system

Abstract

Provide a system. The present invention includes a means for collecting vehicle movement data during a long vacation period; means for analyzing the collected movement data to extract congestion patterns; means for predicting future congestion based on the congestion pattern; means for generating an alternative route based on the predicted congestion; means for displaying the alternative route; means for providing data to a system that varies road tolls based on the predicted congestion; A system including:

Description

[Technical Field]

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

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

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

[0004] Specific congestion on expressways during long holiday periods, especially around popular tourist destinations and service areas (e.g., Umihotaru), causes significant stress and wasted time for many drivers. Such congestion also increases the risk of traffic accidents and increases the management burden for road operators. Therefore, a system that can efficiently predict congestion and present appropriate alternative routes to users is needed. Furthermore, congestion should be alleviated by dynamically setting road tolls based on congestion prediction data. [Means for solving the problem]

[0005] The present invention provides the following means: a means for collecting vehicle movement data during a long holiday period and a means for analyzing the collected movement data to extract congestion patterns; a means for predicting future congestion based on the congestion patterns and a means for generating alternative routes based on the predicted congestion; a means for displaying the alternative routes and a means for providing data to a system that varies road tolls based on the predicted congestion. This allows efficient alternative routes to be presented to users, alleviating congestion and enabling traffic flow control through toll setting.

[0006] "Long holiday periods" refer to periods of consecutive holidays and public holidays during which a particularly large number of vehicle movements are expected throughout the year.

[0007] "Vehicle movement data" refers to data relating to the location, speed, route, and travel time of a vehicle during a specific period of time.

[0008] "Congestion patterns" refer to data patterns that indicate a tendency for concentrated vehicle congestion or traffic jams at specific times or locations.

[0009] "Prediction means" refers to an algorithm or data processing system for predicting congestion conditions for a specific period in the future based on collected data and analyzed congestion patterns.

[0010] An "alternate route" refers to another route that a user can take to avoid a route that is predicted to be congested.

[0011] "Means for providing data" refers to communications capabilities or interfaces for transmitting predicted occupancy and other relevant data to another system or device.

[0012] A "variable toll system" refers to a road management system that can change toll fees based on traffic conditions and congestion forecast data. [Brief explanation of the drawings]

[0013] [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 illustrating 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

[0014] 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.

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

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

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

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The embodiments of the present invention will be specifically described below.

[0035] User Data Acquisition

[0036] Initiating a Data Collection Request

[0037] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period, for example, a period such as Golden Week.

[0038] Start of data collection

[0039] The server starts collecting data based on the specified long-term vacation period and user information, which includes movement data for thousands of users.

[0040] Data Acquisition

[0041] The server retrieves each user's travel data from the database, for example, by querying the travel data for the relevant period using the user ID, and adds the obtained data to the list.

[0042] Data analysis

[0043] Data analysis begins

[0044] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[0045] Individual data analysis

[0046] The server extracts congestion patterns from each user's data, analyzing each data point to identify the times and locations where congestion occurs, and then combines the results into an overall pattern.

[0047] Congestion pattern aggregation

[0048] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information, for example, analyzing the congestion situation around Umihotaru.

[0049] Congestion forecast

[0050] Selecting a Prediction Model

[0051] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[0052] Implementing congestion predictions

[0053] The server inputs the collected congestion patterns and the specified period into the model and makes a prediction, for example, predicting congestion during next year's Golden Week period.

[0054] Saving the results

[0055] The server stores the predicted congestion results in a database and converts them into a format for presentation to the user.

[0056] Alternative route suggestions

[0057] Alternative Route Generation

[0058] The server generates alternative routes based on the congestion forecast, which involves calculating routes that avoid times and locations where congestion is predicted.

[0059] Alternate Route Format

[0060] The server formats the generated alternative routes in a way that is easy for the user to understand.

[0061] Providing alternative routes

[0062] The server sends alternative routes to the terminal and makes them available to the user.

[0063] User Notifications

[0064] The device will then notify the user of the alternative route and encourage them to use it, for example, suggesting a route via the coastal road to avoid the traffic jam at Umihotaru.

[0065] Providing information on fluctuating prices

[0066] Data format conversion

[0067] The server formats the congestion forecast results into a format usable by the pricing system.

[0068] Information transmission

[0069] The server sends the formatted data to the pricing system.

[0070] Pricing optimization

[0071] The pricing system uses the transmitted data to optimize highway tolls, for example by raising tolls during peak hours around Umihotaru to ease congestion.

[0072] Specific examples

[0073] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[0074] The server acquires user movement data during the Golden Week period from the database.

[0075] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[0076] The server predicts the congestion during Golden Week next year and saves the results.

[0077] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[0078] The device notifies the user of alternative routes and encourages them to use them.

[0079] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[0083] Step 2:

[0084] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[0085] Step 3:

[0086] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[0087] Step 4:

[0088] The server analyzes the collected movement data. First, it analyzes each user's data points to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[0089] Step 5:

[0090] The server aggregates the data collected from all users and identifies common congestion patterns, such as the concentration of users in specific service areas or tourist spots (e.g., Umihotaru), and plots the congestion situation on a map.

[0091] Step 6:

[0092] The server selects an appropriate prediction model and sets a model to predict future congestion conditions using the optimal algorithm based on past data.

[0093] Step 7:

[0094] The server inputs the analyzed congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[0095] Step 8:

[0096] The server stores the prediction results in a database and converts them into a format that can be provided to the user for future reference.

[0097] Step 9:

[0098] The server generates alternative routes based on the congestion prediction results, calculates multiple routes to avoid times and locations where congestion is predicted, and selects the optimal alternative route.

[0099] Step 10:

[0100] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[0101] Step 11:

[0102] The server sends the formatted alternative route information to the terminal, allowing the user to check the alternative route in real time.

[0103] Step 12:

[0104] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[0105] Step 13:

[0106] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[0107] Step 14:

[0108] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[0109] Example 1

[0110] 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."

[0111] In recent years, traffic congestion during long holiday periods has become a social problem. This problem not only reduces travel efficiency and road utilization efficiency, but also has a negative impact on the environment due to increased exhaust gas emissions. To solve this problem, it is necessary to predict congestion using past data and provide appropriate alternative routes based on that prediction. However, conventional systems have had problems in that they do not sufficiently provide users with efficient data collection, highly accurate congestion predictions, or the optimization of alternative routes based on those predictions.

[0112] 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.

[0113] In this invention, the server includes: means for a user to send a request for collecting vehicle movement data for a long vacation period from a terminal; means for the server to start collecting movement data for a specified period based on the received request; means for the server to acquire movement data for each user from a database; means for the server to analyze the collected data to extract congestion patterns and perform individual data analysis; means for the server to aggregate congestion patterns and generate comprehensive congestion information; means for the server to select an appropriate prediction model and predict congestion based on past data; means for the server to store the predicted congestion results in a database and format them for provision to the user; means for the server to generate alternative routes based on the congestion prediction results and provide them to the terminal; means for the terminal to notify the user of the received alternative route; and means for the server to format the congestion prediction results in a format usable by a pricing system and transmit them. This allows users to predict congestion in advance and select appropriate alternative routes, thereby achieving efficient transportation operations and reducing time loss and environmental impact due to congestion.

[0114] A "user" is an entity that uses a terminal to access the system and make a request to collect movement data for a specified period of time.

[0115] A "terminal" is a device used by a user to send data collection requests to the system and receive notifications from the server.

[0116] A "server" is a computer system that performs multiple functions such as data collection, analysis, prediction, alternate route generation, and data format conversion.

[0117] "Movement data" refers to data including information such as vehicle location information, travel route, and speed, and indicates the user's movement history.

[0118] "Database" means a system or structured collection of data used to store movement data for collection and analysis.

[0119] A "congestion pattern" is a pattern of data that indicates the traffic congestion that occurs during a specific period and at a specific location.

[0120] A "predictive model" is a mathematical or statistical algorithm used to predict future congestion conditions based on past data.

[0121] An "alternate route" is a suggested alternative travel route to avoid congestion and indicates the optimal route.

[0122] A "pricing system" is a system used to optimize road usage fees based on congestion forecast results.

[0123] The present invention is a system that collects and analyzes vehicle movement data during long holiday periods, predicts congestion, and provides alternative routes. This system consists of three main components: a server, a terminal, and a user. Specific embodiments of the system are described below.

[0124] First, the device used by the user is typically a mobile device such as a smartphone or tablet. The user uses this device to send a request to the server to collect vehicle movement data during a specific period. The specified period is, for example, a long holiday period such as "Golden Week." This request may be generated using a prompt in text format. For example, a prompt such as "Please collect movement data during Golden Week in 2024" may be used.

[0125] When the server receives this request, it starts the data collection process. The server retrieves each user's travel data from the database. This involves database operations such as SQL queries to retrieve travel data for the specified period. The retrieved data includes information such as the vehicle's location, travel route, and speed.

[0126] The collected data is analyzed by a server. The server performs individual data analysis to extract congestion patterns. It identifies the time periods and locations where congestion occurred from each user's movement data and integrates the results into an overall pattern. This analysis forms the basis for understanding the congestion situation at a specific location and time.

[0127] Next, the server selects an appropriate prediction model and uses the generative AI model to predict future congestion conditions. Past congestion patterns and usage data are used as input. For example, a prompt might be entered such as, "Please predict congestion conditions during Golden Week in 2025." The prediction model selects the optimal algorithm based on past data and predicts future congestion conditions with high accuracy.

[0128] The prediction results are stored in a database in formats such as JSON or CSV, and the server uses these to generate alternative routes. Routes that avoid times and locations where congestion is predicted are calculated and provided to the user. For example, it suggests a route that avoids Umihotaru and takes the bayside road between 10:00 and 14:00. The suggestions are formatted with map information and detailed explanations and provided in a way that is easy for users to understand.

[0129] The generated alternative route is then sent back to the device via the server. The device then notifies the user of the received alternative route information and provides appropriate guidance. Notifications are sent via text messages or pop-up notifications, such as "Please use the following alternative route to avoid traffic jams at Umihotaru."

[0130] The server then sends the congestion prediction results to a pricing system. The server then formats the data into a format that the pricing system can use and sends it to the pricing system. The system then optimizes fares based on the data sent and sets fares to alleviate congestion. For example, it can reduce congestion by raising fares during peak hours around Umihotaru.

[0131] The above is a specific embodiment of the present invention. This system allows users to predict traffic congestion in advance and select the optimal alternative route. This is expected to realize efficient traffic management and reduce the burden on the environment.

[0132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0133] Step 1: Initiate a data collection request

[0134] The user sends a request to collect vehicle movement data during a specified long holiday period from the terminal to the server. The input to this process is a prompt statement in which the user specifies the period (e.g., "Please collect movement data during the Golden Week period in 2024"). The output is that this request is transmitted to the server. When the terminal sends the prompt statement, the server receives this request and the data collection process begins.

[0135] Step 2: Start collecting data

[0136] The server starts collecting mobile data for a specified period based on the received request. The input to this process is a data collection request from the terminal, and the output is an instruction to start data collection. The server establishes a database connection and prepares to collect mobile data.

[0137] Step 3: Get the data

[0138] The server retrieves each user's movement data from the database. The input to this process is a list of user IDs to be collected and a specified period, and the output is the retrieved movement data. The server executes SQL queries to collect data, issuing commands such as "Retrieve movement data for user ID 12345 during the Golden Week period."

[0139] Step 4: Begin data analysis

[0140] The server launches a process to analyze the collected movement data. The input of this process is the collected raw data, and the output is a notification that the analysis task has been configured. The server schedules the data analysis tasks and configures them to run in parallel.

[0141] Step 5: Individual data analysis

[0142] The server analyzes congestion patterns from each user's movement data individually. The input to this process is a dataset for each individual user, and the output is information about the time and location of congestion. The server analyzes each data point and obtains a result such as "Congestion occurred on the Chuo Expressway from 10:00 to 14:00 on May 3rd."

[0143] Step 6: Aggregating congestion patterns

[0144] The server aggregates congestion patterns obtained from the data of all users. The input to this process is the individual analysis results of each user, and the output is comprehensive congestion information. The server integrates the data of multiple users and identifies a pattern such as "during Golden Week, congestion will occur around Umihotaru from 10:00 to 14:00."

[0145] Step 7: Select a predictive model

[0146] The server selects an appropriate prediction model and prepares it for crowd prediction. The inputs to this process are past data and analysis results, and the output is the selected prediction model. The server uses the generative AI model to input a prompt such as "Please predict the crowd situation during Golden Week in 2025."

[0147] Step 8: Run congestion forecast

[0148] The server inputs the aggregated congestion patterns and data for the specified period into a prediction model to make a congestion forecast. The inputs to this process are the prediction model and the original data, and the output is the future congestion forecast results. The server runs the prediction model and makes a specific forecast of "Golden Week congestion in 2025."

[0149] Step 9: Save the results

[0150] The server saves the prediction results in a database and formats them for presentation to users. The input to this process is the prediction results, and the output is saved in the database as formatted data. In this saving process, the data is converted into JSON format, CSV format, etc.

[0151] Step 10: Generate Alternate Routes

[0152] The server generates an alternative route based on the congestion forecast results. The input to this process is the congestion forecast results, and the output is the generated alternative route. It is calculated as follows: "Avoid Umihotaru and take the Bayshore Route between 10:00 and 14:00."

[0153] Step 11: Formatting Alternate Routes

[0154] The server formats the generated alternative routes in a way that is easy for the user to understand. The input to this process is the generated alternative route, and the output is formatted alternative route information, such as "Use this route during this time period" with map information and text descriptions.

[0155] Step 12: Provide an alternative route

[0156] The server sends the alternative route to the terminal and provides it to the user. The input of this process is formatted alternative route information, and the output is a transmission notification to the terminal. The server records logs and monitors the transmission status.

[0157] Step 13: User Notification

[0158] The terminal notifies the user of the received alternative route information. The input of this process is the alternative route information sent from the server, and the output is a notification to the user. For example, a pop-up notification may be displayed saying, "To avoid the traffic jam at Umihotaru, please use the following alternative route."

[0159] Step 14: Data Format Conversion

[0160] The server formats the congestion forecast results into a format that can be used by the pricing system. The input to this process is the forecast results, and the output is formatted data. For example, the congestion forecast results are converted into CSV format.

[0161] Step 15: Send information

[0162] The server sends the formatted data to the pricing system. The input to this process is the formatted data and the output is a submission notification. The server confirms and logs the submission of the data to the pricing system.

[0163] Step 16: Optimize your pricing

[0164] The pricing system adjusts the prices based on the data sent. The input to this process is data from the server, and the output is optimized pricing. For example, increasing the price during peak hours around Umihotaru reduces congestion.

[0165] (Application example 1)

[0166] 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."

[0167] Congestion during long holiday periods can be a significant source of stress for many drivers. The resulting inefficiencies and delays during peak hours are also a major challenge. Furthermore, the lack of appropriate alternative route selection and optimization of road tolls is a problem. Therefore, a system that can predict future congestion, provide appropriate alternative routes, notify users, and dynamically adjust toll fees is needed.

[0168] 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.

[0169] In this invention, the server includes means for collecting vehicle movement data during long holiday periods, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for generating alternative routes based on the predicted congestion, means for displaying the alternative routes, means for notifying users of the alternative routes, and means for providing data to a system that varies road tolls based on the predicted congestion, thereby encouraging users to travel efficiently and avoiding congestion during peak hours.

[0170] "Long holiday periods" refer to periods when many people are on vacation at the same time, such as long weekends or holiday seasons, which tend to result in significantly higher traffic volumes than usual.

[0171] "Movement data" refers to information about a vehicle's movement, such as its location, time, and speed. This data is collected from GPS and various sensors.

[0172] "Congestion patterns" refers to data that indicates traffic congestion conditions in a particular time period or area, including traffic volume, vehicle speed, and dwell time.

[0173] "Predicted congestion" is information that indicates traffic congestion conditions that are likely to occur in the future based on past travel data and congestion patterns.

[0174] "Alternate Route" refers to a proposed alternative route to reach a destination to avoid predicted congestion.

[0175] "User notification" is the act of conveying information from the system to the user. This notification may be in the form of voice, text, display, etc.

[0176] A "variable toll system" is a system that dynamically adjusts road usage fees based on traffic congestion and forecast data, making it possible to curb usage during peak times and alleviate congestion.

[0177] The system for implementing this invention includes a series of means for collecting, analyzing, predicting, and notifying vehicle movement data during long vacation periods. The system of this invention is realized by using an on-board computer, a GPS module, and various sensors as hardware, and software such as a database system and a machine learning model.

[0178] First, the server will begin collecting movement data during the long vacation period. This data is collected using the GPS module and various sensors installed in the autonomous vehicle, and data from the user is sent to the server.

[0179] The collected movement data is then analyzed by a server. This analysis involves managing the data using a database system (e.g., MySQL (registered trademark), MongoDB) and extracting congestion patterns using an analytical algorithm (e.g., k-means clustering). Detailed movement data for each user is analyzed to identify specific times and locations of congestion.

[0180] Next, based on the analysis results, the server performs time series prediction using a machine learning model (e.g., TENSORFLOW (registered trademark), PyTorch) to predict future congestion. This prediction uses collected past data and congestion patterns as input to predict future congestion conditions for a specific period.

[0181] An alternative route is then generated based on the prediction results. To generate the alternative route, a map information API (e.g., Google (registered trademark) Maps API) is used to calculate the optimal route, taking into account current traffic conditions and predicted road congestion. The generated alternative route is formatted in a format that is easy for users to understand and sent to the autonomous vehicle's on-board display or smartphone.

[0182] Furthermore, the server notifies the user and presents the generated alternative route. This notification can be provided in the form of voice guidance or text message, helping the user to smoothly use the alternative route.

[0183] Finally, the predicted congestion information is also provided to the toll system, which dynamically optimizes highway tolls and takes measures to alleviate congestion during peak hours. The server converts the congestion prediction results into a format that the toll system can use and provides the appropriate information.

[0184] As a specific example, the system can predict congestion around the Tokyo Bay Aqua-Line (Umihotaru) during Golden Week, and based on the results, generate an alternative route via the Bayshore Route and notify the user. This can reduce stress during long holiday periods such as the New Year holidays and improve travel efficiency.

[0185] The following is an example of a prompt sentence:

[0186] "Design an algorithm to predict traffic congestion around the Tokyo Bay Aqua-Line (Umihotaru) during the Golden Week period and generate alternative routes to avoid the congestion."

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] The terminal specifies a long holiday period (e.g., Golden Week) and sends a movement data collection request to the server. The input includes data specifying the start and end dates of the period. After receiving this request, the server prepares to collect movement data of multiple users during the specified period.

[0190] Step 2:

[0191] The server stores the movement data collected from multiple users in a database system. It receives data from the GPS module and various sensors and stores it in the database. The input data are data points such as user location information, travel time, and travel speed. As an output, each user's movement data is stored in the database.

[0192] Step 3:

[0193] The server analyzes the stored travel data and extracts congestion patterns. This analysis uses a clustering algorithm (e.g., k-means clustering) to identify congestion levels at specific times and locations. The input is the travel data in the database, and the output is the analysis results that indicate busy times and locations.

[0194] Step 4:

[0195] The server uses a generative AI model (e.g., TensorFlow, PyTorch) to predict future congestion based on the analyzed congestion patterns. This prediction uses a time series analysis model to calculate future trends from past data. The input is the congestion pattern and past movement data, and the output is the predicted congestion time period and location.

[0196] Step 5:

[0197] The server generates an alternative route based on the predicted congestion information. It uses a map information API (e.g., Google Maps API) to calculate the optimal route that avoids congestion. The current location, destination, and predicted congestion information are used as input. The output is generated as an alternative route that can be used by the user.

[0198] Step 6:

[0199] The server sends the generated alternative route to the terminal, and the terminal notifies the user. This notification is provided as a voice guide or a text message. The input is the alternative route information, and the output is a notification to the user. Specifically, the alternative route information is presented using a voice output device or a display.

[0200] Step 7:

[0201] The server provides predicted congestion information to a toll system, which dynamically optimizes road usage tolls and alleviates congestion. The input is predicted congestion information, and the output is data converted into a format that can be used by the toll system. The toll system uses this data to adjust tolls during peak hours.

[0202] 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.

[0203] The embodiments of the present invention will be specifically described below.

[0204] User Data Acquisition

[0205] Initiating a Data Collection Request

[0206] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[0207] Start of data collection

[0208] The server receives the user's request and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[0209] Data Acquisition

[0210] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[0211] Data analysis

[0212] Data analysis begins

[0213] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[0214] Individual data analysis

[0215] The server extracts congestion patterns from each user's data. It analyzes each data point to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[0216] Congestion pattern aggregation

[0217] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information. For example, it analyzes the congestion situation around Umihotaru.

[0218] Congestion forecast

[0219] Selecting a Prediction Model

[0220] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[0221] Implementing congestion predictions

[0222] The server inputs the collected congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[0223] Saving the results

[0224] The server stores the prediction results in a database and converts them into a format that can be presented to the user for future reference.

[0225] Alternative route suggestions

[0226] Alternative Route Generation

[0227] The server generates alternative routes based on the congestion prediction results. To avoid times and locations where congestion is predicted, multiple routes are calculated and the optimal alternative route is selected.

[0228] Alternate Route Format

[0229] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[0230] Providing alternative routes

[0231] The server transmits the alternative route information to the terminal, allowing the user to check the alternative route in real time.

[0232] User Notifications

[0233] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[0234] Providing information on fluctuating prices

[0235] Data format conversion

[0236] The server formats the congestion forecast results into a format usable by the pricing system.

[0237] Information transmission

[0238] The server sends the formatted data to the pricing system.

[0239] Pricing optimization

[0240] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[0241] Implementing the Emotion Engine

[0242] Emotion Engine Data Collection

[0243] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[0244] Emotional Data Analysis

[0245] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.).

[0246] Emotional Data Feedback

[0247] Based on the analysis results, the server provides route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[0248] Specific examples

[0249] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[0250] The server acquires user movement data during the Golden Week period from the database.

[0251] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[0252] The server predicts the congestion during Golden Week next year and saves the results.

[0253] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[0254] The device notifies the user of alternative routes and encourages them to use them.

[0255] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[0256] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[0257] The processing flow will be explained below.

[0258] Step 1:

[0259] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period. For example, the user inputs a request to acquire data for the Golden Week period.

[0260] Step 2:

[0261] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and period.

[0262] Step 3:

[0263] The server queries the database for each user's travel data, for example, retrieving all records of travels made by user ID "12345" during the Golden Week period.

[0264] Step 4:

[0265] The server analyzes the collected movement data, specifically analyzing each user's data points to identify the time periods and locations where congestion occurred.

[0266] Step 5:

[0267] The server extracts congestion patterns from each user's movement data and aggregates them comprehensively. For example, it identifies peak times and locations of traffic flow around Umihotaru.

[0268] Step 6:

[0269] The server selects an appropriate prediction model and predicts future congestion based on past data. Specifically, it predicts next year's congestion around Umihotaru based on time-series data.

[0270] Step 7:

[0271] The server stores the prediction results in a database and converts them into a format for providing them to users, for example, into a data format for visualizing the prediction results on a map.

[0272] Step 8:

[0273] The server generates alternative routes based on the congestion prediction results, calculates multiple routes that avoid times and locations where congestion is predicted, and selects the optimal route.

[0274] Step 9:

[0275] The server formats the generated alternative routes in a way that is easy for the user to understand, for example by displaying the route on a map and adding audio guidance.

[0276] Step 10:

[0277] The server sends the formatted alternative route information to the terminal, allowing the user to view the alternative route in real time.

[0278] Step 11:

[0279] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[0280] Step 12:

[0281] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[0282] Step 13:

[0283] The server analyzes the collected emotional data and determines the user's current emotional state (e.g., stress, fatigue, irritation, etc.). For example, if the user is feeling impatient, the server may simplify the display.

[0284] Step 14:

[0285] Based on the analysis results, the server provides alternative route guidance according to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[0286] Step 15:

[0287] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[0288] Step 16:

[0289] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[0290] Example 2

[0291] 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."

[0292] Conventional vehicle movement data collection and congestion prediction systems have difficulty collecting real-time data and optimizing driving routes based on users' emotional states. Furthermore, dynamic adjustment of pricing based on congestion predictions has not been sufficiently implemented, preventing effective congestion relief measures. This often leads to excessive road congestion during certain times of the day, increasing user stress and frustration.

[0293] 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 a user to input a request to collect vehicle movement data for a long vacation period; means for a terminal to transmit the user's request to the server; means for the server to acquire movement data from a database according to the specified long vacation period; means for the server to analyze the acquired movement data and extract congestion patterns; means for the server to predict future congestion conditions based on the extracted congestion patterns; means for the server to generate alternative routes to avoid the predicted congestion; means for the terminal to notify the user of the generated alternative routes; means for the server to transmit congestion prediction results to a pricing system and provide data for dynamically varying road tolls; means for the terminal to monitor the user's facial expressions and voice using cameras and sensors in the vehicle and collect emotional data; and means for the server to analyze the collected emotional data and provide route guidance according to the user's emotional state. This enables effective congestion mitigation through real-time data collection and analysis, route guidance based on the user's emotional state, and dynamic toll adjustment.

[0294] "Long holiday period" refers to a specific long holiday period, including, for example, Golden Week and the New Year holidays.

[0295] "Vehicle movement data" refers to data including information such as vehicle location, travel route, and time of day.

[0296] "User" refers to any individual or legal entity that uses the System.

[0297] "Terminal" refers to a device operated by a user, and includes, for example, a smartphone, a tablet, an in-vehicle terminal, and the like.

[0298] "Server" refers to a central management device that processes, analyzes, stores, etc. data.

[0299] "Database" refers to a system for storing user movement data and analysis results.

[0300] "Congestion patterns" refers to information that indicates the tendency for vehicle concentration and congestion at specific times and locations.

[0301] A "predictive model" refers to a computational model that uses past data and algorithms to predict future congestion conditions.

[0302] "Alternate route" refers to a different travel route than usual to avoid congestion.

[0303] "Price setting system" means a system for managing and dynamically changing road usage fees.

[0304] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, voice, gestures, etc.

[0305] "Real-time" refers to the immediate processing of situations and data occurring at the moment.

[0306] A "data collection request" refers to a request issued by a user via a terminal to a server instructing the server to collect data.

[0307] "Analysis" refers to the process of examining collected data and extracting meaningful information.

[0308] "Notification" refers to sending information from the system to a user terminal and displaying it.

[0309] The system for implementing this invention includes the collection and analysis of vehicle movement data during long holidays, congestion prediction, provision of alternative routes, provision of data to a fare setting system, and implementation of an emotion engine. This system is realized through the interaction of three parties: a server, a terminal, and a user.

[0310] User Data Collection

[0311] The user operates the application on the terminal and inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week). The terminal formats this request in JSON format and sends it to the server using an HTTP request. The server retrieves vehicle movement data from the database according to the specified long holiday period.

[0312] Data analysis

[0313] The server analyzes the acquired travel data and extracts congestion patterns. Specifically, it performs data cleaning to remove incomplete data and outliers. It then clusters travel times and locations to identify the locations and times when congestion occurs.

[0314] Congestion forecast

[0315] The server predicts future congestion situations based on the extracted congestion patterns using past data and a prediction model (e.g., an LSTM model). The prediction results are stored in a database and converted into an appropriate format for presentation to users.

[0316] Providing alternative routes

[0317] The server generates an alternative route to avoid the predicted congestion. Specifically, it searches for the optimal route using Google Maps API or similar and evaluates multiple routes. The generated alternative route information is formatted appropriately and sent to the device. The device then notifies the user of this information and provides guidance using voice guidance or other means.

[0318] Dynamic Pricing

[0319] The server provides data based on the congestion forecast results to a pricing system, which then dynamically adjusts road tolls based on this data, thereby implementing pricing strategies to alleviate congestion during specific times of day.

[0320] Implementing the Emotion Engine

[0321] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data. The server analyzes this emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.). Based on the analysis results, route guidance is provided that matches the user's emotional state. For example, if the user is feeling stressed, the server will suggest more relaxing routes and rest spots.

[0322] Specific examples

[0323] Here is an example of this system:

[0324] A user inputs a request for collecting movement data for a long vacation period into a terminal, and the terminal transmits the request to a server.

[0325] The server acquires and collects user movement data during the Golden Week period from the database.

[0326] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[0327] The server predicts the congestion during Golden Week next year and saves the results.

[0328] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[0329] The device will notify the user of alternative routes and provide voice guidance.

[0330] The server transmits the congestion forecast data to a pricing system, which then adjusts the fees during peak hours accordingly.

[0331] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[0332] Prompt Sentence Examples

[0333] Below are some example prompts to input to a generative AI model:

[0334] 1. "We would like to collect travel data during Golden Week, analyze congestion patterns, and predict congestion for the following year. Please explain the system that will suggest alternative routes to avoid congestion and send the optimal data to the pricing system."

[0335] 2. "Please explain the procedure for a system that collects and analyzes travel data from users during long vacation periods to predict future congestion. Also, please explain how to suggest a relaxing route for users when they feel stressed."

[0336] The above is an embodiment of the present invention.

[0337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0338] Step 1: Initiate a data collection request

[0339] A user inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week) using an application on a terminal. The input data includes a specified date range for the holiday period.

[0340] The terminal formats the user's request in JSON format and sends it to the server using an HTTP request.

[0341] Input: Date range of long-term vacation period, User ID

[0342] Output: Data collection request sent to the server

[0343] Step 2: Prepare for data collection

[0344] The server receives the data collection request from the device and prepares access to the database based on the specified long-term vacation period and user ID, which includes establishing a database connection and generating the necessary SQL queries.

[0345] Input: User ID, specified long-term vacation period

[0346] Output: Database connected and ready to query

[0347] Step 3: Data Acquisition

[0348] The server runs an SQL query to retrieve travel data for a specified period from the database, for example, filtering the data based on dates within a certain range.

[0349] Input: SQL query, database connection

[0350] Output: Acquired vehicle movement data

[0351] Step 4: Data Cleaning

[0352] The server cleans the acquired vehicle movement data to remove incomplete data and outliers, a process that is crucial for obtaining reliable analysis results.

[0353] Input: Captured vehicle movement data

[0354] Output: Cleaned movement data

[0355] Step 5: Extracting congestion patterns

[0356] The server uses the cleaned travel data to extract congestion patterns. Specifically, it performs data clustering and analysis by travel time period to identify times and locations where congestion is likely to occur.

[0357] Input: Cleaned movement data

[0358] Output: Congestion pattern

[0359] Step 6: Prepare for congestion forecasts

[0360] The server analyzes past data based on congestion patterns and selects a congestion prediction model (e.g., LSTM model), while also adjusting the model parameters.

[0361] Input: Congestion Pattern

[0362] Output: Selected predictive model

[0363] Step 7: Run congestion forecast

[0364] The server inputs the congestion pattern and an arbitrary future period into the selected prediction model and simulates future congestion.

[0365] Input: Congestion pattern, future period

[0366] Output: Congestion prediction results

[0367] Step 8: Saving and formatting the results

[0368] The server stores the congestion prediction results in a database and converts them into a format (e.g., JSON format) for providing to users.

[0369] Input: Congestion forecast result

[0370] Output: Formatted prediction results

[0371] Step 9: Alternate Route Generation

[0372] The server calculates alternative routes based on the congestion forecast results, and uses Google Maps APIs to select the optimal route to avoid congestion.

[0373] Input: Congestion forecast result

[0374] Output: Multiple alternative routes

[0375] Step 10: Formatting Alternate Routes

[0376] The server converts the generated alternative routes into a format that is easy for the user to understand (e.g., JSON or map data format).

[0377] Input: Multiple alternative routes

[0378] Output: Formatted alternate routes

[0379] Step 11: Notification of Alternate Routes

[0380] The terminal notifies the user of the alternative route sent from the server, for example, by using a notification pop-up or audio guidance.

[0381] Input: Formatted alternate route

[0382] Output: User notification

[0383] Step 12: Provide data to the pricing system

[0384] The server formats the congestion prediction results into a format that can be used by the pricing system (e.g., CSV format) and sends them to the pricing system using an API.

[0385] Input: Congestion forecast result

[0386] Output: Data sent to the pricing system

[0387] Step 13: Implement pricing

[0388] The pricing system dynamically changes road tolls based on data sent from a server, aiming to reduce congestion during certain times of the day.

[0389] Input: Data to send to the pricing system

[0390] Output: Dynamically changed pricing

[0391] Step 14: Collect emotion data

[0392] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[0393] Input: Camera and sensor information

[0394] Output: Collected emotion data

[0395] Step 15: Analyze the emotion data

[0396] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritability, etc.).

[0397] Input: Collected emotion data

[0398] Output: User's emotional state

[0399] Step 16: Route guidance based on emotion data

[0400] Based on the analysis results, the server generates route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, the server suggests relaxing routes and rest spots.

[0401] Input: User's emotional state

[0402] Output: Route guidance based on emotional state

[0403] (Application example 2)

[0404] 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."

[0405] Road congestion during long holiday periods is a major source of stress for many people. Furthermore, congestion can significantly extend travel times, making time management difficult for trips and business trips. Furthermore, the stress and fatigue felt while driving during congestion can have a negative impact on traffic safety. The present invention aims to solve these problems and improve the user experience when traveling or traveling by providing a system that predicts congestion and provides optimal alternative routes based on the user's emotional state.

[0406] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting vehicle movement data during a long holiday period, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for collecting and analyzing emotional data such as the user's facial expressions and tone of voice, means for generating an alternative route based on the predicted congestion and emotional state, means for displaying the alternative route, and means for providing data to a system that varies road tolls based on the predicted congestion. This makes it possible to predict road congestion during a long holiday period and provide an optimal alternative route based on the user's emotional state.

[0407] "Long holiday periods" are periods when many people take vacations at the same time, and when traffic volume increases.

[0408] "Movement data" refers to data including information such as the current position of the vehicle, the route traveled, the travel time, and the speed.

[0409] A "congestion pattern" is a collection of data that indicates the tendency for traffic volume to increase at specific times and locations.

[0410] "Emotion data" is data that indicates the user's emotional state, such as stress, fatigue, or irritation, obtained by analyzing the user's facial expression and tone of voice.

[0411] "Alternate route" refers to a different route to a destination that is calculated to avoid congestion or other obstacles.

[0412] A "variable fee system" is a mechanism that dynamically changes road usage fees based on traffic volume and congestion forecasts.

[0413] "User's facial expressions and tone of voice" are elements that indicate the user's psychological and emotional state and are collected using cameras and microphones installed in the vehicle.

[0414] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[0415] Hardware and Software Configuration

[0416] Hardware:

[0417] Navigation systems for autonomous vehicles

[0418] Cameras and microphones in the vehicle

[0419] software:

[0420] Server-side API (e.g. Flask / Django)

[0421] Data analysis libraries (e.g., NumPy, SciPy)

[0422] Emotion recognition API (e.g., Microsoft® Azure® Emotion API, Google Cloud Emotion API)

[0423] Road pricing system

[0424] System Overview

[0425] This system is primarily composed of a server and a terminal (autonomous vehicle system). The user collects vehicle movement data during a long vacation period and sends it to the server via middleware. The server analyzes the movement data to determine congestion patterns and predict future congestion. It also uses cameras and microphones inside the vehicle to collect and analyze user emotion data. Based on this data, it generates optimal alternative routes and sends them to the navigation system. It also provides congestion prediction data to the road toll setting system, enabling dynamic toll fluctuations.

[0426] Data collection and analysis

[0427] The device collects vehicle movement data in real time during the long holiday period and sends it to the server. Specifically, this data includes information such as GPS location data, movement speed, and time of day. The server analyzes this data and extracts congestion patterns. For example, it identifies patterns in which congestion frequently occurs on specific roads or during specific time periods.

[0428] Emotion data collection and analysis

[0429] The system uses cameras and microphones installed in the vehicle to collect the user's facial expressions and tone of voice. The server then uses an emotion recognition API to analyze the user's emotional state from this data. For example, it can determine in real time whether the user is feeling stressed or tired.

[0430] Generate optimal alternative routes

[0431] The server generates an optimal alternative route based on the congestion forecast data and the user's emotion data. This route not only avoids areas where congestion is predicted, but may also include routes and rest points where the user can relax. The generated alternative route is sent to the navigation system and displayed to the user.

[0432] Dynamic fluctuations in road tolls

[0433] The server provides congestion forecast data to the road pricing system, which dynamically adjusts road tolls to try to alleviate congestion at specific times and locations.

[0434] Specific examples

[0435] Suppose a user plans to travel during Golden Week. The user enters the travel period into the navigation system and begins collecting vehicle movement data. The server analyzes the collected data and predicts congestion patterns and future congestion based on past data. In addition, the server uses in-vehicle cameras and microphones to analyze the user's emotional data in real time. The server uses this data to generate an optimal alternative route and notify the user. For example, if the user is feeling stressed, the server can also suggest relaxing routes and rest points.

[0436] Prompt Sentence Examples

[0437] "I'm planning to travel during Golden Week. Can you tell me the best route to take to avoid traffic jams? Also, could you suggest some rest stops if I get stressed?"

[0438] In this way, the present invention is a system that improves the travel experience by predicting congestion during long holidays and providing optimal alternative routes based on the user's emotional state.

[0439] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0440] Step 1:

[0441] Initiating a Data Collection Request

[0442] Input: User specifies long-term vacation period and requests vehicle movement data collection.

[0443] Processing: The device receives the user's input and sends the long-term vacation period to the server. Specifically, it uses an API to send the user ID and the specified period.

[0444] Output: The server receives the data collection request and starts preparing for mobile data collection.

[0445] Step 2:

[0446] Starting Data Collection

[0447] Input: The server receives a data collection request.

[0448] Processing: The server prepares to collect movement data for the specified long holiday period and prepares to access the database.

[0449] Output: Data collection is initiated and the server starts collecting movement data from multiple users.

[0450] Step 3:

[0451] Acquiring movement data

[0452] Input: The server retrieves travel data for the long vacation period from the database.

[0453] Processing: The server executes queries to collect movement data for each user. Specifically, it uses SQL queries to obtain the movement history of each user.

[0454] Output: The server collects movement data and prepares it for analysis.

[0455] Step 4:

[0456] Collecting Emotional Data

[0457] Input: Cameras and microphones in the vehicle record the user's facial expressions and tone of voice.

[0458] Processing: The device uses the camera and microphone to collect the user's emotional data and transmit it to the server. Specifically, it captures voice and image data in real time.

[0459] Output: The server stores the received emotion data for analysis.

[0460] Step 5:

[0461] Start of data analysis

[0462] Input: Movement data and emotion data are stored on the server.

[0463] Processing: The server analyzes this data and extracts congestion patterns. It identifies congestion patterns using a data analysis library (e.g., NumPy, SciPy).

[0464] Output: The server extracts congestion patterns and generates data to input into the predictive model.

[0465] Step 6:

[0466] Running a congestion prediction model

[0467] Input: The server inputs congestion pattern data.

[0468] Processing: The server runs a predictive model using past congestion data to predict future congestion. The prediction is made using machine learning algorithms.

[0469] Output: The server generates and stores future congestion prediction results.

[0470] Step 7:

[0471] Generate alternative routes

[0472] Input: The congestion prediction results and user emotion data are input to the server.

[0473] Processing: The server uses this data to generate safe and efficient alternative routes, including selecting routes that are more relaxing for the user based on emotion data.

[0474] Output: The best alternative route is generated and sent to the navigation system.

[0475] Step 8:

[0476] Notification and guidance of alternative routes

[0477] Input: Send the server generated alternative route to the device.

[0478] Processing: The device notifies the user of the alternative route received and displays it on the navigation system, specifically by providing voice guidance and displaying a map.

[0479] Output: The user starts traveling according to the new alternative route.

[0480] Step 9:

[0481] Pricing optimization

[0482] Input: The server provides congestion forecast data to the pricing system.

[0483] Processing: Road pricing systems dynamically adjust toll rates based on congestion forecasts.

[0484] Output: Pricing is optimized and new prices are applied to users.

[0485] 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.

[0486] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0487] 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.

[0488] [Second embodiment]

[0489] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0490] 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.

[0491] 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).

[0492] 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.

[0493] 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.

[0494] 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).

[0495] 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.

[0496] 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.

[0497] 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.

[0498] 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.

[0499] 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.

[0500] 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."

[0501] The embodiments of the present invention will be specifically described below.

[0502] User Data Acquisition

[0503] Initiating a Data Collection Request

[0504] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period, for example, a period such as Golden Week.

[0505] Start of data collection

[0506] The server starts collecting data based on the specified long-term vacation period and user information, which includes movement data for thousands of users.

[0507] Data Acquisition

[0508] The server retrieves each user's travel data from the database, for example, by querying the travel data for the relevant period using the user ID, and adds the obtained data to the list.

[0509] Data analysis

[0510] Data analysis begins

[0511] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[0512] Individual data analysis

[0513] The server extracts congestion patterns from each user's data, analyzing each data point to identify the times and locations where congestion occurs, and then combines the results into an overall pattern.

[0514] Congestion pattern aggregation

[0515] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information, for example, analyzing the congestion situation around Umihotaru.

[0516] Congestion forecast

[0517] Selecting a Prediction Model

[0518] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[0519] Implementing congestion predictions

[0520] The server inputs the collected congestion patterns and the specified period into the model and makes a prediction, for example, predicting congestion during next year's Golden Week period.

[0521] Saving the results

[0522] The server stores the predicted congestion results in a database and converts them into a format for presentation to the user.

[0523] Alternative route suggestions

[0524] Alternative Route Generation

[0525] The server generates alternative routes based on the congestion forecast, which involves calculating routes that avoid times and locations where congestion is predicted.

[0526] Alternate Route Format

[0527] The server formats the generated alternative routes in a way that is easy for the user to understand.

[0528] Providing alternative routes

[0529] The server sends alternative routes to the terminal and makes them available to the user.

[0530] User Notifications

[0531] The device will then notify the user of the alternative route and encourage them to use it, for example, suggesting a route via the coastal road to avoid the traffic jam at Umihotaru.

[0532] Providing information on fluctuating prices

[0533] Data format conversion

[0534] The server formats the congestion forecast results into a format usable by the pricing system.

[0535] Information transmission

[0536] The server sends the formatted data to the pricing system.

[0537] Pricing optimization

[0538] The pricing system uses the transmitted data to optimize highway tolls, for example by raising tolls during peak hours around Umihotaru to ease congestion.

[0539] Specific examples

[0540] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[0541] The server acquires user movement data during the Golden Week period from the database.

[0542] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[0543] The server predicts the congestion during Golden Week next year and saves the results.

[0544] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[0545] The device notifies the user of alternative routes and encourages them to use them.

[0546] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[0547] The processing flow will be explained below.

[0548] Step 1:

[0549] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[0550] Step 2:

[0551] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[0552] Step 3:

[0553] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[0554] Step 4:

[0555] The server analyzes the collected movement data. First, it analyzes each user's data points to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[0556] Step 5:

[0557] The server aggregates the data collected from all users and identifies common congestion patterns, such as the concentration of users in specific service areas or tourist spots (e.g., Umihotaru), and plots the congestion situation on a map.

[0558] Step 6:

[0559] The server selects an appropriate prediction model and sets a model to predict future congestion conditions using the optimal algorithm based on past data.

[0560] Step 7:

[0561] The server inputs the analyzed congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[0562] Step 8:

[0563] The server stores the prediction results in a database and converts them into a format that can be provided to the user for future reference.

[0564] Step 9:

[0565] The server generates alternative routes based on the congestion prediction results, calculates multiple routes to avoid times and locations where congestion is predicted, and selects the optimal alternative route.

[0566] Step 10:

[0567] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[0568] Step 11:

[0569] The server sends the formatted alternative route information to the terminal, allowing the user to check the alternative route in real time.

[0570] Step 12:

[0571] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[0572] Step 13:

[0573] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[0574] Step 14:

[0575] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[0576] Example 1

[0577] 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."

[0578] In recent years, traffic congestion during long holiday periods has become a social problem. This problem not only reduces travel efficiency and road utilization efficiency, but also has a negative impact on the environment due to increased exhaust gas emissions. To solve this problem, it is necessary to predict congestion using past data and provide appropriate alternative routes based on that prediction. However, conventional systems have had problems in that they do not sufficiently provide users with efficient data collection, highly accurate congestion predictions, or the optimization of alternative routes based on those predictions.

[0579] 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.

[0580] In this invention, the server includes: means for a user to send a request for collecting vehicle movement data for a long vacation period from a terminal; means for the server to start collecting movement data for a specified period based on the received request; means for the server to acquire movement data for each user from a database; means for the server to analyze the collected data to extract congestion patterns and perform individual data analysis; means for the server to aggregate congestion patterns and generate comprehensive congestion information; means for the server to select an appropriate prediction model and predict congestion based on past data; means for the server to store the predicted congestion results in a database and format them for provision to the user; means for the server to generate alternative routes based on the congestion prediction results and provide them to the terminal; means for the terminal to notify the user of the received alternative route; and means for the server to format the congestion prediction results in a format usable by a pricing system and transmit them. This allows users to predict congestion in advance and select appropriate alternative routes, thereby achieving efficient transportation operations and reducing time loss and environmental impact due to congestion.

[0581] A "user" is an entity that uses a terminal to access the system and make a request to collect movement data for a specified period of time.

[0582] A "terminal" is a device used by a user to send data collection requests to the system and receive notifications from the server.

[0583] A "server" is a computer system that performs multiple functions such as data collection, analysis, prediction, alternate route generation, and data format conversion.

[0584] "Movement data" refers to data including information such as vehicle location information, travel route, and speed, and indicates the user's movement history.

[0585] "Database" means a system or structured collection of data used to store movement data for collection and analysis.

[0586] A "congestion pattern" is a pattern of data that indicates the traffic congestion that occurs during a specific period and at a specific location.

[0587] A "predictive model" is a mathematical or statistical algorithm used to predict future congestion conditions based on past data.

[0588] An "alternate route" is a suggested alternative travel route to avoid congestion and indicates the optimal route.

[0589] A "pricing system" is a system used to optimize road usage fees based on congestion forecast results.

[0590] The present invention is a system that collects and analyzes vehicle movement data during long holiday periods, predicts congestion, and provides alternative routes. This system consists of three main components: a server, a terminal, and a user. Specific embodiments of the system are described below.

[0591] First, the device used by the user is typically a mobile device such as a smartphone or tablet. The user uses this device to send a request to the server to collect vehicle movement data during a specific period. The specified period is, for example, a long holiday period such as "Golden Week." This request may be generated using a prompt in text format. For example, a prompt such as "Please collect movement data during Golden Week in 2024" may be used.

[0592] When the server receives this request, it starts the data collection process. The server retrieves each user's travel data from the database. This involves database operations such as SQL queries to retrieve travel data for the specified period. The retrieved data includes information such as the vehicle's location, travel route, and speed.

[0593] The collected data is analyzed by a server. The server performs individual data analysis to extract congestion patterns. It identifies the time periods and locations where congestion occurred from each user's movement data and integrates the results into an overall pattern. This analysis forms the basis for understanding the congestion situation at a specific location and time.

[0594] Next, the server selects an appropriate prediction model and uses the generative AI model to predict future congestion conditions. Past congestion patterns and usage data are used as input. For example, a prompt might be entered such as, "Please predict congestion conditions during Golden Week in 2025." The prediction model selects the optimal algorithm based on past data and predicts future congestion conditions with high accuracy.

[0595] The prediction results are stored in a database in formats such as JSON or CSV, and the server uses these to generate alternative routes. Routes that avoid times and locations where congestion is predicted are calculated and provided to the user. For example, it suggests a route that avoids Umihotaru and takes the bayside road between 10:00 and 14:00. The suggestions are formatted with map information and detailed explanations and provided in a way that is easy for users to understand.

[0596] The generated alternative route is then sent back to the device via the server. The device then notifies the user of the received alternative route information and provides appropriate guidance. Notifications are sent via text messages or pop-up notifications, such as "Please use the following alternative route to avoid traffic jams at Umihotaru."

[0597] The server then sends the congestion prediction results to a pricing system. The server then formats the data into a format that the pricing system can use and sends it to the pricing system. The system then optimizes fares based on the data sent and sets fares to alleviate congestion. For example, it can reduce congestion by raising fares during peak hours around Umihotaru.

[0598] The above is a specific embodiment of the present invention. This system allows users to predict traffic congestion in advance and select the optimal alternative route. This is expected to realize efficient traffic management and reduce the burden on the environment.

[0599] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0600] Step 1: Initiate a data collection request

[0601] The user sends a request to collect vehicle movement data during a specified long holiday period from the terminal to the server. The input to this process is a prompt statement in which the user specifies the period (e.g., "Please collect movement data during the Golden Week period in 2024"). The output is that this request is transmitted to the server. When the terminal sends the prompt statement, the server receives this request and the data collection process begins.

[0602] Step 2: Start collecting data

[0603] The server starts collecting mobile data for a specified period based on the received request. The input to this process is a data collection request from the terminal, and the output is an instruction to start data collection. The server establishes a database connection and prepares to collect mobile data.

[0604] Step 3: Get the data

[0605] The server retrieves each user's movement data from the database. The input to this process is a list of user IDs to be collected and a specified period, and the output is the retrieved movement data. The server executes SQL queries to collect data, issuing commands such as "Retrieve movement data for user ID 12345 during the Golden Week period."

[0606] Step 4: Begin data analysis

[0607] The server launches a process to analyze the collected movement data. The input of this process is the collected raw data, and the output is a notification that the analysis task has been configured. The server schedules the data analysis tasks and configures them to run in parallel.

[0608] Step 5: Individual data analysis

[0609] The server analyzes congestion patterns from each user's movement data individually. The input to this process is a dataset for each individual user, and the output is information about the time and location of congestion. The server analyzes each data point and obtains a result such as "Congestion occurred on the Chuo Expressway from 10:00 to 14:00 on May 3rd."

[0610] Step 6: Aggregating congestion patterns

[0611] The server aggregates congestion patterns obtained from the data of all users. The input to this process is the individual analysis results of each user, and the output is comprehensive congestion information. The server integrates the data of multiple users and identifies a pattern such as "during Golden Week, congestion will occur around Umihotaru from 10:00 to 14:00."

[0612] Step 7: Select a predictive model

[0613] The server selects an appropriate prediction model and prepares it for crowd prediction. The inputs to this process are past data and analysis results, and the output is the selected prediction model. The server uses the generative AI model to input a prompt such as "Please predict the crowd situation during Golden Week in 2025."

[0614] Step 8: Run congestion forecast

[0615] The server inputs the aggregated congestion patterns and data for the specified period into a prediction model to make a congestion forecast. The inputs to this process are the prediction model and the original data, and the output is the future congestion forecast results. The server runs the prediction model and makes a specific forecast of "Golden Week congestion in 2025."

[0616] Step 9: Save the results

[0617] The server saves the prediction results in a database and formats them for presentation to users. The input to this process is the prediction results, and the output is saved in the database as formatted data. In this saving process, the data is converted into JSON format, CSV format, etc.

[0618] Step 10: Generate Alternate Routes

[0619] The server generates an alternative route based on the congestion forecast results. The input to this process is the congestion forecast results, and the output is the generated alternative route. It is calculated as follows: "Avoid Umihotaru and take the Bayshore Route between 10:00 and 14:00."

[0620] Step 11: Formatting Alternate Routes

[0621] The server formats the generated alternative routes in a way that is easy for the user to understand. The input to this process is the generated alternative route, and the output is formatted alternative route information, such as "Use this route during this time period" with map information and text descriptions.

[0622] Step 12: Provide an alternative route

[0623] The server sends the alternative route to the terminal and provides it to the user. The input of this process is formatted alternative route information, and the output is a transmission notification to the terminal. The server records logs and monitors the transmission status.

[0624] Step 13: User Notification

[0625] The terminal notifies the user of the received alternative route information. The input of this process is the alternative route information sent from the server, and the output is a notification to the user. For example, a pop-up notification may be displayed saying, "To avoid the traffic jam at Umihotaru, please use the following alternative route."

[0626] Step 14: Data Format Conversion

[0627] The server formats the congestion forecast results into a format that can be used by the pricing system. The input to this process is the forecast results, and the output is formatted data. For example, the congestion forecast results are converted into CSV format.

[0628] Step 15: Send information

[0629] The server sends the formatted data to the pricing system. The input to this process is the formatted data and the output is a submission notification. The server confirms and logs the submission of the data to the pricing system.

[0630] Step 16: Optimize your pricing

[0631] The pricing system adjusts the prices based on the data sent. The input to this process is data from the server, and the output is optimized pricing. For example, increasing the price during peak hours around Umihotaru reduces congestion.

[0632] (Application example 1)

[0633] 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."

[0634] Congestion during long holiday periods can be a significant source of stress for many drivers. The resulting inefficiencies and delays during peak hours are also a major challenge. Furthermore, the lack of appropriate alternative route selection and optimization of road tolls is a problem. Therefore, a system that can predict future congestion, provide appropriate alternative routes, notify users, and dynamically adjust toll fees is needed.

[0635] 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.

[0636] In this invention, the server includes means for collecting vehicle movement data during long holiday periods, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for generating alternative routes based on the predicted congestion, means for displaying the alternative routes, means for notifying users of the alternative routes, and means for providing data to a system that varies road tolls based on the predicted congestion, thereby encouraging users to travel efficiently and avoiding congestion during peak hours.

[0637] "Long holiday periods" refer to periods when many people are on vacation at the same time, such as long weekends or holiday seasons, which tend to result in significantly higher traffic volumes than usual.

[0638] "Movement data" refers to information about a vehicle's movement, such as its location, time, and speed. This data is collected from GPS and various sensors.

[0639] "Congestion patterns" refers to data that indicates traffic congestion conditions in a particular time period or area, including traffic volume, vehicle speed, and dwell time.

[0640] "Predicted congestion" is information that indicates traffic congestion conditions that are likely to occur in the future based on past travel data and congestion patterns.

[0641] "Alternate Route" refers to a proposed alternative route to reach a destination to avoid predicted congestion.

[0642] "User notification" is the act of conveying information from the system to the user. This notification may be in the form of voice, text, display, etc.

[0643] A "variable toll system" is a system that dynamically adjusts road usage fees based on traffic congestion and forecast data, making it possible to curb usage during peak times and alleviate congestion.

[0644] The system for implementing this invention includes a series of means for collecting, analyzing, predicting, and notifying vehicle movement data during long vacation periods. The system of this invention is realized by using an on-board computer, a GPS module, and various sensors as hardware, and software such as a database system and a machine learning model.

[0645] First, the server will begin collecting movement data during the long vacation period. This data is collected using the GPS module and various sensors installed in the autonomous vehicle, and data from the user is sent to the server.

[0646] The collected movement data is then analyzed by the server. This analysis involves managing the data using a database system (e.g., MySQL, MongoDB) and extracting congestion patterns using analytical algorithms (e.g., k-means clustering). Detailed movement data for each user is analyzed to identify specific times and locations of congestion.

[0647] Next, based on the analysis results, the server performs time series prediction using a machine learning model (e.g., TensorFlow, PyTorch) to predict future congestion. This prediction uses collected past data and congestion patterns as inputs to predict future congestion conditions for a specific period.

[0648] An alternative route is then generated based on this prediction. To generate the alternative route, a map information API (e.g., Google Maps API) is used to calculate the optimal route, taking into account current traffic conditions and predicted road congestion. The generated alternative route is formatted in a user-friendly format and sent to the autonomous vehicle's on-board display or smartphone.

[0649] Furthermore, the server notifies the user and presents the generated alternative route. This notification can be provided in the form of voice guidance or text message, helping the user to smoothly use the alternative route.

[0650] Finally, the predicted congestion information is also provided to the toll system, which dynamically optimizes highway tolls and takes measures to alleviate congestion during peak hours. The server converts the congestion prediction results into a format that the toll system can use and provides the appropriate information.

[0651] As a specific example, the system can predict congestion around the Tokyo Bay Aqua-Line (Umihotaru) during Golden Week, and based on the results, generate an alternative route via the Bayshore Route and notify the user. This can reduce stress during long holiday periods such as the New Year holidays and improve travel efficiency.

[0652] The following is an example of a prompt sentence:

[0653] "Design an algorithm to predict traffic congestion around the Tokyo Bay Aqua-Line (Umihotaru) during the Golden Week period and generate alternative routes to avoid the congestion."

[0654] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0655] Step 1:

[0656] The terminal specifies a long holiday period (e.g., Golden Week) and sends a movement data collection request to the server. The input includes data specifying the start and end dates of the period. After receiving this request, the server prepares to collect movement data of multiple users during the specified period.

[0657] Step 2:

[0658] The server stores the movement data collected from multiple users in a database system. It receives data from the GPS module and various sensors and stores it in the database. The input data are data points such as user location information, travel time, and travel speed. As an output, each user's movement data is stored in the database.

[0659] Step 3:

[0660] The server analyzes the stored travel data and extracts congestion patterns. This analysis uses a clustering algorithm (e.g., k-means clustering) to identify congestion levels at specific times and locations. The input is the travel data in the database, and the output is the analysis results that indicate busy times and locations.

[0661] Step 4:

[0662] The server uses a generative AI model (e.g., TensorFlow, PyTorch) to predict future congestion based on the analyzed congestion patterns. This prediction uses a time series analysis model to calculate future trends from past data. The input is the congestion pattern and past movement data, and the output is the predicted congestion time period and location.

[0663] Step 5:

[0664] The server generates an alternative route based on the predicted congestion information. It uses a map information API (e.g., Google Maps API) to calculate the optimal route that avoids congestion. The current location, destination, and predicted congestion information are used as input. The output is generated as an alternative route that can be used by the user.

[0665] Step 6:

[0666] The server sends the generated alternative route to the terminal, and the terminal notifies the user. This notification is provided as a voice guide or a text message. The input is the alternative route information, and the output is a notification to the user. Specifically, the alternative route information is presented using a voice output device or a display.

[0667] Step 7:

[0668] The server provides predicted congestion information to a toll system, which dynamically optimizes road usage tolls and alleviates congestion. The input is predicted congestion information, and the output is data converted into a format that can be used by the toll system. The toll system uses this data to adjust tolls during peak hours.

[0669] 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.

[0670] The embodiments of the present invention will be specifically described below.

[0671] User Data Acquisition

[0672] Initiating a Data Collection Request

[0673] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[0674] Start of data collection

[0675] The server receives the user's request and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[0676] Data Acquisition

[0677] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[0678] Data analysis

[0679] Data analysis begins

[0680] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[0681] Individual data analysis

[0682] The server extracts congestion patterns from each user's data. It analyzes each data point to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[0683] Congestion pattern aggregation

[0684] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information. For example, it analyzes the congestion situation around Umihotaru.

[0685] Congestion forecast

[0686] Selecting a Prediction Model

[0687] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[0688] Implementing congestion predictions

[0689] The server inputs the collected congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[0690] Saving the results

[0691] The server stores the prediction results in a database and converts them into a format that can be presented to the user for future reference.

[0692] Alternative route suggestions

[0693] Alternative Route Generation

[0694] The server generates alternative routes based on the congestion prediction results. To avoid times and locations where congestion is predicted, multiple routes are calculated and the optimal alternative route is selected.

[0695] Alternate Route Format

[0696] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[0697] Providing alternative routes

[0698] The server transmits the alternative route information to the terminal, allowing the user to check the alternative route in real time.

[0699] User Notifications

[0700] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[0701] Providing information on fluctuating prices

[0702] Data format conversion

[0703] The server formats the congestion forecast results into a format usable by the pricing system.

[0704] Information transmission

[0705] The server sends the formatted data to the pricing system.

[0706] Pricing optimization

[0707] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[0708] Implementing the Emotion Engine

[0709] Emotion Engine Data Collection

[0710] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[0711] Emotional Data Analysis

[0712] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.).

[0713] Emotional Data Feedback

[0714] Based on the analysis results, the server provides route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[0715] Specific examples

[0716] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[0717] The server acquires user movement data during the Golden Week period from the database.

[0718] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[0719] The server predicts the congestion during Golden Week next year and saves the results.

[0720] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[0721] The device notifies the user of alternative routes and encourages them to use them.

[0722] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[0723] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[0724] The processing flow will be explained below.

[0725] Step 1:

[0726] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period. For example, the user inputs a request to acquire data for the Golden Week period.

[0727] Step 2:

[0728] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and period.

[0729] Step 3:

[0730] The server queries the database for each user's travel data, for example, retrieving all records of travels made by user ID "12345" during the Golden Week period.

[0731] Step 4:

[0732] The server analyzes the collected movement data, specifically analyzing each user's data points to identify the time periods and locations where congestion occurred.

[0733] Step 5:

[0734] The server extracts congestion patterns from each user's movement data and aggregates them comprehensively. For example, it identifies peak times and locations of traffic flow around Umihotaru.

[0735] Step 6:

[0736] The server selects an appropriate prediction model and predicts future congestion based on past data. Specifically, it predicts next year's congestion around Umihotaru based on time-series data.

[0737] Step 7:

[0738] The server stores the prediction results in a database and converts them into a format for providing them to users, for example, into a data format for visualizing the prediction results on a map.

[0739] Step 8:

[0740] The server generates alternative routes based on the congestion prediction results, calculates multiple routes that avoid times and locations where congestion is predicted, and selects the optimal route.

[0741] Step 9:

[0742] The server formats the generated alternative routes in a way that is easy for the user to understand, for example by displaying the route on a map and adding audio guidance.

[0743] Step 10:

[0744] The server sends the formatted alternative route information to the terminal, allowing the user to view the alternative route in real time.

[0745] Step 11:

[0746] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[0747] Step 12:

[0748] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[0749] Step 13:

[0750] The server analyzes the collected emotional data and determines the user's current emotional state (e.g., stress, fatigue, irritation, etc.). For example, if the user is feeling impatient, the server may simplify the display.

[0751] Step 14:

[0752] Based on the analysis results, the server provides alternative route guidance according to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[0753] Step 15:

[0754] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[0755] Step 16:

[0756] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[0757] Example 2

[0758] 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."

[0759] Conventional vehicle movement data collection and congestion prediction systems have difficulty collecting real-time data and optimizing driving routes based on users' emotional states. Furthermore, dynamic adjustment of pricing based on congestion predictions has not been sufficiently implemented, preventing effective congestion relief measures. This often leads to excessive road congestion during certain times of the day, increasing user stress and frustration.

[0760] 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 a user to input a request to collect vehicle movement data for a long vacation period; means for a terminal to transmit the user's request to the server; means for the server to acquire movement data from a database according to the specified long vacation period; means for the server to analyze the acquired movement data and extract congestion patterns; means for the server to predict future congestion conditions based on the extracted congestion patterns; means for the server to generate alternative routes to avoid the predicted congestion; means for the terminal to notify the user of the generated alternative routes; means for the server to transmit congestion prediction results to a pricing system and provide data for dynamically varying road tolls; means for the terminal to monitor the user's facial expressions and voice using cameras and sensors in the vehicle and collect emotional data; and means for the server to analyze the collected emotional data and provide route guidance according to the user's emotional state. This enables effective congestion mitigation through real-time data collection and analysis, route guidance based on the user's emotional state, and dynamic toll adjustment.

[0761] "Long holiday period" refers to a specific long holiday period, including, for example, Golden Week and the New Year holidays.

[0762] "Vehicle movement data" refers to data including information such as vehicle location, travel route, and time of day.

[0763] "User" refers to any individual or legal entity that uses the System.

[0764] "Terminal" refers to a device operated by a user, and includes, for example, a smartphone, a tablet, an in-vehicle terminal, and the like.

[0765] "Server" refers to a central management device that processes, analyzes, stores, etc. data.

[0766] "Database" refers to a system for storing user movement data and analysis results.

[0767] "Congestion patterns" refers to information that indicates the tendency for vehicle concentration and congestion at specific times and locations.

[0768] A "predictive model" refers to a computational model that uses past data and algorithms to predict future congestion conditions.

[0769] "Alternate route" refers to a different travel route than usual to avoid congestion.

[0770] "Price setting system" means a system for managing and dynamically changing road usage fees.

[0771] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, voice, gestures, etc.

[0772] "Real-time" refers to the immediate processing of situations and data occurring at the moment.

[0773] A "data collection request" refers to a request issued by a user via a terminal to a server instructing the server to collect data.

[0774] "Analysis" refers to the process of examining collected data and extracting meaningful information.

[0775] "Notification" refers to sending information from the system to a user terminal and displaying it.

[0776] The system for implementing this invention includes the collection and analysis of vehicle movement data during long holidays, congestion prediction, provision of alternative routes, provision of data to a fare setting system, and implementation of an emotion engine. This system is realized through the interaction of three parties: a server, a terminal, and a user.

[0777] User Data Collection

[0778] The user operates the application on the terminal and inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week). The terminal formats this request in JSON format and sends it to the server using an HTTP request. The server retrieves vehicle movement data from the database according to the specified long holiday period.

[0779] Data analysis

[0780] The server analyzes the acquired travel data and extracts congestion patterns. Specifically, it performs data cleaning to remove incomplete data and outliers. It then clusters travel times and locations to identify the locations and times when congestion occurs.

[0781] Congestion forecast

[0782] The server predicts future congestion situations based on the extracted congestion patterns using past data and a prediction model (e.g., an LSTM model). The prediction results are stored in a database and converted into an appropriate format for presentation to users.

[0783] Providing alternative routes

[0784] The server generates an alternative route to avoid the predicted congestion. Specifically, it searches for the optimal route using Google Maps API or similar and evaluates multiple routes. The generated alternative route information is formatted appropriately and sent to the device. The device then notifies the user of this information and provides guidance using voice guidance or other means.

[0785] Dynamic Pricing

[0786] The server provides data based on the congestion forecast results to a pricing system, which then dynamically adjusts road tolls based on this data, thereby implementing pricing strategies to alleviate congestion during specific times of day.

[0787] Implementing the Emotion Engine

[0788] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data. The server analyzes this emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.). Based on the analysis results, route guidance is provided that matches the user's emotional state. For example, if the user is feeling stressed, the server will suggest more relaxing routes and rest spots.

[0789] Specific examples

[0790] Here is an example of this system:

[0791] A user inputs a request for collecting movement data for a long vacation period into a terminal, and the terminal transmits the request to a server.

[0792] The server acquires and collects user movement data during the Golden Week period from the database.

[0793] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[0794] The server predicts the congestion during Golden Week next year and saves the results.

[0795] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[0796] The device will notify the user of alternative routes and provide voice guidance.

[0797] The server transmits the congestion forecast data to a pricing system, which then adjusts the fees during peak hours accordingly.

[0798] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[0799] Prompt Sentence Examples

[0800] Below are some example prompts to input to a generative AI model:

[0801] 1. "We would like to collect travel data during Golden Week, analyze congestion patterns, and predict congestion for the following year. Please explain the system that will suggest alternative routes to avoid congestion and send the optimal data to the pricing system."

[0802] 2. "Please explain the procedure for a system that collects and analyzes travel data from users during long vacation periods to predict future congestion. Also, please explain how to suggest a relaxing route for users when they feel stressed."

[0803] The above is an embodiment of the present invention.

[0804] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0805] Step 1: Initiate a data collection request

[0806] A user inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week) using an application on a terminal. The input data includes a specified date range for the holiday period.

[0807] The terminal formats the user's request in JSON format and sends it to the server using an HTTP request.

[0808] Input: Date range of long-term vacation period, User ID

[0809] Output: Data collection request sent to the server

[0810] Step 2: Prepare for data collection

[0811] The server receives the data collection request from the device and prepares access to the database based on the specified long-term vacation period and user ID, which includes establishing a database connection and generating the necessary SQL queries.

[0812] Input: User ID, specified long-term vacation period

[0813] Output: Database connected and ready to query

[0814] Step 3: Data Acquisition

[0815] The server runs an SQL query to retrieve travel data for a specified period from the database, for example, filtering the data based on dates within a certain range.

[0816] Input: SQL query, database connection

[0817] Output: Acquired vehicle movement data

[0818] Step 4: Data Cleaning

[0819] The server cleans the acquired vehicle movement data to remove incomplete data and outliers, a process that is crucial for obtaining reliable analysis results.

[0820] Input: Captured vehicle movement data

[0821] Output: Cleaned movement data

[0822] Step 5: Extracting congestion patterns

[0823] The server uses the cleaned travel data to extract congestion patterns. Specifically, it performs data clustering and analysis by travel time period to identify times and locations where congestion is likely to occur.

[0824] Input: Cleaned movement data

[0825] Output: Congestion pattern

[0826] Step 6: Prepare for congestion forecasts

[0827] The server analyzes past data based on congestion patterns and selects a congestion prediction model (e.g., LSTM model), while also adjusting the model parameters.

[0828] Input: Congestion Pattern

[0829] Output: Selected predictive model

[0830] Step 7: Run congestion forecast

[0831] The server inputs the congestion pattern and an arbitrary future period into the selected prediction model and simulates future congestion.

[0832] Input: Congestion pattern, future period

[0833] Output: Congestion prediction results

[0834] Step 8: Saving and formatting the results

[0835] The server stores the congestion prediction results in a database and converts them into a format (e.g., JSON format) for providing to users.

[0836] Input: Congestion forecast result

[0837] Output: Formatted prediction results

[0838] Step 9: Alternate Route Generation

[0839] The server calculates alternative routes based on the congestion forecast results, and uses Google Maps APIs to select the optimal route to avoid congestion.

[0840] Input: Congestion forecast result

[0841] Output: Multiple alternative routes

[0842] Step 10: Formatting Alternate Routes

[0843] The server converts the generated alternative routes into a format that is easy for the user to understand (e.g., JSON or map data format).

[0844] Input: Multiple alternative routes

[0845] Output: Formatted alternate routes

[0846] Step 11: Notification of Alternate Routes

[0847] The terminal notifies the user of the alternative route sent from the server, for example, by using a notification pop-up or audio guidance.

[0848] Input: Formatted alternate route

[0849] Output: User notification

[0850] Step 12: Provide data to the pricing system

[0851] The server formats the congestion prediction results into a format that can be used by the pricing system (e.g., CSV format) and sends them to the pricing system using an API.

[0852] Input: Congestion forecast result

[0853] Output: Data sent to the pricing system

[0854] Step 13: Implement pricing

[0855] The pricing system dynamically changes road tolls based on data sent from a server, aiming to reduce congestion during certain times of the day.

[0856] Input: Data to send to the pricing system

[0857] Output: Dynamically changed pricing

[0858] Step 14: Collect emotion data

[0859] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[0860] Input: Camera and sensor information

[0861] Output: Collected emotion data

[0862] Step 15: Analyze the emotion data

[0863] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritability, etc.).

[0864] Input: Collected emotion data

[0865] Output: User's emotional state

[0866] Step 16: Route guidance based on emotion data

[0867] Based on the analysis results, the server generates route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, the server suggests relaxing routes and rest spots.

[0868] Input: User's emotional state

[0869] Output: Route guidance based on emotional state

[0870] (Application example 2)

[0871] 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."

[0872] Road congestion during long holiday periods is a major source of stress for many people. Furthermore, congestion can significantly extend travel times, making time management difficult for trips and business trips. Furthermore, the stress and fatigue felt while driving during congestion can have a negative impact on traffic safety. The present invention aims to solve these problems and improve the user experience when traveling or traveling by providing a system that predicts congestion and provides optimal alternative routes based on the user's emotional state.

[0873] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting vehicle movement data during a long holiday period, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for collecting and analyzing emotional data such as the user's facial expressions and tone of voice, means for generating an alternative route based on the predicted congestion and emotional state, means for displaying the alternative route, and means for providing data to a system that varies road tolls based on the predicted congestion. This makes it possible to predict road congestion during a long holiday period and provide an optimal alternative route based on the user's emotional state.

[0874] "Long holiday periods" are periods when many people take vacations at the same time, and when traffic volume increases.

[0875] "Movement data" refers to data including information such as the current position of the vehicle, the route traveled, the travel time, and the speed.

[0876] A "congestion pattern" is a collection of data that indicates the tendency for traffic volume to increase at specific times and locations.

[0877] "Emotion data" is data that indicates the user's emotional state, such as stress, fatigue, or irritation, obtained by analyzing the user's facial expression and tone of voice.

[0878] "Alternate route" refers to a different route to a destination that is calculated to avoid congestion or other obstacles.

[0879] A "variable fee system" is a mechanism that dynamically changes road usage fees based on traffic volume and congestion forecasts.

[0880] "User's facial expressions and tone of voice" are elements that indicate the user's psychological and emotional state and are collected using cameras and microphones installed in the vehicle.

[0881] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[0882] Hardware and Software Configuration

[0883] Hardware:

[0884] Navigation systems for autonomous vehicles

[0885] Cameras and microphones in the vehicle

[0886] software:

[0887] Server-side API (e.g. Flask / Django)

[0888] Data analysis libraries (e.g., NumPy, SciPy)

[0889] Emotion recognition API (e.g. Microsoft Azure Emotion API, Google Cloud Emotion API)

[0890] Road pricing system

[0891] System Overview

[0892] This system is primarily composed of a server and a terminal (autonomous vehicle system). The user collects vehicle movement data during a long vacation period and sends it to the server via middleware. The server analyzes the movement data to determine congestion patterns and predict future congestion. It also uses cameras and microphones inside the vehicle to collect and analyze user emotion data. Based on this data, it generates optimal alternative routes and sends them to the navigation system. It also provides congestion prediction data to the road toll setting system, enabling dynamic toll fluctuations.

[0893] Data collection and analysis

[0894] The device collects vehicle movement data in real time during the long holiday period and sends it to the server. Specifically, this data includes information such as GPS location data, movement speed, and time of day. The server analyzes this data and extracts congestion patterns. For example, it identifies patterns in which congestion frequently occurs on specific roads or during specific time periods.

[0895] Emotion data collection and analysis

[0896] The system uses cameras and microphones installed in the vehicle to collect the user's facial expressions and tone of voice. The server then uses an emotion recognition API to analyze the user's emotional state from this data. For example, it can determine in real time whether the user is feeling stressed or tired.

[0897] Generate optimal alternative routes

[0898] The server generates an optimal alternative route based on the congestion forecast data and the user's emotion data. This route not only avoids areas where congestion is predicted, but may also include routes and rest points where the user can relax. The generated alternative route is sent to the navigation system and displayed to the user.

[0899] Dynamic fluctuations in road tolls

[0900] The server provides congestion forecast data to the road pricing system, which dynamically adjusts road tolls to try to alleviate congestion at specific times and locations.

[0901] Specific examples

[0902] Suppose a user plans to travel during Golden Week. The user enters the travel period into the navigation system and begins collecting vehicle movement data. The server analyzes the collected data and predicts congestion patterns and future congestion based on past data. In addition, the server uses in-vehicle cameras and microphones to analyze the user's emotional data in real time. The server uses this data to generate an optimal alternative route and notify the user. For example, if the user is feeling stressed, the server can also suggest relaxing routes and rest points.

[0903] Prompt Sentence Examples

[0904] "I'm planning to travel during Golden Week. Can you tell me the best route to take to avoid traffic jams? Also, could you suggest some rest stops if I get stressed?"

[0905] In this way, the present invention is a system that improves the travel experience by predicting congestion during long holidays and providing optimal alternative routes based on the user's emotional state.

[0906] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0907] Step 1:

[0908] Initiating a Data Collection Request

[0909] Input: User specifies long-term vacation period and requests vehicle movement data collection.

[0910] Processing: The device receives the user's input and sends the long-term vacation period to the server. Specifically, it uses an API to send the user ID and the specified period.

[0911] Output: The server receives the data collection request and starts preparing for mobile data collection.

[0912] Step 2:

[0913] Starting Data Collection

[0914] Input: The server receives a data collection request.

[0915] Processing: The server prepares to collect movement data for the specified long holiday period and prepares to access the database.

[0916] Output: Data collection is initiated and the server starts collecting movement data from multiple users.

[0917] Step 3:

[0918] Acquiring movement data

[0919] Input: The server retrieves travel data for the long vacation period from the database.

[0920] Processing: The server executes queries to collect movement data for each user. Specifically, it uses SQL queries to obtain the movement history of each user.

[0921] Output: The server collects movement data and prepares it for analysis.

[0922] Step 4:

[0923] Collecting Emotional Data

[0924] Input: Cameras and microphones in the vehicle record the user's facial expressions and tone of voice.

[0925] Processing: The device uses the camera and microphone to collect the user's emotional data and transmit it to the server. Specifically, it captures voice and image data in real time.

[0926] Output: The server stores the received emotion data for analysis.

[0927] Step 5:

[0928] Start of data analysis

[0929] Input: Movement data and emotion data are stored on the server.

[0930] Processing: The server analyzes this data and extracts congestion patterns. It identifies congestion patterns using a data analysis library (e.g., NumPy, SciPy).

[0931] Output: The server extracts congestion patterns and generates data to input into the predictive model.

[0932] Step 6:

[0933] Running a congestion prediction model

[0934] Input: The server inputs congestion pattern data.

[0935] Processing: The server runs a predictive model using past congestion data to predict future congestion. The prediction is made using machine learning algorithms.

[0936] Output: The server generates and stores future congestion prediction results.

[0937] Step 7:

[0938] Generate alternative routes

[0939] Input: The congestion prediction results and user emotion data are input to the server.

[0940] Processing: The server uses this data to generate safe and efficient alternative routes, including selecting routes that are more relaxing for the user based on emotion data.

[0941] Output: The best alternative route is generated and sent to the navigation system.

[0942] Step 8:

[0943] Notification and guidance of alternative routes

[0944] Input: Send the server generated alternative route to the device.

[0945] Processing: The device notifies the user of the alternative route received and displays it on the navigation system, specifically by providing voice guidance and displaying a map.

[0946] Output: The user starts traveling according to the new alternative route.

[0947] Step 9:

[0948] Pricing optimization

[0949] Input: The server provides congestion forecast data to the pricing system.

[0950] Processing: Road pricing systems dynamically adjust toll rates based on congestion forecasts.

[0951] Output: Pricing is optimized and new prices are applied to users.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] [Third embodiment]

[0956] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0957] 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.

[0958] 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).

[0959] 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.

[0960] 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.

[0961] 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).

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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."

[0968] The embodiments of the present invention will be specifically described below.

[0969] User Data Acquisition

[0970] Initiating a Data Collection Request

[0971] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period, for example, a period such as Golden Week.

[0972] Start of data collection

[0973] The server starts collecting data based on the specified long-term vacation period and user information, which includes movement data for thousands of users.

[0974] Data Acquisition

[0975] The server retrieves each user's travel data from the database, for example, by querying the travel data for the relevant period using the user ID, and adds the obtained data to the list.

[0976] Data analysis

[0977] Data analysis begins

[0978] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[0979] Individual data analysis

[0980] The server extracts congestion patterns from each user's data, analyzing each data point to identify the times and locations where congestion occurs, and then combines the results into an overall pattern.

[0981] Congestion pattern aggregation

[0982] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information, for example, analyzing the congestion situation around Umihotaru.

[0983] Congestion forecast

[0984] Selecting a Prediction Model

[0985] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[0986] Implementing congestion predictions

[0987] The server inputs the collected congestion patterns and the specified period into the model and makes a prediction, for example, predicting congestion during next year's Golden Week period.

[0988] Saving the results

[0989] The server stores the predicted congestion results in a database and converts them into a format for presentation to the user.

[0990] Alternative route suggestions

[0991] Alternative Route Generation

[0992] The server generates alternative routes based on the congestion forecast, which involves calculating routes that avoid times and locations where congestion is predicted.

[0993] Alternate Route Format

[0994] The server formats the generated alternative routes in a way that is easy for the user to understand.

[0995] Providing alternative routes

[0996] The server sends alternative routes to the terminal and makes them available to the user.

[0997] User Notifications

[0998] The device will then notify the user of the alternative route and encourage them to use it, for example, suggesting a route via the coastal road to avoid the traffic jam at Umihotaru.

[0999] Providing information on fluctuating prices

[1000] Data format conversion

[1001] The server formats the congestion forecast results into a format usable by the pricing system.

[1002] Information transmission

[1003] The server sends the formatted data to the pricing system.

[1004] Pricing optimization

[1005] The pricing system uses the transmitted data to optimize highway tolls, for example by raising tolls during peak hours around Umihotaru to ease congestion.

[1006] Specific examples

[1007] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[1008] The server acquires user movement data during the Golden Week period from the database.

[1009] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[1010] The server predicts the congestion during Golden Week next year and saves the results.

[1011] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[1012] The device notifies the user of alternative routes and encourages them to use them.

[1013] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[1014] The processing flow will be explained below.

[1015] Step 1:

[1016] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[1017] Step 2:

[1018] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[1019] Step 3:

[1020] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[1021] Step 4:

[1022] The server analyzes the collected movement data. First, it analyzes each user's data points to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[1023] Step 5:

[1024] The server aggregates the data collected from all users and identifies common congestion patterns, such as the concentration of users in specific service areas or tourist spots (e.g., Umihotaru), and plots the congestion situation on a map.

[1025] Step 6:

[1026] The server selects an appropriate prediction model and sets a model to predict future congestion conditions using the optimal algorithm based on past data.

[1027] Step 7:

[1028] The server inputs the analyzed congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[1029] Step 8:

[1030] The server stores the prediction results in a database and converts them into a format that can be provided to the user for future reference.

[1031] Step 9:

[1032] The server generates alternative routes based on the congestion prediction results, calculates multiple routes to avoid times and locations where congestion is predicted, and selects the optimal alternative route.

[1033] Step 10:

[1034] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[1035] Step 11:

[1036] The server sends the formatted alternative route information to the terminal, allowing the user to check the alternative route in real time.

[1037] Step 12:

[1038] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[1039] Step 13:

[1040] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[1041] Step 14:

[1042] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[1043] Example 1

[1044] 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."

[1045] In recent years, traffic congestion during long holiday periods has become a social problem. This problem not only reduces travel efficiency and road utilization efficiency, but also has a negative impact on the environment due to increased exhaust gas emissions. To solve this problem, it is necessary to predict congestion using past data and provide appropriate alternative routes based on that prediction. However, conventional systems have had problems in that they do not sufficiently provide users with efficient data collection, highly accurate congestion predictions, or the optimization of alternative routes based on those predictions.

[1046] 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.

[1047] In this invention, the server includes: means for a user to send a request for collecting vehicle movement data for a long vacation period from a terminal; means for the server to start collecting movement data for a specified period based on the received request; means for the server to acquire movement data for each user from a database; means for the server to analyze the collected data to extract congestion patterns and perform individual data analysis; means for the server to aggregate congestion patterns and generate comprehensive congestion information; means for the server to select an appropriate prediction model and predict congestion based on past data; means for the server to store the predicted congestion results in a database and format them for provision to the user; means for the server to generate alternative routes based on the congestion prediction results and provide them to the terminal; means for the terminal to notify the user of the received alternative route; and means for the server to format the congestion prediction results in a format usable by a pricing system and transmit them. This allows users to predict congestion in advance and select appropriate alternative routes, thereby achieving efficient transportation operations and reducing time loss and environmental impact due to congestion.

[1048] A "user" is an entity that uses a terminal to access the system and make a request to collect movement data for a specified period of time.

[1049] A "terminal" is a device used by a user to send data collection requests to the system and receive notifications from the server.

[1050] A "server" is a computer system that performs multiple functions such as data collection, analysis, prediction, alternate route generation, and data format conversion.

[1051] "Movement data" refers to data including information such as vehicle location information, travel route, and speed, and indicates the user's movement history.

[1052] "Database" means a system or structured collection of data used to store movement data for collection and analysis.

[1053] A "congestion pattern" is a pattern of data that indicates the traffic congestion that occurs during a specific period and at a specific location.

[1054] A "predictive model" is a mathematical or statistical algorithm used to predict future congestion conditions based on past data.

[1055] An "alternate route" is a suggested alternative travel route to avoid congestion and indicates the optimal route.

[1056] A "pricing system" is a system used to optimize road usage fees based on congestion forecast results.

[1057] The present invention is a system that collects and analyzes vehicle movement data during long holiday periods, predicts congestion, and provides alternative routes. This system consists of three main components: a server, a terminal, and a user. Specific embodiments of the system are described below.

[1058] First, the device used by the user is typically a mobile device such as a smartphone or tablet. The user uses this device to send a request to the server to collect vehicle movement data during a specific period. The specified period is, for example, a long holiday period such as "Golden Week." This request may be generated using a prompt in text format. For example, a prompt such as "Please collect movement data during Golden Week in 2024" may be used.

[1059] When the server receives this request, it starts the data collection process. The server retrieves each user's travel data from the database. This involves database operations such as SQL queries to retrieve travel data for the specified period. The retrieved data includes information such as the vehicle's location, travel route, and speed.

[1060] The collected data is analyzed by a server. The server performs individual data analysis to extract congestion patterns. It identifies the time periods and locations where congestion occurred from each user's movement data and integrates the results into an overall pattern. This analysis forms the basis for understanding the congestion situation at a specific location and time.

[1061] Next, the server selects an appropriate prediction model and uses the generative AI model to predict future congestion conditions. Past congestion patterns and usage data are used as input. For example, a prompt might be entered such as, "Please predict congestion conditions during Golden Week in 2025." The prediction model selects the optimal algorithm based on past data and predicts future congestion conditions with high accuracy.

[1062] The prediction results are stored in a database in formats such as JSON or CSV, and the server uses these to generate alternative routes. Routes that avoid times and locations where congestion is predicted are calculated and provided to the user. For example, it suggests a route that avoids Umihotaru and takes the bayside road between 10:00 and 14:00. The suggestions are formatted with map information and detailed explanations and provided in a way that is easy for users to understand.

[1063] The generated alternative route is then sent back to the device via the server. The device then notifies the user of the received alternative route information and provides appropriate guidance. Notifications are sent via text messages or pop-up notifications, such as "Please use the following alternative route to avoid traffic jams at Umihotaru."

[1064] The server then sends the congestion prediction results to a pricing system. The server then formats the data into a format that the pricing system can use and sends it to the pricing system. The system then optimizes fares based on the data sent and sets fares to alleviate congestion. For example, it can reduce congestion by raising fares during peak hours around Umihotaru.

[1065] The above is a specific embodiment of the present invention. This system allows users to predict traffic congestion in advance and select the optimal alternative route. This is expected to realize efficient traffic management and reduce the burden on the environment.

[1066] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1067] Step 1: Initiate a data collection request

[1068] The user sends a request to collect vehicle movement data during a specified long holiday period from the terminal to the server. The input to this process is a prompt statement in which the user specifies the period (e.g., "Please collect movement data during the Golden Week period in 2024"). The output is that this request is transmitted to the server. When the terminal sends the prompt statement, the server receives this request and the data collection process begins.

[1069] Step 2: Start collecting data

[1070] The server starts collecting mobile data for a specified period based on the received request. The input to this process is a data collection request from the terminal, and the output is an instruction to start data collection. The server establishes a database connection and prepares to collect mobile data.

[1071] Step 3: Get the data

[1072] The server retrieves each user's movement data from the database. The input to this process is a list of user IDs to be collected and a specified period, and the output is the retrieved movement data. The server executes SQL queries to collect data, issuing commands such as "Retrieve movement data for user ID 12345 during the Golden Week period."

[1073] Step 4: Begin data analysis

[1074] The server launches a process to analyze the collected movement data. The input of this process is the collected raw data, and the output is a notification that the analysis task has been configured. The server schedules the data analysis tasks and configures them to run in parallel.

[1075] Step 5: Individual data analysis

[1076] The server analyzes congestion patterns from each user's movement data individually. The input to this process is a dataset for each individual user, and the output is information about the time and location of congestion. The server analyzes each data point and obtains a result such as "Congestion occurred on the Chuo Expressway from 10:00 to 14:00 on May 3rd."

[1077] Step 6: Aggregating congestion patterns

[1078] The server aggregates congestion patterns obtained from the data of all users. The input to this process is the individual analysis results of each user, and the output is comprehensive congestion information. The server integrates the data of multiple users and identifies a pattern such as "during Golden Week, congestion will occur around Umihotaru from 10:00 to 14:00."

[1079] Step 7: Select a predictive model

[1080] The server selects an appropriate prediction model and prepares it for crowd prediction. The inputs to this process are past data and analysis results, and the output is the selected prediction model. The server uses the generative AI model to input a prompt such as "Please predict the crowd situation during Golden Week in 2025."

[1081] Step 8: Run congestion forecast

[1082] The server inputs the aggregated congestion patterns and data for the specified period into a prediction model to make a congestion forecast. The inputs to this process are the prediction model and the original data, and the output is the future congestion forecast results. The server runs the prediction model and makes a specific forecast of "Golden Week congestion in 2025."

[1083] Step 9: Save the results

[1084] The server saves the prediction results in a database and formats them for presentation to users. The input to this process is the prediction results, and the output is saved in the database as formatted data. In this saving process, the data is converted into JSON format, CSV format, etc.

[1085] Step 10: Generate Alternate Routes

[1086] The server generates an alternative route based on the congestion forecast results. The input to this process is the congestion forecast results, and the output is the generated alternative route. It is calculated as follows: "Avoid Umihotaru and take the Bayshore Route between 10:00 and 14:00."

[1087] Step 11: Formatting Alternate Routes

[1088] The server formats the generated alternative routes in a way that is easy for the user to understand. The input to this process is the generated alternative route, and the output is formatted alternative route information, such as "Use this route during this time period" with map information and text descriptions.

[1089] Step 12: Provide an alternative route

[1090] The server sends the alternative route to the terminal and provides it to the user. The input of this process is formatted alternative route information, and the output is a transmission notification to the terminal. The server records logs and monitors the transmission status.

[1091] Step 13: User Notification

[1092] The terminal notifies the user of the received alternative route information. The input of this process is the alternative route information sent from the server, and the output is a notification to the user. For example, a pop-up notification may be displayed saying, "To avoid the traffic jam at Umihotaru, please use the following alternative route."

[1093] Step 14: Data Format Conversion

[1094] The server formats the congestion forecast results into a format that can be used by the pricing system. The input to this process is the forecast results, and the output is formatted data. For example, the congestion forecast results are converted into CSV format.

[1095] Step 15: Send information

[1096] The server sends the formatted data to the pricing system. The input to this process is the formatted data and the output is a submission notification. The server confirms and logs the submission of the data to the pricing system.

[1097] Step 16: Optimize your pricing

[1098] The pricing system adjusts the prices based on the data sent. The input to this process is data from the server, and the output is optimized pricing. For example, increasing the price during peak hours around Umihotaru reduces congestion.

[1099] (Application example 1)

[1100] 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."

[1101] Congestion during long holiday periods can be a significant source of stress for many drivers. The resulting inefficiencies and delays during peak hours are also a major challenge. Furthermore, the lack of appropriate alternative route selection and optimization of road tolls is a problem. Therefore, a system that can predict future congestion, provide appropriate alternative routes, notify users, and dynamically adjust toll fees is needed.

[1102] 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.

[1103] In this invention, the server includes means for collecting vehicle movement data during long holiday periods, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for generating alternative routes based on the predicted congestion, means for displaying the alternative routes, means for notifying users of the alternative routes, and means for providing data to a system that varies road tolls based on the predicted congestion, thereby encouraging users to travel efficiently and avoiding congestion during peak hours.

[1104] "Long holiday periods" refer to periods when many people are on vacation at the same time, such as long weekends or holiday seasons, which tend to result in significantly higher traffic volumes than usual.

[1105] "Movement data" refers to information about a vehicle's movement, such as its location, time, and speed. This data is collected from GPS and various sensors.

[1106] "Congestion patterns" refers to data that indicates traffic congestion conditions in a particular time period or area, including traffic volume, vehicle speed, and dwell time.

[1107] "Predicted congestion" is information that indicates traffic congestion conditions that are likely to occur in the future based on past travel data and congestion patterns.

[1108] "Alternate Route" refers to a proposed alternative route to reach a destination to avoid predicted congestion.

[1109] "User notification" is the act of conveying information from the system to the user. This notification may be in the form of voice, text, display, etc.

[1110] A "variable toll system" is a system that dynamically adjusts road usage fees based on traffic congestion and forecast data, making it possible to curb usage during peak times and alleviate congestion.

[1111] The system for implementing this invention includes a series of means for collecting, analyzing, predicting, and notifying vehicle movement data during long vacation periods. The system of this invention is realized by using an on-board computer, a GPS module, and various sensors as hardware, and software such as a database system and a machine learning model.

[1112] First, the server will begin collecting movement data during the long vacation period. This data is collected using the GPS module and various sensors installed in the autonomous vehicle, and data from the user is sent to the server.

[1113] The collected movement data is then analyzed by the server. This analysis involves managing the data using a database system (e.g., MySQL, MongoDB) and extracting congestion patterns using analytical algorithms (e.g., k-means clustering). Detailed movement data for each user is analyzed to identify specific times and locations of congestion.

[1114] Next, based on the analysis results, the server performs time series prediction using a machine learning model (e.g., TensorFlow, PyTorch) to predict future congestion. This prediction uses collected past data and congestion patterns as inputs to predict future congestion conditions for a specific period.

[1115] An alternative route is then generated based on this prediction. To generate the alternative route, a map information API (e.g., Google Maps API) is used to calculate the optimal route, taking into account current traffic conditions and predicted road congestion. The generated alternative route is formatted in a user-friendly format and sent to the autonomous vehicle's on-board display or smartphone.

[1116] Furthermore, the server notifies the user and presents the generated alternative route. This notification can be provided in the form of voice guidance or text message, helping the user to smoothly use the alternative route.

[1117] Finally, the predicted congestion information is also provided to the toll system, which dynamically optimizes highway tolls and takes measures to alleviate congestion during peak hours. The server converts the congestion prediction results into a format that the toll system can use and provides the appropriate information.

[1118] As a specific example, the system can predict congestion around the Tokyo Bay Aqua-Line (Umihotaru) during Golden Week, and based on the results, generate an alternative route via the Bayshore Route and notify the user. This can reduce stress during long holiday periods such as the New Year holidays and improve travel efficiency.

[1119] The following is an example of a prompt sentence:

[1120] "Design an algorithm to predict traffic congestion around the Tokyo Bay Aqua-Line (Umihotaru) during the Golden Week period and generate alternative routes to avoid the congestion."

[1121] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1122] Step 1:

[1123] The terminal specifies a long holiday period (e.g., Golden Week) and sends a movement data collection request to the server. The input includes data specifying the start and end dates of the period. After receiving this request, the server prepares to collect movement data of multiple users during the specified period.

[1124] Step 2:

[1125] The server stores the movement data collected from multiple users in a database system. It receives data from the GPS module and various sensors and stores it in the database. The input data are data points such as user location information, travel time, and travel speed. As an output, each user's movement data is stored in the database.

[1126] Step 3:

[1127] The server analyzes the stored travel data and extracts congestion patterns. This analysis uses a clustering algorithm (e.g., k-means clustering) to identify congestion levels at specific times and locations. The input is the travel data in the database, and the output is the analysis results that indicate busy times and locations.

[1128] Step 4:

[1129] The server uses a generative AI model (e.g., TensorFlow, PyTorch) to predict future congestion based on the analyzed congestion patterns. This prediction uses a time series analysis model to calculate future trends from past data. The input is the congestion pattern and past movement data, and the output is the predicted congestion time period and location.

[1130] Step 5:

[1131] The server generates an alternative route based on the predicted congestion information. It uses a map information API (e.g., Google Maps API) to calculate the optimal route that avoids congestion. The current location, destination, and predicted congestion information are used as input. The output is generated as an alternative route that can be used by the user.

[1132] Step 6:

[1133] The server sends the generated alternative route to the terminal, and the terminal notifies the user. This notification is provided as a voice guide or a text message. The input is the alternative route information, and the output is a notification to the user. Specifically, the alternative route information is presented using a voice output device or a display.

[1134] Step 7:

[1135] The server provides predicted congestion information to a toll system, which dynamically optimizes road usage tolls and alleviates congestion. The input is predicted congestion information, and the output is data converted into a format that can be used by the toll system. The toll system uses this data to adjust tolls during peak hours.

[1136] 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.

[1137] The embodiments of the present invention will be specifically described below.

[1138] User Data Acquisition

[1139] Initiating a Data Collection Request

[1140] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[1141] Start of data collection

[1142] The server receives the user's request and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[1143] Data Acquisition

[1144] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[1145] Data analysis

[1146] Data analysis begins

[1147] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[1148] Individual data analysis

[1149] The server extracts congestion patterns from each user's data. It analyzes each data point to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[1150] Congestion pattern aggregation

[1151] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information. For example, it analyzes the congestion situation around Umihotaru.

[1152] Congestion forecast

[1153] Selecting a Prediction Model

[1154] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[1155] Implementing congestion predictions

[1156] The server inputs the collected congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[1157] Saving the results

[1158] The server stores the prediction results in a database and converts them into a format that can be presented to the user for future reference.

[1159] Alternative route suggestions

[1160] Alternative Route Generation

[1161] The server generates alternative routes based on the congestion prediction results. To avoid times and locations where congestion is predicted, multiple routes are calculated and the optimal alternative route is selected.

[1162] Alternate Route Format

[1163] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[1164] Providing alternative routes

[1165] The server transmits the alternative route information to the terminal, allowing the user to check the alternative route in real time.

[1166] User Notifications

[1167] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[1168] Providing information on fluctuating prices

[1169] Data format conversion

[1170] The server formats the congestion forecast results into a format usable by the pricing system.

[1171] Information transmission

[1172] The server sends the formatted data to the pricing system.

[1173] Pricing optimization

[1174] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[1175] Implementing the Emotion Engine

[1176] Emotion Engine Data Collection

[1177] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[1178] Emotional Data Analysis

[1179] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.).

[1180] Emotional Data Feedback

[1181] Based on the analysis results, the server provides route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[1182] Specific examples

[1183] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[1184] The server acquires user movement data during the Golden Week period from the database.

[1185] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[1186] The server predicts the congestion during Golden Week next year and saves the results.

[1187] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[1188] The device notifies the user of alternative routes and encourages them to use them.

[1189] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[1190] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[1191] The processing flow will be explained below.

[1192] Step 1:

[1193] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period. For example, the user inputs a request to acquire data for the Golden Week period.

[1194] Step 2:

[1195] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and period.

[1196] Step 3:

[1197] The server queries the database for each user's travel data, for example, retrieving all records of travels made by user ID "12345" during the Golden Week period.

[1198] Step 4:

[1199] The server analyzes the collected movement data, specifically analyzing each user's data points to identify the time periods and locations where congestion occurred.

[1200] Step 5:

[1201] The server extracts congestion patterns from each user's movement data and aggregates them comprehensively. For example, it identifies peak times and locations of traffic flow around Umihotaru.

[1202] Step 6:

[1203] The server selects an appropriate prediction model and predicts future congestion based on past data. Specifically, it predicts next year's congestion around Umihotaru based on time-series data.

[1204] Step 7:

[1205] The server stores the prediction results in a database and converts them into a format for providing them to users, for example, into a data format for visualizing the prediction results on a map.

[1206] Step 8:

[1207] The server generates alternative routes based on the congestion prediction results, calculates multiple routes that avoid times and locations where congestion is predicted, and selects the optimal route.

[1208] Step 9:

[1209] The server formats the generated alternative routes in a way that is easy for the user to understand, for example by displaying the route on a map and adding audio guidance.

[1210] Step 10:

[1211] The server sends the formatted alternative route information to the terminal, allowing the user to view the alternative route in real time.

[1212] Step 11:

[1213] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[1214] Step 12:

[1215] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[1216] Step 13:

[1217] The server analyzes the collected emotional data and determines the user's current emotional state (e.g., stress, fatigue, irritation, etc.). For example, if the user is feeling impatient, the server may simplify the display.

[1218] Step 14:

[1219] Based on the analysis results, the server provides alternative route guidance according to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[1220] Step 15:

[1221] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[1222] Step 16:

[1223] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[1224] Example 2

[1225] 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."

[1226] Conventional vehicle movement data collection and congestion prediction systems have difficulty collecting real-time data and optimizing driving routes based on users' emotional states. Furthermore, dynamic adjustment of pricing based on congestion predictions has not been sufficiently implemented, preventing effective congestion relief measures. This often leads to excessive road congestion during certain times of the day, increasing user stress and frustration.

[1227] 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 a user to input a request to collect vehicle movement data for a long vacation period; means for a terminal to transmit the user's request to the server; means for the server to acquire movement data from a database according to the specified long vacation period; means for the server to analyze the acquired movement data and extract congestion patterns; means for the server to predict future congestion conditions based on the extracted congestion patterns; means for the server to generate alternative routes to avoid the predicted congestion; means for the terminal to notify the user of the generated alternative routes; means for the server to transmit congestion prediction results to a pricing system and provide data for dynamically varying road tolls; means for the terminal to monitor the user's facial expressions and voice using cameras and sensors in the vehicle and collect emotional data; and means for the server to analyze the collected emotional data and provide route guidance according to the user's emotional state. This enables effective congestion mitigation through real-time data collection and analysis, route guidance based on the user's emotional state, and dynamic toll adjustment.

[1228] "Long holiday period" refers to a specific long holiday period, including, for example, Golden Week and the New Year holidays.

[1229] "Vehicle movement data" refers to data including information such as vehicle location, travel route, and time of day.

[1230] "User" refers to any individual or legal entity that uses the System.

[1231] "Terminal" refers to a device operated by a user, and includes, for example, a smartphone, a tablet, an in-vehicle terminal, and the like.

[1232] "Server" refers to a central management device that processes, analyzes, stores, etc. data.

[1233] "Database" refers to a system for storing user movement data and analysis results.

[1234] "Congestion patterns" refers to information that indicates the tendency for vehicle concentration and congestion at specific times and locations.

[1235] A "predictive model" refers to a computational model that uses past data and algorithms to predict future congestion conditions.

[1236] "Alternate route" refers to a different travel route than usual to avoid congestion.

[1237] "Price setting system" means a system for managing and dynamically changing road usage fees.

[1238] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, voice, gestures, etc.

[1239] "Real-time" refers to the immediate processing of situations and data occurring at the moment.

[1240] A "data collection request" refers to a request issued by a user via a terminal to a server instructing the server to collect data.

[1241] "Analysis" refers to the process of examining collected data and extracting meaningful information.

[1242] "Notification" refers to sending information from the system to a user terminal and displaying it.

[1243] The system for implementing this invention includes the collection and analysis of vehicle movement data during long holidays, congestion prediction, provision of alternative routes, provision of data to a fare setting system, and implementation of an emotion engine. This system is realized through the interaction of three parties: a server, a terminal, and a user.

[1244] User Data Collection

[1245] The user operates the application on the terminal and inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week). The terminal formats this request in JSON format and sends it to the server using an HTTP request. The server retrieves vehicle movement data from the database according to the specified long holiday period.

[1246] Data analysis

[1247] The server analyzes the acquired travel data and extracts congestion patterns. Specifically, it performs data cleaning to remove incomplete data and outliers. It then clusters travel times and locations to identify the locations and times when congestion occurs.

[1248] Congestion forecast

[1249] The server predicts future congestion situations based on the extracted congestion patterns using past data and a prediction model (e.g., an LSTM model). The prediction results are stored in a database and converted into an appropriate format for presentation to users.

[1250] Providing alternative routes

[1251] The server generates an alternative route to avoid the predicted congestion. Specifically, it searches for the optimal route using Google Maps API or similar and evaluates multiple routes. The generated alternative route information is formatted appropriately and sent to the device. The device then notifies the user of this information and provides guidance using voice guidance or other means.

[1252] Dynamic Pricing

[1253] The server provides data based on the congestion forecast results to a pricing system, which then dynamically adjusts road tolls based on this data, thereby implementing pricing strategies to alleviate congestion during specific times of day.

[1254] Implementing the Emotion Engine

[1255] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data. The server analyzes this emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.). Based on the analysis results, route guidance is provided that matches the user's emotional state. For example, if the user is feeling stressed, the server will suggest more relaxing routes and rest spots.

[1256] Specific examples

[1257] Here is an example of this system:

[1258] A user inputs a request for collecting movement data for a long vacation period into a terminal, and the terminal transmits the request to a server.

[1259] The server acquires and collects user movement data during the Golden Week period from the database.

[1260] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[1261] The server predicts the congestion during Golden Week next year and saves the results.

[1262] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[1263] The device will notify the user of alternative routes and provide voice guidance.

[1264] The server transmits the congestion forecast data to a pricing system, which then adjusts the fees during peak hours accordingly.

[1265] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[1266] Prompt Sentence Examples

[1267] Below are some example prompts to input to a generative AI model:

[1268] 1. "We would like to collect travel data during Golden Week, analyze congestion patterns, and predict congestion for the following year. Please explain the system that will suggest alternative routes to avoid congestion and send the optimal data to the pricing system."

[1269] 2. "Please explain the procedure for a system that collects and analyzes travel data from users during long vacation periods to predict future congestion. Also, please explain how to suggest a relaxing route for users when they feel stressed."

[1270] The above is an embodiment of the present invention.

[1271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1272] Step 1: Initiate a data collection request

[1273] A user inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week) using an application on a terminal. The input data includes a specified date range for the holiday period.

[1274] The terminal formats the user's request in JSON format and sends it to the server using an HTTP request.

[1275] Input: Date range of long-term vacation period, User ID

[1276] Output: Data collection request sent to the server

[1277] Step 2: Prepare for data collection

[1278] The server receives the data collection request from the device and prepares access to the database based on the specified long-term vacation period and user ID, which includes establishing a database connection and generating the necessary SQL queries.

[1279] Input: User ID, specified long-term vacation period

[1280] Output: Database connected and ready to query

[1281] Step 3: Data Acquisition

[1282] The server runs an SQL query to retrieve travel data for a specified period from the database, for example, filtering the data based on dates within a certain range.

[1283] Input: SQL query, database connection

[1284] Output: Acquired vehicle movement data

[1285] Step 4: Data Cleaning

[1286] The server cleans the acquired vehicle movement data to remove incomplete data and outliers, a process that is crucial for obtaining reliable analysis results.

[1287] Input: Captured vehicle movement data

[1288] Output: Cleaned movement data

[1289] Step 5: Extracting congestion patterns

[1290] The server uses the cleaned travel data to extract congestion patterns. Specifically, it performs data clustering and analysis by travel time period to identify times and locations where congestion is likely to occur.

[1291] Input: Cleaned movement data

[1292] Output: Congestion pattern

[1293] Step 6: Prepare for congestion forecasts

[1294] The server analyzes past data based on congestion patterns and selects a congestion prediction model (e.g., LSTM model), while also adjusting the model parameters.

[1295] Input: Congestion Pattern

[1296] Output: Selected predictive model

[1297] Step 7: Run congestion forecast

[1298] The server inputs the congestion pattern and an arbitrary future period into the selected prediction model and simulates future congestion.

[1299] Input: Congestion pattern, future period

[1300] Output: Congestion prediction results

[1301] Step 8: Saving and formatting the results

[1302] The server stores the congestion prediction results in a database and converts them into a format (e.g., JSON format) for providing to users.

[1303] Input: Congestion forecast result

[1304] Output: Formatted prediction results

[1305] Step 9: Alternate Route Generation

[1306] The server calculates alternative routes based on the congestion forecast results, and uses Google Maps APIs to select the optimal route to avoid congestion.

[1307] Input: Congestion forecast result

[1308] Output: Multiple alternative routes

[1309] Step 10: Formatting Alternate Routes

[1310] The server converts the generated alternative routes into a format that is easy for the user to understand (e.g., JSON or map data format).

[1311] Input: Multiple alternative routes

[1312] Output: Formatted alternate routes

[1313] Step 11: Notification of Alternate Routes

[1314] The terminal notifies the user of the alternative route sent from the server, for example, by using a notification pop-up or audio guidance.

[1315] Input: Formatted alternate route

[1316] Output: User notification

[1317] Step 12: Provide data to the pricing system

[1318] The server formats the congestion prediction results into a format that can be used by the pricing system (e.g., CSV format) and sends them to the pricing system using an API.

[1319] Input: Congestion forecast result

[1320] Output: Data sent to the pricing system

[1321] Step 13: Implement pricing

[1322] The pricing system dynamically changes road tolls based on data sent from a server, aiming to reduce congestion during certain times of the day.

[1323] Input: Data to send to the pricing system

[1324] Output: Dynamically changed pricing

[1325] Step 14: Collect emotion data

[1326] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[1327] Input: Camera and sensor information

[1328] Output: Collected emotion data

[1329] Step 15: Analyze the emotion data

[1330] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritability, etc.).

[1331] Input: Collected emotion data

[1332] Output: User's emotional state

[1333] Step 16: Route guidance based on emotion data

[1334] Based on the analysis results, the server generates route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, the server suggests relaxing routes and rest spots.

[1335] Input: User's emotional state

[1336] Output: Route guidance based on emotional state

[1337] (Application example 2)

[1338] 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."

[1339] Road congestion during long holiday periods is a major source of stress for many people. Furthermore, congestion can significantly extend travel times, making time management difficult for trips and business trips. Furthermore, the stress and fatigue felt while driving during congestion can have a negative impact on traffic safety. The present invention aims to solve these problems and improve the user experience when traveling or traveling by providing a system that predicts congestion and provides optimal alternative routes based on the user's emotional state.

[1340] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting vehicle movement data during a long holiday period, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for collecting and analyzing emotional data such as the user's facial expressions and tone of voice, means for generating an alternative route based on the predicted congestion and emotional state, means for displaying the alternative route, and means for providing data to a system that varies road tolls based on the predicted congestion. This makes it possible to predict road congestion during a long holiday period and provide an optimal alternative route based on the user's emotional state.

[1341] "Long holiday periods" are periods when many people take vacations at the same time, and when traffic volume increases.

[1342] "Movement data" refers to data including information such as the current position of the vehicle, the route traveled, the travel time, and the speed.

[1343] A "congestion pattern" is a collection of data that indicates the tendency for traffic volume to increase at specific times and locations.

[1344] "Emotion data" is data that indicates the user's emotional state, such as stress, fatigue, or irritation, obtained by analyzing the user's facial expression and tone of voice.

[1345] "Alternate route" refers to a different route to a destination that is calculated to avoid congestion or other obstacles.

[1346] A "variable fee system" is a mechanism that dynamically changes road usage fees based on traffic volume and congestion forecasts.

[1347] "User's facial expressions and tone of voice" are elements that indicate the user's psychological and emotional state and are collected using cameras and microphones installed in the vehicle.

[1348] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[1349] Hardware and Software Configuration

[1350] Hardware:

[1351] Navigation systems for autonomous vehicles

[1352] Cameras and microphones in the vehicle

[1353] software:

[1354] Server-side API (e.g. Flask / Django)

[1355] Data analysis libraries (e.g., NumPy, SciPy)

[1356] Emotion recognition API (e.g. Microsoft Azure Emotion API, Google Cloud Emotion API)

[1357] Road pricing system

[1358] System Overview

[1359] This system is primarily composed of a server and a terminal (autonomous vehicle system). The user collects vehicle movement data during a long vacation period and sends it to the server via middleware. The server analyzes the movement data to determine congestion patterns and predict future congestion. It also uses cameras and microphones inside the vehicle to collect and analyze user emotion data. Based on this data, it generates optimal alternative routes and sends them to the navigation system. It also provides congestion prediction data to the road toll setting system, enabling dynamic toll fluctuations.

[1360] Data collection and analysis

[1361] The device collects vehicle movement data in real time during the long holiday period and sends it to the server. Specifically, this data includes information such as GPS location data, movement speed, and time of day. The server analyzes this data and extracts congestion patterns. For example, it identifies patterns in which congestion frequently occurs on specific roads or during specific time periods.

[1362] Emotion data collection and analysis

[1363] The system uses cameras and microphones installed in the vehicle to collect the user's facial expressions and tone of voice. The server then uses an emotion recognition API to analyze the user's emotional state from this data. For example, it can determine in real time whether the user is feeling stressed or tired.

[1364] Generate optimal alternative routes

[1365] The server generates an optimal alternative route based on the congestion forecast data and the user's emotion data. This route not only avoids areas where congestion is predicted, but may also include routes and rest points where the user can relax. The generated alternative route is sent to the navigation system and displayed to the user.

[1366] Dynamic fluctuations in road tolls

[1367] The server provides congestion forecast data to the road pricing system, which dynamically adjusts road tolls to try to alleviate congestion at specific times and locations.

[1368] Specific examples

[1369] Suppose a user plans to travel during Golden Week. The user enters the travel period into the navigation system and begins collecting vehicle movement data. The server analyzes the collected data and predicts congestion patterns and future congestion based on past data. In addition, the server uses in-vehicle cameras and microphones to analyze the user's emotional data in real time. The server uses this data to generate an optimal alternative route and notify the user. For example, if the user is feeling stressed, the server can also suggest relaxing routes and rest points.

[1370] Prompt Sentence Examples

[1371] "I'm planning to travel during Golden Week. Can you tell me the best route to take to avoid traffic jams? Also, could you suggest some rest stops if I get stressed?"

[1372] In this way, the present invention is a system that improves the travel experience by predicting congestion during long holidays and providing optimal alternative routes based on the user's emotional state.

[1373] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1374] Step 1:

[1375] Initiating a Data Collection Request

[1376] Input: User specifies long-term vacation period and requests vehicle movement data collection.

[1377] Processing: The device receives the user's input and sends the long-term vacation period to the server. Specifically, it uses an API to send the user ID and the specified period.

[1378] Output: The server receives the data collection request and starts preparing for mobile data collection.

[1379] Step 2:

[1380] Starting Data Collection

[1381] Input: The server receives a data collection request.

[1382] Processing: The server prepares to collect movement data for the specified long holiday period and prepares to access the database.

[1383] Output: Data collection is initiated and the server starts collecting movement data from multiple users.

[1384] Step 3:

[1385] Acquiring movement data

[1386] Input: The server retrieves travel data for the long vacation period from the database.

[1387] Processing: The server executes queries to collect movement data for each user. Specifically, it uses SQL queries to obtain the movement history of each user.

[1388] Output: The server collects movement data and prepares it for analysis.

[1389] Step 4:

[1390] Collecting Emotional Data

[1391] Input: Cameras and microphones in the vehicle record the user's facial expressions and tone of voice.

[1392] Processing: The device uses the camera and microphone to collect the user's emotional data and transmit it to the server. Specifically, it captures voice and image data in real time.

[1393] Output: The server stores the received emotion data for analysis.

[1394] Step 5:

[1395] Start of data analysis

[1396] Input: Movement data and emotion data are stored on the server.

[1397] Processing: The server analyzes this data and extracts congestion patterns. It identifies congestion patterns using a data analysis library (e.g., NumPy, SciPy).

[1398] Output: The server extracts congestion patterns and generates data to input into the predictive model.

[1399] Step 6:

[1400] Running a congestion prediction model

[1401] Input: The server inputs congestion pattern data.

[1402] Processing: The server runs a predictive model using past congestion data to predict future congestion. The prediction is made using machine learning algorithms.

[1403] Output: The server generates and stores future congestion prediction results.

[1404] Step 7:

[1405] Generate alternative routes

[1406] Input: The congestion prediction results and user emotion data are input to the server.

[1407] Processing: The server uses this data to generate safe and efficient alternative routes, including selecting routes that are more relaxing for the user based on emotion data.

[1408] Output: The best alternative route is generated and sent to the navigation system.

[1409] Step 8:

[1410] Notification and guidance of alternative routes

[1411] Input: Send the server generated alternative route to the device.

[1412] Processing: The device notifies the user of the alternative route received and displays it on the navigation system, specifically by providing voice guidance and displaying a map.

[1413] Output: The user starts traveling according to the new alternative route.

[1414] Step 9:

[1415] Pricing optimization

[1416] Input: The server provides congestion forecast data to the pricing system.

[1417] Processing: Road pricing systems dynamically adjust toll rates based on congestion forecasts.

[1418] Output: Pricing is optimized and new prices are applied to users.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] [Fourth embodiment]

[1423] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1424] 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.

[1425] 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).

[1426] 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.

[1427] 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.

[1428] 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).

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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."

[1436] The embodiments of the present invention will be specifically described below.

[1437] User Data Acquisition

[1438] Initiating a Data Collection Request

[1439] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period, for example, a period such as Golden Week.

[1440] Start of data collection

[1441] The server starts collecting data based on the specified long-term vacation period and user information, which includes movement data for thousands of users.

[1442] Data Acquisition

[1443] The server retrieves each user's travel data from the database, for example, by querying the travel data for the relevant period using the user ID, and adds the obtained data to the list.

[1444] Data analysis

[1445] Data analysis begins

[1446] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[1447] Individual data analysis

[1448] The server extracts congestion patterns from each user's data, analyzing each data point to identify the times and locations where congestion occurs, and then combines the results into an overall pattern.

[1449] Congestion pattern aggregation

[1450] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information, for example, analyzing the congestion situation around Umihotaru.

[1451] Congestion forecast

[1452] Selecting a Prediction Model

[1453] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[1454] Implementing congestion predictions

[1455] The server inputs the collected congestion patterns and the specified period into the model and makes a prediction, for example, predicting congestion during next year's Golden Week period.

[1456] Saving the results

[1457] The server stores the predicted congestion results in a database and converts them into a format for presentation to the user.

[1458] Alternative route suggestions

[1459] Alternative Route Generation

[1460] The server generates alternative routes based on the congestion forecast, which involves calculating routes that avoid times and locations where congestion is predicted.

[1461] Alternate Route Format

[1462] The server formats the generated alternative routes in a way that is easy for the user to understand.

[1463] Providing alternative routes

[1464] The server sends alternative routes to the terminal and makes them available to the user.

[1465] User Notifications

[1466] The device will then notify the user of the alternative route and encourage them to use it, for example, suggesting a route via the coastal road to avoid the traffic jam at Umihotaru.

[1467] Providing information on fluctuating prices

[1468] Data format conversion

[1469] The server formats the congestion forecast results into a format usable by the pricing system.

[1470] Information transmission

[1471] The server sends the formatted data to the pricing system.

[1472] Pricing optimization

[1473] The pricing system uses the transmitted data to optimize highway tolls, for example by raising tolls during peak hours around Umihotaru to ease congestion.

[1474] Specific examples

[1475] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[1476] The server acquires user movement data during the Golden Week period from the database.

[1477] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[1478] The server predicts the congestion during Golden Week next year and saves the results.

[1479] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[1480] The device notifies the user of alternative routes and encourages them to use them.

[1481] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[1482] The processing flow will be explained below.

[1483] Step 1:

[1484] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[1485] Step 2:

[1486] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[1487] Step 3:

[1488] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[1489] Step 4:

[1490] The server analyzes the collected movement data. First, it analyzes each user's data points to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[1491] Step 5:

[1492] The server aggregates the data collected from all users and identifies common congestion patterns, such as the concentration of users in specific service areas or tourist spots (e.g., Umihotaru), and plots the congestion situation on a map.

[1493] Step 6:

[1494] The server selects an appropriate prediction model and sets a model to predict future congestion conditions using the optimal algorithm based on past data.

[1495] Step 7:

[1496] The server inputs the analyzed congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[1497] Step 8:

[1498] The server stores the prediction results in a database and converts them into a format that can be provided to the user for future reference.

[1499] Step 9:

[1500] The server generates alternative routes based on the congestion prediction results, calculates multiple routes to avoid times and locations where congestion is predicted, and selects the optimal alternative route.

[1501] Step 10:

[1502] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[1503] Step 11:

[1504] The server sends the formatted alternative route information to the terminal, allowing the user to check the alternative route in real time.

[1505] Step 12:

[1506] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[1507] Step 13:

[1508] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[1509] Step 14:

[1510] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[1511] Example 1

[1512] 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."

[1513] In recent years, traffic congestion during long holiday periods has become a social problem. This problem not only reduces travel efficiency and road utilization efficiency, but also has a negative impact on the environment due to increased exhaust gas emissions. To solve this problem, it is necessary to predict congestion using past data and provide appropriate alternative routes based on that prediction. However, conventional systems have had problems in that they do not sufficiently provide users with efficient data collection, highly accurate congestion predictions, or the optimization of alternative routes based on those predictions.

[1514] 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.

[1515] In this invention, the server includes: means for a user to send a request for collecting vehicle movement data for a long vacation period from a terminal; means for the server to start collecting movement data for a specified period based on the received request; means for the server to acquire movement data for each user from a database; means for the server to analyze the collected data to extract congestion patterns and perform individual data analysis; means for the server to aggregate congestion patterns and generate comprehensive congestion information; means for the server to select an appropriate prediction model and predict congestion based on past data; means for the server to store the predicted congestion results in a database and format them for provision to the user; means for the server to generate alternative routes based on the congestion prediction results and provide them to the terminal; means for the terminal to notify the user of the received alternative route; and means for the server to format the congestion prediction results in a format usable by a pricing system and transmit them. This allows users to predict congestion in advance and select appropriate alternative routes, thereby achieving efficient transportation operations and reducing time loss and environmental impact due to congestion.

[1516] A "user" is an entity that uses a terminal to access the system and make a request to collect movement data for a specified period of time.

[1517] A "terminal" is a device used by a user to send data collection requests to the system and receive notifications from the server.

[1518] A "server" is a computer system that performs multiple functions such as data collection, analysis, prediction, alternate route generation, and data format conversion.

[1519] "Movement data" refers to data including information such as vehicle location information, travel route, and speed, and indicates the user's movement history.

[1520] "Database" means a system or structured collection of data used to store movement data for collection and analysis.

[1521] A "congestion pattern" is a pattern of data that indicates the traffic congestion that occurs during a specific period and at a specific location.

[1522] A "predictive model" is a mathematical or statistical algorithm used to predict future congestion conditions based on past data.

[1523] An "alternate route" is a suggested alternative travel route to avoid congestion and indicates the optimal route.

[1524] A "pricing system" is a system used to optimize road usage fees based on congestion forecast results.

[1525] The present invention is a system that collects and analyzes vehicle movement data during long holiday periods, predicts congestion, and provides alternative routes. This system consists of three main components: a server, a terminal, and a user. Specific embodiments of the system are described below.

[1526] First, the device used by the user is typically a mobile device such as a smartphone or tablet. The user uses this device to send a request to the server to collect vehicle movement data during a specific period. The specified period is, for example, a long holiday period such as "Golden Week." This request may be generated using a prompt in text format. For example, a prompt such as "Please collect movement data during Golden Week in 2024" may be used.

[1527] When the server receives this request, it starts the data collection process. The server retrieves each user's travel data from the database. This involves database operations such as SQL queries to retrieve travel data for the specified period. The retrieved data includes information such as the vehicle's location, travel route, and speed.

[1528] The collected data is analyzed by a server. The server performs individual data analysis to extract congestion patterns. It identifies the time periods and locations where congestion occurred from each user's movement data and integrates the results into an overall pattern. This analysis forms the basis for understanding the congestion situation at a specific location and time.

[1529] Next, the server selects an appropriate prediction model and uses the generative AI model to predict future congestion conditions. Past congestion patterns and usage data are used as input. For example, a prompt might be entered such as, "Please predict congestion conditions during Golden Week in 2025." The prediction model selects the optimal algorithm based on past data and predicts future congestion conditions with high accuracy.

[1530] The prediction results are stored in a database in formats such as JSON or CSV, and the server uses these to generate alternative routes. Routes that avoid times and locations where congestion is predicted are calculated and provided to the user. For example, it suggests a route that avoids Umihotaru and takes the bayside road between 10:00 and 14:00. The suggestions are formatted with map information and detailed explanations and provided in a way that is easy for users to understand.

[1531] The generated alternative route is then sent back to the device via the server. The device then notifies the user of the received alternative route information and provides appropriate guidance. Notifications are sent via text messages or pop-up notifications, such as "Please use the following alternative route to avoid traffic jams at Umihotaru."

[1532] The server then sends the congestion prediction results to a pricing system. The server then formats the data into a format that the pricing system can use and sends it to the pricing system. The system then optimizes fares based on the data sent and sets fares to alleviate congestion. For example, it can reduce congestion by raising fares during peak hours around Umihotaru.

[1533] The above is a specific embodiment of the present invention. This system allows users to predict traffic congestion in advance and select the optimal alternative route. This is expected to realize efficient traffic management and reduce the burden on the environment.

[1534] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1535] Step 1: Initiate a data collection request

[1536] The user sends a request to collect vehicle movement data during a specified long holiday period from the terminal to the server. The input to this process is a prompt statement in which the user specifies the period (e.g., "Please collect movement data during the Golden Week period in 2024"). The output is that this request is transmitted to the server. When the terminal sends the prompt statement, the server receives this request and the data collection process begins.

[1537] Step 2: Start collecting data

[1538] The server starts collecting mobile data for a specified period based on the received request. The input to this process is a data collection request from the terminal, and the output is an instruction to start data collection. The server establishes a database connection and prepares to collect mobile data.

[1539] Step 3: Get the data

[1540] The server retrieves each user's movement data from the database. The input to this process is a list of user IDs to be collected and a specified period, and the output is the retrieved movement data. The server executes SQL queries to collect data, issuing commands such as "Retrieve movement data for user ID 12345 during the Golden Week period."

[1541] Step 4: Begin data analysis

[1542] The server launches a process to analyze the collected movement data. The input of this process is the collected raw data, and the output is a notification that the analysis task has been configured. The server schedules the data analysis tasks and configures them to run in parallel.

[1543] Step 5: Individual data analysis

[1544] The server analyzes congestion patterns from each user's movement data individually. The input to this process is a dataset for each individual user, and the output is information about the time and location of congestion. The server analyzes each data point and obtains a result such as "Congestion occurred on the Chuo Expressway from 10:00 to 14:00 on May 3rd."

[1545] Step 6: Aggregating congestion patterns

[1546] The server aggregates congestion patterns obtained from the data of all users. The input to this process is the individual analysis results of each user, and the output is comprehensive congestion information. The server integrates the data of multiple users and identifies a pattern such as "during Golden Week, congestion will occur around Umihotaru from 10:00 to 14:00."

[1547] Step 7: Select a predictive model

[1548] The server selects an appropriate prediction model and prepares it for crowd prediction. The inputs to this process are past data and analysis results, and the output is the selected prediction model. The server uses the generative AI model to input a prompt such as "Please predict the crowd situation during Golden Week in 2025."

[1549] Step 8: Run congestion forecast

[1550] The server inputs the aggregated congestion patterns and data for the specified period into a prediction model to make a congestion forecast. The inputs to this process are the prediction model and the original data, and the output is the future congestion forecast results. The server runs the prediction model and makes a specific forecast of "Golden Week congestion in 2025."

[1551] Step 9: Save the results

[1552] The server saves the prediction results in a database and formats them for presentation to users. The input to this process is the prediction results, and the output is saved in the database as formatted data. In this saving process, the data is converted into JSON format, CSV format, etc.

[1553] Step 10: Generate Alternate Routes

[1554] The server generates an alternative route based on the congestion forecast results. The input to this process is the congestion forecast results, and the output is the generated alternative route. It is calculated as follows: "Avoid Umihotaru and take the Bayshore Route between 10:00 and 14:00."

[1555] Step 11: Formatting Alternate Routes

[1556] The server formats the generated alternative routes in a way that is easy for the user to understand. The input to this process is the generated alternative route, and the output is formatted alternative route information, such as "Use this route during this time period" with map information and text descriptions.

[1557] Step 12: Provide an alternative route

[1558] The server sends the alternative route to the terminal and provides it to the user. The input of this process is formatted alternative route information, and the output is a transmission notification to the terminal. The server records logs and monitors the transmission status.

[1559] Step 13: User Notification

[1560] The terminal notifies the user of the received alternative route information. The input of this process is the alternative route information sent from the server, and the output is a notification to the user. For example, a pop-up notification may be displayed saying, "To avoid the traffic jam at Umihotaru, please use the following alternative route."

[1561] Step 14: Data Format Conversion

[1562] The server formats the congestion forecast results into a format that can be used by the pricing system. The input to this process is the forecast results, and the output is formatted data. For example, the congestion forecast results are converted into CSV format.

[1563] Step 15: Send information

[1564] The server sends the formatted data to the pricing system. The input to this process is the formatted data and the output is a submission notification. The server confirms and logs the submission of the data to the pricing system.

[1565] Step 16: Optimize your pricing

[1566] The pricing system adjusts the prices based on the data sent. The input to this process is data from the server, and the output is optimized pricing. For example, increasing the price during peak hours around Umihotaru reduces congestion.

[1567] (Application example 1)

[1568] 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."

[1569] Congestion during long holiday periods can be a significant source of stress for many drivers. The resulting inefficiencies and delays during peak hours are also a major challenge. Furthermore, the lack of appropriate alternative route selection and optimization of road tolls is a problem. Therefore, a system that can predict future congestion, provide appropriate alternative routes, notify users, and dynamically adjust toll fees is needed.

[1570] 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.

[1571] In this invention, the server includes means for collecting vehicle movement data during long holiday periods, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for generating alternative routes based on the predicted congestion, means for displaying the alternative routes, means for notifying users of the alternative routes, and means for providing data to a system that varies road tolls based on the predicted congestion, thereby encouraging users to travel efficiently and avoiding congestion during peak hours.

[1572] "Long holiday periods" refer to periods when many people are on vacation at the same time, such as long weekends or holiday seasons, which tend to result in significantly higher traffic volumes than usual.

[1573] "Movement data" refers to information about a vehicle's movement, such as its location, time, and speed. This data is collected from GPS and various sensors.

[1574] "Congestion patterns" refers to data that indicates traffic congestion conditions in a particular time period or area, including traffic volume, vehicle speed, and dwell time.

[1575] "Predicted congestion" is information that indicates traffic congestion conditions that are likely to occur in the future based on past travel data and congestion patterns.

[1576] "Alternate Route" refers to a proposed alternative route to reach a destination to avoid predicted congestion.

[1577] "User notification" is the act of conveying information from the system to the user. This notification may be in the form of voice, text, display, etc.

[1578] A "variable toll system" is a system that dynamically adjusts road usage fees based on traffic congestion and forecast data, making it possible to curb usage during peak times and alleviate congestion.

[1579] The system for implementing this invention includes a series of means for collecting, analyzing, predicting, and notifying vehicle movement data during long vacation periods. The system of this invention is realized by using an on-board computer, a GPS module, and various sensors as hardware, and software such as a database system and a machine learning model.

[1580] First, the server will begin collecting movement data during the long vacation period. This data is collected using the GPS module and various sensors installed in the autonomous vehicle, and data from the user is sent to the server.

[1581] The collected movement data is then analyzed by the server. This analysis involves managing the data using a database system (e.g., MySQL, MongoDB) and extracting congestion patterns using analytical algorithms (e.g., k-means clustering). Detailed movement data for each user is analyzed to identify specific times and locations of congestion.

[1582] Next, based on the analysis results, the server performs time series prediction using a machine learning model (e.g., TensorFlow, PyTorch) to predict future congestion. This prediction uses collected past data and congestion patterns as inputs to predict future congestion conditions for a specific period.

[1583] An alternative route is then generated based on this prediction. To generate the alternative route, a map information API (e.g., Google Maps API) is used to calculate the optimal route, taking into account current traffic conditions and predicted road congestion. The generated alternative route is formatted in a user-friendly format and sent to the autonomous vehicle's on-board display or smartphone.

[1584] Furthermore, the server notifies the user and presents the generated alternative route. This notification can be provided in the form of voice guidance or text message, helping the user to smoothly use the alternative route.

[1585] Finally, the predicted congestion information is also provided to the toll system, which dynamically optimizes highway tolls and takes measures to alleviate congestion during peak hours. The server converts the congestion prediction results into a format that the toll system can use and provides the appropriate information.

[1586] As a specific example, the system can predict congestion around the Tokyo Bay Aqua-Line (Umihotaru) during Golden Week, and based on the results, generate an alternative route via the Bayshore Route and notify the user. This can reduce stress during long holiday periods such as the New Year holidays and improve travel efficiency.

[1587] The following is an example of a prompt sentence:

[1588] "Design an algorithm to predict traffic congestion around the Tokyo Bay Aqua-Line (Umihotaru) during the Golden Week period and generate alternative routes to avoid the congestion."

[1589] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1590] Step 1:

[1591] The terminal specifies a long holiday period (e.g., Golden Week) and sends a movement data collection request to the server. The input includes data specifying the start and end dates of the period. After receiving this request, the server prepares to collect movement data of multiple users during the specified period.

[1592] Step 2:

[1593] The server stores the movement data collected from multiple users in a database system. It receives data from the GPS module and various sensors and stores it in the database. The input data are data points such as user location information, travel time, and travel speed. As an output, each user's movement data is stored in the database.

[1594] Step 3:

[1595] The server analyzes the stored travel data and extracts congestion patterns. This analysis uses a clustering algorithm (e.g., k-means clustering) to identify congestion levels at specific times and locations. The input is the travel data in the database, and the output is the analysis results that indicate busy times and locations.

[1596] Step 4:

[1597] The server uses a generative AI model (e.g., TensorFlow, PyTorch) to predict future congestion based on the analyzed congestion patterns. This prediction uses a time series analysis model to calculate future trends from past data. The input is the congestion pattern and past movement data, and the output is the predicted congestion time period and location.

[1598] Step 5:

[1599] The server generates an alternative route based on the predicted congestion information. It uses a map information API (e.g., Google Maps API) to calculate the optimal route that avoids congestion. The current location, destination, and predicted congestion information are used as input. The output is generated as an alternative route that can be used by the user.

[1600] Step 6:

[1601] The server sends the generated alternative route to the terminal, and the terminal notifies the user. This notification is provided as a voice guide or a text message. The input is the alternative route information, and the output is a notification to the user. Specifically, the alternative route information is presented using a voice output device or a display.

[1602] Step 7:

[1603] The server provides predicted congestion information to a toll system, which dynamically optimizes road usage tolls and alleviates congestion. The input is predicted congestion information, and the output is data converted into a format that can be used by the toll system. The toll system uses this data to adjust tolls during peak hours.

[1604] 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.

[1605] The embodiments of the present invention will be specifically described below.

[1606] User Data Acquisition

[1607] Initiating a Data Collection Request

[1608] The terminal transmits a request to the server to collect vehicle movement data for a long holiday period, for example, a user inputs an instruction specifying a period such as Golden Week.

[1609] Start of data collection

[1610] The server receives the user's request and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and the specified period.

[1611] Data Acquisition

[1612] The server queries the database for each user's travel data, for example, "what kind of travel did user ID 12345 make during the Golden Week period?", and obtains the corresponding travel history.

[1613] Data analysis

[1614] Data analysis begins

[1615] The server analyzes the collected user movement data, which is the first step in extracting congestion patterns.

[1616] Individual data analysis

[1617] The server extracts congestion patterns from each user's data. It analyzes each data point to identify the time periods and locations where congestion occurred. Based on this information, it extracts congestion patterns from each user's movement data.

[1618] Congestion pattern aggregation

[1619] The server aggregates congestion patterns obtained from all user data and generates comprehensive congestion information. For example, it analyzes the congestion situation around Umihotaru.

[1620] Congestion forecast

[1621] Selecting a Prediction Model

[1622] The server selects the appropriate predictive model and determines the optimal algorithm based on historical data.

[1623] Implementing congestion predictions

[1624] The server inputs the collected congestion patterns and the specified period into the model to predict future congestion conditions, for example, during next year's Golden Week period.

[1625] Saving the results

[1626] The server stores the prediction results in a database and converts them into a format that can be presented to the user for future reference.

[1627] Alternative route suggestions

[1628] Alternative Route Generation

[1629] The server generates alternative routes based on the congestion prediction results. To avoid times and locations where congestion is predicted, multiple routes are calculated and the optimal alternative route is selected.

[1630] Alternate Route Format

[1631] The server formats the generated alternative routes in a way that is easy for the user to understand, including how to display the route on a map and adding audio directions.

[1632] Providing alternative routes

[1633] The server transmits the alternative route information to the terminal, allowing the user to check the alternative route in real time.

[1634] User Notifications

[1635] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[1636] Providing information on fluctuating prices

[1637] Data format conversion

[1638] The server formats the congestion forecast results into a format usable by the pricing system.

[1639] Information transmission

[1640] The server sends the formatted data to the pricing system.

[1641] Pricing optimization

[1642] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[1643] Implementing the Emotion Engine

[1644] Emotion Engine Data Collection

[1645] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[1646] Emotional Data Analysis

[1647] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.).

[1648] Emotional Data Feedback

[1649] Based on the analysis results, the server provides route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[1650] Specific examples

[1651] The terminal transmits a request for collecting movement data for a long vacation period to the server.

[1652] The server acquires user movement data during the Golden Week period from the database.

[1653] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[1654] The server predicts the congestion during Golden Week next year and saves the results.

[1655] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[1656] The device notifies the user of alternative routes and encourages them to use them.

[1657] The server sends congestion forecast data to a pricing system, which then adjusts the fees during peak hours.

[1658] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[1659] The processing flow will be explained below.

[1660] Step 1:

[1661] The terminal transmits a request to the server to collect vehicle movement data during a long holiday period. For example, the user inputs a request to acquire data for the Golden Week period.

[1662] Step 2:

[1663] The server receives a request from the user and starts collecting data according to the specified long-term vacation period. Specifically, it prepares to access the database based on the user ID and period.

[1664] Step 3:

[1665] The server queries the database for each user's travel data, for example, retrieving all records of travels made by user ID "12345" during the Golden Week period.

[1666] Step 4:

[1667] The server analyzes the collected movement data, specifically analyzing each user's data points to identify the time periods and locations where congestion occurred.

[1668] Step 5:

[1669] The server extracts congestion patterns from each user's movement data and aggregates them comprehensively. For example, it identifies peak times and locations of traffic flow around Umihotaru.

[1670] Step 6:

[1671] The server selects an appropriate prediction model and predicts future congestion based on past data. Specifically, it predicts next year's congestion around Umihotaru based on time-series data.

[1672] Step 7:

[1673] The server stores the prediction results in a database and converts them into a format for providing them to users, for example, into a data format for visualizing the prediction results on a map.

[1674] Step 8:

[1675] The server generates alternative routes based on the congestion prediction results, calculates multiple routes that avoid times and locations where congestion is predicted, and selects the optimal route.

[1676] Step 9:

[1677] The server formats the generated alternative routes in a way that is easy for the user to understand, for example by displaying the route on a map and adding audio guidance.

[1678] Step 10:

[1679] The server sends the formatted alternative route information to the terminal, allowing the user to view the alternative route in real time.

[1680] Step 11:

[1681] The device notifies the user of the received alternative route and encourages the user to use it, for example, by using a pop-up notification or voice guidance to suggest the alternative route to the user.

[1682] Step 12:

[1683] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[1684] Step 13:

[1685] The server analyzes the collected emotional data and determines the user's current emotional state (e.g., stress, fatigue, irritation, etc.). For example, if the user is feeling impatient, the server may simplify the display.

[1686] Step 14:

[1687] Based on the analysis results, the server provides alternative route guidance according to the user's emotional state. For example, if the user is feeling stressed, it will suggest a more relaxing route or a break.

[1688] Step 15:

[1689] The server formats the congestion forecast results into a format that can be used by the pricing system and sends it to the pricing system, for example, suggesting that fares be increased during certain times of the day.

[1690] Step 16:

[1691] The toll setting system dynamically adjusts highway tolls based on congestion forecast data sent from the server, thereby implementing a toll strategy to alleviate congestion during specific times of day.

[1692] Example 2

[1693] 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."

[1694] Conventional vehicle movement data collection and congestion prediction systems have difficulty collecting real-time data and optimizing driving routes based on users' emotional states. Furthermore, dynamic adjustment of pricing based on congestion predictions has not been sufficiently implemented, preventing effective congestion relief measures. This often leads to excessive road congestion during certain times of the day, increasing user stress and frustration.

[1695] 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 a user to input a request to collect vehicle movement data for a long vacation period; means for a terminal to transmit the user's request to the server; means for the server to acquire movement data from a database according to the specified long vacation period; means for the server to analyze the acquired movement data and extract congestion patterns; means for the server to predict future congestion conditions based on the extracted congestion patterns; means for the server to generate alternative routes to avoid the predicted congestion; means for the terminal to notify the user of the generated alternative routes; means for the server to transmit congestion prediction results to a pricing system and provide data for dynamically varying road tolls; means for the terminal to monitor the user's facial expressions and voice using cameras and sensors in the vehicle and collect emotional data; and means for the server to analyze the collected emotional data and provide route guidance according to the user's emotional state. This enables effective congestion mitigation through real-time data collection and analysis, route guidance based on the user's emotional state, and dynamic toll adjustment.

[1696] "Long holiday period" refers to a specific long holiday period, including, for example, Golden Week and the New Year holidays.

[1697] "Vehicle movement data" refers to data including information such as vehicle location, travel route, and time of day.

[1698] "User" refers to any individual or legal entity that uses the System.

[1699] "Terminal" refers to a device operated by a user, and includes, for example, a smartphone, a tablet, an in-vehicle terminal, and the like.

[1700] "Server" refers to a central management device that processes, analyzes, stores, etc. data.

[1701] "Database" refers to a system for storing user movement data and analysis results.

[1702] "Congestion patterns" refers to information that indicates the tendency for vehicle concentration and congestion at specific times and locations.

[1703] A "predictive model" refers to a computational model that uses past data and algorithms to predict future congestion conditions.

[1704] "Alternate route" refers to a different travel route than usual to avoid congestion.

[1705] "Price setting system" means a system for managing and dynamically changing road usage fees.

[1706] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, voice, gestures, etc.

[1707] "Real-time" refers to the immediate processing of situations and data occurring at the moment.

[1708] A "data collection request" refers to a request issued by a user via a terminal to a server instructing the server to collect data.

[1709] "Analysis" refers to the process of examining collected data and extracting meaningful information.

[1710] "Notification" refers to sending information from the system to a user terminal and displaying it.

[1711] The system for implementing this invention includes the collection and analysis of vehicle movement data during long holidays, congestion prediction, provision of alternative routes, provision of data to a fare setting system, and implementation of an emotion engine. This system is realized through the interaction of three parties: a server, a terminal, and a user.

[1712] User Data Collection

[1713] The user operates the application on the terminal and inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week). The terminal formats this request in JSON format and sends it to the server using an HTTP request. The server retrieves vehicle movement data from the database according to the specified long holiday period.

[1714] Data analysis

[1715] The server analyzes the acquired travel data and extracts congestion patterns. Specifically, it performs data cleaning to remove incomplete data and outliers. It then clusters travel times and locations to identify the locations and times when congestion occurs.

[1716] Congestion forecast

[1717] The server predicts future congestion situations based on the extracted congestion patterns using past data and a prediction model (e.g., an LSTM model). The prediction results are stored in a database and converted into an appropriate format for presentation to users.

[1718] Providing alternative routes

[1719] The server generates an alternative route to avoid the predicted congestion. Specifically, it searches for the optimal route using Google Maps API or similar and evaluates multiple routes. The generated alternative route information is formatted appropriately and sent to the device. The device then notifies the user of this information and provides guidance using voice guidance or other means.

[1720] Dynamic Pricing

[1721] The server provides data based on the congestion forecast results to a pricing system, which then dynamically adjusts road tolls based on this data, thereby implementing pricing strategies to alleviate congestion during specific times of day.

[1722] Implementing the Emotion Engine

[1723] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data. The server analyzes this emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritation, etc.). Based on the analysis results, route guidance is provided that matches the user's emotional state. For example, if the user is feeling stressed, the server will suggest more relaxing routes and rest spots.

[1724] Specific examples

[1725] Here is an example of this system:

[1726] A user inputs a request for collecting movement data for a long vacation period into a terminal, and the terminal transmits the request to a server.

[1727] The server acquires and collects user movement data during the Golden Week period from the database.

[1728] The server analyzes the collected data to extract and aggregate congestion patterns around Umihotaru.

[1729] The server predicts the congestion during Golden Week next year and saves the results.

[1730] The server generates an alternative route to avoid congestion and sends it to the device, specifically suggesting a route via the Bayshore Route.

[1731] The device will notify the user of alternative routes and provide voice guidance.

[1732] The server transmits the congestion forecast data to a pricing system, which then adjusts the fees during peak hours accordingly.

[1733] The device monitors the user's facial expressions and voice, and if the user is feeling stressed, the server suggests a relaxing route.

[1734] Prompt Sentence Examples

[1735] Below are some example prompts to input to a generative AI model:

[1736] 1. "We would like to collect travel data during Golden Week, analyze congestion patterns, and predict congestion for the following year. Please explain the system that will suggest alternative routes to avoid congestion and send the optimal data to the pricing system."

[1737] 2. "Please explain the procedure for a system that collects and analyzes travel data from users during long vacation periods to predict future congestion. Also, please explain how to suggest a relaxing route for users when they feel stressed."

[1738] The above is an embodiment of the present invention.

[1739] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1740] Step 1: Initiate a data collection request

[1741] A user inputs a request to collect vehicle movement data for a long holiday period (e.g., Golden Week) using an application on a terminal. The input data includes a specified date range for the holiday period.

[1742] The terminal formats the user's request in JSON format and sends it to the server using an HTTP request.

[1743] Input: Date range of long-term vacation period, User ID

[1744] Output: Data collection request sent to the server

[1745] Step 2: Prepare for data collection

[1746] The server receives the data collection request from the device and prepares access to the database based on the specified long-term vacation period and user ID, which includes establishing a database connection and generating the necessary SQL queries.

[1747] Input: User ID, specified long-term vacation period

[1748] Output: Database connected and ready to query

[1749] Step 3: Data Acquisition

[1750] The server runs an SQL query to retrieve travel data for a specified period from the database, for example, filtering the data based on dates within a certain range.

[1751] Input: SQL query, database connection

[1752] Output: Acquired vehicle movement data

[1753] Step 4: Data Cleaning

[1754] The server cleans the acquired vehicle movement data to remove incomplete data and outliers, a process that is crucial for obtaining reliable analysis results.

[1755] Input: Captured vehicle movement data

[1756] Output: Cleaned movement data

[1757] Step 5: Extracting congestion patterns

[1758] The server uses the cleaned travel data to extract congestion patterns. Specifically, it performs data clustering and analysis by travel time period to identify times and locations where congestion is likely to occur.

[1759] Input: Cleaned movement data

[1760] Output: Congestion pattern

[1761] Step 6: Prepare for congestion forecasts

[1762] The server analyzes past data based on congestion patterns and selects a congestion prediction model (e.g., LSTM model), while also adjusting the model parameters.

[1763] Input: Congestion Pattern

[1764] Output: Selected predictive model

[1765] Step 7: Run congestion forecast

[1766] The server inputs the congestion pattern and an arbitrary future period into the selected prediction model and simulates future congestion.

[1767] Input: Congestion pattern, future period

[1768] Output: Congestion prediction results

[1769] Step 8: Saving and formatting the results

[1770] The server stores the congestion prediction results in a database and converts them into a format (e.g., JSON format) for providing to users.

[1771] Input: Congestion forecast result

[1772] Output: Formatted prediction results

[1773] Step 9: Alternate Route Generation

[1774] The server calculates alternative routes based on the congestion forecast results, and uses Google Maps APIs to select the optimal route to avoid congestion.

[1775] Input: Congestion forecast result

[1776] Output: Multiple alternative routes

[1777] Step 10: Formatting Alternate Routes

[1778] The server converts the generated alternative routes into a format that is easy for the user to understand (e.g., JSON or map data format).

[1779] Input: Multiple alternative routes

[1780] Output: Formatted alternate routes

[1781] Step 11: Notification of Alternate Routes

[1782] The terminal notifies the user of the alternative route sent from the server, for example, by using a notification pop-up or audio guidance.

[1783] Input: Formatted alternate route

[1784] Output: User notification

[1785] Step 12: Provide data to the pricing system

[1786] The server formats the congestion prediction results into a format that can be used by the pricing system (e.g., CSV format) and sends them to the pricing system using an API.

[1787] Input: Congestion forecast result

[1788] Output: Data sent to the pricing system

[1789] Step 13: Implement pricing

[1790] The pricing system dynamically changes road tolls based on data sent from a server, aiming to reduce congestion during certain times of the day.

[1791] Input: Data to send to the pricing system

[1792] Output: Dynamically changed pricing

[1793] Step 14: Collect emotion data

[1794] The device uses cameras and sensors inside the vehicle to monitor the user's facial expressions and tone of voice in real time and collect emotional data.

[1795] Input: Camera and sensor information

[1796] Output: Collected emotion data

[1797] Step 15: Analyze the emotion data

[1798] The server analyzes the collected emotional data to determine the user's current emotional state (e.g., stress, fatigue, irritability, etc.).

[1799] Input: Collected emotion data

[1800] Output: User's emotional state

[1801] Step 16: Route guidance based on emotion data

[1802] Based on the analysis results, the server generates route guidance that corresponds to the user's emotional state. For example, if the user is feeling stressed, the server suggests relaxing routes and rest spots.

[1803] Input: User's emotional state

[1804] Output: Route guidance based on emotional state

[1805] (Application example 2)

[1806] 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."

[1807] Road congestion during long holiday periods is a major source of stress for many people. Furthermore, congestion can significantly extend travel times, making time management difficult for trips and business trips. Furthermore, the stress and fatigue felt while driving during congestion can have a negative impact on traffic safety. The present invention aims to solve these problems and improve the user experience when traveling or traveling by providing a system that predicts congestion and provides optimal alternative routes based on the user's emotional state.

[1808] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting vehicle movement data during a long holiday period, means for analyzing the collected movement data to extract congestion patterns, means for predicting future congestion based on the congestion patterns, means for collecting and analyzing emotional data such as the user's facial expressions and tone of voice, means for generating an alternative route based on the predicted congestion and emotional state, means for displaying the alternative route, and means for providing data to a system that varies road tolls based on the predicted congestion. This makes it possible to predict road congestion during a long holiday period and provide an optimal alternative route based on the user's emotional state.

[1809] "Long holiday periods" are periods when many people take vacations at the same time, and when traffic volume increases.

[1810] "Movement data" refers to data including information such as the current position of the vehicle, the route traveled, the travel time, and the speed.

[1811] A "congestion pattern" is a collection of data that indicates the tendency for traffic volume to increase at specific times and locations.

[1812] "Emotion data" is data that indicates the user's emotional state, such as stress, fatigue, or irritation, obtained by analyzing the user's facial expression and tone of voice.

[1813] "Alternate route" refers to a different route to a destination that is calculated to avoid congestion or other obstacles.

[1814] A "variable fee system" is a mechanism that dynamically changes road usage fees based on traffic volume and congestion forecasts.

[1815] "User's facial expressions and tone of voice" are elements that indicate the user's psychological and emotional state and are collected using cameras and microphones installed in the vehicle.

[1816] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[1817] Hardware and Software Configuration

[1818] Hardware:

[1819] Navigation systems for autonomous vehicles

[1820] Cameras and microphones in the vehicle

[1821] software:

[1822] Server-side API (e.g. Flask / Django)

[1823] Data analysis libraries (e.g., NumPy, SciPy)

[1824] Emotion recognition API (e.g. Microsoft Azure Emotion API, Google Cloud Emotion API)

[1825] Road pricing system

[1826] System Overview

[1827] This system is primarily composed of a server and a terminal (autonomous vehicle system). The user collects vehicle movement data during a long vacation period and sends it to the server via middleware. The server analyzes the movement data to determine congestion patterns and predict future congestion. It also uses cameras and microphones inside the vehicle to collect and analyze user emotion data. Based on this data, it generates optimal alternative routes and sends them to the navigation system. It also provides congestion prediction data to the road toll setting system, enabling dynamic toll fluctuations.

[1828] Data collection and analysis

[1829] The device collects vehicle movement data in real time during the long holiday period and sends it to the server. Specifically, this data includes information such as GPS location data, movement speed, and time of day. The server analyzes this data and extracts congestion patterns. For example, it identifies patterns in which congestion frequently occurs on specific roads or during specific time periods.

[1830] Emotion data collection and analysis

[1831] The system uses cameras and microphones installed in the vehicle to collect the user's facial expressions and tone of voice. The server then uses an emotion recognition API to analyze the user's emotional state from this data. For example, it can determine in real time whether the user is feeling stressed or tired.

[1832] Generate optimal alternative routes

[1833] The server generates an optimal alternative route based on the congestion forecast data and the user's emotion data. This route not only avoids areas where congestion is predicted, but may also include routes and rest points where the user can relax. The generated alternative route is sent to the navigation system and displayed to the user.

[1834] Dynamic fluctuations in road tolls

[1835] The server provides congestion forecast data to the road pricing system, which dynamically adjusts road tolls to try to alleviate congestion at specific times and locations.

[1836] Specific examples

[1837] Suppose a user plans to travel during Golden Week. The user enters the travel period into the navigation system and begins collecting vehicle movement data. The server analyzes the collected data and predicts congestion patterns and future congestion based on past data. In addition, the server uses in-vehicle cameras and microphones to analyze the user's emotional data in real time. The server uses this data to generate an optimal alternative route and notify the user. For example, if the user is feeling stressed, the server can also suggest relaxing routes and rest points.

[1838] Prompt Sentence Examples

[1839] "I'm planning to travel during Golden Week. Can you tell me the best route to take to avoid traffic jams? Also, could you suggest some rest stops if I get stressed?"

[1840] In this way, the present invention is a system that improves the travel experience by predicting congestion during long holidays and providing optimal alternative routes based on the user's emotional state.

[1841] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1842] Step 1:

[1843] Initiating a Data Collection Request

[1844] Input: User specifies long-term vacation period and requests vehicle movement data collection.

[1845] Processing: The device receives the user's input and sends the long-term vacation period to the server. Specifically, it uses an API to send the user ID and the specified period.

[1846] Output: The server receives the data collection request and starts preparing for mobile data collection.

[1847] Step 2:

[1848] Starting Data Collection

[1849] Input: The server receives a data collection request.

[1850] Processing: The server prepares to collect movement data for the specified long holiday period and prepares to access the database.

[1851] Output: Data collection is initiated and the server starts collecting movement data from multiple users.

[1852] Step 3:

[1853] Acquiring movement data

[1854] Input: The server retrieves travel data for the long vacation period from the database.

[1855] Processing: The server executes queries to collect movement data for each user. Specifically, it uses SQL queries to obtain the movement history of each user.

[1856] Output: The server collects movement data and prepares it for analysis.

[1857] Step 4:

[1858] Collecting Emotional Data

[1859] Input: Cameras and microphones in the vehicle record the user's facial expressions and tone of voice.

[1860] Processing: The device uses the camera and microphone to collect the user's emotional data and transmit it to the server. Specifically, it captures voice and image data in real time.

[1861] Output: The server stores the received emotion data for analysis.

[1862] Step 5:

[1863] Start of data analysis

[1864] Input: Movement data and emotion data are stored on the server.

[1865] Processing: The server analyzes this data and extracts congestion patterns. It identifies congestion patterns using a data analysis library (e.g., NumPy, SciPy).

[1866] Output: The server extracts congestion patterns and generates data to input into the predictive model.

[1867] Step 6:

[1868] Running a congestion prediction model

[1869] Input: The server inputs congestion pattern data.

[1870] Processing: The server runs a predictive model using past congestion data to predict future congestion. The prediction is made using machine learning algorithms.

[1871] Output: The server generates and stores future congestion prediction results.

[1872] Step 7:

[1873] Generate alternative routes

[1874] Input: The congestion prediction results and user emotion data are input to the server.

[1875] Processing: The server uses this data to generate safe and efficient alternative routes, including selecting routes that are more relaxing for the user based on emotion data.

[1876] Output: The best alternative route is generated and sent to the navigation system.

[1877] Step 8:

[1878] Notification and guidance of alternative routes

[1879] Input: Send the server generated alternative route to the device.

[1880] Processing: The device notifies the user of the alternative route received and displays it on the navigation system, specifically by providing voice guidance and displaying a map.

[1881] Output: The user starts traveling according to the new alternative route.

[1882] Step 9:

[1883] Pricing optimization

[1884] Input: The server provides congestion forecast data to the pricing system.

[1885] Processing: Road pricing systems dynamically adjust toll rates based on congestion forecasts.

[1886] Output: Pricing is optimized and new prices are applied to users.

[1887] 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.

[1888] 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.

[1889] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1890] 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.

[1891] 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.

[1892] 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.

[1893] 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).

[1894] 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.

[1895] 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."

[1896] 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.

[1897] 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).

[1898] 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.

[1899] 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.

[1900] 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.

[1901] 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.

[1902] 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.

[1903] 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.

[1904] 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.

[1905] 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.

[1906] 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.

[1907] 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.

[1908] The following is further disclosed regarding the above embodiment.

[1909] (Claim 1)

[1910] a means for collecting vehicle movement data during the extended holiday period;

[1911] means for analyzing the collected movement data to extract congestion patterns;

[1912] means for predicting future congestion based on the congestion pattern;

[1913] means for generating an alternative route based on the predicted congestion;

[1914] means for dis...

Claims

1. a means for collecting vehicle movement data during the extended holiday period; means for analyzing the collected movement data to extract congestion patterns; means for predicting future congestion based on the congestion pattern; means for generating an alternative route based on the predicted congestion; means for displaying the alternative route; means for providing data to a system that varies road tolls based on the predicted congestion; A system including:

2. The means for collecting vehicle movement data during the long vacation period includes:

10. The system of claim 1, wherein the system collects mobility data from a plurality of users.

3. The means for generating an alternative route comprises:

10. The system of claim 1, wherein multiple routes are evaluated to avoid locations and times where congestion is predicted.

Images