System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a user's input; means for pre-processing the collected external information; means for inputting the pre-processed information and the user's input information to a generative AI model to generate a prediction result; means for generating recommendation information that suggests an optimal travel route or departure time based on the generated prediction result; and means for transmitting the generated recommendation information to a user device.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, congestion and traffic jams are major factors that cause economic losses and psychological burdens. This reduces the quality of life of individuals and makes efficient travel and leisure activities difficult. To solve this problem, a system is needed that can predict congestion and traffic jams in real time and provide users with optimal travel routes and departure times. [Means for solving the problem]

[0005] The present invention solves this problem by providing a system including: a means for receiving user input; a means for collecting external data; a means for preprocessing the collected external data; a means for inputting the preprocessed data and the user's input data into a generative AI model and generating a prediction result; a means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result; and a means for transmitting the generated recommendation information to a user terminal.

[0006] "User" refers to an individual or group that uses this system to receive suggestions about travel routes and departure times.

[0007] "User input" refers to information provided by a user to the system, including destination, desired departure time, wait time tolerance, etc.

[0008] "External data" refers to information collected in real time from outside the system, including weather data, people flow data, public transportation operation status, search trends, and the like.

[0009] A "means of collection" is a method or device that the system uses to obtain external data or user input.

[0010] "Preprocessing" refers to the process of cleaning the collected data, converting its format, filling in missing values, correcting outliers, etc.

[0011] A "generative AI model" is a machine learning model or algorithm that predicts future congestion and congestion based on collected data and user input.

[0012] "Prediction results" are information about future congestion, traffic jams, and optimal travel routes and departure times that the generative AI model generates based on user input and external data.

[0013] "Recommended information" is information including the optimal travel route, departure time, and related coupon and promotion information provided to the user based on the prediction results.

[0014] The "transmitting means" refers to a method or device that the system uses to transmit the recommendation information to the user terminal.

[0015] The "displaying means" refers to a method or device for visually providing the user with the recommended information received by the user terminal. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[0038] Specifically, users input their destination, desired departure time, and acceptable waiting time through a smartphone app. The device then sends this input data to a server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation status, and search trends.

[0039] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[0040] Based on the prediction results, the server generates recommendation information, which may include information about departure times, travel routes, and even discount coupons for the user. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[0041] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[0042] For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route number 5." The server generates recommendation information based on this information and sends it to Mr. A's device. The device notifies Mr. A in the form of "Leaving at 2:30 PM and taking bus route number 5." A discount coupon that can be used within the shopping mall is also provided.

[0043] In this way, the system allows users to avoid congestion and traffic jams, enabling efficient and comfortable travel.

[0044] The processing flow will be explained below.

[0045] Step 1:

[0046] The user opens the smartphone app and enters their destination, desired departure time, and acceptable waiting time.

[0047] Example: Person A enters into the app the following information: "Shopping mall in City A," departure time: 2:00 PM, acceptable waiting time: 15 minutes or less.

[0048] Step 2:

[0049] The terminal transmits the user's input data to the server.

[0050] Example: Data entered by user A is sent from the device to the server.

[0051] Step 3:

[0052] The server collects the necessary data from an external API.

[0053] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[0054] Step 4:

[0055] The server preprocesses the collected external data.

[0056] Delete unnecessary data, fill in missing values, and correct outliers.

[0057] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[0058] Step 5:

[0059] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[0060] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[0061] Step 6:

[0062] The server generates recommendations based on the prediction results.

[0063] Generate recommendations including travel routes, departure times, relevant coupons, etc.

[0064] Example: Generate a recommendation to depart at 2:30 PM and take bus route 5.

[0065] Step 7:

[0066] The server transmits the generated recommendation information to the user terminal.

[0067] Example: Recommended information is sent to Mr. A's smartphone.

[0068] Step 8:

[0069] The recommended information received by the terminal is visually displayed to the user.

[0070] Example: The app tells you to leave at 2:30 PM and take bus route 5, and also offers a shopping mall coupon.

[0071] Step 9:

[0072] The user sees the recommendations and takes action.

[0073] Example: Person A leaves at 2:30 pm and takes the recommended bus route.

[0074] Example 1

[0075] 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."

[0076] In modern times, urban congestion and traffic jams are one of the problems that significantly impair the efficiency and comfort of travel. In particular, due to the wide range of external factors, such as sudden weather changes, irregular pedestrian flows, and public transportation delays, it is difficult to propose optimal travel routes and departure times that take these factors into account. Furthermore, it is necessary to consider the user's time and tolerance for waiting times at the destination, making manual planning extremely cumbersome and inefficient.

[0077] 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.

[0078] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal, thereby making it possible to provide users with optimal travel routes and departure times in real time.

[0079] "User input" refers to information such as the destination, desired departure time, and waiting time tolerance that the user provides through the terminal.

[0080] "External data" refers to data collected from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[0081] "Preprocessing" refers to processes such as filling in missing values ​​in collected external data, correcting outliers, and standardizing data formats.

[0082] A "generative AI model" is an artificial intelligence model that predicts congestion and traffic jams and calculates optimal travel routes and departure times based on preprocessed data and user input data.

[0083] The "prediction results" are information calculated by the generative AI model on the optimal travel route and departure time for the user, including predictions of congestion and traffic jams.

[0084] "Recommended information" is information such as the optimal travel route and departure time for the user, as well as related discount coupons, generated based on the prediction results.

[0085] A "user terminal" is a device used by a user, such as a smartphone or tablet, that receives and displays the recommended information sent from the server.

[0086] "Cleaning" is the process of correcting missing or outlier values ​​in data to create accurate and consistent data.

[0087] "Collection" refers to the operation in which the server obtains external data such as weather data, people flow data, public transportation operation status, and search trends through an external API.

[0088] A "discount coupon" is information provided to a user to receive a discount at a store or service.

[0089] MODE FOR CARRYING OUT THE INVENTION

[0090] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[0091] Hardware and Software

[0092] 1. Hardware: Server, user device (smartphone)

[0093] 2. Software: Smartphone app, external API (weather data, people flow data, public transport operation status, search trends), generative AI model

[0094] Explanation of characteristic program processing

[0095] 1. User input

[0096] The user starts the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. For example, Mr. A inputs "Shopping Mall in City A," departure time "2:00 PM," and waiting time tolerance "within 15 minutes."

[0097] 2. Sending data from the device to the server

[0098] The terminal sends the data entered by the user to the server. Specifically, when the submit button on the input form is pressed, the terminal converts the user's input data into JSON format and sends an HTTP request to the server's API endpoint.

[0099] 3. Collection of external data by the server

[0100] The server uses external APIs to collect necessary data in real time based on the received user data. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transport operation status from the Transit API.

[0101] 4. Data preprocessing by the server

[0102] The collected data cannot be used as is, so it is preprocessed on the server. Specifically, missing values ​​are filled in, outliers are corrected, and the data format is standardized. For example, if there is missing weather data, it is filled in by guessing based on past data.

[0103] 5. Data input and prediction for generative AI model

[0104] The preprocessed data and user input data are input into the generative AI model. Based on this data, the generative AI model predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user. For example, it predicts that "departing at 2:30 PM and taking bus route 5" is optimal.

[0105] 6. Server-generated recommendations

[0106] Based on the predictions from the generative AI model, the server generates recommendations for the user, including specific travel routes, departure times, and even discount coupons. For example, it generates a message such as, "Leave at 2:30 PM and take bus route 5."

[0107] 7. Sending recommended information to the user's device

[0108] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device.

[0109] 8. Display of recommendations by device

[0110] The device analyzes the received recommendations and visually displays them to the user, such as in a pop-up notification or in-app message box, suggesting "Leave at 2:30 PM and take bus route 5," and also offering discount coupons for use within the shopping mall.

[0111] Specific examples

[0112] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters their destination as "Shopping Mall in City A," their departure time as "2:00 PM," and their acceptable waiting time as "within 15 minutes" into a smartphone app. The device sends this input data to the server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time. For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route 5." The server generates recommendation information based on this information and sends it to Person A's device. The device notifies Person A in the form of "Leaving at 2:30 PM and taking bus route 5." A discount coupon that can be used within the shopping mall is also provided.

[0113] Prompt Sentence Examples

[0114] An example of a prompt sentence is, "Please predict the best route and departure time for the user to go to the shopping mall on Sunday afternoon, and provide recommendations to avoid crowds and traffic jams. The user's input data is the destination "Shopping Mall in City A", the departure time "2:00 PM", and the waiting time tolerance "within 15 minutes."

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

[0116] Step 1: User Input

[0117] A user launches a smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The input data includes information provided by the user using an input form within the app. For example, the user might input "Destination: Shopping mall in the city," "Departure time: 2:00 PM," and "Waiting time tolerance: within 15 minutes."

[0118] Step 2: Send data from the device to the server

[0119] The device converts the input data into JSON format and sends an HTTP request to the server's API endpoint. Specifically, when the user presses the send button, the input data is transferred to the server. The input data includes the user's destination, desired departure time, and waiting time tolerance.

[0120] Step 3: Collecting external data by the server

[0121] The server uses external APIs to collect necessary external data based on the input data received from the user. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transportation operation status from the Transit API. The collected data is updated in real time.

[0122] Step 4: Preprocessing the data on the server

[0123] The server preprocesses the collected external data. This preprocessing includes filling in missing values ​​and correcting outliers. For example, if there are missing values ​​in weather data, it fills in the missing values ​​with estimated values ​​using past data. It receives external data as input and outputs preprocessed data.

[0124] Step 5: Input data into the generative AI model and make predictions

[0125] The server inputs the preprocessed data and user input data into the generative AI model. The generative AI model uses this data to predict congestion and traffic jams, and calculates the optimal travel route and departure time. For example, the model predicts that "departing at 2:30 PM and taking bus route 5" is optimal. Here, it receives the input data and preprocessed data and outputs the predicted results.

[0126] Step 6: Server Generates Recommendations

[0127] The server generates recommended information based on the prediction results. The recommended information includes the user's optimal travel route, departure time, discount coupons, etc. The specific operation when generating recommended information is to refer to the prediction results from the AI ​​model and assemble a series of suggested information. The input is the prediction results, and the output is recommended information.

[0128] Step 7: Sending recommendations to the user's device

[0129] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device. Here, the recommendation information is received as input and the data to be sent to the user's device is output.

[0130] Step 8: View device recommendations

[0131] The device analyzes the received recommendation information and visually displays it to the user. Specifically, it displays the appropriate departure time and travel route in a pop-up notification or in a message field within the app. Discount coupons are also displayed within the app. Here, the received recommendation information is received as input, and the data to be displayed to the user is output.

[0132] (Application example 1)

[0133] 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."

[0134] This system solves the problem of improving the user experience by improving the operational efficiency of autonomous vehicles, avoiding congestion and traffic jams, and proposing optimal travel routes and departure times. It also aims to smooth the flow of road traffic and reduce traffic congestion by adjusting parameters in real time during operation.

[0135] 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.

[0136] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, means for transmitting the generated recommendation information to a user terminal, means for automatically adjusting operation parameters of the autonomous vehicle based on the generated recommendation information, and means for optimizing the vehicle's operation route and operation timing in cooperation with a car system. This enables efficient travel to a user's destination, smooths traffic flow, and reduces traffic congestion.

[0137] The "means for receiving user input" is an interface that allows the user to input information such as the destination, desired departure time, and acceptable waiting time via a device such as a smartphone or tablet.

[0138] "Means for collecting external data" refers to a system for collecting necessary information from external APIs via the Internet, such as weather data, traffic data, people flow data, and public transportation operation status.

[0139] "Means for preprocessing collected external data" refers to the process of preparing collected data in a state that makes it possible to analyze it, such as by filling in missing values, correcting outliers, and standardizing data formats.

[0140] "Means for inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a system for inputting preprocessed external data and user input data into an artificial intelligence model to predict congestion and traffic jams.

[0141] The "means for generating recommended information that suggests optimal travel routes and departure times" is a system that creates recommended information on the most efficient travel routes and departure times for users based on the prediction results obtained from the generative AI model.

[0142] The "means for transmitting the generated recommended information to the user terminal" is a system that transmits the recommended information created by the server to the user's smartphone or tablet, allowing the user to receive the information.

[0143] The "means for automatically adjusting the operating parameters of an autonomous vehicle based on the generated recommendation information" is a system for automatically setting and adjusting operating parameters of an autonomous vehicle, such as the operating route, speed, and stopping locations, in accordance with the recommendation information.

[0144] "Means for optimizing vehicle routes and operation timings in cooperation with car systems" refers to an interface and control system that communicates with the internal systems of an autonomous vehicle and optimizes routes and operation schedules in real time.

[0145] "User Device" means a smartphone, tablet, or other mobile device used by a User to input and receive information.

[0146] This invention is a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users, thereby improving the operating efficiency of autonomous vehicles. A specific embodiment of the system will be described.

[0147] First, the user enters information such as their destination, desired departure time, and acceptable waiting time through a smartphone application. This information is then sent to the server. The server then collects data such as weather data, traffic data, people flow data, and public transportation operation status from external APIs. This involves using external services such as weather APIs, people flow analysis APIs, and traffic information APIs.

[0148] The server then preprocesses the collected data, using data processing libraries like Pandas and NumPy to fill in missing values ​​and correct outliers. The preprocessed data and user input data are then fed into a generative AI model (for example, a model using TensorFlow or PyTorch) to predict congestion and traffic jams.

[0149] The generative AI model calculates the optimal travel route and departure time. Based on this, the server generates recommendations for the user. These recommendations include specific departure times, the means of transportation to be used, and even the route of the autonomous vehicle. This information is sent to the user's smartphone and presented visually.

[0150] Furthermore, the system automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations. This adjustment is made in cooperation with the vehicle's on-board computer and operating system, for example, optimizing the route to the destination and adjusting the speed automatically.

[0151] As a concrete example, consider the case where a user wants to go to the office in an autonomous taxi. The user enters the destination as "office," the departure time as "9:00 AM," and the waiting time tolerance as "within 10 minutes" into a smartphone app. The server collects weather and traffic data and predicts the optimal travel route and departure time. Based on the prediction results, it is determined that "departing at 8:45 AM and using main road A" is optimal. This information is sent to the autonomous taxi's operation system, and the vehicle automatically operates according to the set route.

[0152] An example prompt is:

[0153] Destination: Office

[0154] Departure time: 8:45 AM

[0155] Weather data: Clear skies

[0156] Traffic data: No traffic jams

[0157] Departure time optimization: 10 minute waiting time tolerance

[0158] This invention allows users to avoid congestion and traffic jams and travel to their destinations efficiently and comfortably. Furthermore, by adjusting the operating parameters of autonomous vehicles in real time, traffic flow can be smoothed and traffic congestion can be reduced.

[0159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0160] Step 1:

[0161] The user inputs their destination, desired departure time, and acceptable waiting time through a smartphone app. The device collects this input data and sends it to the server.

[0162] Input: Destination, desired departure time, waiting time tolerance

[0163] Output: Sending input data to the server

[0164] Step 2:

[0165] The server collects external data such as weather data, traffic data, people flow data, and public transport operation status from external APIs. Specifically, it uses weather APIs, people flow analysis APIs, traffic information APIs, etc.

[0166] Input: Data collection request from external API

[0167] Output: Collected weather data, traffic data, people flow data, and operation status data

[0168] Step 3:

[0169] The server preprocesses the external data collected by the server, specifically by using the Pandas and NumPy libraries to impute missing values, correct outliers, and standardize the data format.

[0170] Input: Collected external data

[0171] Output: Preprocessed data

[0172] Step 4:

[0173] The server inputs the preprocessed data and user input data into a generative AI model to predict congestion and traffic jams. The generative AI model is implemented using TensorFlow and PyTorch.

[0174] Input: Preprocessed data, user input data

[0175] Output: Predicted congestion and traffic jams

[0176] Step 5:

[0177] Based on the prediction results, the server generates recommendations for the user on the optimal travel route and departure time, including specific departure times, the means of transportation to be used, and the route of the autonomous vehicle.

[0178] Input: Predicted results of congestion and traffic jams

[0179] Output: Optimal travel route, departure time, and recommendations

[0180] Step 6:

[0181] The server sends the generated recommendation information to the user's smartphone, which receives the recommendation information and visually presents it to the user.

[0182] Input: Generated recommendations

[0183] Output: Send to user's smartphone, display notification

[0184] Step 7:

[0185] The server automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations, specifically optimizing route planning, speed adjustment, and stopping locations in cooperation with the vehicle's on-board computer.

[0186] Input: Generated recommendations

[0187] Output: Adjustment of operating parameters of autonomous vehicles

[0188] 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.

[0189] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotional state.

[0190] Specifically, the system operates in the following steps.

[0191] First, the user opens the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The device then sends this input data to the server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[0192] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[0193] Furthermore, the emotion engine recognizes the user's emotions based on the user's input data and external data. Based on the user's emotional state recognized by the emotion engine, the server adjusts the generated prediction results and recommendation information. For example, if the user is feeling stressed, the server may suggest a less congested route.

[0194] Based on the adjusted prediction results, the server generates recommendation information, which includes information on departure times and travel routes, as well as customized discount coupons tailored to the user's emotions. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[0195] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[0196] For example, suppose the optimal route is predicted to be "departing at 2:30 PM and taking bus route number 5." The server recognizes Person A's emotions based on the emotion engine. In this case, if Person A is feeling stressed, the server will suggest an alternative route to avoid crowds. The adjusted recommendation information is sent to Person A's device, and Person A receives information that they should depart at 2:30 PM and take bus route number 5. They will also be provided with a discount coupon that can be used within the shopping mall.

[0197] In this way, the system avoids congestion and traffic jams and provides customized travel suggestions based on the user's emotional state, making travel more efficient and comfortable.

[0198] The processing flow will be explained below.

[0199] The present invention relates to a system that predicts congestion and traffic jams, recognizes the user's emotions, and proposes optimal travel routes and departure times. Specific processing steps of the system are shown below.

[0200] Step 1:

[0201] A user opens a smartphone app and enters input data regarding their destination, desired departure time, wait tolerance, and current emotional state.

[0202] Example: Person A enters into the app, "Shopping mall in City A," departure time is 2:00 PM, waiting time tolerance is within 15 minutes, and "I'm feeling stressed."

[0203] Step 2:

[0204] The terminal transmits the user's input data to the server.

[0205] Example: Data entered by user A is sent from the device to the server.

[0206] Step 3:

[0207] The server collects the necessary data from an external API.

[0208] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[0209] Step 4:

[0210] The server preprocesses the collected external data.

[0211] Delete unnecessary data, fill in missing values, and correct outliers.

[0212] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[0213] Step 5:

[0214] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[0215] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[0216] Step 6:

[0217] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and external data.

[0218] Example: An emotion engine analyzes the input "I'm feeling stressed" and recognizes the user's emotional state.

[0219] Step 7:

[0220] The server adjusts the generated prediction results and recommendation information based on the user's emotional state recognized by the emotion engine.

[0221] Example: Considering that Person A is feeling stressed, the server suggests a less congested route.

[0222] Step 8:

[0223] The server generates recommendations based on the adjusted prediction results.

[0224] In addition to departure times and travel routes, it also includes customized discount coupons tailored to the user's emotions.

[0225] Example: Generate a recommendation to take bus route 5 for a 2:30 PM departure, plus offer a relaxation coupon.

[0226] Step 9:

[0227] The server transmits the generated recommendation information to the user terminal.

[0228] Example: Recommended information is sent to Mr. A's smartphone.

[0229] Step 10:

[0230] The recommended information received by the terminal is visually displayed to the user.

[0231] Example: The app says, "Leave at 2:30 PM and take bus route 5. You also have a stress-reducing coupon available."

[0232] Step 11:

[0233] The user sees the recommendations and takes action.

[0234] Example: Person A leaves at 2:30 PM, takes the recommended bus route, and uses the provided coupon to receive a relaxing service.

[0235] Through the above processing steps, the system not only predicts congestion and traffic jams, but also provides customized travel suggestions based on the user's emotional state, enabling efficient and comfortable travel.

[0236] Example 2

[0237] 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."

[0238] In modern society, it is important to suggest optimal travel routes that avoid congestion and traffic jams. However, existing systems do not consider the user's emotional state and do not improve the user experience. In addition, they lack the ability to provide accurate recommendations due to insufficient preprocessing of data collected in real time. Furthermore, they are unable to provide customized recommendations that meet the user's specific needs.

[0239] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model and generating a prediction result, means for generating recommended information that suggests an optimal travel route and departure time based on the generated prediction result, means for recognizing the user's emotion and adjusting the recommended information based on the emotion, and means for transmitting the generated recommended information to the user terminal. This makes it possible to provide highly accurate recommended information based on the user's emotional state.

[0240] The "means for receiving user input" refers to a means for providing an interface that allows a user to input necessary information such as a destination, desired departure time, and acceptable waiting time to the system.

[0241] "Means for collecting external data" refers to means for obtaining external information such as weather, pedestrian flow, public transportation operation status, and search trends in real time.

[0242] The "means for preprocessing collected external data" refers to a means for performing data cleansing processing such as complementing missing values ​​in the collected external data and correcting outliers.

[0243] "Means of inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a means of predicting congestion and traffic jams using an AI model by combining preprocessed data with user input information.

[0244] "Means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to means for determining the optimal travel route and departure time for a user based on the prediction results obtained by an AI model, and creating recommended information.

[0245] The "means for recognizing the user's emotions and adjusting the recommended information based on the emotions" refers to a means for analyzing the user's emotional state and adjusting the recommended information in accordance with emotions such as stress or joy.

[0246] The "means for transmitting the generated recommendation information to the user terminal" refers to a means for transmitting the generated recommendation information to the user's device and providing it visually.

[0247] MODE FOR CARRYING OUT THE INVENTION

[0248] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system also aims to provide a more comfortable travel experience by recognizing the user's emotions and providing customized recommendations based on those emotions.

[0249] System configuration

[0250] This system consists of the following elements:

[0251] User interface: The user enters information such as the destination, desired departure time, and waiting time tolerance through a smartphone app.

[0252] Data collection module: Uses APIs to collect external data in real time, such as weather, people flow, public transport operation status, search trends, etc. Specific examples of APIs include OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[0253] Data cleansing module: Cleanses the collected data, filling in missing values ​​and correcting outliers.

[0254] Generative AI model: Predicts congestion and traffic jams based on cleansed data and user input data. TensorFlow is used as the AI ​​model.

[0255] Emotion engine: Recognizes the user's emotions based on user input data and external data. Specifically, it uses IBM Watson Tone Analyzer.

[0256] Recommendation generation module: Generates recommendations regarding optimal travel routes and departure times based on prediction results and sentiment information.

[0257] Information delivery module: The generated recommendation information is sent to the user's device and presented visually.

[0258] Specific measures include:

[0259] Means of receiving user input: Using a smartphone app, users input their destination, desired departure time, and waiting time tolerance.

[0260] Means of collecting external data: Various external data (weather, people flow, traffic conditions, search trends) are collected using API keys.

[0261] Preprocessing the collected external data: imputing missing values ​​and correcting outliers in the collected data.

[0262] A means of inputting data into a generative AI model and generating prediction results: Predict congestion and traffic jams using cleansed data and user input data.

[0263] Means for generating recommendation information: Based on the prediction results, recommendation information is generated that suggests the optimal travel route and departure time.

[0264] Means for tailoring recommendation information based on emotions: The recommendation information is tailored based on the user's emotional state recognized by the emotion engine.

[0265] Means for transmitting generated recommendation information to user terminal: The server transmits the generated recommendation information to the user's smartphone.

[0266] Specific examples

[0267] For example, consider the case where user A wants to go to a shopping mall in city A on a Sunday afternoon. User A launches the smartphone app and enters "Shopping Mall in City A" as the destination, "2 PM" as the departure time, and "within 15 minutes" as the waiting time tolerance. The device sends this data in JSON format to the server. The server collects and cleans external data from the OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[0268] The cleansed data and user input data are input into the TensorFlow model, and the system predicts the optimal travel route and departure time. For example, if it predicts that "it is best to depart at 2:30 pm and take bus route 5," the server uses IBM Watson Tone Analyzer to check whether User A is feeling stressed.

[0269] If the user is recognized as "stressed," the server generates another recommendation, such as "Leave at 3 PM and take bus route 7" to avoid the crowds. This recommendation also includes discount coupons that can be used at the shopping mall.

[0270] Finally, the generated recommendations are sent to the user's smartphone and displayed as notifications or pop-ups within the app.

[0271] Prompt Sentence Examples

[0272] "Destination: A City Shopping Mall"

[0273] "Departure time: 2 PM"

[0274] "Wait time tolerance: 15 minutes or less"

[0275] "User Emotions: Stress"

[0276] This system will enable users to avoid congestion and traffic jams and provide customized travel suggestions based on their emotional state.

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1:

[0279] The user launches the smartphone app and inputs the necessary information, specifically the destination, desired departure time, and waiting time tolerance. The input data is the destination (e.g., shopping mall in City A), departure time (e.g., 2:00 PM), and waiting time tolerance (e.g., within 15 minutes).

[0280] Step 2:

[0281] The device sends the user's input data to the server. Specifically, the input data for destination, departure time, and waiting time tolerance is converted into JSON format and sent to the server. Input: Input data from the user. Output: JSON data sent to the server.

[0282] Step 3:

[0283] The server collects external data. Specifically, it collects weather information from the OpenWeatherMap API, people flow data from the Google Maps API, and real-time public transportation operation status from the Local Transit APIs. Input: API key and request. Output: Weather data, people flow data, and traffic condition data.

[0284] Step 4:

[0285] The server cleanses the data collected. Specifically, it complements missing data and corrects outliers. For example, if there is a gap in the weather data, it complements it using surrounding data. Input: Collected external data. Output: Cleansed data.

[0286] Step 5:

[0287] The server inputs the cleansed data and user input data into the generative AI model to generate prediction results. Specifically, a TensorFlow model is used to predict congestion and traffic jams. The model uses prompt statements such as: "Destination: Shopping Mall in City A," "Departure time: 2:00 PM," and "Tolerance for waiting time: within 15 minutes." Input: Cleansed data, user input data. Output: Congestion prediction results.

[0288] Step 6:

[0289] The server uses an emotion engine to recognize the user's emotions. Specifically, it uses IBM Watson Tone Analyzer to analyze emotions from the user's text input or voice data. Input: User's text input or voice data. Output: User's emotional state (e.g., feeling stressed).

[0290] Step 7:

[0291] The server generates recommendation information based on the prediction results and emotional information. Specifically, it determines the optimal travel route and departure time by taking into account the congestion prediction results and the user's emotional state. For example, if the user is feeling stressed, it will recommend a route with less congestion. Input: Congestion prediction results, emotional information. Output: Customized recommendation information.

[0292] Step 8:

[0293] The server sends the generated recommendation information to the user's device. Specifically, it converts the recommendation information into JSON format and sends it to the user's smartphone. Input: Customized recommendation information. Output: JSON format recommendation information data.

[0294] Step 9:

[0295] The recommended information received by the device is visually presented to the user. Specifically, it is displayed as a notification or pop-up within the smartphone app. For example, it may display information such as "Leave at 3pm and take bus route number 7" or a discount coupon that can be used at a shopping mall. Input: Recommended information sent from the server. Output: Visual information provided to the user.

[0296] (Application example 2)

[0297] 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."

[0298] The present invention relates to a system that provides a user with an efficient and comfortable travel experience by avoiding congestion and traffic jams when traveling. In particular, the present invention aims to improve the riding experience of autonomous vehicles by providing more personalized recommendation information that takes into account the user's emotional state. Conventional technologies do not provide travel recommendations that reflect the user's emotional state, and therefore may suggest stressful routes or departure times.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0300] In this invention, the server includes a means for receiving user input, a means for collecting external data, and a means for preprocessing the collected external data. This makes it possible to propose optimal travel routes and departure times to users based on real-time information such as weather data, people flow data, and public transportation operation status. Furthermore, by adding a means for generating recommendation information that proposes optimal travel routes and departure times based on the generated prediction results, a means for transmitting the generated recommendation information to a user terminal, and a means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state, it becomes possible to provide customized travel suggestions that take the user's emotions into consideration. This not only allows users to avoid congestion and traffic jams, but also allows them to enjoy less stressful routes and services tailored to their situation, improving the quality of their overall travel experience.

[0301] A "means for receiving user input" is a device or software that provides an interface for a user to input data such as destination, desired departure time, and wait time tolerance.

[0302] "Means for collecting external data" refers to devices or software that acquire external information in real time, such as weather data, people flow data, public transportation operation status, and search trends.

[0303] The "means for preprocessing collected external data" refers to a device or software that performs processing to complement missing values ​​and correct outliers in the collected external data and convert it into the required format.

[0304] "Means for inputting preprocessed data and user input data into a generative AI model and generating a prediction result" refers to a device or software that provides preprocessed data and user input data to an AI model and generates a prediction result for the optimal travel route and departure time based on that data.

[0305] The "means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to a device or software that creates recommended information including optimal travel routes and departure times for a user based on the generated prediction results.

[0306] The "means for transmitting the generated recommendation information to the user terminal" refers to a communication device or software for transmitting the recommendation information to the user terminal (such as a smartphone).

[0307] "Means for using an emotion engine to recognize a user's emotional state and for adjusting recommendations based on the recognized emotional state" refers to a device or software that evaluates a user's emotional state based on user input data and external data, and adapts or modifies recommendations based on the evaluation.

[0308] The present invention is a system for avoiding congestion and traffic jams when a user travels, and providing an efficient and comfortable travel experience, and is intended to be particularly applied to autonomous vehicles. Specific embodiments are described below.

[0309] The server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal.The server also includes means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state.

[0310] Users use a smartphone app to input data such as their destination, desired departure time, and acceptable waiting time. This input data is sent to a server. The server then collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs (e.g., OpenWeatherMap API and Google Maps API). The collected external data is preprocessed using a programming language such as Python. This preprocessing involves filling in missing values ​​and correcting outliers.

[0311] The preprocessed data and user input data are input into a generative AI model. This AI model predicts the optimal travel route and departure time and generates a prediction result. Based on the generated prediction result, the server generates recommended information for the user, including the optimal travel route and departure time. At this time, the emotion engine recognizes the user's emotional state and adjusts the recommended information by suggesting less crowded routes, entertainment, etc.

[0312] The generated recommendation information is sent from the server to the user's device and displayed on the user's smartphone. For example, if a user plans to go to the shopping mall at 2:00 PM, the server predicts that the best option would be to leave at 2:30 PM and take bus route 5. If the user is feeling stressed, the server will make a customized suggestion such as taking route 3, which will avoid the crowds, and playing relaxing music.

[0313] Example prompt sentence:

[0314] "The user wants to depart for the destination 'City Center' at '14:00' and their emotional state is 'Stressed'. Please predict the optimal route and departure time based on weather data and people flow data, and generate relaxing suggestions."

[0315] This allows users to reach their destination efficiently, avoiding crowds and traffic jams, and provides a comfortable travel experience that suits their emotional state.

[0316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0317] Step 1:

[0318] The user opens the smartphone app and inputs their destination, desired departure time, waiting time tolerance, and emotional state. The smartphone app then transmits the data entered by the user to the server.

[0319] Input data: destination, desired departure time, waiting time tolerance, emotional state

[0320] Output Data: Input data sent to the server

[0321] Step 2:

[0322] The server collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs. Examples of external APIs used include the OpenWeatherMap API and Google Maps API. This data is stored on the server.

[0323] Input data: Weather data, people flow data, and public transportation status obtained from external APIs

[0324] Output data: Stored external data

[0325] Step 3:

[0326] The server preprocesses the collected external data. This involves using programming languages ​​such as Python to fill in missing values, correct outliers, and convert the data into the required format. This process improves the quality of the data and makes it suitable for input into AI models.

[0327] Input data: Stored external data

[0328] Output data: Preprocessed data

[0329] Step 4:

[0330] The preprocessed data and user input data are input into the generative AI model to generate a prediction. The AI ​​model then predicts the optimal travel route and departure time based on the input data. For example, it may predict that the user should take the "Route 5" bus at 2:30 PM.

[0331] Input data: Preprocessed data, user input data

[0332] Output data: Prediction results (optimal travel route and departure time)

[0333] Step 5:

[0334] The server generates recommendations based on the prediction results, suggesting optimal travel routes and departure times. In addition, the emotion engine recognizes the user's emotional state and adjusts the recommendations based on that emotional state. For example, if the user is feeling stressed, it will suggest less crowded routes and provide relaxing music.

[0335] Input data: prediction results, user's emotional state

[0336] Output: Tailored recommendations

[0337] Step 6:

[0338] The server then sends the adjusted recommendation information to the user's device, which then visually displays the received recommendation information and indicates the next action the user should take. For example, the recommendation "Leave at 2:30 PM and take the Route 5 bus" or a discount coupon for a shopping mall is displayed.

[0339] Input data: Tailored recommendations

[0340] Output data: Recommendation information displayed on the user's device

[0341] Step 7:

[0342] Users travel according to the recommended information displayed on their smartphone app and board an autonomous vehicle. In the process, they enjoy a comfortable travel experience by using the recommended route and receiving suggested services.

[0343] Input data: Recommendation information displayed on the user's device

[0344] Output data: User's actual travel experience

[0345] 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.

[0346] 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.

[0347] 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.

[0348] [Second embodiment]

[0349] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0350] 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.

[0351] 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).

[0352] 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.

[0353] 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.

[0354] 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).

[0355] 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.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] 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."

[0361] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[0362] Specifically, users input their destination, desired departure time, and acceptable waiting time through a smartphone app. The device then sends this input data to a server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation status, and search trends.

[0363] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[0364] Based on the prediction results, the server generates recommendation information, which may include information about departure times, travel routes, and even discount coupons for the user. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[0365] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[0366] For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route number 5." The server generates recommendation information based on this information and sends it to Mr. A's device. The device notifies Mr. A in the form of "Leaving at 2:30 PM and taking bus route number 5." A discount coupon that can be used within the shopping mall is also provided.

[0367] In this way, the system allows users to avoid congestion and traffic jams, enabling efficient and comfortable travel.

[0368] The processing flow will be explained below.

[0369] Step 1:

[0370] The user opens the smartphone app and enters their destination, desired departure time, and acceptable waiting time.

[0371] Example: Person A enters into the app the following information: "Shopping mall in City A," departure time: 2:00 PM, acceptable waiting time: 15 minutes or less.

[0372] Step 2:

[0373] The terminal transmits the user's input data to the server.

[0374] Example: Data entered by user A is sent from the device to the server.

[0375] Step 3:

[0376] The server collects the necessary data from an external API.

[0377] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[0378] Step 4:

[0379] The server preprocesses the collected external data.

[0380] Delete unnecessary data, fill in missing values, and correct outliers.

[0381] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[0382] Step 5:

[0383] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[0384] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[0385] Step 6:

[0386] The server generates recommendations based on the prediction results.

[0387] Generate recommendations including travel routes, departure times, relevant coupons, etc.

[0388] Example: Generate a recommendation to depart at 2:30 PM and take bus route 5.

[0389] Step 7:

[0390] The server transmits the generated recommendation information to the user terminal.

[0391] Example: Recommended information is sent to Mr. A's smartphone.

[0392] Step 8:

[0393] The recommended information received by the terminal is visually displayed to the user.

[0394] Example: The app tells you to leave at 2:30 PM and take bus route 5, and also offers a shopping mall coupon.

[0395] Step 9:

[0396] The user sees the recommendations and takes action.

[0397] Example: Person A leaves at 2:30 pm and takes the recommended bus route.

[0398] Example 1

[0399] 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."

[0400] In modern times, urban congestion and traffic jams are one of the problems that significantly impair the efficiency and comfort of travel. In particular, due to the wide range of external factors, such as sudden weather changes, irregular pedestrian flows, and public transportation delays, it is difficult to propose optimal travel routes and departure times that take these factors into account. Furthermore, it is necessary to consider the user's time and tolerance for waiting times at the destination, making manual planning extremely cumbersome and inefficient.

[0401] 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.

[0402] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal, thereby making it possible to provide users with optimal travel routes and departure times in real time.

[0403] "User input" refers to information such as the destination, desired departure time, and waiting time tolerance that the user provides through the terminal.

[0404] "External data" refers to data collected from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[0405] "Preprocessing" refers to processes such as filling in missing values ​​in collected external data, correcting outliers, and standardizing data formats.

[0406] A "generative AI model" is an artificial intelligence model that predicts congestion and traffic jams and calculates optimal travel routes and departure times based on preprocessed data and user input data.

[0407] The "prediction results" are information calculated by the generative AI model on the optimal travel route and departure time for the user, including predictions of congestion and traffic jams.

[0408] "Recommended information" is information such as the optimal travel route and departure time for the user, as well as related discount coupons, generated based on the prediction results.

[0409] A "user terminal" is a device used by a user, such as a smartphone or tablet, that receives and displays the recommended information sent from the server.

[0410] "Cleaning" is the process of correcting missing or outlier values ​​in data to create accurate and consistent data.

[0411] "Collection" refers to the operation in which the server obtains external data such as weather data, people flow data, public transportation operation status, and search trends through an external API.

[0412] A "discount coupon" is information provided to a user to receive a discount at a store or service.

[0413] MODE FOR CARRYING OUT THE INVENTION

[0414] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[0415] Hardware and Software

[0416] 1. Hardware: Server, user device (smartphone)

[0417] 2. Software: Smartphone app, external API (weather data, people flow data, public transport operation status, search trends), generative AI model

[0418] Explanation of characteristic program processing

[0419] 1. User input

[0420] The user starts the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. For example, Mr. A inputs "Shopping Mall in City A," departure time "2:00 PM," and waiting time tolerance "within 15 minutes."

[0421] 2. Sending data from the device to the server

[0422] The terminal sends the data entered by the user to the server. Specifically, when the submit button on the input form is pressed, the terminal converts the user's input data into JSON format and sends an HTTP request to the server's API endpoint.

[0423] 3. Collection of external data by the server

[0424] The server uses external APIs to collect necessary data in real time based on the received user data. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transport operation status from the Transit API.

[0425] 4. Data preprocessing by the server

[0426] The collected data cannot be used as is, so it is preprocessed on the server. Specifically, missing values ​​are filled in, outliers are corrected, and the data format is standardized. For example, if there is missing weather data, it is filled in by guessing based on past data.

[0427] 5. Data input and prediction for generative AI model

[0428] The preprocessed data and user input data are input into the generative AI model. Based on this data, the generative AI model predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user. For example, it predicts that "departing at 2:30 PM and taking bus route 5" is optimal.

[0429] 6. Server-generated recommendations

[0430] Based on the predictions from the generative AI model, the server generates recommendations for the user, including specific travel routes, departure times, and even discount coupons. For example, it generates a message such as, "Leave at 2:30 PM and take bus route 5."

[0431] 7. Sending recommended information to the user's device

[0432] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device.

[0433] 8. Display of recommendations by device

[0434] The device analyzes the received recommendations and visually displays them to the user, such as in a pop-up notification or in-app message box, suggesting "Leave at 2:30 PM and take bus route 5," and also offering discount coupons for use within the shopping mall.

[0435] Specific examples

[0436] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters their destination as "Shopping Mall in City A," their departure time as "2:00 PM," and their acceptable waiting time as "within 15 minutes" into a smartphone app. The device sends this input data to the server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time. For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route 5." The server generates recommendation information based on this information and sends it to Person A's device. The device notifies Person A in the form of "Leaving at 2:30 PM and taking bus route 5." A discount coupon that can be used within the shopping mall is also provided.

[0437] Prompt Sentence Examples

[0438] An example of a prompt sentence is, "Please predict the best route and departure time for the user to go to the shopping mall on Sunday afternoon, and provide recommendations to avoid crowds and traffic jams. The user's input data is the destination "Shopping Mall in City A", the departure time "2:00 PM", and the waiting time tolerance "within 15 minutes."

[0439] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0440] Step 1: User Input

[0441] A user launches a smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The input data includes information provided by the user using an input form within the app. For example, the user might input "Destination: Shopping mall in the city," "Departure time: 2:00 PM," and "Waiting time tolerance: within 15 minutes."

[0442] Step 2: Send data from the device to the server

[0443] The device converts the input data into JSON format and sends an HTTP request to the server's API endpoint. Specifically, when the user presses the send button, the input data is transferred to the server. The input data includes the user's destination, desired departure time, and waiting time tolerance.

[0444] Step 3: Collecting external data by the server

[0445] The server uses external APIs to collect necessary external data based on the input data received from the user. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transportation operation status from the Transit API. The collected data is updated in real time.

[0446] Step 4: Preprocessing the data on the server

[0447] The server preprocesses the collected external data. This preprocessing includes filling in missing values ​​and correcting outliers. For example, if there are missing values ​​in weather data, it fills in the missing values ​​with estimated values ​​using past data. It receives external data as input and outputs preprocessed data.

[0448] Step 5: Input data into the generative AI model and make predictions

[0449] The server inputs the preprocessed data and user input data into the generative AI model. The generative AI model uses this data to predict congestion and traffic jams, and calculates the optimal travel route and departure time. For example, the model predicts that "departing at 2:30 PM and taking bus route 5" is optimal. Here, it receives the input data and preprocessed data and outputs the predicted results.

[0450] Step 6: Server Generates Recommendations

[0451] The server generates recommended information based on the prediction results. The recommended information includes the user's optimal travel route, departure time, discount coupons, etc. The specific operation when generating recommended information is to refer to the prediction results from the AI ​​model and assemble a series of suggested information. The input is the prediction results, and the output is recommended information.

[0452] Step 7: Sending recommendations to the user's device

[0453] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device. Here, the recommendation information is received as input and the data to be sent to the user's device is output.

[0454] Step 8: View device recommendations

[0455] The device analyzes the received recommendation information and visually displays it to the user. Specifically, it displays the appropriate departure time and travel route in a pop-up notification or in a message field within the app. Discount coupons are also displayed within the app. Here, the received recommendation information is received as input, and the data to be displayed to the user is output.

[0456] (Application example 1)

[0457] 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."

[0458] This system solves the problem of improving the user experience by improving the operational efficiency of autonomous vehicles, avoiding congestion and traffic jams, and proposing optimal travel routes and departure times. It also aims to smooth the flow of road traffic and reduce traffic congestion by adjusting parameters in real time during operation.

[0459] 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.

[0460] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, means for transmitting the generated recommendation information to a user terminal, means for automatically adjusting operation parameters of the autonomous vehicle based on the generated recommendation information, and means for optimizing the vehicle's operation route and operation timing in cooperation with a car system. This enables efficient travel to a user's destination, smooths traffic flow, and reduces traffic congestion.

[0461] The "means for receiving user input" is an interface that allows the user to input information such as the destination, desired departure time, and acceptable waiting time via a device such as a smartphone or tablet.

[0462] "Means for collecting external data" refers to a system for collecting necessary information from external APIs via the Internet, such as weather data, traffic data, people flow data, and public transportation operation status.

[0463] "Means for preprocessing collected external data" refers to the process of preparing collected data in a state that makes it possible to analyze it, such as by filling in missing values, correcting outliers, and standardizing data formats.

[0464] "Means for inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a system for inputting preprocessed external data and user input data into an artificial intelligence model to predict congestion and traffic jams.

[0465] The "means for generating recommended information that suggests optimal travel routes and departure times" is a system that creates recommended information on the most efficient travel routes and departure times for users based on the prediction results obtained from the generative AI model.

[0466] The "means for transmitting the generated recommended information to the user terminal" is a system that transmits the recommended information created by the server to the user's smartphone or tablet, allowing the user to receive the information.

[0467] The "means for automatically adjusting the operating parameters of an autonomous vehicle based on the generated recommendation information" is a system for automatically setting and adjusting operating parameters of an autonomous vehicle, such as the operating route, speed, and stopping locations, in accordance with the recommendation information.

[0468] "Means for optimizing vehicle routes and operation timings in cooperation with car systems" refers to an interface and control system that communicates with the internal systems of an autonomous vehicle and optimizes routes and operation schedules in real time.

[0469] "User Device" means a smartphone, tablet, or other mobile device used by a User to input and receive information.

[0470] This invention is a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users, thereby improving the operating efficiency of autonomous vehicles. A specific embodiment of the system will be described.

[0471] First, the user enters information such as their destination, desired departure time, and acceptable waiting time through a smartphone application. This information is then sent to the server. The server then collects data such as weather data, traffic data, people flow data, and public transportation operation status from external APIs. This involves using external services such as weather APIs, people flow analysis APIs, and traffic information APIs.

[0472] The server then preprocesses the collected data, using data processing libraries like Pandas and NumPy to fill in missing values ​​and correct outliers. The preprocessed data and user input data are then fed into a generative AI model (for example, a model using TensorFlow or PyTorch) to predict congestion and traffic jams.

[0473] The generative AI model calculates the optimal travel route and departure time. Based on this, the server generates recommendations for the user. These recommendations include specific departure times, the means of transportation to be used, and even the route of the autonomous vehicle. This information is sent to the user's smartphone and presented visually.

[0474] Furthermore, the system automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations. This adjustment is made in cooperation with the vehicle's on-board computer and operating system, for example, optimizing the route to the destination and adjusting the speed automatically.

[0475] As a concrete example, consider the case where a user wants to go to the office in an autonomous taxi. The user enters the destination as "office," the departure time as "9:00 AM," and the waiting time tolerance as "within 10 minutes" into a smartphone app. The server collects weather and traffic data and predicts the optimal travel route and departure time. Based on the prediction results, it is determined that "departing at 8:45 AM and using main road A" is optimal. This information is sent to the autonomous taxi's operation system, and the vehicle automatically operates according to the set route.

[0476] An example prompt is:

[0477] Destination: Office

[0478] Departure time: 8:45 AM

[0479] Weather data: Clear skies

[0480] Traffic data: No traffic jams

[0481] Departure time optimization: 10 minute waiting time tolerance

[0482] This invention allows users to avoid congestion and traffic jams and travel to their destinations efficiently and comfortably. Furthermore, by adjusting the operating parameters of autonomous vehicles in real time, traffic flow can be smoothed and traffic congestion can be reduced.

[0483] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0484] Step 1:

[0485] The user inputs their destination, desired departure time, and acceptable waiting time through a smartphone app. The device collects this input data and sends it to the server.

[0486] Input: Destination, desired departure time, waiting time tolerance

[0487] Output: Sending input data to the server

[0488] Step 2:

[0489] The server collects external data such as weather data, traffic data, people flow data, and public transport operation status from external APIs. Specifically, it uses weather APIs, people flow analysis APIs, traffic information APIs, etc.

[0490] Input: Data collection request from external API

[0491] Output: Collected weather data, traffic data, people flow data, and operation status data

[0492] Step 3:

[0493] The server preprocesses the external data collected by the server, specifically by using the Pandas and NumPy libraries to impute missing values, correct outliers, and standardize the data format.

[0494] Input: Collected external data

[0495] Output: Preprocessed data

[0496] Step 4:

[0497] The server inputs the preprocessed data and user input data into a generative AI model to predict congestion and traffic jams. The generative AI model is implemented using TensorFlow and PyTorch.

[0498] Input: Preprocessed data, user input data

[0499] Output: Predicted congestion and traffic jams

[0500] Step 5:

[0501] Based on the prediction results, the server generates recommendations for the user on the optimal travel route and departure time, including specific departure times, the means of transportation to be used, and the route of the autonomous vehicle.

[0502] Input: Predicted results of congestion and traffic jams

[0503] Output: Optimal travel route, departure time, and recommendations

[0504] Step 6:

[0505] The server sends the generated recommendation information to the user's smartphone, which receives the recommendation information and visually presents it to the user.

[0506] Input: Generated recommendations

[0507] Output: Send to user's smartphone, display notification

[0508] Step 7:

[0509] The server automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations, specifically optimizing route planning, speed adjustment, and stopping locations in cooperation with the vehicle's on-board computer.

[0510] Input: Generated recommendations

[0511] Output: Adjustment of operating parameters of autonomous vehicles

[0512] 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.

[0513] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotional state.

[0514] Specifically, the system operates in the following steps.

[0515] First, the user opens the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The device then sends this input data to the server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[0516] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[0517] Furthermore, the emotion engine recognizes the user's emotions based on the user's input data and external data. Based on the user's emotional state recognized by the emotion engine, the server adjusts the generated prediction results and recommendation information. For example, if the user is feeling stressed, the server may suggest a less congested route.

[0518] Based on the adjusted prediction results, the server generates recommendation information, which includes information on departure times and travel routes, as well as customized discount coupons tailored to the user's emotions. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[0519] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[0520] For example, suppose the optimal route is predicted to be "departing at 2:30 PM and taking bus route number 5." The server recognizes Person A's emotions based on the emotion engine. In this case, if Person A is feeling stressed, the server will suggest an alternative route to avoid crowds. The adjusted recommendation information is sent to Person A's device, and Person A receives information that they should depart at 2:30 PM and take bus route number 5. They will also be provided with a discount coupon that can be used within the shopping mall.

[0521] In this way, the system avoids congestion and traffic jams and provides customized travel suggestions based on the user's emotional state, making travel more efficient and comfortable.

[0522] The processing flow will be explained below.

[0523] The present invention relates to a system that predicts congestion and traffic jams, recognizes the user's emotions, and proposes optimal travel routes and departure times. Specific processing steps of the system are shown below.

[0524] Step 1:

[0525] A user opens a smartphone app and enters input data regarding their destination, desired departure time, wait tolerance, and current emotional state.

[0526] Example: Person A enters into the app, "Shopping mall in City A," departure time is 2:00 PM, waiting time tolerance is within 15 minutes, and "I'm feeling stressed."

[0527] Step 2:

[0528] The terminal transmits the user's input data to the server.

[0529] Example: Data entered by user A is sent from the device to the server.

[0530] Step 3:

[0531] The server collects the necessary data from an external API.

[0532] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[0533] Step 4:

[0534] The server preprocesses the collected external data.

[0535] Delete unnecessary data, fill in missing values, and correct outliers.

[0536] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[0537] Step 5:

[0538] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[0539] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[0540] Step 6:

[0541] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and external data.

[0542] Example: An emotion engine analyzes the input "I'm feeling stressed" and recognizes the user's emotional state.

[0543] Step 7:

[0544] The server adjusts the generated prediction results and recommendation information based on the user's emotional state recognized by the emotion engine.

[0545] Example: Considering that Person A is feeling stressed, the server suggests a less congested route.

[0546] Step 8:

[0547] The server generates recommendations based on the adjusted prediction results.

[0548] In addition to departure times and travel routes, it also includes customized discount coupons tailored to the user's emotions.

[0549] Example: Generate a recommendation to take bus route 5 for a 2:30 PM departure, plus offer a relaxation coupon.

[0550] Step 9:

[0551] The server transmits the generated recommendation information to the user terminal.

[0552] Example: Recommended information is sent to Mr. A's smartphone.

[0553] Step 10:

[0554] The recommended information received by the terminal is visually displayed to the user.

[0555] Example: The app says, "Leave at 2:30 PM and take bus route 5. You also have a stress-reducing coupon available."

[0556] Step 11:

[0557] The user sees the recommendations and takes action.

[0558] Example: Person A leaves at 2:30 PM, takes the recommended bus route, and uses the provided coupon to receive a relaxing service.

[0559] Through the above processing steps, the system not only predicts congestion and traffic jams, but also provides customized travel suggestions based on the user's emotional state, enabling efficient and comfortable travel.

[0560] Example 2

[0561] 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."

[0562] In modern society, it is important to suggest optimal travel routes that avoid congestion and traffic jams. However, existing systems do not consider the user's emotional state and do not improve the user experience. In addition, they lack the ability to provide accurate recommendations due to insufficient preprocessing of data collected in real time. Furthermore, they are unable to provide customized recommendations that meet the user's specific needs.

[0563] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model and generating a prediction result, means for generating recommended information that suggests an optimal travel route and departure time based on the generated prediction result, means for recognizing the user's emotion and adjusting the recommended information based on the emotion, and means for transmitting the generated recommended information to the user terminal. This makes it possible to provide highly accurate recommended information based on the user's emotional state.

[0564] The "means for receiving user input" refers to a means for providing an interface that allows a user to input necessary information such as a destination, desired departure time, and acceptable waiting time to the system.

[0565] "Means for collecting external data" refers to means for obtaining external information such as weather, pedestrian flow, public transportation operation status, and search trends in real time.

[0566] The "means for preprocessing collected external data" refers to a means for performing data cleansing processing such as complementing missing values ​​in the collected external data and correcting outliers.

[0567] "Means of inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a means of predicting congestion and traffic jams using an AI model by combining preprocessed data with user input information.

[0568] "Means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to means for determining the optimal travel route and departure time for a user based on the prediction results obtained by an AI model, and creating recommended information.

[0569] The "means for recognizing the user's emotions and adjusting the recommended information based on the emotions" refers to a means for analyzing the user's emotional state and adjusting the recommended information in accordance with emotions such as stress or joy.

[0570] The "means for transmitting the generated recommendation information to the user terminal" refers to a means for transmitting the generated recommendation information to the user's device and providing it visually.

[0571] MODE FOR CARRYING OUT THE INVENTION

[0572] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system also aims to provide a more comfortable travel experience by recognizing the user's emotions and providing customized recommendations based on those emotions.

[0573] System configuration

[0574] This system consists of the following elements:

[0575] User interface: The user enters information such as the destination, desired departure time, and waiting time tolerance through a smartphone app.

[0576] Data collection module: Uses APIs to collect external data in real time, such as weather, people flow, public transport operation status, search trends, etc. Specific examples of APIs include OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[0577] Data cleansing module: Cleanses the collected data, filling in missing values ​​and correcting outliers.

[0578] Generative AI model: Predicts congestion and traffic jams based on cleansed data and user input data. TensorFlow is used as the AI ​​model.

[0579] Emotion engine: Recognizes the user's emotions based on user input data and external data. Specifically, it uses IBM Watson Tone Analyzer.

[0580] Recommendation generation module: Generates recommendations regarding optimal travel routes and departure times based on prediction results and sentiment information.

[0581] Information delivery module: The generated recommendation information is sent to the user's device and presented visually.

[0582] Specific measures include:

[0583] Means of receiving user input: Using a smartphone app, users input their destination, desired departure time, and waiting time tolerance.

[0584] Means of collecting external data: Various external data (weather, people flow, traffic conditions, search trends) are collected using API keys.

[0585] Preprocessing the collected external data: imputing missing values ​​and correcting outliers in the collected data.

[0586] A means of inputting data into a generative AI model and generating prediction results: Predict congestion and traffic jams using cleansed data and user input data.

[0587] Means for generating recommendation information: Based on the prediction results, recommendation information is generated that suggests the optimal travel route and departure time.

[0588] Means for tailoring recommendation information based on emotions: The recommendation information is tailored based on the user's emotional state recognized by the emotion engine.

[0589] Means for transmitting generated recommendation information to user terminal: The server transmits the generated recommendation information to the user's smartphone.

[0590] Specific examples

[0591] For example, consider the case where user A wants to go to a shopping mall in city A on a Sunday afternoon. User A launches the smartphone app and enters "Shopping Mall in City A" as the destination, "2 PM" as the departure time, and "within 15 minutes" as the waiting time tolerance. The device sends this data in JSON format to the server. The server collects and cleans external data from the OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[0592] The cleansed data and user input data are input into the TensorFlow model, and the system predicts the optimal travel route and departure time. For example, if it predicts that "it is best to depart at 2:30 pm and take bus route 5," the server uses IBM Watson Tone Analyzer to check whether User A is feeling stressed.

[0593] If the user is recognized as "stressed," the server generates another recommendation, such as "Leave at 3 PM and take bus route 7" to avoid the crowds. This recommendation also includes discount coupons that can be used at the shopping mall.

[0594] Finally, the generated recommendations are sent to the user's smartphone and displayed as notifications or pop-ups within the app.

[0595] Prompt Sentence Examples

[0596] "Destination: A City Shopping Mall"

[0597] "Departure time: 2 PM"

[0598] "Wait time tolerance: 15 minutes or less"

[0599] "User Emotions: Stress"

[0600] This system will enable users to avoid congestion and traffic jams and provide customized travel suggestions based on their emotional state.

[0601] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0602] Step 1:

[0603] The user launches the smartphone app and inputs the necessary information, specifically the destination, desired departure time, and waiting time tolerance. The input data is the destination (e.g., shopping mall in City A), departure time (e.g., 2:00 PM), and waiting time tolerance (e.g., within 15 minutes).

[0604] Step 2:

[0605] The device sends the user's input data to the server. Specifically, the input data for destination, departure time, and waiting time tolerance is converted into JSON format and sent to the server. Input: Input data from the user. Output: JSON data sent to the server.

[0606] Step 3:

[0607] The server collects external data. Specifically, it collects weather information from the OpenWeatherMap API, people flow data from the Google Maps API, and real-time public transportation operation status from the Local Transit APIs. Input: API key and request. Output: Weather data, people flow data, and traffic condition data.

[0608] Step 4:

[0609] The server cleanses the data collected. Specifically, it complements missing data and corrects outliers. For example, if there is a gap in the weather data, it complements it using surrounding data. Input: Collected external data. Output: Cleansed data.

[0610] Step 5:

[0611] The server inputs the cleansed data and user input data into the generative AI model to generate prediction results. Specifically, a TensorFlow model is used to predict congestion and traffic jams. The model uses prompt statements such as: "Destination: Shopping Mall in City A," "Departure time: 2:00 PM," and "Tolerance for waiting time: within 15 minutes." Input: Cleansed data, user input data. Output: Congestion prediction results.

[0612] Step 6:

[0613] The server uses an emotion engine to recognize the user's emotions. Specifically, it uses IBM Watson Tone Analyzer to analyze emotions from the user's text input or voice data. Input: User's text input or voice data. Output: User's emotional state (e.g., feeling stressed).

[0614] Step 7:

[0615] The server generates recommendation information based on the prediction results and emotional information. Specifically, it determines the optimal travel route and departure time by taking into account the congestion prediction results and the user's emotional state. For example, if the user is feeling stressed, it will recommend a route with less congestion. Input: Congestion prediction results, emotional information. Output: Customized recommendation information.

[0616] Step 8:

[0617] The server sends the generated recommendation information to the user's device. Specifically, it converts the recommendation information into JSON format and sends it to the user's smartphone. Input: Customized recommendation information. Output: JSON format recommendation information data.

[0618] Step 9:

[0619] The recommended information received by the device is visually presented to the user. Specifically, it is displayed as a notification or pop-up within the smartphone app. For example, it may display information such as "Leave at 3pm and take bus route number 7" or a discount coupon that can be used at a shopping mall. Input: Recommended information sent from the server. Output: Visual information provided to the user.

[0620] (Application example 2)

[0621] 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."

[0622] The present invention relates to a system that provides a user with an efficient and comfortable travel experience by avoiding congestion and traffic jams when traveling. In particular, the present invention aims to improve the riding experience of autonomous vehicles by providing more personalized recommendation information that takes into account the user's emotional state. Conventional technologies do not provide travel recommendations that reflect the user's emotional state, and therefore may suggest stressful routes or departure times.

[0623] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0624] In this invention, the server includes a means for receiving user input, a means for collecting external data, and a means for preprocessing the collected external data. This makes it possible to propose optimal travel routes and departure times to users based on real-time information such as weather data, people flow data, and public transportation operation status. Furthermore, by adding a means for generating recommendation information that proposes optimal travel routes and departure times based on the generated prediction results, a means for transmitting the generated recommendation information to a user terminal, and a means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state, it becomes possible to provide customized travel suggestions that take the user's emotions into consideration. This not only allows users to avoid congestion and traffic jams, but also allows them to enjoy less stressful routes and services tailored to their situation, improving the quality of their overall travel experience.

[0625] A "means for receiving user input" is a device or software that provides an interface for a user to input data such as destination, desired departure time, and wait time tolerance.

[0626] "Means for collecting external data" refers to devices or software that acquire external information in real time, such as weather data, people flow data, public transportation operation status, and search trends.

[0627] The "means for preprocessing collected external data" refers to a device or software that performs processing to complement missing values ​​and correct outliers in the collected external data and convert it into the required format.

[0628] "Means for inputting preprocessed data and user input data into a generative AI model and generating a prediction result" refers to a device or software that provides preprocessed data and user input data to an AI model and generates a prediction result for the optimal travel route and departure time based on that data.

[0629] The "means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to a device or software that creates recommended information including optimal travel routes and departure times for a user based on the generated prediction results.

[0630] The "means for transmitting the generated recommendation information to the user terminal" refers to a communication device or software for transmitting the recommendation information to the user terminal (such as a smartphone).

[0631] "Means for using an emotion engine to recognize a user's emotional state and for adjusting recommendations based on the recognized emotional state" refers to a device or software that evaluates a user's emotional state based on user input data and external data, and adapts or modifies recommendations based on the evaluation.

[0632] The present invention is a system for avoiding congestion and traffic jams when a user travels, and providing an efficient and comfortable travel experience, and is intended to be particularly applied to autonomous vehicles. Specific embodiments are described below.

[0633] The server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal.The server also includes means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state.

[0634] Users use a smartphone app to input data such as their destination, desired departure time, and acceptable waiting time. This input data is sent to a server. The server then collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs (e.g., OpenWeatherMap API and Google Maps API). The collected external data is preprocessed using a programming language such as Python. This preprocessing involves filling in missing values ​​and correcting outliers.

[0635] The preprocessed data and user input data are input into a generative AI model. This AI model predicts the optimal travel route and departure time and generates a prediction result. Based on the generated prediction result, the server generates recommended information for the user, including the optimal travel route and departure time. At this time, the emotion engine recognizes the user's emotional state and adjusts the recommended information by suggesting less crowded routes, entertainment, etc.

[0636] The generated recommendation information is sent from the server to the user's device and displayed on the user's smartphone. For example, if a user plans to go to the shopping mall at 2:00 PM, the server predicts that the best option would be to leave at 2:30 PM and take bus route 5. If the user is feeling stressed, the server will make a customized suggestion such as taking route 3, which will avoid the crowds, and playing relaxing music.

[0637] Example prompt sentence:

[0638] "The user wants to depart for the destination 'City Center' at '14:00' and their emotional state is 'Stressed'. Please predict the optimal route and departure time based on weather data and people flow data, and generate relaxing suggestions."

[0639] This allows users to reach their destination efficiently, avoiding crowds and traffic jams, and provides a comfortable travel experience that suits their emotional state.

[0640] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0641] Step 1:

[0642] The user opens the smartphone app and inputs their destination, desired departure time, waiting time tolerance, and emotional state. The smartphone app then transmits the data entered by the user to the server.

[0643] Input data: destination, desired departure time, waiting time tolerance, emotional state

[0644] Output Data: Input data sent to the server

[0645] Step 2:

[0646] The server collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs. Examples of external APIs used include the OpenWeatherMap API and Google Maps API. This data is stored on the server.

[0647] Input data: Weather data, people flow data, and public transportation status obtained from external APIs

[0648] Output data: Stored external data

[0649] Step 3:

[0650] The server preprocesses the collected external data. This involves using programming languages ​​such as Python to fill in missing values, correct outliers, and convert the data into the required format. This process improves the quality of the data and makes it suitable for input into AI models.

[0651] Input data: Stored external data

[0652] Output data: Preprocessed data

[0653] Step 4:

[0654] The preprocessed data and user input data are input into the generative AI model to generate a prediction. The AI ​​model then predicts the optimal travel route and departure time based on the input data. For example, it may predict that the user should take the "Route 5" bus at 2:30 PM.

[0655] Input data: Preprocessed data, user input data

[0656] Output data: Prediction results (optimal travel route and departure time)

[0657] Step 5:

[0658] The server generates recommendations based on the prediction results, suggesting optimal travel routes and departure times. In addition, the emotion engine recognizes the user's emotional state and adjusts the recommendations based on that emotional state. For example, if the user is feeling stressed, it will suggest less crowded routes and provide relaxing music.

[0659] Input data: prediction results, user's emotional state

[0660] Output: Tailored recommendations

[0661] Step 6:

[0662] The server then sends the adjusted recommendation information to the user's device, which then visually displays the received recommendation information and indicates the next action the user should take. For example, the recommendation "Leave at 2:30 PM and take the Route 5 bus" or a discount coupon for a shopping mall is displayed.

[0663] Input data: Tailored recommendations

[0664] Output data: Recommendation information displayed on the user's device

[0665] Step 7:

[0666] Users travel according to the recommended information displayed on their smartphone app and board an autonomous vehicle. In the process, they enjoy a comfortable travel experience by using the recommended route and receiving suggested services.

[0667] Input data: Recommendation information displayed on the user's device

[0668] Output data: User's actual travel experience

[0669] 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.

[0670] 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.

[0671] 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.

[0672] [Third embodiment]

[0673] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0674] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0675] 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).

[0676] 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.

[0677] 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.

[0678] 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).

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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."

[0685] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[0686] Specifically, users input their destination, desired departure time, and acceptable waiting time through a smartphone app. The device then sends this input data to a server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation status, and search trends.

[0687] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[0688] Based on the prediction results, the server generates recommendation information, which may include information about departure times, travel routes, and even discount coupons for the user. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[0689] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[0690] For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route number 5." The server generates recommendation information based on this information and sends it to Mr. A's device. The device notifies Mr. A in the form of "Leaving at 2:30 PM and taking bus route number 5." A discount coupon that can be used within the shopping mall is also provided.

[0691] In this way, the system allows users to avoid congestion and traffic jams, enabling efficient and comfortable travel.

[0692] The processing flow will be explained below.

[0693] Step 1:

[0694] The user opens the smartphone app and enters their destination, desired departure time, and acceptable waiting time.

[0695] Example: Person A enters into the app the following information: "Shopping mall in City A," departure time: 2:00 PM, acceptable waiting time: 15 minutes or less.

[0696] Step 2:

[0697] The terminal transmits the user's input data to the server.

[0698] Example: Data entered by user A is sent from the device to the server.

[0699] Step 3:

[0700] The server collects the necessary data from an external API.

[0701] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[0702] Step 4:

[0703] The server preprocesses the collected external data.

[0704] Delete unnecessary data, fill in missing values, and correct outliers.

[0705] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[0706] Step 5:

[0707] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[0708] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[0709] Step 6:

[0710] The server generates recommendations based on the prediction results.

[0711] Generate recommendations including travel routes, departure times, relevant coupons, etc.

[0712] Example: Generate a recommendation to depart at 2:30 PM and take bus route 5.

[0713] Step 7:

[0714] The server transmits the generated recommendation information to the user terminal.

[0715] Example: Recommended information is sent to Mr. A's smartphone.

[0716] Step 8:

[0717] The recommended information received by the terminal is visually displayed to the user.

[0718] Example: The app tells you to leave at 2:30 PM and take bus route 5, and also offers a shopping mall coupon.

[0719] Step 9:

[0720] The user sees the recommendations and takes action.

[0721] Example: Person A leaves at 2:30 pm and takes the recommended bus route.

[0722] Example 1

[0723] 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."

[0724] In modern times, urban congestion and traffic jams are one of the problems that significantly impair the efficiency and comfort of travel. In particular, due to the wide range of external factors, such as sudden weather changes, irregular pedestrian flows, and public transportation delays, it is difficult to propose optimal travel routes and departure times that take these factors into account. Furthermore, it is necessary to consider the user's time and tolerance for waiting times at the destination, making manual planning extremely cumbersome and inefficient.

[0725] 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.

[0726] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal, thereby making it possible to provide users with optimal travel routes and departure times in real time.

[0727] "User input" refers to information such as the destination, desired departure time, and waiting time tolerance that the user provides through the terminal.

[0728] "External data" refers to data collected from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[0729] "Preprocessing" refers to processes such as filling in missing values ​​in collected external data, correcting outliers, and standardizing data formats.

[0730] A "generative AI model" is an artificial intelligence model that predicts congestion and traffic jams and calculates optimal travel routes and departure times based on preprocessed data and user input data.

[0731] The "prediction results" are information calculated by the generative AI model on the optimal travel route and departure time for the user, including predictions of congestion and traffic jams.

[0732] "Recommended information" is information such as the optimal travel route and departure time for the user, as well as related discount coupons, generated based on the prediction results.

[0733] A "user terminal" is a device used by a user, such as a smartphone or tablet, that receives and displays the recommended information sent from the server.

[0734] "Cleaning" is the process of correcting missing or outlier values ​​in data to create accurate and consistent data.

[0735] "Collection" refers to the operation in which the server obtains external data such as weather data, people flow data, public transportation operation status, and search trends through an external API.

[0736] A "discount coupon" is information provided to a user to receive a discount at a store or service.

[0737] MODE FOR CARRYING OUT THE INVENTION

[0738] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[0739] Hardware and Software

[0740] 1. Hardware: Server, user device (smartphone)

[0741] 2. Software: Smartphone app, external API (weather data, people flow data, public transport operation status, search trends), generative AI model

[0742] Explanation of characteristic program processing

[0743] 1. User input

[0744] The user starts the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. For example, Mr. A inputs "Shopping Mall in City A," departure time "2:00 PM," and waiting time tolerance "within 15 minutes."

[0745] 2. Sending data from the device to the server

[0746] The terminal sends the data entered by the user to the server. Specifically, when the submit button on the input form is pressed, the terminal converts the user's input data into JSON format and sends an HTTP request to the server's API endpoint.

[0747] 3. Collection of external data by the server

[0748] The server uses external APIs to collect necessary data in real time based on the received user data. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transport operation status from the Transit API.

[0749] 4. Data preprocessing by the server

[0750] The collected data cannot be used as is, so it is preprocessed on the server. Specifically, missing values ​​are filled in, outliers are corrected, and the data format is standardized. For example, if there is missing weather data, it is filled in by guessing based on past data.

[0751] 5. Data input and prediction for generative AI model

[0752] The preprocessed data and user input data are input into the generative AI model. Based on this data, the generative AI model predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user. For example, it predicts that "departing at 2:30 PM and taking bus route 5" is optimal.

[0753] 6. Server-generated recommendations

[0754] Based on the predictions from the generative AI model, the server generates recommendations for the user, including specific travel routes, departure times, and even discount coupons. For example, it generates a message such as, "Leave at 2:30 PM and take bus route 5."

[0755] 7. Sending recommended information to the user's device

[0756] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device.

[0757] 8. Display of recommendations by device

[0758] The device analyzes the received recommendations and visually displays them to the user, such as in a pop-up notification or in-app message box, suggesting "Leave at 2:30 PM and take bus route 5," and also offering discount coupons for use within the shopping mall.

[0759] Specific examples

[0760] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters their destination as "Shopping Mall in City A," their departure time as "2:00 PM," and their acceptable waiting time as "within 15 minutes" into a smartphone app. The device sends this input data to the server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time. For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route 5." The server generates recommendation information based on this information and sends it to Person A's device. The device notifies Person A in the form of "Leaving at 2:30 PM and taking bus route 5." A discount coupon that can be used within the shopping mall is also provided.

[0761] Prompt Sentence Examples

[0762] An example of a prompt sentence is, "Please predict the best route and departure time for the user to go to the shopping mall on Sunday afternoon, and provide recommendations to avoid crowds and traffic jams. The user's input data is the destination "Shopping Mall in City A", the departure time "2:00 PM", and the waiting time tolerance "within 15 minutes."

[0763] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0764] Step 1: User Input

[0765] A user launches a smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The input data includes information provided by the user using an input form within the app. For example, the user might input "Destination: Shopping mall in the city," "Departure time: 2:00 PM," and "Waiting time tolerance: within 15 minutes."

[0766] Step 2: Send data from the device to the server

[0767] The device converts the input data into JSON format and sends an HTTP request to the server's API endpoint. Specifically, when the user presses the send button, the input data is transferred to the server. The input data includes the user's destination, desired departure time, and waiting time tolerance.

[0768] Step 3: Collecting external data by the server

[0769] The server uses external APIs to collect necessary external data based on the input data received from the user. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transportation operation status from the Transit API. The collected data is updated in real time.

[0770] Step 4: Preprocessing the data on the server

[0771] The server preprocesses the collected external data. This preprocessing includes filling in missing values ​​and correcting outliers. For example, if there are missing values ​​in weather data, it fills in the missing values ​​with estimated values ​​using past data. It receives external data as input and outputs preprocessed data.

[0772] Step 5: Input data into the generative AI model and make predictions

[0773] The server inputs the preprocessed data and user input data into the generative AI model. The generative AI model uses this data to predict congestion and traffic jams, and calculates the optimal travel route and departure time. For example, the model predicts that "departing at 2:30 PM and taking bus route 5" is optimal. Here, it receives the input data and preprocessed data and outputs the predicted results.

[0774] Step 6: Server Generates Recommendations

[0775] The server generates recommended information based on the prediction results. The recommended information includes the user's optimal travel route, departure time, discount coupons, etc. The specific operation when generating recommended information is to refer to the prediction results from the AI ​​model and assemble a series of suggested information. The input is the prediction results, and the output is recommended information.

[0776] Step 7: Sending recommendations to the user's device

[0777] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device. Here, the recommendation information is received as input and the data to be sent to the user's device is output.

[0778] Step 8: View device recommendations

[0779] The device analyzes the received recommendation information and visually displays it to the user. Specifically, it displays the appropriate departure time and travel route in a pop-up notification or in a message field within the app. Discount coupons are also displayed within the app. Here, the received recommendation information is received as input, and the data to be displayed to the user is output.

[0780] (Application example 1)

[0781] 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."

[0782] This system solves the problem of improving the user experience by improving the operational efficiency of autonomous vehicles, avoiding congestion and traffic jams, and proposing optimal travel routes and departure times. It also aims to smooth the flow of road traffic and reduce traffic congestion by adjusting parameters in real time during operation.

[0783] 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.

[0784] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, means for transmitting the generated recommendation information to a user terminal, means for automatically adjusting operation parameters of the autonomous vehicle based on the generated recommendation information, and means for optimizing the vehicle's operation route and operation timing in cooperation with a car system. This enables efficient travel to a user's destination, smooths traffic flow, and reduces traffic congestion.

[0785] The "means for receiving user input" is an interface that allows the user to input information such as the destination, desired departure time, and acceptable waiting time via a device such as a smartphone or tablet.

[0786] "Means for collecting external data" refers to a system for collecting necessary information from external APIs via the Internet, such as weather data, traffic data, people flow data, and public transportation operation status.

[0787] "Means for preprocessing collected external data" refers to the process of preparing collected data in a state that makes it analyzable, such as by filling in missing values, correcting outliers, and standardizing data formats.

[0788] "Means for inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a system for inputting preprocessed external data and user input data into an artificial intelligence model to predict congestion and traffic jams.

[0789] The "means for generating recommended information that suggests optimal travel routes and departure times" is a system that creates recommended information on the most efficient travel routes and departure times for users based on the prediction results obtained from the generative AI model.

[0790] The "means for transmitting the generated recommended information to the user terminal" is a system that transmits the recommended information created by the server to the user's smartphone or tablet, allowing the user to receive the information.

[0791] The "means for automatically adjusting the operating parameters of an autonomous vehicle based on the generated recommendation information" is a system for automatically setting and adjusting operating parameters of an autonomous vehicle, such as the operating route, speed, and stopping locations, in accordance with the recommendation information.

[0792] "Means for optimizing vehicle routes and operation timings in cooperation with car systems" refers to an interface and control system that communicates with the internal systems of an autonomous vehicle and optimizes routes and operation schedules in real time.

[0793] "User Device" means a smartphone, tablet, or other mobile device used by a User to input and receive information.

[0794] This invention is a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users, thereby improving the operating efficiency of autonomous vehicles. A specific embodiment of the system will be described.

[0795] First, the user enters information such as their destination, desired departure time, and acceptable waiting time through a smartphone application. This information is then sent to the server. The server then collects data such as weather data, traffic data, people flow data, and public transportation operation status from external APIs. This involves using external services such as weather APIs, people flow analysis APIs, and traffic information APIs.

[0796] The server then preprocesses the collected data, using data processing libraries like Pandas and NumPy to fill in missing values ​​and correct outliers. The preprocessed data and user input data are then fed into a generative AI model (for example, a model using TensorFlow or PyTorch) to predict congestion and traffic jams.

[0797] The generative AI model calculates the optimal travel route and departure time. Based on this, the server generates recommendations for the user. These recommendations include specific departure times, the means of transportation to be used, and even the route of the autonomous vehicle. This information is sent to the user's smartphone and presented visually.

[0798] Furthermore, the system automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations. This adjustment is made in cooperation with the vehicle's on-board computer and operating system, for example, optimizing the route to the destination and adjusting the speed automatically.

[0799] As a concrete example, consider the case where a user wants to go to the office in an autonomous taxi. The user enters the destination as "office," the departure time as "9:00 AM," and the waiting time tolerance as "within 10 minutes" into a smartphone app. The server collects weather and traffic data and predicts the optimal travel route and departure time. Based on the prediction results, it is determined that "departing at 8:45 AM and using main road A" is optimal. This information is sent to the autonomous taxi's operation system, and the vehicle automatically operates according to the set route.

[0800] An example prompt is:

[0801] Destination: Office

[0802] Departure time: 8:45 AM

[0803] Weather data: Clear skies

[0804] Traffic data: No traffic jams

[0805] Departure time optimization: 10 minute waiting time tolerance

[0806] This invention allows users to avoid congestion and traffic jams and travel to their destinations efficiently and comfortably. Furthermore, by adjusting the operating parameters of autonomous vehicles in real time, traffic flow can be smoothed and traffic congestion can be reduced.

[0807] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0808] Step 1:

[0809] The user inputs their destination, desired departure time, and acceptable waiting time through a smartphone app. The device collects this input data and sends it to the server.

[0810] Input: Destination, desired departure time, waiting time tolerance

[0811] Output: Sending input data to the server

[0812] Step 2:

[0813] The server collects external data such as weather data, traffic data, people flow data, and public transport operation status from external APIs. Specifically, it uses weather APIs, people flow analysis APIs, traffic information APIs, etc.

[0814] Input: Data collection request from external API

[0815] Output: Collected weather data, traffic data, people flow data, and operation status data

[0816] Step 3:

[0817] The server preprocesses the external data collected by the server, specifically by using the Pandas and NumPy libraries to impute missing values, correct outliers, and standardize the data format.

[0818] Input: Collected external data

[0819] Output: Preprocessed data

[0820] Step 4:

[0821] The server inputs the preprocessed data and user input data into a generative AI model to predict congestion and traffic jams. The generative AI model is implemented using TensorFlow and PyTorch.

[0822] Input: Preprocessed data, user input data

[0823] Output: Predicted congestion and traffic jams

[0824] Step 5:

[0825] Based on the prediction results, the server generates recommendations for the user on the optimal travel route and departure time, including specific departure times, the means of transportation to be used, and the route of the autonomous vehicle.

[0826] Input: Predicted results of congestion and traffic jams

[0827] Output: Optimal travel route, departure time, and recommendations

[0828] Step 6:

[0829] The server sends the generated recommendation information to the user's smartphone, which receives the recommendation information and visually presents it to the user.

[0830] Input: Generated recommendations

[0831] Output: Send to user's smartphone, display notification

[0832] Step 7:

[0833] The server automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations, specifically optimizing route planning, speed adjustment, and stopping locations in cooperation with the vehicle's on-board computer.

[0834] Input: Generated recommendations

[0835] Output: Adjustment of operating parameters of autonomous vehicles

[0836] 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.

[0837] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotional state.

[0838] Specifically, the system operates in the following steps.

[0839] First, the user opens the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The device then sends this input data to the server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[0840] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[0841] Furthermore, the emotion engine recognizes the user's emotions based on the user's input data and external data. Based on the user's emotional state recognized by the emotion engine, the server adjusts the generated prediction results and recommendation information. For example, if the user is feeling stressed, the server may suggest a less congested route.

[0842] Based on the adjusted prediction results, the server generates recommendation information, which includes information on departure times and travel routes, as well as customized discount coupons tailored to the user's emotions. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[0843] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[0844] For example, suppose the optimal route is predicted to be "departing at 2:30 PM and taking bus route number 5." The server recognizes Person A's emotions based on the emotion engine. In this case, if Person A is feeling stressed, the server will suggest an alternative route to avoid crowds. The adjusted recommendation information is sent to Person A's device, and Person A receives information that they should depart at 2:30 PM and take bus route number 5. They will also be provided with a discount coupon that can be used within the shopping mall.

[0845] In this way, the system avoids congestion and traffic jams and provides customized travel suggestions based on the user's emotional state, making travel more efficient and comfortable.

[0846] The processing flow will be explained below.

[0847] The present invention relates to a system that predicts congestion and traffic jams, recognizes the user's emotions, and proposes optimal travel routes and departure times. Specific processing steps of the system are shown below.

[0848] Step 1:

[0849] A user opens a smartphone app and enters input data regarding their destination, desired departure time, wait tolerance, and current emotional state.

[0850] Example: Person A enters into the app, "Shopping mall in City A," departure time is 2:00 PM, waiting time tolerance is within 15 minutes, and "I'm feeling stressed."

[0851] Step 2:

[0852] The terminal transmits the user's input data to the server.

[0853] Example: Data entered by user A is sent from the device to the server.

[0854] Step 3:

[0855] The server collects the necessary data from an external API.

[0856] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[0857] Step 4:

[0858] The server preprocesses the collected external data.

[0859] Delete unnecessary data, fill in missing values, and correct outliers.

[0860] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[0861] Step 5:

[0862] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[0863] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[0864] Step 6:

[0865] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and external data.

[0866] Example: An emotion engine analyzes the input "I'm feeling stressed" and recognizes the user's emotional state.

[0867] Step 7:

[0868] The server adjusts the generated prediction results and recommendation information based on the user's emotional state recognized by the emotion engine.

[0869] Example: Considering that Person A is feeling stressed, the server suggests a less congested route.

[0870] Step 8:

[0871] The server generates recommendations based on the adjusted prediction results.

[0872] In addition to departure times and travel routes, it also includes customized discount coupons tailored to the user's emotions.

[0873] Example: Generate a recommendation to take bus route 5 for a 2:30 PM departure, plus offer a relaxation coupon.

[0874] Step 9:

[0875] The server transmits the generated recommendation information to the user terminal.

[0876] Example: Recommended information is sent to Mr. A's smartphone.

[0877] Step 10:

[0878] The recommended information received by the terminal is visually displayed to the user.

[0879] Example: The app says, "Leave at 2:30 PM and take bus route 5. You also have a stress-reducing coupon available."

[0880] Step 11:

[0881] The user sees the recommendations and takes action.

[0882] Example: Person A leaves at 2:30 PM, takes the recommended bus route, and uses the provided coupon to receive a relaxing service.

[0883] Through the above processing steps, the system not only predicts congestion and traffic jams, but also provides customized travel suggestions based on the user's emotional state, enabling efficient and comfortable travel.

[0884] Example 2

[0885] 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."

[0886] In modern society, it is important to suggest optimal travel routes that avoid congestion and traffic jams. However, existing systems do not consider the user's emotional state and do not improve the user experience. In addition, they lack the ability to provide accurate recommendations due to insufficient preprocessing of data collected in real time. Furthermore, they are unable to provide customized recommendations that meet the user's specific needs.

[0887] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model and generating a prediction result, means for generating recommended information that suggests an optimal travel route and departure time based on the generated prediction result, means for recognizing the user's emotion and adjusting the recommended information based on the emotion, and means for transmitting the generated recommended information to the user terminal. This makes it possible to provide highly accurate recommended information based on the user's emotional state.

[0888] The "means for receiving user input" refers to a means for providing an interface that allows a user to input necessary information such as a destination, desired departure time, and acceptable waiting time to the system.

[0889] "Means for collecting external data" refers to means for obtaining external information such as weather, pedestrian flow, public transportation operation status, and search trends in real time.

[0890] The "means for preprocessing collected external data" refers to a means for performing data cleansing processing such as complementing missing values ​​in the collected external data and correcting outliers.

[0891] "Means of inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a means of predicting congestion and traffic jams using an AI model by combining preprocessed data with user input information.

[0892] "Means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to means for determining the optimal travel route and departure time for a user based on the prediction results obtained by an AI model, and creating recommended information.

[0893] The "means for recognizing the user's emotions and adjusting the recommended information based on the emotions" refers to a means for analyzing the user's emotional state and adjusting the recommended information in accordance with emotions such as stress or joy.

[0894] The "means for transmitting the generated recommendation information to the user terminal" refers to a means for transmitting the generated recommendation information to the user's device and providing it visually.

[0895] MODE FOR CARRYING OUT THE INVENTION

[0896] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system also aims to provide a more comfortable travel experience by recognizing the user's emotions and providing customized recommendations based on those emotions.

[0897] System configuration

[0898] This system consists of the following elements:

[0899] User interface: The user enters information such as the destination, desired departure time, and waiting time tolerance through a smartphone app.

[0900] Data collection module: Uses APIs to collect external data in real time, such as weather, people flow, public transport operation status, search trends, etc. Specific examples of APIs include OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[0901] Data cleansing module: Cleanses the collected data, filling in missing values ​​and correcting outliers.

[0902] Generative AI model: Predicts congestion and traffic jams based on cleansed data and user input data. TensorFlow is used as the AI ​​model.

[0903] Emotion engine: Recognizes the user's emotions based on user input data and external data. Specifically, it uses IBM Watson Tone Analyzer.

[0904] Recommendation generation module: Generates recommendations regarding optimal travel routes and departure times based on prediction results and sentiment information.

[0905] Information delivery module: The generated recommendation information is sent to the user's device and presented visually.

[0906] Specific measures include:

[0907] Means of receiving user input: Using a smartphone app, users input their destination, desired departure time, and waiting time tolerance.

[0908] Means of collecting external data: Various external data (weather, people flow, traffic conditions, search trends) are collected using API keys.

[0909] Preprocessing the collected external data: imputing missing values ​​and correcting outliers in the collected data.

[0910] A means of inputting data into a generative AI model and generating prediction results: Predict congestion and traffic jams using cleansed data and user input data.

[0911] Means for generating recommendation information: Based on the prediction results, recommendation information is generated that suggests the optimal travel route and departure time.

[0912] Means for tailoring recommendation information based on emotions: The recommendation information is tailored based on the user's emotional state recognized by the emotion engine.

[0913] Means for transmitting generated recommendation information to user terminal: The server transmits the generated recommendation information to the user's smartphone.

[0914] Specific examples

[0915] For example, consider the case where user A wants to go to a shopping mall in city A on a Sunday afternoon. User A launches the smartphone app and enters "Shopping Mall in City A" as the destination, "2 PM" as the departure time, and "within 15 minutes" as the waiting time tolerance. The device sends this data in JSON format to the server. The server collects and cleans external data from the OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[0916] The cleansed data and user input data are input into the TensorFlow model, and the system predicts the optimal travel route and departure time. For example, if it predicts that "it is best to depart at 2:30 pm and take bus route 5," the server uses IBM Watson Tone Analyzer to check whether User A is feeling stressed.

[0917] If the user is recognized as "stressed," the server generates another recommendation, such as "Leave at 3 PM and take bus route 7" to avoid the crowds. This recommendation also includes discount coupons that can be used at the shopping mall.

[0918] Finally, the generated recommendations are sent to the user's smartphone and displayed as notifications or pop-ups within the app.

[0919] Prompt Sentence Examples

[0920] "Destination: A City Shopping Mall"

[0921] "Departure time: 2 PM"

[0922] "Wait time tolerance: 15 minutes or less"

[0923] "User Emotions: Stress"

[0924] This system will enable users to avoid congestion and traffic jams and provide customized travel suggestions based on their emotional state.

[0925] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0926] Step 1:

[0927] The user launches the smartphone app and inputs the necessary information, specifically the destination, desired departure time, and waiting time tolerance. The input data is the destination (e.g., shopping mall in City A), departure time (e.g., 2:00 PM), and waiting time tolerance (e.g., within 15 minutes).

[0928] Step 2:

[0929] The device sends the user's input data to the server. Specifically, the input data for destination, departure time, and waiting time tolerance is converted into JSON format and sent to the server. Input: Input data from the user. Output: JSON data sent to the server.

[0930] Step 3:

[0931] The server collects external data. Specifically, it collects weather information from the OpenWeatherMap API, people flow data from the Google Maps API, and real-time public transportation operation status from the Local Transit APIs. Input: API key and request. Output: Weather data, people flow data, and traffic condition data.

[0932] Step 4:

[0933] The server cleanses the data collected. Specifically, it complements missing data and corrects outliers. For example, if there is a gap in the weather data, it complements it using surrounding data. Input: Collected external data. Output: Cleansed data.

[0934] Step 5:

[0935] The server inputs the cleansed data and user input data into the generative AI model to generate prediction results. Specifically, a TensorFlow model is used to predict congestion and traffic jams. The model uses prompt statements such as: "Destination: Shopping Mall in City A," "Departure time: 2:00 PM," and "Tolerance for waiting time: within 15 minutes." Input: Cleansed data, user input data. Output: Congestion prediction results.

[0936] Step 6:

[0937] The server uses an emotion engine to recognize the user's emotions. Specifically, it uses IBM Watson Tone Analyzer to analyze emotions from the user's text input or voice data. Input: User's text input or voice data. Output: User's emotional state (e.g., feeling stressed).

[0938] Step 7:

[0939] The server generates recommendation information based on the prediction results and emotional information. Specifically, it determines the optimal travel route and departure time by taking into account the congestion prediction results and the user's emotional state. For example, if the user is feeling stressed, it will recommend a route with less congestion. Input: Congestion prediction results, emotional information. Output: Customized recommendation information.

[0940] Step 8:

[0941] The server sends the generated recommendation information to the user's device. Specifically, it converts the recommendation information into JSON format and sends it to the user's smartphone. Input: Customized recommendation information. Output: JSON format recommendation information data.

[0942] Step 9:

[0943] The recommended information received by the device is visually presented to the user. Specifically, it is displayed as a notification or pop-up within the smartphone app. For example, it may display information such as "Leave at 3pm and take bus route number 7" or a discount coupon that can be used at a shopping mall. Input: Recommended information sent from the server. Output: Visual information provided to the user.

[0944] (Application example 2)

[0945] 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."

[0946] The present invention relates to a system that provides a user with an efficient and comfortable travel experience by avoiding congestion and traffic jams when traveling. In particular, the present invention aims to improve the riding experience of autonomous vehicles by providing more personalized recommendation information that takes into account the user's emotional state. Conventional technologies do not provide travel recommendations that reflect the user's emotional state, and therefore may suggest stressful routes or departure times.

[0947] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0948] In this invention, the server includes a means for receiving user input, a means for collecting external data, and a means for preprocessing the collected external data. This makes it possible to propose optimal travel routes and departure times to users based on real-time information such as weather data, people flow data, and public transportation operation status. Furthermore, by adding a means for generating recommendation information that proposes optimal travel routes and departure times based on the generated prediction results, a means for transmitting the generated recommendation information to a user terminal, and a means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state, it becomes possible to provide customized travel suggestions that take the user's emotions into consideration. This not only allows users to avoid congestion and traffic jams, but also allows them to enjoy less stressful routes and services tailored to their situation, improving the quality of their overall travel experience.

[0949] A "means for receiving user input" is a device or software that provides an interface for a user to input data such as destination, desired departure time, and wait time tolerance.

[0950] "Means for collecting external data" refers to devices or software that acquire external information in real time, such as weather data, people flow data, public transportation operation status, and search trends.

[0951] The "means for preprocessing collected external data" refers to a device or software that performs processing to complement missing values ​​and correct outliers in the collected external data and convert it into the required format.

[0952] "Means for inputting preprocessed data and user input data into a generative AI model and generating a prediction result" refers to a device or software that provides preprocessed data and user input data to an AI model and generates a prediction result for the optimal travel route and departure time based on that data.

[0953] The "means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to a device or software that creates recommended information including optimal travel routes and departure times for a user based on the generated prediction results.

[0954] The "means for transmitting the generated recommendation information to the user terminal" refers to a communication device or software for transmitting the recommendation information to the user terminal (such as a smartphone).

[0955] "Means for using an emotion engine to recognize a user's emotional state and for adjusting recommendations based on the recognized emotional state" refers to a device or software that evaluates a user's emotional state based on user input data and external data, and adapts or modifies recommendations based on the evaluation.

[0956] The present invention is a system for avoiding congestion and traffic jams when a user travels, and providing an efficient and comfortable travel experience, and is intended to be particularly applied to autonomous vehicles. Specific embodiments are described below.

[0957] The server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal.The server also includes means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state.

[0958] Users use a smartphone app to input data such as their destination, desired departure time, and acceptable waiting time. This input data is sent to a server. The server then collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs (e.g., OpenWeatherMap API and Google Maps API). The collected external data is preprocessed using a programming language such as Python. This preprocessing involves filling in missing values ​​and correcting outliers.

[0959] The preprocessed data and user input data are input into a generative AI model. This AI model predicts the optimal travel route and departure time and generates a prediction result. Based on the generated prediction result, the server generates recommended information for the user, including the optimal travel route and departure time. At this time, the emotion engine recognizes the user's emotional state and adjusts the recommended information by suggesting less crowded routes, entertainment, etc.

[0960] The generated recommendation information is sent from the server to the user's device and displayed on the user's smartphone. For example, if a user plans to go to the shopping mall at 2:00 PM, the server predicts that the best option would be to leave at 2:30 PM and take bus route 5. If the user is feeling stressed, the server will make a customized suggestion such as taking route 3, which will avoid the crowds, and playing relaxing music.

[0961] Example prompt sentence:

[0962] "The user wants to depart for the destination 'City Center' at '14:00' and their emotional state is 'Stressed'. Please predict the optimal route and departure time based on weather data and people flow data, and generate relaxing suggestions."

[0963] This allows users to reach their destination efficiently, avoiding crowds and traffic jams, and provides a comfortable travel experience that suits their emotional state.

[0964] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0965] Step 1:

[0966] The user opens the smartphone app and inputs their destination, desired departure time, waiting time tolerance, and emotional state. The smartphone app then transmits the data entered by the user to the server.

[0967] Input data: destination, desired departure time, waiting time tolerance, emotional state

[0968] Output Data: Input data sent to the server

[0969] Step 2:

[0970] The server collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs. Examples of external APIs used include the OpenWeatherMap API and Google Maps API. This data is stored on the server.

[0971] Input data: Weather data, people flow data, and public transportation status obtained from external APIs

[0972] Output data: Stored external data

[0973] Step 3:

[0974] The server preprocesses the collected external data. This involves using programming languages ​​such as Python to fill in missing values, correct outliers, and convert the data into the required format. This process improves the quality of the data and makes it suitable for input into AI models.

[0975] Input data: Stored external data

[0976] Output data: Preprocessed data

[0977] Step 4:

[0978] The preprocessed data and user input data are input into the generative AI model to generate a prediction. The AI ​​model then predicts the optimal travel route and departure time based on the input data. For example, it may predict that the user should take the "Route 5" bus at 2:30 PM.

[0979] Input data: Preprocessed data, user input data

[0980] Output data: Prediction results (optimal travel route and departure time)

[0981] Step 5:

[0982] The server generates recommendations based on the prediction results, suggesting optimal travel routes and departure times. In addition, the emotion engine recognizes the user's emotional state and adjusts the recommendations based on that emotional state. For example, if the user is feeling stressed, it will suggest less crowded routes and provide relaxing music.

[0983] Input data: prediction results, user's emotional state

[0984] Output: Tailored recommendations

[0985] Step 6:

[0986] The server then sends the adjusted recommendation information to the user's device, which then visually displays the received recommendation information and indicates the next action the user should take. For example, the recommendation "Leave at 2:30 PM and take the Route 5 bus" or a discount coupon for a shopping mall is displayed.

[0987] Input data: Tailored recommendations

[0988] Output data: Recommendation information displayed on the user's device

[0989] Step 7:

[0990] Users travel according to the recommended information displayed on their smartphone app and board an autonomous vehicle. In the process, they enjoy a comfortable travel experience by using the recommended route and receiving suggested services.

[0991] Input data: Recommendation information displayed on the user's device

[0992] Output data: User's actual travel experience

[0993] 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.

[0994] 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.

[0995] 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.

[0996] [Fourth embodiment]

[0997] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0998] 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.

[0999] 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).

[1000] 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.

[1001] 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.

[1002] 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).

[1003] 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.

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] 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.

[1009] 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."

[1010] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[1011] Specifically, users input their destination, desired departure time, and acceptable waiting time through a smartphone app. The device then sends this input data to a server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation status, and search trends.

[1012] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[1013] Based on the prediction results, the server generates recommendation information, which may include information about departure times, travel routes, and even discount coupons for the user. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[1014] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[1015] For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route number 5." The server generates recommendation information based on this information and sends it to Mr. A's device. The device notifies Mr. A in the form of "Leaving at 2:30 PM and taking bus route number 5." A discount coupon that can be used within the shopping mall is also provided.

[1016] In this way, the system allows users to avoid congestion and traffic jams, enabling efficient and comfortable travel.

[1017] The processing flow will be explained below.

[1018] Step 1:

[1019] The user opens the smartphone app and enters their destination, desired departure time, and acceptable waiting time.

[1020] Example: Person A enters into the app the following information: "Shopping mall in City A," departure time: 2:00 PM, acceptable waiting time: 15 minutes or less.

[1021] Step 2:

[1022] The terminal transmits the user's input data to the server.

[1023] Example: Data entered by user A is sent from the device to the server.

[1024] Step 3:

[1025] The server collects the necessary data from an external API.

[1026] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[1027] Step 4:

[1028] The server preprocesses the collected external data.

[1029] Delete unnecessary data, fill in missing values, and correct outliers.

[1030] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[1031] Step 5:

[1032] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[1033] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[1034] Step 6:

[1035] The server generates recommendations based on the prediction results.

[1036] Generate recommendations including travel routes, departure times, relevant coupons, etc.

[1037] Example: Generate a recommendation to depart at 2:30 PM and take bus route 5.

[1038] Step 7:

[1039] The server transmits the generated recommendation information to the user terminal.

[1040] Example: Recommended information is sent to Mr. A's smartphone.

[1041] Step 8:

[1042] The recommended information received by the terminal is visually displayed to the user.

[1043] Example: The app tells you to leave at 2:30 PM and take bus route 5, and also offers a shopping mall coupon.

[1044] Step 9:

[1045] The user sees the recommendations and takes action.

[1046] Example: Person A leaves at 2:30 pm and takes the recommended bus route.

[1047] Example 1

[1048] 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."

[1049] In modern times, urban congestion and traffic jams are one of the problems that significantly impair the efficiency and comfort of travel. In particular, due to the wide range of external factors, such as sudden weather changes, irregular pedestrian flows, and public transportation delays, it is difficult to propose optimal travel routes and departure times that take these factors into account. Furthermore, it is necessary to consider the user's time and tolerance for waiting times at the destination, making manual planning extremely cumbersome and inefficient.

[1050] 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.

[1051] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal, thereby making it possible to provide users with optimal travel routes and departure times in real time.

[1052] "User input" refers to information such as the destination, desired departure time, and waiting time tolerance that the user provides through the terminal.

[1053] "External data" refers to data collected from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[1054] "Preprocessing" refers to processes such as filling in missing values ​​in collected external data, correcting outliers, and standardizing data formats.

[1055] A "generative AI model" is an artificial intelligence model that predicts congestion and traffic jams and calculates optimal travel routes and departure times based on preprocessed data and user input data.

[1056] The "prediction results" are information calculated by the generative AI model on the optimal travel route and departure time for the user, including predictions of congestion and traffic jams.

[1057] "Recommended information" is information such as the optimal travel route and departure time for the user, as well as related discount coupons, generated based on the prediction results.

[1058] A "user terminal" is a device used by a user, such as a smartphone or tablet, that receives and displays the recommended information sent from the server.

[1059] "Cleaning" is the process of correcting missing or outlier values ​​in data to create accurate and consistent data.

[1060] "Collection" refers to the operation in which the server obtains external data such as weather data, people flow data, public transportation operation status, and search trends through an external API.

[1061] A "discount coupon" is information provided to a user to receive a discount at a store or service.

[1062] MODE FOR CARRYING OUT THE INVENTION

[1063] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system includes a means for receiving user input, a means for collecting external data, a means for preprocessing the collected external data, a means for inputting the preprocessed data and the user's input data into a generative AI model to generate prediction results, a means for generating recommendation information based on the generated prediction results, and a means for transmitting the generated recommendation information to a user terminal.

[1064] Hardware and Software

[1065] 1. Hardware: Server, user device (smartphone)

[1066] 2. Software: Smartphone app, external API (weather data, people flow data, public transport operation status, search trends), generative AI model

[1067] Explanation of characteristic program processing

[1068] 1. User input

[1069] The user starts the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. For example, Mr. A inputs "Shopping Mall in City A," departure time "2:00 PM," and waiting time tolerance "within 15 minutes."

[1070] 2. Sending data from the device to the server

[1071] The terminal sends the data entered by the user to the server. Specifically, when the submit button on the input form is pressed, the terminal converts the user's input data into JSON format and sends an HTTP request to the server's API endpoint.

[1072] 3. Collection of external data by the server

[1073] The server uses external APIs to collect necessary data in real time based on the received user data. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transport operation status from the Transit API.

[1074] 4. Data preprocessing by the server

[1075] The collected data cannot be used as is, so it is preprocessed on the server. Specifically, missing values ​​are filled in, outliers are corrected, and the data format is standardized. For example, if there is missing weather data, it is filled in by guessing based on past data.

[1076] 5. Data input and prediction for generative AI model

[1077] The preprocessed data and user input data are input into the generative AI model. Based on this data, the generative AI model predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user. For example, it predicts that "departing at 2:30 PM and taking bus route 5" is optimal.

[1078] 6. Server-generated recommendations

[1079] Based on the predictions from the generative AI model, the server generates recommendations for the user, including specific travel routes, departure times, and even discount coupons. For example, it generates a message such as, "Leave at 2:30 PM and take bus route 5."

[1080] 7. Sending recommended information to the user's device

[1081] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device.

[1082] 8. Display of recommendations by device

[1083] The device analyzes the received recommendations and visually displays them to the user, such as in a pop-up notification or in-app message box, suggesting "Leave at 2:30 PM and take bus route 5," and also offering discount coupons for use within the shopping mall.

[1084] Specific examples

[1085] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters their destination as "Shopping Mall in City A," their departure time as "2:00 PM," and their acceptable waiting time as "within 15 minutes" into a smartphone app. The device sends this input data to the server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time. For example, suppose the optimal route is predicted to be "Leaving at 2:30 PM and taking bus route 5." The server generates recommendation information based on this information and sends it to Person A's device. The device notifies Person A in the form of "Leaving at 2:30 PM and taking bus route 5." A discount coupon that can be used within the shopping mall is also provided.

[1086] Prompt Sentence Examples

[1087] An example of a prompt sentence is, "Please predict the best route and departure time for the user to go to the shopping mall on Sunday afternoon, and provide recommendations to avoid crowds and traffic jams. The user's input data is the destination "Shopping Mall in City A", the departure time "2:00 PM", and the waiting time tolerance "within 15 minutes."

[1088] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1089] Step 1: User Input

[1090] A user launches a smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The input data includes information provided by the user using an input form within the app. For example, the user might input "Destination: Shopping mall in the city," "Departure time: 2:00 PM," and "Waiting time tolerance: within 15 minutes."

[1091] Step 2: Send data from the device to the server

[1092] The device converts the input data into JSON format and sends an HTTP request to the server's API endpoint. Specifically, when the user presses the send button, the input data is transferred to the server. The input data includes the user's destination, desired departure time, and waiting time tolerance.

[1093] Step 3: Collecting external data by the server

[1094] The server uses external APIs to collect necessary external data based on the input data received from the user. For example, it obtains weather data from the Weather API, people flow data from the Crowd API, and public transportation operation status from the Transit API. The collected data is updated in real time.

[1095] Step 4: Preprocessing the data on the server

[1096] The server preprocesses the collected external data. This preprocessing includes filling in missing values ​​and correcting outliers. For example, if there are missing values ​​in weather data, it fills in the missing values ​​with estimated values ​​using past data. It receives external data as input and outputs preprocessed data.

[1097] Step 5: Input data into the generative AI model and make predictions

[1098] The server inputs the preprocessed data and user input data into the generative AI model. The generative AI model uses this data to predict congestion and traffic jams, and calculates the optimal travel route and departure time. For example, the model predicts that "departing at 2:30 PM and taking bus route 5" is optimal. Here, it receives the input data and preprocessed data and outputs the predicted results.

[1099] Step 6: Server Generates Recommendations

[1100] The server generates recommended information based on the prediction results. The recommended information includes the user's optimal travel route, departure time, discount coupons, etc. The specific operation when generating recommended information is to refer to the prediction results from the AI ​​model and assemble a series of suggested information. The input is the prediction results, and the output is recommended information.

[1101] Step 7: Sending recommendations to the user's device

[1102] The server sends the generated recommendation information to the user's device. Specifically, it packages the recommendation information in JSON format and returns an HTTP response to the API endpoint of the user's device. Here, the recommendation information is received as input and the data to be sent to the user's device is output.

[1103] Step 8: View device recommendations

[1104] The device analyzes the received recommendation information and visually displays it to the user. Specifically, it displays the appropriate departure time and travel route in a pop-up notification or in a message field within the app. Discount coupons are also displayed within the app. Here, the received recommendation information is received as input, and the data to be displayed to the user is output.

[1105] (Application example 1)

[1106] 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."

[1107] This system solves the problem of improving the user experience by improving the operational efficiency of autonomous vehicles, avoiding congestion and traffic jams, and proposing optimal travel routes and departure times. It also aims to smooth the flow of road traffic and reduce traffic congestion by adjusting parameters in real time during operation.

[1108] 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.

[1109] In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, means for transmitting the generated recommendation information to a user terminal, means for automatically adjusting operation parameters of the autonomous vehicle based on the generated recommendation information, and means for optimizing the vehicle's operation route and operation timing in cooperation with a car system. This enables efficient travel to a user's destination, smooths traffic flow, and reduces traffic congestion.

[1110] The "means for receiving user input" is an interface that allows the user to input information such as the destination, desired departure time, and acceptable waiting time via a device such as a smartphone or tablet.

[1111] "Means for collecting external data" refers to a system for collecting necessary information from external APIs via the Internet, such as weather data, traffic data, people flow data, and public transportation operation status.

[1112] "Means for preprocessing collected external data" refers to the process of preparing collected data in a state that makes it possible to analyze it, such as by filling in missing values, correcting outliers, and standardizing data formats.

[1113] "Means for inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a system for inputting preprocessed external data and user input data into an artificial intelligence model to predict congestion and traffic jams.

[1114] The "means for generating recommended information that suggests optimal travel routes and departure times" is a system that creates recommended information on the most efficient travel routes and departure times for users based on the prediction results obtained from the generative AI model.

[1115] The "means for transmitting the generated recommended information to the user terminal" is a system that transmits the recommended information created by the server to the user's smartphone or tablet, allowing the user to receive the information.

[1116] The "means for automatically adjusting the operating parameters of an autonomous vehicle based on the generated recommendation information" is a system for automatically setting and adjusting operating parameters of an autonomous vehicle, such as the operating route, speed, and stopping locations, in accordance with the recommendation information.

[1117] "Means for optimizing vehicle routes and operation timings in cooperation with car systems" refers to an interface and control system that communicates with the internal systems of an autonomous vehicle and optimizes routes and operation schedules in real time.

[1118] "User Device" means a smartphone, tablet, or other mobile device used by a User to input and receive information.

[1119] This invention is a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users, thereby improving the operating efficiency of autonomous vehicles. A specific embodiment of the system will be described.

[1120] First, the user enters information such as their destination, desired departure time, and acceptable waiting time through a smartphone application. This information is then sent to the server. The server then collects data such as weather data, traffic data, people flow data, and public transportation operation status from external APIs. This involves using external services such as weather APIs, people flow analysis APIs, and traffic information APIs.

[1121] The server then preprocesses the collected data, using data processing libraries like Pandas and NumPy to fill in missing values ​​and correct outliers. The preprocessed data and user input data are then fed into a generative AI model (for example, a model using TensorFlow or PyTorch) to predict congestion and traffic jams.

[1122] The generative AI model calculates the optimal travel route and departure time. Based on this, the server generates recommendations for the user. These recommendations include specific departure times, the means of transportation to be used, and even the route of the autonomous vehicle. This information is sent to the user's smartphone and presented visually.

[1123] Furthermore, the system automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations. This adjustment is made in cooperation with the vehicle's on-board computer and operating system, for example, optimizing the route to the destination and adjusting the speed automatically.

[1124] As a concrete example, consider the case where a user wants to go to the office in an autonomous taxi. The user enters the destination as "office," the departure time as "9:00 AM," and the waiting time tolerance as "within 10 minutes" into a smartphone app. The server collects weather and traffic data and predicts the optimal travel route and departure time. Based on the prediction results, it is determined that "departing at 8:45 AM and using main road A" is optimal. This information is sent to the autonomous taxi's operation system, and the vehicle automatically operates according to the set route.

[1125] An example prompt is:

[1126] Destination: Office

[1127] Departure time: 8:45 AM

[1128] Weather data: Clear skies

[1129] Traffic data: No traffic jams

[1130] Departure time optimization: 10 minute waiting time tolerance

[1131] This invention allows users to avoid congestion and traffic jams and travel to their destinations efficiently and comfortably. Furthermore, by adjusting the operating parameters of autonomous vehicles in real time, traffic flow can be smoothed and traffic congestion can be reduced.

[1132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1133] Step 1:

[1134] The user inputs their destination, desired departure time, and acceptable waiting time through a smartphone app. The device collects this input data and sends it to the server.

[1135] Input: Destination, desired departure time, waiting time tolerance

[1136] Output: Sending input data to the server

[1137] Step 2:

[1138] The server collects external data such as weather data, traffic data, people flow data, and public transport operation status from external APIs. Specifically, it uses weather APIs, people flow analysis APIs, traffic information APIs, etc.

[1139] Input: Data collection request from external API

[1140] Output: Collected weather data, traffic data, people flow data, and operation status data

[1141] Step 3:

[1142] The server preprocesses the external data collected by the server, specifically by using the Pandas and NumPy libraries to impute missing values, correct outliers, and standardize the data format.

[1143] Input: Collected external data

[1144] Output: Preprocessed data

[1145] Step 4:

[1146] The server inputs the preprocessed data and user input data into a generative AI model to predict congestion and traffic jams. The generative AI model is implemented using TensorFlow and PyTorch.

[1147] Input: Preprocessed data, user input data

[1148] Output: Predicted congestion and traffic jams

[1149] Step 5:

[1150] Based on the prediction results, the server generates recommendations for the user on the optimal travel route and departure time, including specific departure times, the means of transportation to be used, and the route of the autonomous vehicle.

[1151] Input: Predicted results of congestion and traffic jams

[1152] Output: Optimal travel route, departure time, and recommendations

[1153] Step 6:

[1154] The server sends the generated recommendation information to the user's smartphone, which receives the recommendation information and visually presents it to the user.

[1155] Input: Generated recommendations

[1156] Output: Send to user's smartphone, display notification

[1157] Step 7:

[1158] The server automatically adjusts the autonomous vehicle's operating parameters based on the generated recommendations, specifically optimizing route planning, speed adjustment, and stopping locations in cooperation with the vehicle's on-board computer.

[1159] Input: Generated recommendations

[1160] Output: Adjustment of operating parameters of autonomous vehicles

[1161] 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.

[1162] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotional state.

[1163] Specifically, the system operates in the following steps.

[1164] First, the user opens the smartphone app and inputs their destination, desired departure time, and waiting time tolerance. The device then sends this input data to the server, which then collects external data in real time from external APIs, such as weather data, people flow data, public transportation operation status, and search trends.

[1165] The server then cleans the collected external data and converts it into the required format. Specifically, it fills in missing values ​​and corrects outliers. The preprocessed data and user input are then input into a generative AI model. The generative AI model then predicts congestion and traffic jams and calculates the optimal travel route and departure time for the user.

[1166] Furthermore, the emotion engine recognizes the user's emotions based on the user's input data and external data. Based on the user's emotional state recognized by the emotion engine, the server adjusts the generated prediction results and recommendation information. For example, if the user is feeling stressed, the server may suggest a less congested route.

[1167] Based on the adjusted prediction results, the server generates recommendation information, which includes information on departure times and travel routes, as well as customized discount coupons tailored to the user's emotions. The generated recommendation information is sent to the user's device, which then visually presents the received recommendation information to the user.

[1168] As a concrete example, consider the case where Person A wants to go to a shopping mall in City A on a Sunday afternoon. Person A enters the destination as "Shopping Mall in City A," the departure time as "2:00 PM," and the waiting time tolerance as "within 15 minutes" into a smartphone app. The device sends this input data to a server. The server collects and preprocesses external data such as weather data, people flow data, and bus operation status. This data is then input into a generative AI model to predict the optimal travel route and departure time.

[1169] For example, suppose the optimal route is predicted to be "departing at 2:30 PM and taking bus route number 5." The server recognizes Person A's emotions based on the emotion engine. In this case, if Person A is feeling stressed, the server will suggest an alternative route to avoid crowds. The adjusted recommendation information is sent to Person A's device, and Person A receives information that they should depart at 2:30 PM and take bus route number 5. They will also be provided with a discount coupon that can be used within the shopping mall.

[1170] In this way, the system avoids congestion and traffic jams and provides customized travel suggestions based on the user's emotional state, making travel more efficient and comfortable.

[1171] The processing flow will be explained below.

[1172] The present invention relates to a system that predicts congestion and traffic jams, recognizes the user's emotions, and proposes optimal travel routes and departure times. Specific processing steps of the system are shown below.

[1173] Step 1:

[1174] A user opens a smartphone app and enters input data regarding their destination, desired departure time, wait tolerance, and current emotional state.

[1175] Example: Person A enters into the app, "Shopping mall in City A," departure time is 2:00 PM, waiting time tolerance is within 15 minutes, and "I'm feeling stressed."

[1176] Step 2:

[1177] The terminal transmits the user's input data to the server.

[1178] Example: Data entered by user A is sent from the device to the server.

[1179] Step 3:

[1180] The server collects the necessary data from an external API.

[1181] Example: The server retrieves data from a weather data API, a people flow data API, and a public transport operation status API.

[1182] Step 4:

[1183] The server preprocesses the collected external data.

[1184] Delete unnecessary data, fill in missing values, and correct outliers.

[1185] Example: Imputing missing values ​​in weather data and correcting outliers in people flow data.

[1186] Step 5:

[1187] The server inputs the preprocessed data and user input data into the generative AI model to generate prediction results.

[1188] Example: Based on person A's destination and departure time, a generative AI model predicts the optimal travel route and time.

[1189] Step 6:

[1190] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and external data.

[1191] Example: An emotion engine analyzes the input "I'm feeling stressed" and recognizes the user's emotional state.

[1192] Step 7:

[1193] The server adjusts the generated prediction results and recommendation information based on the user's emotional state recognized by the emotion engine.

[1194] Example: Considering that Person A is feeling stressed, the server suggests a less congested route.

[1195] Step 8:

[1196] The server generates recommendations based on the adjusted prediction results.

[1197] In addition to departure times and travel routes, it also includes customized discount coupons tailored to the user's emotions.

[1198] Example: Generate a recommendation to take bus route 5 for a 2:30 PM departure, plus offer a relaxation coupon.

[1199] Step 9:

[1200] The server transmits the generated recommendation information to the user terminal.

[1201] Example: Recommended information is sent to Mr. A's smartphone.

[1202] Step 10:

[1203] The recommended information received by the terminal is visually displayed to the user.

[1204] Example: The app says, "Leave at 2:30 PM and take bus route 5. You also have a stress-reducing coupon available."

[1205] Step 11:

[1206] The user sees the recommendations and takes action.

[1207] Example: Person A leaves at 2:30 PM, takes the recommended bus route, and uses the provided coupon to receive a relaxing service.

[1208] Through the above processing steps, the system not only predicts congestion and traffic jams, but also provides customized travel suggestions based on the user's emotional state, enabling efficient and comfortable travel.

[1209] Example 2

[1210] 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."

[1211] In modern society, it is important to suggest optimal travel routes that avoid congestion and traffic jams. However, existing systems do not consider the user's emotional state and do not improve the user experience. In addition, they lack the ability to provide accurate recommendations due to insufficient preprocessing of data collected in real time. Furthermore, they are unable to provide customized recommendations that meet the user's specific needs.

[1212] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model and generating a prediction result, means for generating recommended information that suggests an optimal travel route and departure time based on the generated prediction result, means for recognizing the user's emotion and adjusting the recommended information based on the emotion, and means for transmitting the generated recommended information to the user terminal. This makes it possible to provide highly accurate recommended information based on the user's emotional state.

[1213] The "means for receiving user input" refers to a means for providing an interface that allows a user to input necessary information such as a destination, desired departure time, and acceptable waiting time to the system.

[1214] "Means for collecting external data" refers to means for obtaining external information such as weather, pedestrian flow, public transportation operation status, and search trends in real time.

[1215] The "means for preprocessing collected external data" refers to a means for performing data cleansing processing such as complementing missing values ​​in the collected external data and correcting outliers.

[1216] "Means of inputting preprocessed data and user input data into a generative AI model to generate a prediction result" refers to a means of predicting congestion and traffic jams using an AI model by combining preprocessed data with user input information.

[1217] "Means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to means for determining the optimal travel route and departure time for a user based on the prediction results obtained by an AI model, and creating recommended information.

[1218] The "means for recognizing the user's emotions and adjusting the recommended information based on the emotions" refers to a means for analyzing the user's emotional state and adjusting the recommended information in accordance with emotions such as stress or joy.

[1219] The "means for transmitting the generated recommendation information to the user terminal" refers to a means for transmitting the generated recommendation information to the user's device and providing it visually.

[1220] MODE FOR CARRYING OUT THE INVENTION

[1221] The present invention relates to a system that predicts congestion and traffic jams and suggests optimal travel routes and departure times to users. The system also aims to provide a more comfortable travel experience by recognizing the user's emotions and providing customized recommendations based on those emotions.

[1222] System configuration

[1223] This system consists of the following elements:

[1224] User interface: The user enters information such as the destination, desired departure time, and waiting time tolerance through a smartphone app.

[1225] Data collection module: Uses APIs to collect external data in real time, such as weather, people flow, public transport operation status, search trends, etc. Specific examples of APIs include OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[1226] Data cleansing module: Cleanses the collected data, filling in missing values ​​and correcting outliers.

[1227] Generative AI model: Predicts congestion and traffic jams based on cleansed data and user input data. TensorFlow is used as the AI ​​model.

[1228] Emotion engine: Recognizes the user's emotions based on user input data and external data. Specifically, it uses IBM Watson Tone Analyzer.

[1229] Recommendation generation module: Generates recommendations regarding optimal travel routes and departure times based on prediction results and sentiment information.

[1230] Information delivery module: The generated recommendation information is sent to the user's device and presented visually.

[1231] Specific measures include:

[1232] Means of receiving user input: Using a smartphone app, users input their destination, desired departure time, and waiting time tolerance.

[1233] Means of collecting external data: Various external data (weather, people flow, traffic conditions, search trends) are collected using API keys.

[1234] Preprocessing the collected external data: imputing missing values ​​and correcting outliers in the collected data.

[1235] A means of inputting data into a generative AI model and generating prediction results: Predict congestion and traffic jams using cleansed data and user input data.

[1236] Means for generating recommendation information: Based on the prediction results, recommendation information is generated that suggests the optimal travel route and departure time.

[1237] Means for tailoring recommendation information based on emotions: The recommendation information is tailored based on the user's emotional state recognized by the emotion engine.

[1238] Means for transmitting generated recommendation information to user terminal: The server transmits the generated recommendation information to the user's smartphone.

[1239] Specific examples

[1240] For example, consider the case where user A wants to go to a shopping mall in city A on a Sunday afternoon. User A launches the smartphone app and enters "Shopping Mall in City A" as the destination, "2 PM" as the departure time, and "within 15 minutes" as the waiting time tolerance. The device sends this data in JSON format to the server. The server collects and cleans external data from the OpenWeatherMap API, Google Maps API, and Local Transit APIs.

[1241] The cleansed data and user input data are input into the TensorFlow model, and the system predicts the optimal travel route and departure time. For example, if it predicts that "it is best to depart at 2:30 pm and take bus route 5," the server uses IBM Watson Tone Analyzer to check whether User A is feeling stressed.

[1242] If the user is recognized as "stressed," the server generates another recommendation, such as "Leave at 3 PM and take bus route 7" to avoid the crowds. This recommendation also includes discount coupons that can be used at the shopping mall.

[1243] Finally, the generated recommendations are sent to the user's smartphone and displayed as notifications or pop-ups within the app.

[1244] Prompt Sentence Examples

[1245] "Destination: A City Shopping Mall"

[1246] "Departure time: 2 PM"

[1247] "Wait time tolerance: 15 minutes or less"

[1248] "User Emotions: Stress"

[1249] This system will enable users to avoid congestion and traffic jams and provide customized travel suggestions based on their emotional state.

[1250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1251] Step 1:

[1252] The user launches the smartphone app and inputs the necessary information, specifically the destination, desired departure time, and waiting time tolerance. The input data is the destination (e.g., shopping mall in City A), departure time (e.g., 2:00 PM), and waiting time tolerance (e.g., within 15 minutes).

[1253] Step 2:

[1254] The device sends the user's input data to the server. Specifically, the input data for destination, departure time, and waiting time tolerance is converted into JSON format and sent to the server. Input: Input data from the user. Output: JSON data sent to the server.

[1255] Step 3:

[1256] The server collects external data. Specifically, it collects weather information from the OpenWeatherMap API, people flow data from the Google Maps API, and real-time public transportation operation status from the Local Transit APIs. Input: API key and request. Output: Weather data, people flow data, and traffic condition data.

[1257] Step 4:

[1258] The server cleanses the data collected. Specifically, it complements missing data and corrects outliers. For example, if there is a gap in the weather data, it complements it using surrounding data. Input: Collected external data. Output: Cleansed data.

[1259] Step 5:

[1260] The server inputs the cleansed data and user input data into the generative AI model to generate prediction results. Specifically, a TensorFlow model is used to predict congestion and traffic jams. The model uses prompt statements such as: "Destination: Shopping Mall in City A," "Departure time: 2:00 PM," and "Tolerance for waiting time: within 15 minutes." Input: Cleansed data, user input data. Output: Congestion prediction results.

[1261] Step 6:

[1262] The server uses an emotion engine to recognize the user's emotions. Specifically, it uses IBM Watson Tone Analyzer to analyze emotions from the user's text input or voice data. Input: User's text input or voice data. Output: User's emotional state (e.g., feeling stressed).

[1263] Step 7:

[1264] The server generates recommendation information based on the prediction results and emotional information. Specifically, it determines the optimal travel route and departure time by taking into account the congestion prediction results and the user's emotional state. For example, if the user is feeling stressed, it will recommend a route with less congestion. Input: Congestion prediction results, emotional information. Output: Customized recommendation information.

[1265] Step 8:

[1266] The server sends the generated recommendation information to the user's device. Specifically, it converts the recommendation information into JSON format and sends it to the user's smartphone. Input: Customized recommendation information. Output: JSON format recommendation information data.

[1267] Step 9:

[1268] The recommended information received by the device is visually presented to the user. Specifically, it is displayed as a notification or pop-up within the smartphone app. For example, it may display information such as "Leave at 3pm and take bus route number 7" or a discount coupon that can be used at a shopping mall. Input: Recommended information sent from the server. Output: Visual information provided to the user.

[1269] (Application example 2)

[1270] 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."

[1271] The present invention relates to a system that provides a user with an efficient and comfortable travel experience by avoiding congestion and traffic jams when traveling. In particular, the present invention aims to improve the riding experience of autonomous vehicles by providing more personalized recommendation information that takes into account the user's emotional state. Conventional technologies do not provide travel recommendations that reflect the user's emotional state, and therefore may suggest stressful routes or departure times.

[1272] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1273] In this invention, the server includes a means for receiving user input, a means for collecting external data, and a means for preprocessing the collected external data. This makes it possible to propose optimal travel routes and departure times to users based on real-time information such as weather data, people flow data, and public transportation operation status. Furthermore, by adding a means for generating recommendation information that proposes optimal travel routes and departure times based on the generated prediction results, a means for transmitting the generated recommendation information to a user terminal, and a means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state, it becomes possible to provide customized travel suggestions that take the user's emotions into consideration. This not only allows users to avoid congestion and traffic jams, but also allows them to enjoy less stressful routes and services tailored to their situation, improving the quality of their overall travel experience.

[1274] A "means for receiving user input" is a device or software that provides an interface for a user to input data such as destination, desired departure time, and wait time tolerance.

[1275] "Means for collecting external data" refers to devices or software that acquire external information in real time, such as weather data, people flow data, public transportation operation status, and search trends.

[1276] The "means for preprocessing collected external data" refers to a device or software that performs processing to complement missing values ​​and correct outliers in the collected external data and convert it into the required format.

[1277] "Means for inputting preprocessed data and user input data into a generative AI model and generating a prediction result" refers to a device or software that provides preprocessed data and user input data to an AI model and generates a prediction result for the optimal travel route and departure time based on that data.

[1278] The "means for generating recommended information that suggests optimal travel routes and departure times based on the generated prediction results" refers to a device or software that creates recommended information including optimal travel routes and departure times for a user based on the generated prediction results.

[1279] The "means for transmitting the generated recommendation information to the user terminal" refers to a communication device or software for transmitting the recommendation information to the user terminal (such as a smartphone).

[1280] "Means for using an emotion engine to recognize a user's emotional state and for adjusting recommendations based on the recognized emotional state" refers to a device or software that evaluates a user's emotional state based on user input data and external data, and adapts or modifies recommendations based on the evaluation.

[1281] The present invention is a system for avoiding congestion and traffic jams when a user travels, and providing an efficient and comfortable travel experience, and is intended to be particularly applied to autonomous vehicles. Specific embodiments are described below.

[1282] The server includes means for receiving user input, means for collecting external data, means for preprocessing the collected external data, means for inputting the preprocessed data and the user's input data into a generative AI model to generate a prediction result, means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction result, and means for transmitting the generated recommendation information to a user terminal.The server also includes means for using an emotion engine that recognizes the user's emotional state and adjusting the recommendation information based on the recognized emotional state.

[1283] Users use a smartphone app to input data such as their destination, desired departure time, and acceptable waiting time. This input data is sent to a server. The server then collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs (e.g., OpenWeatherMap API and Google Maps API). The collected external data is preprocessed using a programming language such as Python. This preprocessing involves filling in missing values ​​and correcting outliers.

[1284] The preprocessed data and user input data are input into a generative AI model. This AI model predicts the optimal travel route and departure time and generates a prediction result. Based on the generated prediction result, the server generates recommended information for the user, including the optimal travel route and departure time. At this time, the emotion engine recognizes the user's emotional state and adjusts the recommended information by suggesting less crowded routes, entertainment, etc.

[1285] The generated recommendation information is sent from the server to the user's device and displayed on the user's smartphone. For example, if a user plans to go to the shopping mall at 2:00 PM, the server predicts that the best option would be to leave at 2:30 PM and take bus route 5. If the user is feeling stressed, the server will make a customized suggestion such as taking route 3, which will avoid the crowds, and playing relaxing music.

[1286] Example prompt sentence:

[1287] "The user wants to depart for the destination 'City Center' at '14:00' and their emotional state is 'Stressed'. Please predict the optimal route and departure time based on weather data and people flow data, and generate relaxing suggestions."

[1288] This allows users to reach their destination efficiently, avoiding crowds and traffic jams, and provides a comfortable travel experience that suits their emotional state.

[1289] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1290] Step 1:

[1291] The user opens the smartphone app and inputs their destination, desired departure time, waiting time tolerance, and emotional state. The smartphone app then transmits the data entered by the user to the server.

[1292] Input data: destination, desired departure time, waiting time tolerance, emotional state

[1293] Output Data: Input data sent to the server

[1294] Step 2:

[1295] The server collects external data such as weather data, people flow data, and public transportation operation status in real time from external APIs. Examples of external APIs used include the OpenWeatherMap API and Google Maps API. This data is stored on the server.

[1296] Input data: Weather data, people flow data, and public transportation status obtained from external APIs

[1297] Output data: Stored external data

[1298] Step 3:

[1299] The server preprocesses the collected external data. This involves using programming languages ​​such as Python to fill in missing values, correct outliers, and convert the data into the required format. This process improves the quality of the data and makes it suitable for input into AI models.

[1300] Input data: Stored external data

[1301] Output data: Preprocessed data

[1302] Step 4:

[1303] The preprocessed data and user input data are input into the generative AI model to generate a prediction. The AI ​​model then predicts the optimal travel route and departure time based on the input data. For example, it may predict that the user should take the "Route 5" bus at 2:30 PM.

[1304] Input data: Preprocessed data, user input data

[1305] Output data: Prediction results (optimal travel route and departure time)

[1306] Step 5:

[1307] The server generates recommendations based on the prediction results, suggesting optimal travel routes and departure times. In addition, the emotion engine recognizes the user's emotional state and adjusts the recommendations based on that emotional state. For example, if the user is feeling stressed, it will suggest less crowded routes and provide relaxing music.

[1308] Input data: prediction results, user's emotional state

[1309] Output: Tailored recommendations

[1310] Step 6:

[1311] The server then sends the adjusted recommendation information to the user's device, which then visually displays the received recommendation information and indicates the next action the user should take. For example, the recommendation "Leave at 2:30 PM and take the Route 5 bus" or a discount coupon for a shopping mall is displayed.

[1312] Input data: Tailored recommendations

[1313] Output data: Recommendation information displayed on the user's device

[1314] Step 7:

[1315] Users travel according to the recommended information displayed on their smartphone app and board an autonomous vehicle. In the process, they enjoy a comfortable travel experience by using the recommended route and receiving suggested services.

[1316] Input data: Recommendation information displayed on the user's device

[1317] Output data: User's actual travel experience

[1318] 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.

[1319] 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.

[1320] 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 robot 414.

[1321] 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.

[1322] 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.

[1323] 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.

[1324] 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).

[1325] 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.

[1326] 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."

[1327] 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.

[1328] 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).

[1329] 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.

[1330] 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.

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] The following is further disclosed regarding the above embodiment.

[1340] (Claim 1)

[1341] means for receiving user input;

[1342] a means for collecting external data;

[1343] a means for preprocessing the collected external data;

[1344] A means for inputting the preprocessed data and user input data into a generative AI model to generate a prediction result;

[1345] A means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction results;

[1346] means for transmitting the generated recommendation information to a user terminal;

[1347] A system including:

[1348] (Claim 2)

[1349] A system, wherein a user terminal further comprises means for receiving the recommendation information transmitted from the system according to claim 1 and displaying it to the user.

[1350] (Claim 3)

[1351] 10. The system of claim 1, further comprising: means for recommending a suggested travel route based on the generated prediction results, taking into account a wait time tolerance, a destination, and a departure time based on user input data.

[1352] "Example 1"

[1353] (Claim 1)

[1354] means for receiving user input;

[1355] a means for collecting external data;

[1356] a means for preprocessing the collected external data;

[1357] A means for inputting the preprocessed data and user input data into a generative AI model to generate a prediction result;

[1358] A means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction results;

[1359] means for transmitting the generated recommendation information to a user terminal;

[1360] A system including:

[1361] (Claim 2)

[1362] A system, wherein a user terminal further comprises means for receiving the recommendation information transmitted from the system according to claim 1 and displaying it to the user.

[1363] (Claim 3)

[1364] 10. The system of claim 1, further comprising: means for recommending a suggested travel route based on the generated prediction results, taking into account a wait time tolerance, a destination, and a departure time based on user input data.

[1365] (Claim 4)

[1366] A means for receiving user input data and inputting it into the generative AI model together with preprocessed external data;

[1367] A means to identify optimal travel routes and departure times based on the predictions received from the generative AI model;

[1368] A means to include discount coupons in recommendations;

[1369] The system of claim 1 further comprising:

[1370] "Application Example 1"

[1371] (Claim 1)

[1372] means for receiving user input;

[1373] a means for collecting external data;

[1374] a means for preprocessing the collected external data;

[1375] A means for inputting the preprocessed data and user input data into a generative AI model to generate a prediction result;

[1376] A means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction results;

[1377] means for transmitting the generated recommendation information to a user terminal;

[1378] means for automatically adjusting operating parameters of the autonomous vehicle based on the generated recommendation information;

[1379] A means for optimizing vehicle routes and timings in cooperation with the car system;

[1380] A system including:

[1381] (Claim 2)

[1382] A system, wherein a user terminal further comprises means for receiving the recommendation information transmitted from the system according to claim 1 and displaying it to the user.

[1383] (Claim 3)

[1384] 10. The system of claim 1, further comprising: means for recommending a suggested travel route based on the generated prediction results, taking into account a wait time tolerance, a destination, and a departure time based on user input data.

[1385] "Example 2: Combining Emotion Engines"

[1386] (Claim 1)

[1387] means for receiving user input;

[1388] a means for collecting external data;

[1389] a means for preprocessing the collected external data;

[1390] A means for inputting the preprocessed data and user input data into a generative AI model to generate a prediction result;

[1391] A means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction results;

[1392] means for recognizing a user's emotion and adjusting the recommendation information based on the emotion;

[1393] means for transmitting the generated recommendation information to a user terminal;

[1394] A system including:

[1395] (Claim 2)

[1396] A system, wherein a user terminal further comprises means for receiving the recommendation information transmitted from the system according to claim 1 and displaying it to the user.

[1397] (Claim 3)

[1398] 10. The system of claim 1, further comprising: means for recommending a suggested travel route based on the generated prediction results, taking into account a wait time tolerance, a destination, and a departure time based on user input data.

[1399] "Application example 2 when combining emotion engines"

[1400] New Claims

[1401] (Claim 1)

[1402] means for receiving user input;

[1403] a means for collecting external data;

[1404] a means for preprocessing the collected external data;

[1405] A means for inputting the preprocessed data and user input data into a generative AI model to generate a prediction result;

[1406] A means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction results;

[1407] means for transmitting the generated recommendation information to a user terminal;

[1408] a means for using an emotion engine that recognizes an emotional state of a user and adjusting the recommendations based on the recognized emotional state;

[1409] A system including:

[1410] (Claim 2)

[1411] A system, wherein a user terminal further comprises means for receiving the recommendation information transmitted from the system according to claim 1 and displaying it to the user.

[1412] (Claim 3)

[1413] 10. The system of claim 1, further comprising: means for recommending a suggested travel route based on the generated prediction results, taking into account a wait time tolerance, a destination, and a departure time based on user input data. [Explanation of symbols]

[1414] 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 receiving user input; a means for collecting external data; a means for preprocessing the collected external data; A means for inputting the preprocessed data and user input data into a generative AI model to generate a prediction result; A means for generating recommendation information that suggests optimal travel routes and departure times based on the generated prediction results; means for transmitting the generated recommendation information to a user terminal; A system including:

2. The system according to claim 1, further comprising means for a user terminal to receive the recommendation information transmitted from the system and display it to the user.

3. The system of claim 1 , further comprising: means for recommending a suggested travel route based on the generated prediction results, taking into account a wait time tolerance, a destination, and a departure time based on user input data.

Images