

[0593] Step 6:

[0594] The server proposes the optimal departure time and vehicle. Based on the prediction results, the server calculates the optimal departure time and vehicle to use to avoid congestion and generates a proposal. This proposal is obtained as the output.

[0595] Step 7:

[0596] The server sends the proposal results to the user's terminal. The generated proposal results are then sent via the network to the user's smartphone or in-car display, where they are input into the user's terminal and displayed.

[0597] Step 8:

[0598] The user's device displays the proposed results. The optimal departure time and vehicle are displayed on the user's device, and the user can confirm and select the information.

[0599] Step 9:

[0600] The server sends instructions to the autonomous vehicle to pick up the user based on the optimal departure time and route. After the optimal route and time are determined, the autonomous vehicle receives instructions to dynamically pick up the user based on the optimal route and time. This initiates the operation of the autonomous vehicle to pick up the user.

[0601] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0602] This invention is a system in which a user inputs their departure point, destination, and desired departure time, and the server connects to a real-time database of transportation companies to obtain information based on this information, and then uses generative AI to predict congestion and suggest the optimal departure time and vehicle.Furthermore, by combining this system with an emotion engine, the system recognizes the user's emotions and makes optimal suggestions taking into account that emotional information.

[0603] The user submits a request

[0604] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine that acquires emotional information from the user's facial expressions and voice.

[0605] The server receives and processes the request

[0606] The server receives and analyzes the request data sent from the user terminal, which includes the departure point, destination, desired departure time, and emotion information.

[0607] Real-time data acquisition and congestion prediction

[0608] The server connects to the transportation company's real-time database to retrieve current congestion, delay, and availability information related to the specified departure and destination. Generative AI then predicts congestion within the next few hours, including the desired departure time. Based on past and real-time data, the generative AI predicts congestion levels, potential delays, and availability for each time period.

[0609] Generating suggestions based on user's emotional information

[0610] The server provides the generative AI with the user's emotional information obtained by the emotion engine. The generative AI then makes adjustments based on the emotional information and suggests the optimal departure time and vehicle that takes the user's emotions into consideration. For example, if the user is stressed, it will prioritize suggestions that further avoid congestion.

[0611] Sending and displaying proposal results

[0612] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal might be displayed that says, "Depart at 6:30 PM and use car 8 of the Chuo Line Rapid." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[0613] Implementation by concrete example

[0614] For example, consider a case where a user travels from Tokyo Station to Shinjuku Station. The user inputs "Tokyo Station" and "Shinjuku Station" into the app, as well as the desired departure time of "18:00." Furthermore, the emotion engine detects that the user is feeling stressed from their facial expression (operation of the user's device). This information is then sent to the server (operation of the user's device).

[0615] The server connects to a real-time database and obtains information on congestion and delays on Chuo Line rapid trains, as well as car availability (server operation). Furthermore, it uses generative AI to predict the level of congestion for each time period and makes optimal suggestions based on emotional information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8" (server operation).

[0616] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user (operation of the user terminal). The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[0617] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[0618] The processing flow will be explained below.

[0619] Step 1:

[0620] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), and the emotion engine begins to acquire emotion information from the user's facial expressions and voice.

[0621] Step 2:

[0622] The user inputs the departure point, destination, and desired departure time and clicks the search button. At this time, the emotion engine recognizes the user's emotion and acquires emotion information. This input information and emotion information are sent from the user terminal to the server.

[0623] Step 3:

[0624] The server analyzes the request data received from the user terminal, including the departure point, destination, desired departure time, and emotion information.

[0625] Step 4:

[0626] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[0627] Step 5:

[0628] The server inputs the acquired real-time data into a generative AI to predict congestion for the next few hours, including the desired departure time. The generative AI uses past and real-time data to predict the level of congestion, potential delays, and availability for each time period.

[0629] Step 6:

[0630] The server provides the emotion information obtained from the emotion engine to the generative AI, which then adjusts the optimal suggestions based on the user's emotions. For example, if the user is stressed, the generative AI will select a less stressful time slot to generate suggestions.

[0631] Step 7:

[0632] The server generates data based on generative AI and emotion information to suggest optimal departure times and vehicles to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and take car 8 of the Chuo Line Rapid."

[0633] Step 8:

[0634] The server transmits the generated proposal data to the user terminal.

[0635] Step 9:

[0636] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0637] In this way, users can choose more comfortable means of transportation that take emotional information into account.

[0638] Example 2

[0639] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0640] When using conventional public transport, it is difficult for users to know the congestion situation or delay information in advance, and as a result, they cannot avoid stressful situations such as crowded trains and traffic jams.In addition, personalized travel suggestions that take into account the user's emotional information are not provided, so solutions that fully consider the user's comfort have not been provided.

[0641] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for adjusting the optimal departure time and vehicle taking into account the user's emotional information, a means for connecting to a real-time database of transportation means and acquiring current congestion status, delay information, and availability information, and a means for predicting congestion for multiple time periods including the user's desired time period by utilizing generative artificial intelligence. This enables the user to receive suggestions for avoiding congestion and realizing a more comfortable and less stressful trip.

[0642] A "user" is an individual or group that uses the system to input a departure point, destination, and desired departure time and view transportation information.

[0643] The "starting point" is the point from which the user starts traveling.

[0644] A "destination" is a point where a user completes their journey.

[0645] The "desired departure time" is the specific time at which the user wishes to start traveling.

[0646] "User terminal" refers to an electronic device (e.g., smartphone, personal computer) used by a user to input data into the system and view results.

[0647] "Server" means a centralized computer system that receives and analyzes information sent by users and performs appropriate processing.

[0648] "Transportation" refers to public or private means of transportation such as trains, buses, and taxis.

[0649] A "real-time database" is a database that provides real-time information on current congestion, delays, and availability related to transportation means.

[0650] "Generative artificial intelligence" is a machine learning model that uses past and current data to make predictions and suggestions.

[0651] "Crowd prediction" refers to the process in which generative artificial intelligence predicts future congestion situations based on past and real-time data.

[0652] "Emotion information" is data indicating the emotional state of the user, such as stress or satisfaction, obtained from the user's facial expression, voice, etc.

[0653] "Proposal results" are information about optimal departure times and vehicles provided to users based on data analyzed and predicted by generative artificial intelligence.

[0654] "Crowding status" is information that indicates the current number of people using a means of transportation and how available it is.

[0655] "Delay information" is information that indicates the degree to which transportation means are not operating according to the scheduled time.

[0656] "Vacancy information" refers to information about the availability of each vehicle and seat of a means of transportation.

[0657] "Parsing" refers to the act of the server understanding the information sent by the user and converting it into the form required for the next processing step.

[0658] "Adjusting" refers to the act of the generative AI optimizing the suggestions based on the user's wishes and emotional state.

[0659] This system allows users to input their departure point, destination, and desired departure time, and then the server connects to a real-time database of transportation modes to obtain information based on this information, uses generative artificial intelligence to predict congestion, and suggests optimal departure times and vehicles. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and makes optimal suggestions based on that emotional information.

[0660] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine, which can obtain emotional information from the user's facial expressions and voice.

[0661] The server receives and analyzes the request data sent from the user device. The sent data includes the origin, destination, desired departure time, and emotion information. The server connects to a real-time database of transportation modes to obtain current congestion, delay information, and availability information related to the specified origin and destination. It then uses generative artificial intelligence (e.g., a general deep learning model) to predict congestion within the next few hours, including the desired departure time.

[0662] The generative AI predicts congestion levels, potential delays, and availability for each time period based on past and real-time data. Furthermore, the server provides the user's emotional information obtained by the emotion engine to the generative AI, which then makes adjustments based on the emotional information and suggests optimal departure times and vehicles that take the user's emotions into consideration. For example, if the user is stressed, the AI ​​will prioritize suggestions that further avoid congestion.

[0663] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal may be presented such as "Depart at 6:30 PM and take car 8 on the Chuo Line." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[0664] As a concrete example, consider the case where a user is traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00." The emotion engine then detects stress from the user's facial expression. This information is sent to the server. The server connects to a real-time database to obtain information on congestion and delays on the Chuo Line, as well as the availability of train cars. It then uses generative artificial intelligence to predict the level of congestion for each time period and makes optimal suggestions based on the emotion information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8."

[0665] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user. The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[0666] (Example prompt)

[0667] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[0668] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[0669] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0670] Step 1: User submits request

[0671] The user opens a transportation search app on their device, such as a smartphone or PC. They enter their departure point (e.g., Tokyo Station), destination (e.g., Shinjuku Station), and desired departure time (e.g., 6:00 p.m.), and click the search button. The app, which is equipped with an emotion engine, analyzes the user's facial expressions and voice in real time through the device's camera and microphone to obtain emotional information.

[0672] Specific behavior:

[0673] 1. The user enters their departure point, destination, and desired departure time into the app's input fields.

[0674] 2. The emotion engine uses the device's camera and microphone to obtain the user's emotional information.

[0675] 3. The input information and emotional information are sent to the server.

[0676] Input: departure point, destination, desired departure time, emotional information

[0677] Output: Request data sent to the server

[0678] Step 2: The server receives and processes the request

[0679] The server receives a request sent from the user terminal. The received data includes the origin, destination, desired departure time, and emotion information. This information is analyzed and converted into the form required for the next processing step.

[0680] Specific behavior:

[0681] 1. The server receives and analyzes the request data.

[0682] 2. Store the parsed data in variables (origin, destination, desired departure time, emotion information).

[0683] Input: Request data (origin, destination, desired departure time, emotional information)

[0684] Output: Parsed data (stored in a variable)

[0685] Step 3: Acquire and analyze real-time data

[0686] The server connects to a real-time database of transportation modes, retrieving current congestion, delay, and availability information related to the specified origin and destination, and then analyzing and organizing the retrieved data.

[0687] Specific behavior:

[0688] 1. The server connects to the specified API endpoint.

[0689] 2. Obtain real-time data (crowding, delay information, availability information) for the specified departure and destination.

[0690] 3. Analyze the acquired data and extract and organize the necessary information.

[0691] Input: Departure point, Destination

[0692] Output: Real-time data (congestion status, delay information, availability information)

[0693] Step 4: Congestion prediction using generative AI

[0694] The server uses generative artificial intelligence to predict congestion within the next few hours, including the desired departure time, based on past and real-time data. It also predicts the level of congestion, potential delays, and availability for each time slot.

[0695] Specific behavior:

[0696] 1. The server inputs past data and acquired real-time data into the generative artificial intelligence.

[0697] 2. Generative AI analyzes the data and predicts congestion during a specific time period (for example, between 6:00 PM and 9:00 PM).

[0698] Input: Historical data, real-time data

[0699] Output: Congestion forecast data (congestion level for each time period, possibility of delay, availability)

[0700] Step 5: Generate suggestions taking into account user's emotional information

[0701] The server provides the user's emotional information obtained from the emotion engine to the generative artificial intelligence, which takes the emotional information into consideration and selects the optimal departure time and vehicle to reduce the user's stress.

[0702] Specific behavior:

[0703] 1. The server inputs the user's emotional information into the generative AI.

[0704] 2. Generative AI takes emotional information into account and generates optimal suggestions based on congestion prediction data.

[0705] Input: Emotional information, congestion prediction data

[0706] Output: Optimal departure time and vehicle suggestions

[0707] Step 6: Submit and view the proposal results

[0708] The server sends the generated proposal results to the user terminal, which analyzes the proposal results and displays the optimal departure time and vehicle information to the user.

[0709] Specific behavior:

[0710] 1. The server sends the proposal results in JSON format to the user device.

[0711] 2. The user device analyzes the suggestion results and displays on the screen, "Please use car 8 on the Chuo Line at 6:30 p.m."

[0712] Input: Proposal results (optimal departure time and vehicle)

[0713] Output: Suggestion results displayed on the user's device

[0714] Example prompt:

[0715] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[0716] This system suggests optimal transportation methods that avoid crowds to users, enabling them to travel more comfortably and with less stress.

[0717] (Application example 2)

[0718] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0719] In modern transportation, users often experience stress due to congestion and delays. Conventional navigation systems and transportation suggestion systems provide optimal suggestions based on real-time congestion and delay information, but do not take into account the user's emotional state. As a result, users may travel without feeling fully comfortable. Furthermore, it is difficult to integrate and analyze data from multiple transportation modes, making it difficult to propose efficient transportation options. Therefore, there is a need for a system that takes into account the user's emotional state and suggests more comfortable and efficient transportation options.

[0720] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities to obtain current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative AI, means for proposing optimal departure times and transportation modes, means for acquiring the user's emotional information using an emotion recognition engine, means for adjusting the proposal results based on the acquired emotional information, means for transmitting the adjusted proposal results to the user terminal, and means for displaying the proposal results to the user. This not only enables the user to avoid congestion and delays, but also enables the user to receive suggestions for comfortable transportation modes that take into account their current emotional state.

[0721] "User" refers to a person who uses the system to input a departure point, destination, and desired departure time.

[0722] "Start point" refers to the point where the user starts their journey.

[0723] "Destination" refers to the point where the user ends their journey.

[0724] "Desired departure time" refers to the time at which the user wishes to start traveling.

[0725] "Server" refers to a computer system that receives and analyzes information sent by users.

[0726] "Real-time transportation database" refers to a database that provides current congestion, delay, and availability information.

[0727] "Generative AI" refers to artificial intelligence that predicts congestion based on past and current data.

[0728] "Congestion prediction" refers to the prediction made by generative AI of the level of congestion, possibility of delays, and availability at each time slot.

[0729] The "optimal departure time" refers to the most suitable time for the user to start traveling, determined in consideration of congestion forecasts and the user's emotional information.

[0730] "Means of transportation" refers to the means of transportation used by the user, such as public transport or automobiles.

[0731] An "emotion recognition engine" refers to a system that acquires emotional information from a user's facial expressions and voice.

[0732] "Emotion information" refers to the user's emotional state (stress, relaxation, etc.) acquired by the emotion recognition engine.

[0733] "Proposal result" refers to information about the optimal departure time and transportation means provided to the user by the server.

[0734] "User terminal" refers to a device used by a user, such as a smartphone or an in-vehicle display.

[0735] To implement this invention, the following system configuration is required: The system is configured using a server, a user terminal, a real-time database of transportation, a generative AI model, and an emotion recognition engine.

[0736] Hardware and software used

[0737] Hardware:

[0738] Smartphones and in-car displays (devices where users input their departure point, destination, and desired departure time)

[0739] Camera and microphone (used by the emotion recognition engine to capture the user's facial expressions and voice information)

[0740] Server (the central system that processes all data)

[0741] software:

[0742] Navigation applications (where users enter information and receive suggested results)

[0743] Emotion recognition engine (a system that acquires user emotional information)

[0744] Real-time transport data API (obtaining congestion status, delay information, and availability information)

[0745] Generative AI model (artificial intelligence model for congestion prediction)

[0746] Data processing and calculation

[0747] 1. Processing on the user terminal side

[0748] Users input their departure point, destination, and desired departure time using a smartphone or in-car display, and the emotion recognition engine then captures the user's emotional information through the camera and microphone.

[0749] The user terminal transmits this information to the server.

[0750] 2. Server-side processing

[0751] The server receives and analyzes the data sent from the user's device. The server connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[0752] Generative AI models are used to predict congestion levels, potential delays, and availability at each time of day.

[0753] Based on the user's emotional information obtained from the emotion recognition engine, the system proposes the optimal departure time and transportation method, adjusted by a generative AI model.

[0754] The adjusted proposal results are sent back to the user terminal.

[0755] 3. Processing on the user terminal side

[0756] The user device receives the proposed results sent from the server and displays them to the user, who can then select the optimal means of transportation that takes into account their current emotional state.

[0757] Specific examples

[0758] For example, consider the case where User A travels from Tokyo Station to Shinjuku Station in an autonomous vehicle. User A enters "Tokyo Station" and "Shinjuku Station" as well as the desired arrival time of "19:00" into his smartphone and sets it to automatically determine the departure time. From information acquired through the camera and microphone, the system detects that User A is feeling stressed. The server uses a generative AI model to propose an optimal route and departure time (17:45) based on congestion predictions and emotional information, and sends the results to User A's smartphone. User A can then review the proposal and choose a more comfortable and efficient mode of transportation.

[0759] Prompt Sentence Examples

[0760] To help a user travel from Tokyo Station to Shinjuku Station, please consider their emotional information and suggest the optimal route and departure time. The user is currently in a stressful state and their desired arrival time is 7:00 PM. Please use past and current traffic data to predict congestion, and then generate suggestions by integrating the prediction results with the user's emotional information.

[0761] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0762] Program processing flow

[0763] Step 1:

[0764] The user inputs the departure point, destination, and desired departure time into a smartphone or in-car display. At this time, the camera and microphone are used to capture the user's emotional information (e.g., stress, relaxation). This input information is sent from the user's device to the server.

[0765] Input: departure point, destination, desired departure time, user emotion information

[0766] Output: Request data sent to the server

[0767] Specific operation: Information is entered into an input form on a smartphone or in-car display, and the emotion recognition engine uses the camera and microphone to capture emotional information. Press the send button to send the information to the server.

[0768] Step 2:

[0769] The server receives and analyzes the request data sent from the user terminal, and also connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[0770] Input: Request data, data from transit agency real-time database

[0771] Output: Current congestion status, delay information, availability information

[0772] Specific operation: The server analyzes the request data and extracts the necessary information. It connects to the transportation company's real-time database API to retrieve the data. The retrieved data is then classified into congestion status, delay information, and availability information.

[0773] Step 3:

[0774] The server uses a generative AI model to predict congestion for multiple time periods, including the desired time slot, based on past and current traffic data, while also taking into account emotional information obtained from an emotion recognition engine.

[0775] Input: congestion status, delay information, availability information, past traffic data, user emotion information

[0776] Output: Congestion forecast results for each time period

[0777] How it works: The generative AI model uses past and current data to predict congestion levels at each time of day, adjusting the predictions based on emotional information obtained from the emotion recognition engine.

[0778] Step 4:

[0779] The server then proposes optimal departure times and modes of transportation to the user based on the congestion prediction results and emotion information. These proposals are then sent back to the user's device.

[0780] Input: Congestion prediction results, emotion information

[0781] Output: Recommendations for optimal departure time and transportation

[0782] Specific operation: Based on the adjusted prediction results, the generative AI model calculates the optimal departure time and transportation method, generates the proposed results as data, and sends it to the user's device.

[0783] Step 5:

[0784] The user terminal receives the proposed results sent from the server and displays them to the user, who can then select the most comfortable and efficient means of transportation based on the proposed results.

[0785] Input: Suggestion results from the server

[0786] Output: The suggested results that are displayed to the user

[0787] Specific operation: The user device receives the proposed results and displays them on the screen. The user checks the results and selects the most suitable transportation method for them.

[0788] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0789] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0790] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0791] [Third embodiment]

[0792] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0793] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0794] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0795] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0796] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0797] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0798] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0799] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0800] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0801] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0802] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0803] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0804] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, the server connects to a real-time database of transportation companies based on that data, uses generative AI to predict congestion, and suggests the optimal departure time and vehicle.

[0805] The user submits a request

[0806] A user uses a transportation search app to input their departure point, destination, and desired departure time. For example, the user inputs "Tokyo Station" as the departure point, "Shinjuku Station" as the destination, and "6:00 PM" as the desired departure time. This information is sent from the user's device to the server.

[0807] The server receives and processes the request

[0808] The server receives the request sent by the user, analyzes the received information, and accesses the transportation company's real-time database to obtain current congestion status, delay information, and availability information.

[0809] Congestion prediction and optimal proposal generation

[0810] The server uses generative AI to predict congestion for multiple time periods, including the desired departure time specified by the user. The generative AI uses past and real-time data to predict the level of congestion, the possibility of delays, and availability for each time period. Based on these predictions, the server proposes the optimal departure time and vehicle to the user. For example, if the user's desired time of 18:00 is very crowded, the server generates a proposal to change the departure time to 18:30 and use an available car on the Chuo Line Rapid (e.g., car 8).

[0811] Sending and displaying proposal results

[0812] The server sends the generated proposal results to the user's terminal. The user's terminal receives the proposal results and displays the optimal departure time and vehicle information for the user. For example, the user receives a proposal to "depart at 6:30 PM and use car 8 of the Chuo Line Rapid."

[0813] Implementation by concrete example

[0814] For example, consider a user traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00" (user device operation). This information is sent to the server. The server connects to a real-time database to obtain congestion information, delay information, and car availability for the Chuo Line Rapid (server operation). It then uses generative AI to predict the congestion level for each time period and suggests the optimal departure time and car (server operation). Finally, the server generates a suggestion to "depart at 18:30 and use car 8" and sends it to the user's device (server operation). The user's device displays this suggestion to the user, allowing them to travel in a way that avoids crowds.

[0815] This system is extremely useful, not only because it allows users to avoid crowded trains and traffic jams, but also because it allows service providers to manage their resources more efficiently.

[0816] The processing flow will be explained below.

[0817] Step 1:

[0818] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), etc.

[0819] Step 2:

[0820] The user inputs the departure point, destination, and desired departure time, and clicks the search button. This input information is sent to the server by the user terminal.

[0821] Step 3:

[0822] The server analyzes the request data received from the user terminal, including the origin, destination, and desired departure time.

[0823] Step 4:

[0824] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[0825] Step 5:

[0826] The server inputs the acquired real-time data into a generative AI to predict congestion levels for the next few hours, including the desired departure time. The generative AI then predicts congestion levels, possible delays, and availability for each time period.

[0827] Step 6:

[0828] Based on the predictions made by the generative AI, the server generates data to suggest optimal departure times and train cars to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and use car 8 of the Chuo Line Rapid."

[0829] Step 7:

[0830] The server transmits the generated proposal data to the user terminal.

[0831] Step 8:

[0832] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0833] In this way, users can choose the most suitable means of transportation that avoids congestion.

[0834] Example 1

[0835] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0836] In modern transportation, congestion often makes it difficult for users to travel efficiently and comfortably. Congestion is particularly severe during certain times of the day, such as rush hour and tourist season, and users face overcrowded trains and road congestion. Such congestion can be stressful for users, causing travel delays and forcing them to change their plans. Furthermore, congestion poses challenges for transportation agencies and road operators, as it can lead to reduced service quality and make operation management more difficult. Therefore, there is a need for a system that can predict congestion in real time and suggest optimal travel methods and times for users.

[0837] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0838] In this invention, the server includes means for a user to input a departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities and obtaining current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative artificial intelligence, means for proposing optimal departure times and vehicles based on the prediction results, means for transmitting the proposal results to a user terminal, means for displaying the proposal results to the user, and means for using past data and real-time data to predict congestion levels for multiple time periods, thereby enabling a user to select the optimal transportation means and time to avoid congestion in real time.

[0839] "User" refers to an individual user who uses the system to search for transportation travel information and receive suggestions on the best travel method and time.

[0840] "Start point" refers to the location where the user begins their journey.

[0841] "Destination" refers to the location where the user completes their journey.

[0842] "Desired departure time" refers to the time at which the user wishes to begin their journey.

[0843] "Server" refers to the central computing system that analyzes information submitted by users, obtains real-time data, performs congestion predictions, and generates and transmits proposal results.

[0844] "User terminal" refers to the device that a user uses to operate a transportation search app, and is typically a mobile device such as a smartphone or tablet.

[0845] A "real-time transportation database" refers to a database that holds the latest information about transportation, such as current congestion status, delay information, and availability information.

[0846] "Generative AI" refers to an AI model that has the ability to predict future congestion situations using past and real-time data.

[0847] "Congestion prediction" refers to the process in which generative artificial intelligence analyzes past and real-time data to predict future congestion conditions on public transport at specific times of the day.

[0848] "Proposal Report" refers to a document of proposals including the optimal departure time and vehicle for the user, created by the server based on the results of congestion predictions made by the generative artificial intelligence.

[0849] "Multiple modes of transportation" refers to multiple different modes of public transportation, such as trains and buses, that a user may use for travel.

[0850] "Data integration" refers to the process of centrally managing and comprehensively analyzing information obtained from multiple data sources.

[0851] System Overview

[0852] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, a server connects to a real-time database of transportation services based on that data, uses generative artificial intelligence to predict congestion, and suggests the optimal departure time and vehicle. In the description of the embodiment of the invention, specific program processing, and the hardware and software used will be described.

[0853] User Operation

[0854] A user opens a transportation search application on a user device such as a smartphone or tablet and inputs the origin, destination, and desired departure time. For example, consider the following information:

[0855] Departure point: Tokyo Station

[0856] Destination: Shinjuku Station

[0857] Desired departure time: 6:00 PM

[0858] This information is sent to the server in JSON format when the user taps the "Search" button.

[0859] Server Processing

[0860] Receiving and parsing the request

[0861] The server receives the data sent by the user through an HTTP POST request. Then, the server parses the received JSON data and extracts the origin, destination, and desired departure time. This process is handled by the data analysis module in the server.

[0862] Real-time data acquisition

[0863] The server sends an API request to the transit agency's real-time database. In this particular operation, the server invokes an API endpoint such as:

[0864] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[0865] This API request allows the server to obtain real-time data including current congestion status, delay information, and availability information.

[0866] Implementing congestion predictions

[0867] Next, the server uses generative artificial intelligence (e.g., GPT-3.5) to predict congestion. The server provides the collected historical and real-time data as input to the AI ​​model, which predicts congestion over multiple time periods. Below is an example of a prompt for congestion prediction:

[0868] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[0869] The generative AI returns congestion prediction results based on this prompt, and the server analyzes these results. For example, it predicts the level of congestion for each time slot between 6:00 PM and 7:00 PM.

[0870] Generating optimal proposals

[0871] The server then proposes the optimal departure time and vehicle to the user based on the predictions made by the generative AI. This proposal is reported in the form of a report with information such as the following:

[0872] Recommended departure time: 6:30 PM

[0873] Route and vehicle: Chuo Line Rapid No. 8

[0874] Sending and displaying proposal results

[0875] The server sends the generated proposal report to the user's device. The secure protocol HTTPS is used for communication, and the data is encrypted before transmission. The user's device analyzes the proposal report received from the server and displays it to the user in an intuitive interface.

[0876] Specific examples

[0877] For example, if a user wants to travel from Tokyo Station to Shinjuku Station at 6:00 PM, they open the app on their device and enter the information above. The server receives this information, acquires real-time data, predicts congestion using generative artificial intelligence, and suggests the optimal means of transportation to the user. Finally, the server displays the suggestion to the user: "Depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[0878] This system allows users to avoid crowds and provides an efficient and comfortable travel experience.

[0879] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0880] Step 1:

[0881] The user inputs the starting point, destination, and desired departure time. Specifically, the user opens a transportation search app on a user device such as a smartphone or tablet. In the input form that appears, the user enters the following information:

[0882] Departure point: Tokyo Station

[0883] Destination: Shinjuku Station

[0884] Desired departure time: 6:00 PM

[0885] When the user taps the "Search" button, this information is sent to the server in JSON format (input).

[0886] Step 2:

[0887] The server receives the request sent by the user. The server receives the data via an HTTP POST request and parses the received JSON data. For example, the following data is extracted:

[0888] Departure point: Tokyo Station

[0889] Destination: Shinjuku Station

[0890] Desired departure time: 6:00 PM

[0891] Based on this information, the server proceeds to the next step in the process (output).

[0892] Step 3:

[0893] The server sends an API request to the transport agency's real-time database to get the current congestion, delay, and availability information. For example, it calls the following API endpoint:

[0894] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[0895] The server analyzes the information obtained from this API request and obtains the following data (input):

[0896] Current congestion: High

[0897] Delay Information: None

[0898] Vehicle availability: Limited

[0899] This information is used in the next step (output).

[0900] Step 4:

[0901] The server inputs the collected real-time and past data into a generative AI model to predict congestion. The prompt is constructed as follows:

[0902] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[0903] The congestion prediction results returned by the generative AI are in the following format (input):

[0904] 18:00: Very high

[0905] 18:15: High

[0906] 18:30: Medium

[0907] 18:45: Low

[0908] 19:00: Very low

[0909] Based on this prediction result, the optimal proposal is generated (output) in the next step.

[0910] Step 5:

[0911] The server generates optimal departure time and vehicle recommendations for the user based on the predictions of the generative AI. For example, the following recommendations are generated:

[0912] Recommended departure time: 6:30 PM

[0913] Route and vehicle: Chuo Line Rapid No. 8

[0914] This proposal report will be generated in JSON format and will look something like this (input):

[0915] json

[0916] {

[0917] "recommended_departure_time": "18:30",

[0918] "recommended_vehicle": "Chuo Line Rapid Car No. 8"

[0919] }

[0920] The generated report is sent to the user terminal (output).

[0921] Step 6:

[0922] The server sends the generated proposal report to the user terminal. The secure protocol HTTPS is used for communication, and encrypted data is sent. The user terminal receives the proposal report from the server (input).

[0923] Step 7:

[0924] The user device analyzes the received proposal report and displays it in an intuitive interface for the user. Specifically, the following information is displayed on the screen:

[0925] Recommended departure time: 6:30 PM

[0926] Route and vehicle: Chuo Line Rapid No. 8

[0927] This allows the user to select a means of transportation that avoids congestion (output).

[0928] (Application example 1)

[0929] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0930] In recent years, congestion and traffic jams on public transport have become increasingly serious, causing significant stress for users during travel. As a result, users are seeking more efficient and comfortable means of transportation. However, current systems do not adequately provide real-time congestion predictions or avoidance strategies. Furthermore, with the increasing number of autonomous vehicles, dynamic operation according to traffic conditions is required. With current technology, even if users input their departure point, destination, and desired departure time, optimal suggestions are not provided that take into account real-time congestion and traffic conditions, resulting in reduced user convenience. This issue needs to be resolved.

[0931] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0932] In this invention, the server includes: a means for a user to input their departure point, destination, and desired departure time; a means for transmitting the input information to the server; a means for analyzing the information received by the server; a means for connecting to a real-time database of transportation facilities and acquiring current congestion status, delay information, and availability information; a means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; a means for proposing an optimal departure time and vehicle; a means for transmitting the proposal results to a user terminal; a means for displaying the proposal results to the user; and a means for an autonomous vehicle to pick up the user based on the proposed optimal departure time and route. This allows users to avoid congestion and traffic jams and travel to their destination efficiently and comfortably. Furthermore, autonomous vehicles dynamically selecting optimal routes and efficiently picking up users improves traffic flow and convenience.

[0933] "Means for the user to input the departure point, destination, and desired departure time" refers to means for providing an interface for the user to input their current location, destination, and desired departure time.

[0934] The "means for transmitting input information to a server" refers to a communication means for transmitting data input by a user to a server via a network.

[0935] The "means for analyzing the information received by the server" refers to the means by which the server analyzes the information sent by the user and understands details such as the destination and departure time.

[0936] "Means for connecting to a real-time database of a transportation facility and obtaining current congestion status, delay information, and availability information" refers to a means for a server to connect to a transportation facility's database in real time and obtain the latest congestion status, delay information, and availability information.

[0937] "Means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period" refers to means for using generative AI to predict congestion conditions for multiple time periods, including the user's desired time period.

[0938] The "means of suggesting the optimal departure time and vehicle" is a means of suggesting the optimal departure time and vehicle to be used for the user based on the acquired data and the prediction results of the generative AI.

[0939] The "means for transmitting the proposal results to the user terminal" is a communication means for transmitting the proposal results generated by the server to the terminal used by the user.

[0940] The "means for displaying the proposal results to the user" refers to the means for displaying the received proposal results on the user's terminal so that the user can confirm and use the information.

[0941] "Means for an autonomous vehicle to pick you up based on the proposed optimal departure time and route" refers to means for an autonomous vehicle to pick you up at a specified location based on the optimal departure time and route predicted by the server.

[0942] This invention provides a system that allows users to travel to their destinations efficiently and comfortably by optimizing an autonomous vehicle. How this system is implemented will be described below in detail.

[0943] System Overview

[0944] The user inputs their departure point, destination, and desired departure time via a smartphone app or in-car display. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. The server then suggests the optimal departure time and route, and sends this information to the autonomous vehicle. The autonomous vehicle then picks up the user based on this suggestion. This entire process is achieved using high-precision data analysis and AI technology.

[0945] Hardware and software used

[0946] Smartphones and in-car displays: Interfaces for users to input information.

[0947] Server: A central system for receiving, analyzing, and generating AI-based predictions.

[0948] Real-time traffic database: A database that provides congestion, delay, and availability information.

[0949] Generative AI models: Custom AI models using PyTorch or TensorFlow.

[0950] Communication module: A network communication function for transmitting data between the user terminal and the server, and between the server and the autonomous vehicle.

[0951] Data processing flow

[0952] 1. User input: The user enters the departure point, destination, and desired departure time using a smartphone app or the in-car display.

[0953] 2. Data transmission: The data entered by the user is transmitted from the interface to the server.

[0954] 3. Obtaining real-time data: The server connects to the real-time traffic database and obtains current congestion, delay, and availability information.

[0955] 4. Generative AI prediction: The server uses generative AI models to predict congestion levels, potential delays, and availability across multiple time periods.

[0956] 5. Generating optimal proposals: Based on the prediction results, the server proposes the optimal departure time and vehicle route to be used.

[0957] 6. Notification of proposed results: The proposed departure time and route are sent to the user's terminal and displayed for the user to review.

[0958] 7. Dispatch of autonomous vehicles: Based on the proposed route, an autonomous vehicle is dynamically dispatched to pick up the user.

[0959] Specific examples

[0960] For example, if a user wants to travel from Station A to Station B around 6:00 PM, they would enter Station A, Station B, and the desired time of 6:00 PM into the smartphone app. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. As a result, it predicts that 6:15 PM is the best time to travel, and that car 8 of the Chuo Line Rapid train is available. The server then sends the proposal to the user's smartphone, where the user can review it. If they agree, an autonomous vehicle will come to pick them up based on the prediction.

[0961] Example prompt sentences to use

[0962] Prompt: "Predict the optimal departure time and route given the following conditions: departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data."

[0963] As described above, in order to put this invention into practice, it is necessary to build a series of systems that utilize advanced data analysis and AI technology to optimize user mobility.

[0964] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0965] Step 1:

[0966] The user inputs the departure point, destination, and desired departure time on a smartphone app or on the in-car display. The information the user inputs is the departure point, destination, and desired departure time.

[0967] Step 2:

[0968] The device sends the entered information to the server. In this step, the data entered by the user is sent to the server via the internet via a smartphone app or in-car display. Here, the user's intention is conveyed to the server as input.

[0969] Step 3:

[0970] The server analyzes the received information. In this step, the server analyzes the information submitted by the user, such as origin, destination, and desired departure time. The analysis results in an output that allows the server to understand the user's travel requirements.

[0971] Step 4:

[0972] The server connects to the real-time database of the transport agency to get the current congestion status, delay information, and availability information. Here, the server uses the API of the real-time database to collect the latest data related to the transport agency. This data is sent as input to the server, and the latest traffic information is obtained as output.

[0973] Step 5:

[0974] The server uses a generative AI model to predict congestion levels for multiple time periods, including the user's desired time period. Specifically, it combines past data and real-time data to predict congestion levels, potential delays, and availability. In this process, the server uses AI frameworks such as PyTorch and TensorFlow to make predictions using prompt statements as input. An example prompt statement is, "Predict the optimal departure time and route under the following conditions: Conditions: Departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data." The predicted results are then output.

[0975] Step 6:

[0976] The server proposes the optimal departure time and vehicle. Based on the prediction results, the server calculates the optimal departure time and vehicle to use to avoid congestion and generates a proposal. This proposal is obtained as the output.

[0977] Step 7:

[0978] The server sends the proposal results to the user's terminal. The generated proposal results are then sent via the network to the user's smartphone or in-car display, where they are input into the user's terminal and displayed.

[0979] Step 8:

[0980] The user's device displays the proposed results. The optimal departure time and vehicle are displayed on the user's device, and the user can confirm and select the information.

[0981] Step 9:

[0982] The server sends instructions to the autonomous vehicle to pick up the user based on the optimal departure time and route. After the optimal route and time are determined, the autonomous vehicle receives instructions to dynamically pick up the user based on the optimal route and time. This initiates the operation of the autonomous vehicle to pick up the user.

[0983] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0984] This invention is a system in which a user inputs their departure point, destination, and desired departure time, and the server connects to a real-time database of transportation companies to obtain information based on this information, and then uses generative AI to predict congestion and suggest the optimal departure time and vehicle.Furthermore, by combining this system with an emotion engine, the system recognizes the user's emotions and makes optimal suggestions taking into account that emotional information.

[0985] The user submits a request

[0986] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine that acquires emotional information from the user's facial expressions and voice.

[0987] The server receives and processes the request

[0988] The server receives and analyzes the request data sent from the user terminal, which includes the departure point, destination, desired departure time, and emotion information.

[0989] Real-time data acquisition and congestion prediction

[0990] The server connects to the transportation company's real-time database to retrieve current congestion, delay, and availability information related to the specified departure and destination. Generative AI then predicts congestion within the next few hours, including the desired departure time. Based on past and real-time data, the generative AI predicts congestion levels, potential delays, and availability for each time period.

[0991] Generating suggestions based on user's emotional information

[0992] The server provides the generative AI with the user's emotional information obtained by the emotion engine. The generative AI then makes adjustments based on the emotional information and suggests the optimal departure time and vehicle that takes the user's emotions into consideration. For example, if the user is stressed, it will prioritize suggestions that further avoid congestion.

[0993] Sending and displaying proposal results

[0994] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal might be displayed that says, "Depart at 6:30 PM and use car 8 of the Chuo Line Rapid." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[0995] Implementation by concrete example

[0996] For example, consider a case where a user travels from Tokyo Station to Shinjuku Station. The user inputs "Tokyo Station" and "Shinjuku Station" into the app, as well as the desired departure time of "18:00." Furthermore, the emotion engine detects that the user is feeling stressed from their facial expression (operation of the user's device). This information is then sent to the server (operation of the user's device).

[0997] The server connects to a real-time database and obtains information on congestion and delays on Chuo Line rapid trains, as well as car availability (server operation). Furthermore, it uses generative AI to predict the level of congestion for each time period and makes optimal suggestions based on emotional information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8" (server operation).

[0998] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user (operation of the user terminal). The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[0999] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[1000] The processing flow will be explained below.

[1001] Step 1:

[1002] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), and the emotion engine begins to acquire emotion information from the user's facial expressions and voice.

[1003] Step 2:

[1004] The user inputs the departure point, destination, and desired departure time and clicks the search button. At this time, the emotion engine recognizes the user's emotion and acquires emotion information. This input information and emotion information are sent from the user terminal to the server.

[1005] Step 3:

[1006] The server analyzes the request data received from the user terminal, including the departure point, destination, desired departure time, and emotion information.

[1007] Step 4:

[1008] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[1009] Step 5:

[1010] The server inputs the acquired real-time data into a generative AI to predict congestion for the next few hours, including the desired departure time. The generative AI uses past and real-time data to predict the level of congestion, potential delays, and availability for each time period.

[1011] Step 6:

[1012] The server provides the emotion information obtained from the emotion engine to the generative AI, which then adjusts the optimal suggestions based on the user's emotions. For example, if the user is stressed, the generative AI will select a less stressful time slot to generate suggestions.

[1013] Step 7:

[1014] The server generates data based on generative AI and emotion information to suggest optimal departure times and vehicles to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and take car 8 of the Chuo Line Rapid."

[1015] Step 8:

[1016] The server transmits the generated proposal data to the user terminal.

[1017] Step 9:

[1018] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[1019] In this way, users can choose more comfortable means of transportation that take emotional information into account.

[1020] Example 2

[1021] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1022] When using conventional public transport, it is difficult for users to know the congestion situation or delay information in advance, and as a result, they cannot avoid stressful situations such as crowded trains and traffic jams.In addition, personalized travel suggestions that take into account the user's emotional information are not provided, so solutions that fully consider the user's comfort have not been provided.

[1023] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for adjusting the optimal departure time and vehicle taking into account the user's emotional information, a means for connecting to a real-time database of transportation means and acquiring current congestion status, delay information, and availability information, and a means for predicting congestion for multiple time periods including the user's desired time period by utilizing generative artificial intelligence. This enables the user to receive suggestions for avoiding congestion and realizing a more comfortable and less stressful trip.

[1024] A "user" is an individual or group that uses the system to input a departure point, destination, and desired departure time and view transportation information.

[1025] The "starting point" is the point from which the user starts traveling.

[1026] A "destination" is a point where a user completes their journey.

[1027] The "desired departure time" is the specific time at which the user wishes to start traveling.

[1028] "User terminal" refers to an electronic device (e.g., smartphone, personal computer) used by a user to input data into the system and view results.

[1029] "Server" means a centralized computer system that receives and analyzes information sent by users and performs appropriate processing.

[1030] "Transportation" refers to public or private means of transportation such as trains, buses, and taxis.

[1031] A "real-time database" is a database that provides real-time information on current congestion, delays, and availability related to transportation means.

[1032] "Generative artificial intelligence" is a machine learning model that uses past and current data to make predictions and suggestions.

[1033] "Crowd prediction" refers to the process in which generative artificial intelligence predicts future congestion situations based on past and real-time data.

[1034] "Emotion information" is data indicating the emotional state of the user, such as stress or satisfaction, obtained from the user's facial expression, voice, etc.

[1035] "Proposal results" are information about optimal departure times and vehicles provided to users based on data analyzed and predicted by generative artificial intelligence.

[1036] "Crowding status" is information that indicates the current number of people using a means of transportation and how available it is.

[1037] "Delay information" is information that indicates the degree to which transportation means are not operating according to the scheduled time.

[1038] "Vacancy information" refers to information about the availability of each vehicle and seat of a means of transportation.

[1039] "Parsing" refers to the act of the server understanding the information sent by the user and converting it into the form required for the next processing step.

[1040] "Adjusting" refers to the act of the generative AI optimizing the suggestions based on the user's wishes and emotional state.

[1041] This system allows users to input their departure point, destination, and desired departure time, and then the server connects to a real-time database of transportation modes to obtain information based on this information, uses generative artificial intelligence to predict congestion, and suggests optimal departure times and vehicles. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and makes optimal suggestions based on that emotional information.

[1042] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine, which can obtain emotional information from the user's facial expressions and voice.

[1043] The server receives and analyzes the request data sent from the user device. The sent data includes the origin, destination, desired departure time, and emotion information. The server connects to a real-time database of transportation modes to obtain current congestion, delay information, and availability information related to the specified origin and destination. It then uses generative artificial intelligence (e.g., a general deep learning model) to predict congestion within the next few hours, including the desired departure time.

[1044] The generative AI predicts congestion levels, potential delays, and availability for each time period based on past and real-time data. Furthermore, the server provides the user's emotional information obtained by the emotion engine to the generative AI, which then makes adjustments based on the emotional information and suggests optimal departure times and vehicles that take the user's emotions into consideration. For example, if the user is stressed, the AI ​​will prioritize suggestions that further avoid congestion.

[1045] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal may be presented such as "Depart at 6:30 PM and take car 8 on the Chuo Line." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[1046] As a concrete example, consider the case where a user is traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00." The emotion engine then detects stress from the user's facial expression. This information is sent to the server. The server connects to a real-time database to obtain information on congestion and delays on the Chuo Line, as well as the availability of train cars. It then uses generative artificial intelligence to predict the level of congestion for each time period and makes optimal suggestions based on the emotion information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8."

[1047] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user. The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[1048] (Example prompt)

[1049] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[1050] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[1051] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1052] Step 1: User submits request

[1053] The user opens a transportation search app on their device, such as a smartphone or PC. They enter their departure point (e.g., Tokyo Station), destination (e.g., Shinjuku Station), and desired departure time (e.g., 6:00 p.m.), and click the search button. The app, which is equipped with an emotion engine, analyzes the user's facial expressions and voice in real time through the device's camera and microphone to obtain emotional information.

[1054] Specific behavior:

[1055] 1. The user enters their departure point, destination, and desired departure time into the app's input fields.

[1056] 2. The emotion engine uses the device's camera and microphone to obtain the user's emotional information.

[1057] 3. The input information and emotional information are sent to the server.

[1058] Input: departure point, destination, desired departure time, emotional information

[1059] Output: Request data sent to the server

[1060] Step 2: The server receives and processes the request

[1061] The server receives a request sent from the user terminal. The received data includes the origin, destination, desired departure time, and emotion information. This information is analyzed and converted into the form required for the next processing step.

[1062] Specific behavior:

[1063] 1. The server receives and analyzes the request data.

[1064] 2. Store the parsed data in variables (origin, destination, desired departure time, emotion information).

[1065] Input: Request data (origin, destination, desired departure time, emotional information)

[1066] Output: Parsed data (stored in a variable)

[1067] Step 3: Acquire and analyze real-time data

[1068] The server connects to a real-time database of transportation modes, retrieving current congestion, delay, and availability information related to the specified origin and destination, and then analyzing and organizing the retrieved data.

[1069] Specific behavior:

[1070] 1. The server connects to the specified API endpoint.

[1071] 2. Obtain real-time data (crowding, delay information, availability information) for the specified departure and destination.

[1072] 3. Analyze the acquired data and extract and organize the necessary information.

[1073] Input: Departure point, Destination

[1074] Output: Real-time data (congestion status, delay information, availability information)

[1075] Step 4: Congestion prediction using generative AI

[1076] The server uses generative artificial intelligence to predict congestion within the next few hours, including the desired departure time, based on past and real-time data. It also predicts the level of congestion, potential delays, and availability for each time slot.

[1077] Specific behavior:

[1078] 1. The server inputs past data and acquired real-time data into the generative artificial intelligence.

[1079] 2. Generative AI analyzes the data and predicts congestion during a specific time period (for example, between 6:00 PM and 9:00 PM).

[1080] Input: Historical data, real-time data

[1081] Output: Congestion forecast data (congestion level for each time period, possibility of delay, availability)

[1082] Step 5: Generate suggestions taking into account user's emotional information

[1083] The server provides the user's emotional information obtained from the emotion engine to the generative artificial intelligence, which takes the emotional information into consideration and selects the optimal departure time and vehicle to reduce the user's stress.

[1084] Specific behavior:

[1085] 1. The server inputs the user's emotional information into the generative AI.

[1086] 2. Generative AI takes emotional information into account and generates optimal suggestions based on congestion prediction data.

[1087] Input: Emotional information, congestion prediction data

[1088] Output: Optimal departure time and vehicle suggestions

[1089] Step 6: Submit and view the proposal results

[1090] The server sends the generated proposal results to the user terminal, which analyzes the proposal results and displays the optimal departure time and vehicle information to the user.

[1091] Specific behavior:

[1092] 1. The server sends the proposal results in JSON format to the user device.

[1093] 2. The user device analyzes the suggestion results and displays on the screen, "Please use car 8 on the Chuo Line at 6:30 p.m."

[1094] Input: Proposal results (optimal departure time and vehicle)

[1095] Output: Suggestion results displayed on the user's device

[1096] Example prompt:

[1097] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[1098] This system suggests optimal transportation methods that avoid crowds to users, enabling them to travel more comfortably and with less stress.

[1099] (Application example 2)

[1100] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1101] In modern transportation, users often experience stress due to congestion and delays. Conventional navigation systems and transportation suggestion systems provide optimal suggestions based on real-time congestion and delay information, but do not take into account the user's emotional state. As a result, users may travel without feeling fully comfortable. Furthermore, it is difficult to integrate and analyze data from multiple transportation modes, making it difficult to propose efficient transportation options. Therefore, there is a need for a system that takes into account the user's emotional state and suggests more comfortable and efficient transportation options.

[1102] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities to obtain current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative AI, means for proposing optimal departure times and transportation modes, means for acquiring the user's emotional information using an emotion recognition engine, means for adjusting the proposal results based on the acquired emotional information, means for transmitting the adjusted proposal results to the user terminal, and means for displaying the proposal results to the user. This not only enables the user to avoid congestion and delays, but also enables the user to receive suggestions for comfortable transportation modes that take into account their current emotional state.

[1103] "User" refers to a person who uses the system to input a departure point, destination, and desired departure time.

[1104] "Start point" refers to the point where the user starts their journey.

[1105] "Destination" refers to the point where the user ends their journey.

[1106] "Desired departure time" refers to the time at which the user wishes to start traveling.

[1107] "Server" refers to a computer system that receives and analyzes information sent by users.

[1108] "Real-time transportation database" refers to a database that provides current congestion, delay, and availability information.

[1109] "Generative AI" refers to artificial intelligence that predicts congestion based on past and current data.

[1110] "Congestion prediction" refers to the prediction made by generative AI of the level of congestion, possibility of delays, and availability at each time slot.

[1111] The "optimal departure time" refers to the most suitable time for the user to start traveling, determined in consideration of congestion forecasts and the user's emotional information.

[1112] "Means of transportation" refers to the means of transportation used by the user, such as public transport or automobiles.

[1113] An "emotion recognition engine" refers to a system that acquires emotional information from a user's facial expressions and voice.

[1114] "Emotion information" refers to the user's emotional state (stress, relaxation, etc.) acquired by the emotion recognition engine.

[1115] "Proposal result" refers to information about the optimal departure time and transportation means provided to the user by the server.

[1116] "User terminal" refers to a device used by a user, such as a smartphone or an in-vehicle display.

[1117] To implement this invention, the following system configuration is required: The system is configured using a server, a user terminal, a real-time database of transportation, a generative AI model, and an emotion recognition engine.

[1118] Hardware and software used

[1119] Hardware:

[1120] Smartphones and in-car displays (devices where users input their departure point, destination, and desired departure time)

[1121] Camera and microphone (used by the emotion recognition engine to capture the user's facial expressions and voice information)

[1122] Server (the central system that processes all data)

[1123] software:

[1124] Navigation applications (where users enter information and receive suggested results)

[1125] Emotion recognition engine (a system that acquires user emotional information)

[1126] Real-time transport data API (obtaining congestion status, delay information, and availability information)

[1127] Generative AI model (artificial intelligence model for congestion prediction)

[1128] Data processing and calculation

[1129] 1. Processing on the user terminal side

[1130] Users input their departure point, destination, and desired departure time using a smartphone or in-car display, and the emotion recognition engine then captures the user's emotional information through the camera and microphone.

[1131] The user terminal transmits this information to the server.

[1132] 2. Server-side processing

[1133] The server receives and analyzes the data sent from the user's device. The server connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[1134] Generative AI models are used to predict congestion levels, potential delays, and availability at each time of day.

[1135] Based on the user's emotional information obtained from the emotion recognition engine, the system proposes the optimal departure time and transportation method, adjusted by a generative AI model.

[1136] The adjusted proposal results are sent back to the user terminal.

[1137] 3. Processing on the user terminal side

[1138] The user device receives the proposed results sent from the server and displays them to the user, who can then select the optimal means of transportation that takes into account their current emotional state.

[1139] Specific examples

[1140] For example, consider the case where User A travels from Tokyo Station to Shinjuku Station in an autonomous vehicle. User A enters "Tokyo Station" and "Shinjuku Station" as well as the desired arrival time of "19:00" into his smartphone and sets it to automatically determine the departure time. From information acquired through the camera and microphone, the system detects that User A is feeling stressed. The server uses a generative AI model to propose an optimal route and departure time (17:45) based on congestion predictions and emotional information, and sends the results to User A's smartphone. User A can then review the proposal and choose a more comfortable and efficient mode of transportation.

[1141] Prompt Sentence Examples

[1142] To help a user travel from Tokyo Station to Shinjuku Station, please consider their emotional information and suggest the optimal route and departure time. The user is currently in a stressful state and their desired arrival time is 7:00 PM. Please use past and current traffic data to predict congestion, and then generate suggestions by integrating the prediction results with the user's emotional information.

[1143] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1144] Program processing flow

[1145] Step 1:

[1146] The user inputs the departure point, destination, and desired departure time into a smartphone or in-car display. At this time, the camera and microphone are used to capture the user's emotional information (e.g., stress, relaxation). This input information is sent from the user's device to the server.

[1147] Input: departure point, destination, desired departure time, user emotion information

[1148] Output: Request data sent to the server

[1149] Specific operation: Information is entered into an input form on a smartphone or in-car display, and the emotion recognition engine uses the camera and microphone to capture emotional information. Press the send button to send the information to the server.

[1150] Step 2:

[1151] The server receives and analyzes the request data sent from the user terminal, and also connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[1152] Input: Request data, data from transit agency real-time database

[1153] Output: Current congestion status, delay information, availability information

[1154] Specific operation: The server analyzes the request data and extracts the necessary information. It connects to the transportation company's real-time database API to retrieve the data. The retrieved data is then classified into congestion status, delay information, and availability information.

[1155] Step 3:

[1156] The server uses a generative AI model to predict congestion for multiple time periods, including the desired time slot, based on past and current traffic data, while also taking into account emotional information obtained from an emotion recognition engine.

[1157] Input: congestion status, delay information, availability information, past traffic data, user emotion information

[1158] Output: Congestion forecast results for each time period

[1159] How it works: The generative AI model uses past and current data to predict congestion levels at each time of day, adjusting the predictions based on emotional information obtained from the emotion recognition engine.

[1160] Step 4:

[1161] The server then proposes optimal departure times and modes of transportation to the user based on the congestion prediction results and emotion information. These proposals are then sent back to the user's device.

[1162] Input: Congestion prediction results, emotion information

[1163] Output: Recommendations for optimal departure time and transportation

[1164] Specific operation: Based on the adjusted prediction results, the generative AI model calculates the optimal departure time and transportation method, generates the proposed results as data, and sends it to the user's device.

[1165] Step 5:

[1166] The user terminal receives the proposed results sent from the server and displays them to the user, who can then select the most comfortable and efficient means of transportation based on the proposed results.

[1167] Input: Suggestion results from the server

[1168] Output: The suggested results that are displayed to the user

[1169] Specific operation: The user device receives the proposed results and displays them on the screen. The user checks the results and selects the most suitable transportation method for them.

[1170] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1171] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1172] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1173] [Fourth embodiment]

[1174] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1175] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1176] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1177] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1178] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1179] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1180] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1181] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1182] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1183] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1184] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1185] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1186] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1187] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, the server connects to a real-time database of transportation companies based on that data, uses generative AI to predict congestion, and suggests the optimal departure time and vehicle.

[1188] The user submits a request

[1189] A user uses a transportation search app to input their departure point, destination, and desired departure time. For example, the user inputs "Tokyo Station" as the departure point, "Shinjuku Station" as the destination, and "6:00 PM" as the desired departure time. This information is sent from the user's device to the server.

[1190] The server receives and processes the request

[1191] The server receives the request sent by the user, analyzes the received information, and accesses the transportation company's real-time database to obtain current congestion status, delay information, and availability information.

[1192] Congestion prediction and optimal proposal generation

[1193] The server uses generative AI to predict congestion for multiple time periods, including the desired departure time specified by the user. The generative AI uses past and real-time data to predict the level of congestion, the possibility of delays, and availability for each time period. Based on these predictions, the server proposes the optimal departure time and vehicle to the user. For example, if the user's desired time of 18:00 is very crowded, the server generates a proposal to change the departure time to 18:30 and use an available car on the Chuo Line Rapid (e.g., car 8).

[1194] Sending and displaying proposal results

[1195] The server sends the generated proposal results to the user's terminal. The user's terminal receives the proposal results and displays the optimal departure time and vehicle information for the user. For example, the user receives a proposal to "depart at 6:30 PM and use car 8 of the Chuo Line Rapid."

[1196] Implementation by concrete example

[1197] For example, consider a user traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00" (user device operation). This information is sent to the server. The server connects to a real-time database to obtain congestion information, delay information, and car availability for the Chuo Line Rapid (server operation). It then uses generative AI to predict the congestion level for each time period and suggests the optimal departure time and car (server operation). Finally, the server generates a suggestion to "depart at 18:30 and use car 8" and sends it to the user's device (server operation). The user's device displays this suggestion to the user, allowing them to travel in a way that avoids crowds.

[1198] This system is extremely useful, not only because it allows users to avoid crowded trains and traffic jams, but also because it allows service providers to manage their resources more efficiently.

[1199] The processing flow will be explained below.

[1200] Step 1:

[1201] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), etc.

[1202] Step 2:

[1203] The user inputs the departure point, destination, and desired departure time, and clicks the search button. This input information is sent to the server by the user terminal.

[1204] Step 3:

[1205] The server analyzes the request data received from the user terminal, including the origin, destination, and desired departure time.

[1206] Step 4:

[1207] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[1208] Step 5:

[1209] The server inputs the acquired real-time data into a generative AI to predict congestion levels for the next few hours, including the desired departure time. The generative AI then predicts congestion levels, possible delays, and availability for each time period.

[1210] Step 6:

[1211] Based on the predictions made by the generative AI, the server generates data to suggest optimal departure times and train cars to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and use car 8 of the Chuo Line Rapid."

[1212] Step 7:

[1213] The server transmits the generated proposal data to the user terminal.

[1214] Step 8:

[1215] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[1216] In this way, users can choose the most suitable means of transportation that avoids congestion.

[1217] Example 1

[1218] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1219] In modern transportation, congestion often makes it difficult for users to travel efficiently and comfortably. Congestion is particularly severe during certain times of the day, such as rush hour and tourist season, and users face overcrowded trains and road congestion. Such congestion can be stressful for users, causing travel delays and forcing them to change their plans. Furthermore, congestion poses challenges for transportation agencies and road operators, as it can lead to reduced service quality and make operation management more difficult. Therefore, there is a need for a system that can predict congestion in real time and suggest optimal travel methods and times for users.

[1220] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1221] In this invention, the server includes means for a user to input a departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities and obtaining current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative artificial intelligence, means for proposing optimal departure times and vehicles based on the prediction results, means for transmitting the proposal results to a user terminal, means for displaying the proposal results to the user, and means for using past data and real-time data to predict congestion levels for multiple time periods, thereby enabling a user to select the optimal transportation means and time to avoid congestion in real time.

[1222] "User" refers to an individual user who uses the system to search for transportation travel information and receive suggestions on the best travel method and time.

[1223] "Start point" refers to the location where the user begins their journey.

[1224] "Destination" refers to the location where the user completes their journey.

[1225] "Desired departure time" refers to the time at which the user wishes to begin their journey.

[1226] "Server" refers to the central computing system that analyzes information submitted by users, obtains real-time data, performs congestion predictions, and generates and transmits proposal results.

[1227] "User terminal" refers to the device that a user uses to operate a transportation search app, and is typically a mobile device such as a smartphone or tablet.

[1228] A "real-time transportation database" refers to a database that holds the latest information about transportation, such as current congestion status, delay information, and availability information.

[1229] "Generative AI" refers to an AI model that has the ability to predict future congestion situations using past and real-time data.

[1230] "Congestion prediction" refers to the process in which generative artificial intelligence analyzes past and real-time data to predict future congestion conditions on public transport at specific times of the day.

[1231] "Proposal Report" refers to a document of proposals including the optimal departure time and vehicle for the user, created by the server based on the results of congestion predictions made by the generative artificial intelligence.

[1232] "Multiple modes of transportation" refers to multiple different modes of public transportation, such as trains and buses, that a user may use for travel.

[1233] "Data integration" refers to the process of centrally managing and comprehensively analyzing information obtained from multiple data sources.

[1234] System Overview

[1235] This invention is a system in which, when a user inputs their departure point, destination, and desired departure time, a server connects to a real-time database of transportation services based on that data, uses generative artificial intelligence to predict congestion, and suggests the optimal departure time and vehicle. In the description of the embodiment of the invention, specific program processing, and the hardware and software used will be described.

[1236] User Operation

[1237] A user opens a transportation search application on a user device such as a smartphone or tablet and inputs the origin, destination, and desired departure time. For example, consider the following information:

[1238] Departure point: Tokyo Station

[1239] Destination: Shinjuku Station

[1240] Desired departure time: 6:00 PM

[1241] This information is sent to the server in JSON format when the user taps the "Search" button.

[1242] Server Processing

[1243] Receiving and parsing the request

[1244] The server receives the data sent by the user through an HTTP POST request. Then, the server parses the received JSON data and extracts the origin, destination, and desired departure time. This process is handled by the data analysis module in the server.

[1245] Real-time data acquisition

[1246] The server sends an API request to the transit agency's real-time database. In this particular operation, the server invokes an API endpoint such as:

[1247] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[1248] This API request allows the server to obtain real-time data including current congestion status, delay information, and availability information.

[1249] Implementing congestion predictions

[1250] Next, the server uses generative artificial intelligence (e.g., GPT-3.5) to predict congestion. The server provides the collected historical and real-time data as input to the AI ​​model, which predicts congestion over multiple time periods. Below is an example of a prompt for congestion prediction:

[1251] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[1252] The generative AI returns congestion prediction results based on this prompt, and the server analyzes these results. For example, it predicts the level of congestion for each time slot between 6:00 PM and 7:00 PM.

[1253] Generating optimal proposals

[1254] The server then proposes the optimal departure time and vehicle to the user based on the predictions made by the generative AI. This proposal is reported in the form of a report with information such as the following:

[1255] Recommended departure time: 6:30 PM

[1256] Route and vehicle: Chuo Line Rapid No. 8

[1257] Sending and displaying proposal results

[1258] The server sends the generated proposal report to the user's device. The secure protocol HTTPS is used for communication, and the data is encrypted before transmission. The user's device analyzes the proposal report received from the server and displays it to the user in an intuitive interface.

[1259] Specific examples

[1260] For example, if a user wants to travel from Tokyo Station to Shinjuku Station at 6:00 PM, they open the app on their device and enter the information above. The server receives this information, acquires real-time data, predicts congestion using generative artificial intelligence, and suggests the optimal means of transportation to the user. Finally, the server displays the suggestion to the user: "Depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[1261] This system allows users to avoid crowds and provides an efficient and comfortable travel experience.

[1262] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1263] Step 1:

[1264] The user inputs the starting point, destination, and desired departure time. Specifically, the user opens a transportation search app on a user device such as a smartphone or tablet. In the input form that appears, the user enters the following information:

[1265] Departure point: Tokyo Station

[1266] Destination: Shinjuku Station

[1267] Desired departure time: 6:00 PM

[1268] When the user taps the "Search" button, this information is sent to the server in JSON format (input).

[1269] Step 2:

[1270] The server receives the request sent by the user. The server receives the data via an HTTP POST request and parses the received JSON data. For example, the following data is extracted:

[1271] Departure point: Tokyo Station

[1272] Destination: Shinjuku Station

[1273] Desired departure time: 6:00 PM

[1274] Based on this information, the server proceeds to the next step in the process (output).

[1275] Step 3:

[1276] The server sends an API request to the transport agency's real-time database to get the current congestion, delay, and availability information. For example, it calls the following API endpoint:

[1277] GET / api / transport / status?departure_area=Tokyo Station&destination_area=Shinjuku Station

[1278] The server analyzes the information obtained from this API request and obtains the following data (input):

[1279] Current congestion: High

[1280] Delay Information: None

[1281] Vehicle availability: Limited

[1282] This information is used in the next step (output).

[1283] Step 4:

[1284] The server inputs the collected real-time and past data into a generative AI model to predict congestion. The prompt is constructed as follows:

[1285] A user wants to travel from Tokyo Station to Shinjuku Station at 18:00. Based on that, please predict the congestion for each departure time between 18:00 and 19:00.

[1286] The congestion prediction results returned by the generative AI are in the following format (input):

[1287] 18:00: Very high

[1288] 18:15: High

[1289] 18:30: Medium

[1290] 18:45: Low

[1291] 19:00: Very low

[1292] Based on this prediction result, the optimal proposal is generated (output) in the next step.

[1293] Step 5:

[1294] The server generates optimal departure time and vehicle recommendations for the user based on the predictions of the generative AI. For example, the following recommendations are generated:

[1295] Recommended departure time: 6:30 PM

[1296] Route and vehicle: Chuo Line Rapid No. 8

[1297] This proposal report will be generated in JSON format and will look something like this (input):

[1298] json

[1299] {

[1300] "recommended_departure_time": "18:30",

[1301] "recommended_vehicle": "Chuo Line Rapid Car No. 8"

[1302] }

[1303] The generated report is sent to the user terminal (output).

[1304] Step 6:

[1305] The server sends the generated proposal report to the user terminal. The secure protocol HTTPS is used for communication, and encrypted data is sent. The user terminal receives the proposal report from the server (input).

[1306] Step 7:

[1307] The user device analyzes the received proposal report and displays it in an intuitive interface for the user. Specifically, the following information is displayed on the screen:

[1308] Recommended departure time: 6:30 PM

[1309] Route and vehicle: Chuo Line Rapid No. 8

[1310] This allows the user to select a means of transportation that avoids congestion (output).

[1311] (Application example 1)

[1312] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1313] In recent years, congestion and traffic jams on public transport have become increasingly serious, causing significant stress for users during travel. As a result, users are seeking more efficient and comfortable means of transportation. However, current systems do not adequately provide real-time congestion predictions or avoidance strategies. Furthermore, with the increasing number of autonomous vehicles, dynamic operation according to traffic conditions is required. With current technology, even if users input their departure point, destination, and desired departure time, optimal suggestions are not provided that take into account real-time congestion and traffic conditions, resulting in reduced user convenience. This issue needs to be resolved.

[1314] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1315] In this invention, the server includes: a means for a user to input their departure point, destination, and desired departure time; a means for transmitting the input information to the server; a means for analyzing the information received by the server; a means for connecting to a real-time database of transportation facilities and acquiring current congestion status, delay information, and availability information; a means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; a means for proposing an optimal departure time and vehicle; a means for transmitting the proposal results to a user terminal; a means for displaying the proposal results to the user; and a means for an autonomous vehicle to pick up the user based on the proposed optimal departure time and route. This allows users to avoid congestion and traffic jams and travel to their destination efficiently and comfortably. Furthermore, autonomous vehicles dynamically selecting optimal routes and efficiently picking up users improves traffic flow and convenience.

[1316] "Means for the user to input the departure point, destination, and desired departure time" refers to means for providing an interface for the user to input their current location, destination, and desired departure time.

[1317] The "means for transmitting input information to a server" refers to a communication means for transmitting data input by a user to a server via a network.

[1318] The "means for analyzing the information received by the server" refers to the means by which the server analyzes the information sent by the user and understands details such as the destination and departure time.

[1319] "Means for connecting to a real-time database of a transportation facility and obtaining current congestion status, delay information, and availability information" refers to a means for a server to connect to a transportation facility's database in real time and obtain the latest congestion status, delay information, and availability information.

[1320] "Means for utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period" refers to means for using generative AI to predict congestion conditions for multiple time periods, including the user's desired time period.

[1321] The "means of suggesting the optimal departure time and vehicle" is a means of suggesting the optimal departure time and vehicle to be used for the user based on the acquired data and the prediction results of the generative AI.

[1322] The "means for transmitting the proposal results to the user terminal" is a communication means for transmitting the proposal results generated by the server to the terminal used by the user.

[1323] The "means for displaying the proposal results to the user" refers to the means for displaying the received proposal results on the user's terminal so that the user can confirm and use the information.

[1324] "Means for an autonomous vehicle to pick you up based on the proposed optimal departure time and route" refers to means for an autonomous vehicle to pick you up at a specified location based on the optimal departure time and route predicted by the server.

[1325] This invention provides a system that allows users to travel to their destinations efficiently and comfortably by optimizing an autonomous vehicle. How this system is implemented will be described below in detail.

[1326] System Overview

[1327] The user inputs their departure point, destination, and desired departure time via a smartphone app or in-car display. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. The server then suggests the optimal departure time and route, and sends this information to the autonomous vehicle. The autonomous vehicle then picks up the user based on this suggestion. This entire process is achieved using high-precision data analysis and AI technology.

[1328] Hardware and software used

[1329] Smartphones and in-car displays: Interfaces for users to input information.

[1330] Server: A central system for receiving, analyzing, and generating AI-based predictions.

[1331] Real-time traffic database: A database that provides congestion, delay, and availability information.

[1332] Generative AI models: Custom AI models using PyTorch or TensorFlow.

[1333] Communication module: A network communication function for transmitting data between the user terminal and the server, and between the server and the autonomous vehicle.

[1334] Data processing flow

[1335] 1. User input: The user enters the departure point, destination, and desired departure time using a smartphone app or the in-car display.

[1336] 2. Data transmission: The data entered by the user is transmitted from the interface to the server.

[1337] 3. Obtaining real-time data: The server connects to the real-time traffic database and obtains current congestion, delay, and availability information.

[1338] 4. Generative AI prediction: The server uses generative AI models to predict congestion levels, potential delays, and availability across multiple time periods.

[1339] 5. Generating optimal proposals: Based on the prediction results, the server proposes the optimal departure time and vehicle route to be used.

[1340] 6. Notification of proposed results: The proposed departure time and route are sent to the user's terminal and displayed for the user to review.

[1341] 7. Dispatch of autonomous vehicles: Based on the proposed route, an autonomous vehicle is dynamically dispatched to pick up the user.

[1342] Specific examples

[1343] For example, if a user wants to travel from Station A to Station B around 6:00 PM, they would enter Station A, Station B, and the desired time of 6:00 PM into the smartphone app. This information is sent to a server, which retrieves real-time traffic data and uses generative AI to predict congestion. As a result, it predicts that 6:15 PM is the best time to travel, and that car 8 of the Chuo Line Rapid train is available. The server then sends the proposal to the user's smartphone, where the user can review it. If they agree, an autonomous vehicle will come to pick them up based on the prediction.

[1344] Example prompt sentences to use

[1345] Prompt: "Predict the optimal departure time and route given the following conditions: departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data."

[1346] As described above, in order to put this invention into practice, it is necessary to build a series of systems that utilize advanced data analysis and AI technology to optimize user mobility.

[1347] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1348] Step 1:

[1349] The user inputs the departure point, destination, and desired departure time on a smartphone app or on the in-car display. The information the user inputs is the departure point, destination, and desired departure time.

[1350] Step 2:

[1351] The device sends the entered information to the server. In this step, the data entered by the user is sent to the server via the internet via a smartphone app or in-car display. Here, the user's intention is conveyed to the server as input.

[1352] Step 3:

[1353] The server analyzes the received information. In this step, the server analyzes the information submitted by the user, such as origin, destination, and desired departure time. The analysis results in an output that allows the server to understand the user's travel requirements.

[1354] Step 4:

[1355] The server connects to the real-time database of the transport agency to get the current congestion status, delay information, and availability information. Here, the server uses the API of the real-time database to collect the latest data related to the transport agency. This data is sent as input to the server, and the latest traffic information is obtained as output.

[1356] Step 5:

[1357] The server uses a generative AI model to predict congestion levels for multiple time periods, including the user's desired time period. Specifically, it combines past data and real-time data to predict congestion levels, potential delays, and availability. In this process, the server uses AI frameworks such as PyTorch and TensorFlow to make predictions using prompt statements as input. An example prompt statement is, "Predict the optimal departure time and route under the following conditions: Conditions: Departure point = Station A, destination = Station B, desired time = 18:00, past congestion data, current traffic data." The predicted results are then output.

[1358] Step 6:

[1359] The server proposes the optimal departure time and vehicle. Based on the prediction results, the server calculates the optimal departure time and vehicle to use to avoid congestion and generates a proposal. This proposal is obtained as the output.

[1360] Step 7:

[1361] The server sends the proposal results to the user's terminal. The generated proposal results are then sent via the network to the user's smartphone or in-car display, where they are input into the user's terminal and displayed.

[1362] Step 8:

[1363] The user's device displays the proposed results. The optimal departure time and vehicle are displayed on the user's device, and the user can confirm and select the information.

[1364] Step 9:

[1365] The server sends instructions to the autonomous vehicle to pick up the user based on the optimal departure time and route. After the optimal route and time are determined, the autonomous vehicle receives instructions to dynamically pick up the user based on the optimal route and time. This initiates the operation of the autonomous vehicle to pick up the user.

[1366] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1367] This invention is a system in which a user inputs their departure point, destination, and desired departure time, and the server connects to a real-time database of transportation companies to obtain information based on this information, and then uses generative AI to predict congestion and suggest the optimal departure time and vehicle.Furthermore, by combining this system with an emotion engine, the system recognizes the user's emotions and makes optimal suggestions taking into account that emotional information.

[1368] The user submits a request

[1369] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine that acquires emotional information from the user's facial expressions and voice.

[1370] The server receives and processes the request

[1371] The server receives and analyzes the request data sent from the user terminal, which includes the departure point, destination, desired departure time, and emotion information.

[1372] Real-time data acquisition and congestion prediction

[1373] The server connects to the transportation company's real-time database to retrieve current congestion, delay, and availability information related to the specified departure and destination. Generative AI then predicts congestion within the next few hours, including the desired departure time. Based on past and real-time data, the generative AI predicts congestion levels, potential delays, and availability for each time period.

[1374] Generating suggestions based on user's emotional information

[1375] The server provides the generative AI with the user's emotional information obtained by the emotion engine. The generative AI then makes adjustments based on the emotional information and suggests the optimal departure time and vehicle that takes the user's emotions into consideration. For example, if the user is stressed, it will prioritize suggestions that further avoid congestion.

[1376] Sending and displaying proposal results

[1377] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal might be displayed that says, "Depart at 6:30 PM and use car 8 of the Chuo Line Rapid." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[1378] Implementation by concrete example

[1379] For example, consider a case where a user travels from Tokyo Station to Shinjuku Station. The user inputs "Tokyo Station" and "Shinjuku Station" into the app, as well as the desired departure time of "18:00." Furthermore, the emotion engine detects that the user is feeling stressed from their facial expression (operation of the user's device). This information is then sent to the server (operation of the user's device).

[1380] The server connects to a real-time database and obtains information on congestion and delays on Chuo Line rapid trains, as well as car availability (server operation). Furthermore, it uses generative AI to predict the level of congestion for each time period and makes optimal suggestions based on emotional information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8" (server operation).

[1381] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user (operation of the user terminal). The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[1382] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[1383] The processing flow will be explained below.

[1384] Step 1:

[1385] The user terminal displays an interface for the user to input the departure point (e.g., "Tokyo Station"), destination (e.g., "Shinjuku Station"), and desired departure time (e.g., "18:00"), and the emotion engine begins to acquire emotion information from the user's facial expressions and voice.

[1386] Step 2:

[1387] The user inputs the departure point, destination, and desired departure time and clicks the search button. At this time, the emotion engine recognizes the user's emotion and acquires emotion information. This input information and emotion information are sent from the user terminal to the server.

[1388] Step 3:

[1389] The server analyzes the request data received from the user terminal, including the departure point, destination, desired departure time, and emotion information.

[1390] Step 4:

[1391] The server connects to the transportation agency's real-time database and retrieves current congestion, delay, and availability information related to the specified origin and destination via API requests.

[1392] Step 5:

[1393] The server inputs the acquired real-time data into a generative AI to predict congestion for the next few hours, including the desired departure time. The generative AI uses past and real-time data to predict the level of congestion, potential delays, and availability for each time period.

[1394] Step 6:

[1395] The server provides the emotion information obtained from the emotion engine to the generative AI, which then adjusts the optimal suggestions based on the user's emotions. For example, if the user is stressed, the generative AI will select a less stressful time slot to generate suggestions.

[1396] Step 7:

[1397] The server generates data based on generative AI and emotion information to suggest optimal departure times and vehicles to users. For example, it might suggest, "Since 18:00 is crowded, depart at 18:30 and take car 8 of the Chuo Line Rapid."

[1398] Step 8:

[1399] The server transmits the generated proposal data to the user terminal.

[1400] Step 9:

[1401] The user device analyzes the recommendations received from the server and displays the optimal departure time and vehicle information for the user. For example, it displays a recommendation to "depart at 6:30 PM and take car 8 of the Chuo Line Rapid."

[1402] In this way, users can choose more comfortable means of transportation that take emotional information into account.

[1403] Example 2

[1404] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1405] When using conventional public transport, it is difficult for users to know the congestion situation or delay information in advance, and as a result, they cannot avoid stressful situations such as crowded trains and traffic jams.In addition, personalized travel suggestions that take into account the user's emotional information are not provided, so solutions that fully consider the user's comfort have not been provided.

[1406] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for adjusting the optimal departure time and vehicle taking into account the user's emotional information, a means for connecting to a real-time database of transportation means and acquiring current congestion status, delay information, and availability information, and a means for predicting congestion for multiple time periods including the user's desired time period by utilizing generative artificial intelligence. This enables the user to receive suggestions for avoiding congestion and realizing a more comfortable and less stressful trip.

[1407] A "user" is an individual or group that uses the system to input a departure point, destination, and desired departure time and view transportation information.

[1408] The "starting point" is the point from which the user starts traveling.

[1409] A "destination" is a point where a user completes their journey.

[1410] The "desired departure time" is the specific time at which the user wishes to start traveling.

[1411] "User terminal" refers to an electronic device (e.g., smartphone, personal computer) used by a user to input data into the system and view results.

[1412] "Server" means a centralized computer system that receives and analyzes information sent by users and performs appropriate processing.

[1413] "Transportation" refers to public or private means of transportation such as trains, buses, and taxis.

[1414] A "real-time database" is a database that provides real-time information on current congestion, delays, and availability related to transportation means.

[1415] "Generative artificial intelligence" is a machine learning model that uses past and current data to make predictions and suggestions.

[1416] "Crowd prediction" refers to the process in which generative artificial intelligence predicts future congestion situations based on past and real-time data.

[1417] "Emotion information" is data indicating the emotional state of the user, such as stress or satisfaction, obtained from the user's facial expression, voice, etc.

[1418] "Proposal results" are information about optimal departure times and vehicles provided to users based on data analyzed and predicted by generative artificial intelligence.

[1419] "Crowding status" is information that indicates the current number of people using a means of transportation and how available it is.

[1420] "Delay information" is information that indicates the degree to which transportation means are not operating according to the scheduled time.

[1421] "Vacancy information" refers to information about the availability of each vehicle and seat of a means of transportation.

[1422] "Parsing" refers to the act of the server understanding the information sent by the user and converting it into the form required for the next processing step.

[1423] "Adjusting" refers to the act of the generative AI optimizing the suggestions based on the user's wishes and emotional state.

[1424] This system allows users to input their departure point, destination, and desired departure time, and then the server connects to a real-time database of transportation modes to obtain information based on this information, uses generative artificial intelligence to predict congestion, and suggests optimal departure times and vehicles. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and makes optimal suggestions based on that emotional information.

[1425] Users use a transportation search app on their device, such as a smartphone or PC. They input their departure point, destination, and desired departure time, and send a request to the server. The app also incorporates an emotion engine, which can obtain emotional information from the user's facial expressions and voice.

[1426] The server receives and analyzes the request data sent from the user device. The sent data includes the origin, destination, desired departure time, and emotion information. The server connects to a real-time database of transportation modes to obtain current congestion, delay information, and availability information related to the specified origin and destination. It then uses generative artificial intelligence (e.g., a general deep learning model) to predict congestion within the next few hours, including the desired departure time.

[1427] The generative AI predicts congestion levels, potential delays, and availability for each time period based on past and real-time data. Furthermore, the server provides the user's emotional information obtained by the emotion engine to the generative AI, which then makes adjustments based on the emotional information and suggests optimal departure times and vehicles that take the user's emotions into consideration. For example, if the user is stressed, the AI ​​will prioritize suggestions that further avoid congestion.

[1428] The server sends the generated proposal results to the user's device. The user's device analyzes the proposal results and displays the optimal departure time and vehicle information to the user. For example, a proposal may be presented such as "Depart at 6:30 PM and take car 8 on the Chuo Line." By receiving proposals based on emotional information, the user can select a more comfortable means of transportation.

[1429] As a concrete example, consider the case where a user is traveling from Tokyo Station to Shinjuku Station. The user enters "Tokyo Station" and "Shinjuku Station" into the app, along with the desired departure time of "18:00." The emotion engine then detects stress from the user's facial expression. This information is sent to the server. The server connects to a real-time database to obtain information on congestion and delays on the Chuo Line, as well as the availability of train cars. It then uses generative artificial intelligence to predict the level of congestion for each time period and makes optimal suggestions based on the emotion information. For example, it generates a suggestion such as, "Since 18:00 is crowded, depart at 18:30 and use car 8."

[1430] Finally, the server sends the generated suggestions to the user's terminal, which then displays the suggestions to the user. The user receives suggestions based on emotion information, allowing them to avoid congestion and travel with less stress.

[1431] (Example prompt)

[1432] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[1433] This system not only allows users to avoid crowded trains and traffic jams, but also enables service providers to manage resources more efficiently, and by taking into account users' emotional information, it can provide more personalized services.

[1434] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1435] Step 1: User submits request

[1436] The user opens a transportation search app on their device, such as a smartphone or PC. They enter their departure point (e.g., Tokyo Station), destination (e.g., Shinjuku Station), and desired departure time (e.g., 6:00 p.m.), and click the search button. The app, which is equipped with an emotion engine, analyzes the user's facial expressions and voice in real time through the device's camera and microphone to obtain emotional information.

[1437] Specific behavior:

[1438] 1. The user enters their departure point, destination, and desired departure time into the app's input fields.

[1439] 2. The emotion engine uses the device's camera and microphone to obtain the user's emotional information.

[1440] 3. The input information and emotional information are sent to the server.

[1441] Input: departure point, destination, desired departure time, emotional information

[1442] Output: Request data sent to the server

[1443] Step 2: The server receives and processes the request

[1444] The server receives a request sent from the user terminal. The received data includes the origin, destination, desired departure time, and emotion information. This information is analyzed and converted into the form required for the next processing step.

[1445] Specific behavior:

[1446] 1. The server receives and analyzes the request data.

[1447] 2. Store the parsed data in variables (origin, destination, desired departure time, emotion information).

[1448] Input: Request data (origin, destination, desired departure time, emotional information)

[1449] Output: Parsed data (stored in a variable)

[1450] Step 3: Acquire and analyze real-time data

[1451] The server connects to a real-time database of transportation modes, retrieving current congestion, delay, and availability information related to the specified origin and destination, and then analyzing and organizing the retrieved data.

[1452] Specific behavior:

[1453] 1. The server connects to the specified API endpoint.

[1454] 2. Obtain real-time data (crowding, delay information, availability information) for the specified departure and destination.

[1455] 3. Analyze the acquired data and extract and organize the necessary information.

[1456] Input: Departure point, Destination

[1457] Output: Real-time data (congestion status, delay information, availability information)

[1458] Step 4: Congestion prediction using generative AI

[1459] The server uses generative artificial intelligence to predict congestion within the next few hours, including the desired departure time, based on past and real-time data. It also predicts the level of congestion, potential delays, and availability for each time slot.

[1460] Specific behavior:

[1461] 1. The server inputs past data and acquired real-time data into the generative artificial intelligence.

[1462] 2. Generative AI analyzes the data and predicts congestion during a specific time period (for example, between 6:00 PM and 9:00 PM).

[1463] Input: Historical data, real-time data

[1464] Output: Congestion forecast data (congestion level for each time period, possibility of delay, availability)

[1465] Step 5: Generate suggestions taking into account user's emotional information

[1466] The server provides the user's emotional information obtained from the emotion engine to the generative artificial intelligence, which takes the emotional information into consideration and selects the optimal departure time and vehicle to reduce the user's stress.

[1467] Specific behavior:

[1468] 1. The server inputs the user's emotional information into the generative AI.

[1469] 2. Generative AI takes emotional information into account and generates optimal suggestions based on congestion prediction data.

[1470] Input: Emotional information, congestion prediction data

[1471] Output: Optimal departure time and vehicle suggestions

[1472] Step 6: Submit and view the proposal results

[1473] The server sends the generated proposal results to the user terminal, which analyzes the proposal results and displays the optimal departure time and vehicle information to the user.

[1474] Specific behavior:

[1475] 1. The server sends the proposal results in JSON format to the user device.

[1476] 2. The user device analyzes the suggestion results and displays on the screen, "Please use car 8 on the Chuo Line at 6:30 p.m."

[1477] Input: Proposal results (optimal departure time and vehicle)

[1478] Output: Suggestion results displayed on the user's device

[1479] Example prompt:

[1480] The user wants to travel from Tokyo Station to Shinjuku Station. The desired departure time is 18:00, but the user is currently feeling stressed. Based on the current congestion situation and delay information, please suggest the optimal departure time and vehicle to avoid congestion.

[1481] This system suggests optimal transportation methods that avoid crowds to users, enabling them to travel more comfortably and with less stress.

[1482] (Application example 2)

[1483] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1484] In modern transportation, users often experience stress due to congestion and delays. Conventional navigation systems and transportation suggestion systems provide optimal suggestions based on real-time congestion and delay information, but do not take into account the user's emotional state. As a result, users may travel without feeling fully comfortable. Furthermore, it is difficult to integrate and analyze data from multiple transportation modes, making it difficult to propose efficient transportation options. Therefore, there is a need for a system that takes into account the user's emotional state and suggests more comfortable and efficient transportation options.

[1485] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their departure point, destination, and desired departure time, means for transmitting the input information to the server, means for analyzing the information received by the server, means for connecting to a real-time database of transportation facilities to obtain current congestion status, delay information, and availability information, means for predicting congestion for multiple time periods including the user's desired time period using generative AI, means for proposing optimal departure times and transportation modes, means for acquiring the user's emotional information using an emotion recognition engine, means for adjusting the proposal results based on the acquired emotional information, means for transmitting the adjusted proposal results to the user terminal, and means for displaying the proposal results to the user. This not only enables the user to avoid congestion and delays, but also enables the user to receive suggestions for comfortable transportation modes that take into account their current emotional state.

[1486] "User" refers to a person who uses the system to input a departure point, destination, and desired departure time.

[1487] "Start point" refers to the point where the user starts their journey.

[1488] "Destination" refers to the point where the user ends their journey.

[1489] "Desired departure time" refers to the time at which the user wishes to start traveling.

[1490] "Server" refers to a computer system that receives and analyzes information sent by users.

[1491] "Real-time transportation database" refers to a database that provides current congestion, delay, and availability information.

[1492] "Generative AI" refers to artificial intelligence that predicts congestion based on past and current data.

[1493] "Congestion prediction" refers to the prediction made by generative AI of the level of congestion, possibility of delays, and availability at each time slot.

[1494] The "optimal departure time" refers to the most suitable time for the user to start traveling, determined in consideration of congestion forecasts and the user's emotional information.

[1495] "Means of transportation" refers to the means of transportation used by the user, such as public transport or automobiles.

[1496] An "emotion recognition engine" refers to a system that acquires emotional information from a user's facial expressions and voice.

[1497] "Emotion information" refers to the user's emotional state (stress, relaxation, etc.) acquired by the emotion recognition engine.

[1498] "Proposal result" refers to information about the optimal departure time and transportation means provided to the user by the server.

[1499] "User terminal" refers to a device used by a user, such as a smartphone or an in-vehicle display.

[1500] To implement this invention, the following system configuration is required: The system is configured using a server, a user terminal, a real-time database of transportation, a generative AI model, and an emotion recognition engine.

[1501] Hardware and software used

[1502] Hardware:

[1503] Smartphones and in-car displays (devices where users input their departure point, destination, and desired departure time)

[1504] Camera and microphone (used by the emotion recognition engine to capture the user's facial expressions and voice information)

[1505] Server (the central system that processes all data)

[1506] software:

[1507] Navigation applications (where users enter information and receive suggested results)

[1508] Emotion recognition engine (a system that acquires user emotional information)

[1509] Real-time transport data API (obtaining congestion status, delay information, and availability information)

[1510] Generative AI model (artificial intelligence model for congestion prediction)

[1511] Data processing and calculation

[1512] 1. Processing on the user terminal side

[1513] Users input their departure point, destination, and desired departure time using a smartphone or in-car display, and the emotion recognition engine then captures the user's emotional information through the camera and microphone.

[1514] The user terminal transmits this information to the server.

[1515] 2. Server-side processing

[1516] The server receives and analyzes the data sent from the user's device. The server connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[1517] Generative AI models are used to predict congestion levels, potential delays, and availability at each time of day.

[1518] Based on the user's emotional information obtained from the emotion recognition engine, the system proposes the optimal departure time and transportation method, adjusted by a generative AI model.

[1519] The adjusted proposal results are sent back to the user terminal.

[1520] 3. Processing on the user terminal side

[1521] The user device receives the proposed results sent from the server and displays them to the user, who can then select the optimal means of transportation that takes into account their current emotional state.

[1522] Specific examples

[1523] For example, consider the case where User A travels from Tokyo Station to Shinjuku Station in an autonomous vehicle. User A enters "Tokyo Station" and "Shinjuku Station" as well as the desired arrival time of "19:00" into his smartphone and sets it to automatically determine the departure time. From information acquired through the camera and microphone, the system detects that User A is feeling stressed. The server uses a generative AI model to propose an optimal route and departure time (17:45) based on congestion predictions and emotional information, and sends the results to User A's smartphone. User A can then review the proposal and choose a more comfortable and efficient mode of transportation.

[1524] Prompt Sentence Examples

[1525] To help a user travel from Tokyo Station to Shinjuku Station, please consider their emotional information and suggest the optimal route and departure time. The user is currently in a stressful state and their desired arrival time is 7:00 PM. Please use past and current traffic data to predict congestion, and then generate suggestions by integrating the prediction results with the user's emotional information.

[1526] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1527] Program processing flow

[1528] Step 1:

[1529] The user inputs the departure point, destination, and desired departure time into a smartphone or in-car display. At this time, the camera and microphone are used to capture the user's emotional information (e.g., stress, relaxation). This input information is sent from the user's device to the server.

[1530] Input: departure point, destination, desired departure time, user emotion information

[1531] Output: Request data sent to the server

[1532] Specific operation: Information is entered into an input form on a smartphone or in-car display, and the emotion recognition engine uses the camera and microphone to capture emotional information. Press the send button to send the information to the server.

[1533] Step 2:

[1534] The server receives and analyzes the request data sent from the user terminal, and also connects to the transportation company's real-time database to obtain information on current congestion, delays, and availability.

[1535] Input: Request data, data from transit agency real-time database

[1536] Output: Current congestion status, delay information, availability information

[1537] Specific operation: The server analyzes the request data and extracts the necessary information. It connects to the transportation company's real-time database API to retrieve the data. The retrieved data is then classified into congestion status, delay information, and availability information.

[1538] Step 3:

[1539] The server uses a generative AI model to predict congestion for multiple time periods, including the desired time slot, based on past and current traffic data, while also taking into account emotional information obtained from an emotion recognition engine.

[1540] Input: congestion status, delay information, availability information, past traffic data, user emotion information

[1541] Output: Congestion forecast results for each time period

[1542] How it works: The generative AI model uses past and current data to predict congestion levels at each time of day, adjusting the predictions based on emotional information obtained from the emotion recognition engine.

[1543] Step 4:

[1544] The server then proposes optimal departure times and modes of transportation to the user based on the congestion prediction results and emotion information. These proposals are then sent back to the user's device.

[1545] Input: Congestion prediction results, emotion information

[1546] Output: Recommendations for optimal departure time and transportation

[1547] Specific operation: Based on the adjusted prediction results, the generative AI model calculates the optimal departure time and transportation method, generates the proposed results as data, and sends it to the user's device.

[1548] Step 5:

[1549] The user terminal receives the proposed results sent from the server and displays them to the user, who can then select the most comfortable and efficient means of transportation based on the proposed results.

[1550] Input: Suggestion results from the server

[1551] Output: The suggested results that are displayed to the user

[1552] Specific operation: The user device receives the proposed results and displays them on the screen. The user checks the results and selects the most suitable transportation method for them.

[1553] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1554] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1555] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1556] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1557] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1558] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1559] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1560] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1561] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1562] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1563] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1564] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1565] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1566] 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.

[1567] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1568] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1569] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1570] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1571] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1572] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1573] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1574] The following is further disclosed regarding the above embodiment.

[1575] (Claim 1)

[1576] means for a user to input an origin, destination, and desired departure time;

[1577] means for transmitting the input information to a server;

[1578] means for analyzing the received information by the server;

[1579] A means for connecting to a real-time database of a transportation agency to obtain current congestion status, delay information, and availability information;

[1580] A means of utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; and

[1581] A means of suggesting the best departure time and vehicle;

[1582] means for transmitting the proposal results to a user terminal;

[1583] means for displaying the recommendation results to the user;

[1584] A system including:

[1585] (Claim 2)

[1586] A means for the generative AI to predict congestion, possibility of delays, and availability;

[1587] The system further includes a means for generating a suggestion that allows the user to avoid crowded trains and traffic jams based on the prediction result.

[1588] 10. The system of claim 1.

[1589] (Claim 3)

[1590] said means for connecting to said real-time database of transportation facilities;

[1591] including a means to acquire data from multiple transportation agencies and integrate and analyze that data;

[1592] 10. The system of claim 1.

[1593] "Example 1"

[1594] (Claim 1)

[1595] means for a user to input an origin, destination, and desired departure time;

[1596] means for transmitting the input information to a server;

[1597] means for analyzing the received information by the server;

[1598] A means for connecting to a real-time database of a transportation agency to obtain current congestion status, delay information, and availability information;

[1599] A means for predicting congestion for multiple time periods, including the user's desired time period, using generative artificial intelligence;

[1600] A means for proposing an optimal departure time and vehicle based on the prediction results;

[1601] means for transmitting the proposal results to a user terminal;

[1602] means for displaying the recommendation results to the user;

[1603] The system includes a means for using historical and real-time data to predict congestion levels over multiple time periods.

[1604] (Claim 2)

[1605] A means for the generative artificial intelligence to predict congestion, possibility of delays, and availability;

[1606] and means for generating a suggestion for the user to avoid crowds based on the prediction result.

[1607] 10. The system of claim 1.

[1608] (Claim 3)

[1609] The means for connecting to the real-time database of transportation facilities includes means for acquiring data from a plurality of transportation facilities and integrating and analyzing the data.

[1610] 10. The system of claim 1.

[1611] "Application Example 1"

[1612] (Claim 1)

[1613] means for a user to input an origin, destination, and desired departure time;

[1614] means for transmitting the input information to a server;

[1615] means for analyzing the received information by the server;

[1616] A means for connecting to a real-time database of a transportation agency to obtain current congestion status, delay information, and availability information;

[1617] A means of utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; and

[1618] A means of suggesting the best departure time and vehicle;

[1619] means for transmitting the proposal results to a user terminal;

[1620] means for displaying the recommendation results to the user;

[1621] A means for an autonomous vehicle to pick you up based on a suggested optimal departure time and route; and

[1622] A system including:

[1623] (Claim 2)

[1624] A means for the generative AI to predict congestion, possibility of delays, and availability;

[1625] A means for generating suggestions that allow users to avoid crowded trains and traffic jams based on the prediction results;

[1626] and means for instructing the automated vehicle on a suggested optimal departure time and route.

[1627] 10. The system of claim 1.

[1628] (Claim 3)

[1629] said means for connecting to said real-time database of transportation facilities;

[1630] including a means to acquire data from multiple transportation agencies and integrate and analyze that data;

[1631] 10. The system of claim 1.

[1632] "Example 2: Combining Emotion Engines"

[1633] (Claim 1)

[1634] means for a user to input an origin, destination, and desired departure time;

[1635] means for transmitting the input information to a server;

[1636] means for analyzing the received information by the server;

[1637] A means for connecting to a real-time database of transportation modes to obtain current congestion status, delay information, and availability information;

[1638] A means for predicting congestion for multiple time periods, including the user's desired time period, using generative artificial intelligence;

[1639] A means for adjusting the optimal departure time and vehicle in consideration of the user's emotional information;

[1640] means for transmitting the proposal results to a user terminal;

[1641] means for displaying the recommendation results to the user;

[1642] A system including:

[1643] (Claim 2)

[1644] A means for the generative artificial intelligence to predict congestion, possibility of delay, availability, and user emotional information;

[1645] and means for generating a suggestion for the user to avoid crowded public transport based on the prediction result.

[1646] 10. The system of claim 1.

[1647] (Claim 3)

[1648] means for connecting to said real-time database of transportation means;

[1649] including a means for acquiring data from multiple modes of transportation and integrating and analyzing the data;

[1650] 10. The system of claim 1.

[1651] "Application example 2 when combining emotion engines"

[1652] (Claim 1)

[1653] means for a user to input an origin, destination, and desired departure time;

[1654] means for transmitting the input information to a server;

[1655] means for analyzing the received information by the server;

[1656] A means for connecting to a real-time database of a transportation agency to obtain current congestion status, delay information, and availability information;

[1657] A means of utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; and

[1658] A way to suggest the best departure time and transportation method,

[1659] means for acquiring user emotion information using an emotion recognition engine;

[1660] a means for adjusting the proposal results based on the acquired emotional information;

[1661] means for transmitting the adjusted proposal result to a user terminal;

[1662] means for displaying the recommendation results to the user;

[1663] A system including:

[1664] (Claim 2)

[1665] The system of claim 1 further includes means for the generative AI to predict congestion, likelihood of delays, and availability, and to generate suggestions that allow users to avoid crowded trains, traffic jams, and stress based on the prediction results and emotional information.

[1666] (Claim 3)

[1667] 10. The system of claim 1, wherein the means for connecting to the real-time database of transit agencies includes means for obtaining data from multiple transit agencies and integrating and analyzing the data. [Explanation of symbols]

[1668] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to input an origin, destination, and desired departure time; means for transmitting the input information to a server; means for analyzing the received information by the server; A means for connecting to a real-time database of a transportation agency to obtain current congestion status, delay information, and availability information; A means of utilizing generative AI to predict congestion for multiple time periods, including the user's desired time period; and A means of suggesting the best departure time and vehicle; means for transmitting the proposal results to a user terminal; means for displaying the recommendation results to the user; A system including:

2. A means for the generative AI to predict congestion, possibility of delays, and availability; The system further includes a means for generating a suggestion that allows the user to avoid crowded trains and traffic jams based on the prediction result. The system of claim 1 .

3. said means for connecting to said real-time database of transportation facilities; including a means to acquire data from multiple transportation agencies and integrate and analyze that data; The system of claim 1 .

Images