System

Abstract

To provide a system capable of achieving efficient car sharing without requiring time and effort of a user.SOLUTION: Means for acquiring vehicle use result data of a user, means for acquiring external schedule data of the user, means for analyzing the vehicle use result data and the external schedule data and learning a vehicle use pattern of the user, means for predicting a vehicle rental schedule, means for proposing the predicted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule to a reservation system, and means for acquiring a rental request from a demand-side user, A system comprising: means for matching a schedule; means for sending a notification to a user and a demand-side user when a loan is made; and means for confirming a reservation and sharing detailed information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Even if a personally owned vehicle is registered with a car sharing service, there are challenges, such as the time required to register available rental times in the system and the difficulty of flexible rental settings that fit one's schedule. This problem is particularly acute among men in their 30s and 40s who often spend their weekends traveling or pursuing hobbies. Another issue is that the hassle of managing rental schedules means registered vehicles end up unused and wasted. There is a need to solve these challenges and realize efficient car sharing. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: a system including means for acquiring vehicle usage history data of a user, means for acquiring external schedule data of the user, means for analyzing the vehicle usage history data and the external schedule data and learning the user's vehicle usage patterns, means for predicting a vehicle rental schedule, means for proposing the predicted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in a reservation system, means for acquiring rental requests from demand-side users and matching them with schedules, means for sending notifications to the user and demand-side users when rental is confirmed, and means for confirming reservations and sharing detailed information. This allows users to realize efficient car sharing without any hassle.

[0006] "Vehicle usage history data" refers to information such as the past mileage, usage time, and usage location of a vehicle owned by a user.

[0007] "External schedule data" refers to schedule information acquired from an external schedule management tool such as the user's Google (registered trademark) calendar or Time Tree.

[0008] "AI model" refers to an artificial intelligence model that analyzes vehicle usage history data and external schedule data to learn and predict users' vehicle usage patterns.

[0009] "Vehicle rental schedule" refers to a schedule indicating the dates, times, and hours when a vehicle is available for rental.

[0010] "Proposed schedule" refers to the rental time plan proposed to the user based on the vehicle rental schedule predicted by the AI ​​model.

[0011] "Approved schedule" refers to the loan schedule that the user has confirmed, revised, and finally approved after the proposed schedule.

[0012] A "reservation system" refers to a system that manages rental schedules and establishes reservations between users and demand-side users.

[0013] "Demand-side user" refers to a user who wishes to rent a vehicle through a car sharing service.

[0014] "Rental Request" refers to a request by a Demand User indicating a desire to rent a vehicle at a specific date and time.

[0015] "Matching" refers to the process of comparing loan requests with approval schedules to find the optimal match.

[0016] "Notification means" refers to a mechanism for sending notifications of vehicle rental agreements and proposed schedules to users and demand-side users. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system for efficiently using privately owned vehicles for car sharing. This system uses an AI model to predict vehicle rental schedules based on vehicle usage history data and external schedule data, and proposes them to users. The following describes the overall operation flow of the system and a specific example.

[0039] Overall system overview

[0040] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these into an AI model for analysis. The AI ​​model predicts the time periods when the vehicle can be rented and proposes them to the user. The user confirms and modifies the proposed schedule, and finally approves it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[0041] Server Operation

[0042] 1. Data collection and analysis

[0043] The server retrieves the user's vehicle usage history data from the database, including information such as mileage, usage time, and usage location.

[0044] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[0045] The server inputs the collected data into an AI model to learn the user's vehicle usage patterns.

[0046] 2. Predictions and proposals

[0047] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and this predicted schedule is sent to the user's device by the server and proposed to the user.

[0048] 3. Reservation management and matching

[0049] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[0050] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[0051] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[0052] Device behavior

[0053] 1. Receiving and checking the schedule

[0054] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[0055] Users can check the proposed schedule on their devices and make corrections as necessary.

[0056] 2. Receiving Notifications

[0057] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[0058] User Actions

[0059] 1. Check and approve the schedule

[0060] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[0061] 2. Loan Management

[0062] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[0063] Specific examples

[0064] For example, if a user has travel plans for the weekend, the schedule information is registered in Google Calendar or Time Tree. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to demand users. When the demand user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand user.

[0065] In this way, this system significantly reduces the user's workload and realizes efficient car sharing.

[0066] The processing flow will be explained below.

[0067] Program processing flow

[0068] Step 1:

[0069] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[0070] Step 2:

[0071] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[0072] Step 3:

[0073] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[0074] Step 4:

[0075] The server retrieves the vehicle rental schedule predicted by the AI ​​model, which includes the dates, times, and times when the vehicle is available for rental.

[0076] Step 5:

[0077] The server then performs optimization based on the predicted schedule and generates an optimal lending schedule. It also combines lending demand data to create a schedule tailored to times of high demand.

[0078] Step 6:

[0079] The server sends the proposed rental schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[0080] Step 7:

[0081] The user checks the proposed lending schedule on the terminal and makes any necessary corrections. The user then checks the details of the schedule and approves or corrects it.

[0082] Step 8:

[0083] The server receives the schedule that the user has approved or modified, records it as the final approved schedule, and reflects it in the reservation system.

[0084] Step 9:

[0085] The server updates the confirmed available rental time in the reservation system, and reflects the available rental schedule in real time.

[0086] Step 10:

[0087] When a rental request arrives at the server from a user on the demand side, the server retrieves it and performs optimal matching, finding the best match between the request and the schedule.

[0088] Step 11:

[0089] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[0090] Step 12:

[0091] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[0092] The above are the specific steps in the processing flow of the system.

[0093] Example 1

[0094] 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."

[0095] In modern society, improving the utilization efficiency of mobility (e.g., vehicles) is an important issue. Sharing privately owned mobility can reduce the burden on the environment and increase economic efficiency. However, if schedules are created without taking into account users' mobility usage patterns and external timetable data, utilization efficiency may decrease. In addition, it is a significant effort for users to manually adjust their own schedules. Therefore, automatic prediction and matching of mobility rental schedules is required.

[0096] 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.

[0097] In this invention, the server includes means for acquiring user's mobile device usage history data, means for acquiring user's external timetable data, means for analyzing the mobile device usage history data and the external timetable data and learning the user's mobile device usage patterns, means for using a generative AI model to predict a mobile device rental schedule, means for proposing the predicted mobile device rental schedule to the user, means for receiving approval of the proposed mobile device rental schedule from the user, means for updating the approved mobile device rental schedule in a reservation system, means for acquiring rental requests from demand-side users and matching them with rental schedules, means for sending notifications to the user and demand-side users when rental is confirmed, and means for confirming reservations and sharing detailed information. This eliminates the need for users to manually adjust their schedules and enables automatic optimization of mobile device rental schedules.

[0098] "User" means an individual or legal entity that owns a vehicle and provides that vehicle to the car sharing system.

[0099] "Mobile object" refers to a means of transportation, such as a vehicle, that is owned and available for rent by a User.

[0100] "Usage history data" refers to information about how a user has used a vehicle in the past, including data such as distance traveled, time of use, and location of use.

[0101] "External Timetable Data" refers to data about a user's schedule and event information obtained through Google Calendar or other schedule management tools.

[0102] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and predict future mobility usage patterns.

[0103] "Proposal" is an operation in which the server sends the predicted rental schedule of the mobile object to the user terminal and asks the user to confirm or modify it.

[0104] "Approval" means that the user reviews and ultimately agrees to the proposed lending schedule.

[0105] "Reservation System" means a system for recording approved vehicle rental schedules and managing rental status.

[0106] A "demand user" is an individual or a corporation that wishes to use a mobile unit on a rental basis.

[0107] "Matching" refers to the process of matching the demand user's lending request with the lending schedule approved by the user to find the optimal combination.

[0108] "Notification" is a message to convey important information such as the completion of a loan or a schedule change to users and demand-side users.

[0109] "Detailed information" refers to specific details regarding the rental status and schedule, and is information shared with users and demand-side users.

[0110] An "information terminal" is a device used by a user to check the proposed lending schedule and approve or modify it, and includes a smartphone, PC, etc.

[0111] This invention is a system for efficiently sharing privately owned vehicles (e.g., cars). The system uses an AI model to predict vehicle rental schedules based on users' vehicle usage history data and external timetable data, and proposes them to users. After obtaining users' approval, the system matches the optimized schedule with users on the demand side, realizing efficient vehicle sharing.

[0112] Server Operation

[0113] 1. Data Collection

[0114] The server first retrieves the user's transportation usage history data from the database. This data consists of the vehicle's mileage, usage time, and usage location. Next, the server uses an API to collect external timetable data. This data includes the user's schedule and event information from Google Calendar and other schedule management tools.

[0115] 2. Data Analysis

[0116] The server preprocesses the collected data and inputs it into an AI model (using, for example, Tensorflow (registered trademark) or PyTorch). The AI ​​model learns the user's mobile device usage patterns and predicts the mobile device rental schedule based on this.

[0117] 3. Schedule proposal

[0118] The predicted schedule is sent from the server to the user's device, where the user can review the proposed schedule and make any necessary adjustments.

[0119] 4. Approval of forecast schedule

[0120] After the user approves the proposed schedule, it is sent to the server, which updates the reservation system with the approved schedule, reflecting available rental times in real time.

[0121] 5. Reservation management and matching

[0122] When a rental request is received from a demand user, the server performs optimal matching. The server selects the best match between the schedule and the request, and sends a notification to the user and the demand user if the rental is successful.

[0123] Device behavior

[0124] 1. Receiving and checking the schedule

[0125] The user's terminal receives and displays the mobile rental schedule sent from the server. The user can check the proposed schedule on the terminal and make corrections as necessary.

[0126] 2. Receiving Notifications

[0127] If the rental is successful, a notification is sent to the user's terminal and the reservation details are displayed.

[0128] User Actions

[0129] 1. Check and approve the schedule

[0130] The user can check the proposed schedule on the terminal and make any necessary corrections. When the user finally approves the schedule, the information is sent to the server.

[0131] 2. Loan Management

[0132] The user can receive a notification sent from the server and check the details of the confirmed reservation, which allows the user to smoothly manage the rental of the mobile object.

[0133] Specific examples

[0134] For example, if a user has a trip planned for the weekend, the schedule information is registered in Google Calendar. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time period after the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When the demand-side user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand-side user.

[0135] Prompt Sentence Examples

[0136] "If a user has scheduled this weekend in their Google Calendar, predict the available rental times based on past vehicle usage data and output the suggested schedule."

[0137] This system saves users the trouble of manually adjusting their schedules and enables efficient vehicle rental.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1: Data collection

[0140] input

[0141] User mobility usage data

[0142] External timetable data (e.g. Google Calendar)

[0143] Server Operation

[0144] The server retrieves the user's vehicle usage history data from the database, including information such as the distance traveled, the time of use, and the location of use.

[0145] The server obtains the user's external timetable data using the API of Google Calendar or other schedule management tools.

[0146] output

[0147] Acquired mobility usage data and external timetable data

[0148] Specific actions

[0149] For example, the server retrieves vehicle usage data for the past six months from "User A's" database and retrieves future schedule information from "User A's calendar" via an API.

[0150] Step 2: Data analysis

[0151] input

[0152] Acquired mobile usage data

[0153] External timetable data

[0154] Server Operation

[0155] The server preprocesses both sets of data into an input format for the AI ​​model, for example by normalizing the data and extracting features.

[0156] The processed data is input into a generative AI model (e.g., TensorFlow or PyTorch) to learn the user's mobility usage patterns.

[0157] output

[0158] Pre-trained AI model

[0159] Mobile rental schedule forecast results

[0160] Specific actions

[0161] The server preprocesses usage data and schedule data, generates input data such as "Tuesday, 9:00 AM to 12:00 PM patterns," and analyzes it using an AI model.

[0162] Step 3: Schedule proposal

[0163] input

[0164] Mobile rental schedule forecast results

[0165] Server Operation

[0166] Based on the prediction results, a lending schedule suitable for the user is created.

[0167] The server transmits this predicted schedule to the user's terminal.

[0168] Device behavior

[0169] The user's device (smartphone or PC) receives and displays the proposed schedule sent from the server.

[0170] output

[0171] Proposed Lending Schedule

[0172] Specific actions

[0173] The user's smartphone app displays "Next available rental time: Wednesday from 2:00 PM to 5:00 PM."

[0174] Step 4: Review and approve the proposed schedule

[0175] input

[0176] Proposed Lending Schedule

[0177] User Actions

[0178] The user checks the proposed schedule on the terminal and makes corrections as necessary.

[0179] Once the user approves the schedule, the information is sent to the server.

[0180] output

[0181] Revised or approved schedule

[0182] Specific actions

[0183] The user changes the time on their smartphone from "Wednesday 2pm to 5pm" to "Thursday 10am to 1pm" and approves it.

[0184] Step 5: Update your booking management

[0185] input

[0186] Approved Schedule

[0187] Server Operation

[0188] The server updates the reservation system with the approved schedule and updates the database with available rental times.

[0189] output

[0190] Updated booking information

[0191] Specific actions

[0192] The server updates the database information to record that "User A can rent a vehicle from 10:00 AM to 1:00 PM on Thursdays."

[0193] Step 6: Matching the Lending Request

[0194] input

[0195] Lending request from demand side user

[0196] Updated booking information

[0197] Server Operation

[0198] The server receives the demand user's rental request and matches it with the approved schedule.

[0199] Find the best match and schedule to accommodate your request.

[0200] output

[0201] Matching results

[0202] Specific actions

[0203] The server receives a request from user B on the demand side and checks it against the information in the reservation system.

[0204] Step 7: Sending notifications

[0205] input

[0206] Matching results

[0207] Server Operation

[0208] If a match is made, the server sends a notification to the user and the demand user. Notification services such as Firebase and Twilio are used for this process.

[0209] Device behavior

[0210] The user's terminal receives the notification and confirms that the loan has been made.

[0211] output

[0212] Notification of loan completion

[0213] Specific actions

[0214] For example, the server notifies user A and demand user B that a match has been made via Firebase Cloud Messaging, and the device displays the message "Loan confirmed."

[0215] This processing flow enables users to efficiently share vehicles and optimize operations.

[0216] (Application example 1)

[0217] 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."

[0218] To efficiently utilize privately owned vehicles for car sharing using smartphones and other devices, it is essential to predict usage schedules and operate them optimally. However, conventional systems require a great deal of time and effort to manage schedules and operate vehicles. Furthermore, as the use of autonomous vehicles continues to increase, there is a significant lack of systems to properly manage and operate them. Therefore, there is a need for a system that allows privately owned vehicles, especially autonomous vehicles, to be efficiently used for car sharing.

[0219] 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.

[0220] In this invention, the server includes means for acquiring a user's vehicle usage history data, means for acquiring the user's external schedule data, means for analyzing the vehicle usage history data and the external schedule data and learning the user's vehicle usage patterns, means for predicting a vehicle rental schedule, means for proposing the predicted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in a reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, means for confirming the reservation and sharing detailed information, means for moving an autonomous vehicle to a specified time and place based on the approved vehicle rental schedule, and means for remotely operating the autonomous vehicle via a user terminal. This allows efficient management of rental schedules for autonomous vehicles owned by individuals, enabling smooth rental and return to users.

[0221] "User's vehicle usage history data" refers to information such as the time, distance, and location when the user uses the vehicle.

[0222] "External schedule data" is data about the user's schedules and appointments obtained from the calendar or schedule management service used by the user.

[0223] The "vehicle usage pattern" indicates the vehicle usage tendencies and habits analyzed based on the user's past vehicle usage record data and external schedule data.

[0224] The "vehicle rental schedule" is a schedule indicating the dates and times and periods during which a vehicle can be rented.

[0225] A "reservation system" is a system for managing vehicle rental schedules and matching with demand-side users.

[0226] A "demand user" refers to a user who wishes to rent a vehicle.

[0227] An "autonomous vehicle" is a vehicle that can autonomously perform driving operations by itself.

[0228] "Remote control" means controlling the operation and functions of a vehicle using a device such as a smartphone without being physically near the vehicle.

[0229] This invention relates to a system for efficiently using privately owned self-driving vehicles for car sharing. Specific embodiments of this system will be described below.

[0230] System configuration

[0231] The system consists of the following main components: a server, a user terminal, a demand-side user terminal, and an autonomous vehicle.

[0232] 1. Server

[0233] The server is equipped with the following software and data processing means:

[0234] Data collection module: Uses databases and APIs (for external schedules) to obtain user vehicle usage data and external schedule data. Examples include the Google Calendar API and the Time Tree API.

[0235] Analysis and prediction module: Analyzes data using machine learning libraries such as TensorFlow and predicts vehicle rental schedules.

[0236] Reservation management module: Based on the prediction results of the AI ​​model, the module proposes rental schedules to users and updates the approved schedules in a cloud-based reservation system, which uses cloud services such as Firebase and AWS (registered trademark).

[0237] Autonomous driving collaboration module: Uses the autonomous vehicle API to remotely control and move vehicles based on approved schedules.

[0238] 2. User Device

[0239] Notification and Schedule Management: The smartphone app displays the proposed vehicle rental schedule received from the server, and the user can confirm and modify it. For example, this applies to iOS and Android apps.

[0240] Remote control: Equipped with the ability to move and remotely control the vehicle.

[0241] 3. Demand-side user terminal

[0242] Request and confirmation: The demand-side user sends a request to rent a vehicle and receives a confirmation of the rental from the server.

[0243] 4. Self-driving vehicles

[0244] Transmission of vehicle operation data: The vehicle itself transmits driving data (e.g., GPS data, usage status) to the server.

[0245] Autonomous driving and remote control: Based on instructions received from the server via API, the autonomous driving function is used to move or return the vehicle.

[0246] Data processing and calculation

[0247] Data collection: The server collects the user's vehicle usage history data and external schedule data via API, which stores past usage history and future schedules in a database.

[0248] Data analysis: TensorFlow is used to analyze collected data and learn vehicle usage patterns, which then predicts the best times and dates for when the vehicle will be available for rental.

[0249] Schedule management: The predicted rental schedule is sent to the user's device, where the user can confirm and modify it, and the final rental schedule is determined. The determined schedule is then reflected in the cloud reservation system and updated as needed.

[0250] Autonomous driving collaboration: Based on the approved rental schedule, an autonomous vehicle will travel to the designated time and location, enabling users and demand users to share vehicles smoothly.

[0251] Specific examples

[0252] If a user has travel plans for the weekend, the plan is registered in advance in the schedule management service. The server retrieves this information and analyzes it along with past usage records. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this prediction to the user, who confirms and approves it. The approved schedule is reflected in the cloud reservation system and is also made public to demand users. When the demand user sends a request, the server performs optimal matching, and ultimately notifies both the user and the demand user.

[0253] Prompt Sentence Examples

[0254] "This app analyzes your vehicle usage data and schedule to suggest the optimal car sharing schedule. What features do you need?"

[0255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0256] Step 1:

[0257] Data collection

[0258] The server retrieves the user's vehicle usage history data from the database and also retrieves external schedule data via an API. Specifically, it uses the Google Calendar API and Time Tree API to collect the user's schedule information. The input at this stage is the vehicle usage history data and external schedule data, and the output is structured data that includes these data.

[0259] Step 2:

[0260] Data analysis

[0261] The server analyzes the collected vehicle usage history data and external schedule data. Using a generative AI model such as TensorFlow, it analyzes this data and learns the user's vehicle usage patterns. The input is the structured data collected in step 1, and the output is the vehicle usage pattern obtained through the analysis and the predicted rental availability time. Specifically, it identifies usage frequency and patterns from past data and predicts the optimal future rental schedule.

[0262] Step 3:

[0263] Schedule proposal

[0264] The server generates an optimal rental schedule based on the analysis results and sends it to the user's device. The user is notified via a smartphone app. A GUI (Graphical User Interface) is displayed on the app, allowing the user to confirm and modify the schedule. The input to this step is the analysis results obtained in step 2, and the output is a proposed schedule sent to the user's device. Specifically, the user confirms the proposed schedule and modifies it as necessary.

[0265] Step 4:

[0266] Schedule Approval

[0267] The user checks the proposed schedule on the terminal, makes any necessary corrections, and then gives final approval. The user's input is the action of checking, correcting, and approving the proposed lending schedule, and the output is the approved lending schedule that is sent to the server. Specifically, when the user clicks the "Approve" button in the application, the changes are uploaded to the server in real time.

[0268] Step 5:

[0269] Schedule updates and booking management

[0270] The server updates the approved rental schedule to the cloud-based reservation system, which updates and publishes the available rental time slots in real time. The input to this step is the approved schedule sent in step 4, and the output is the updated rental schedule in the reservation system. Specifically, the system updates the database in real time to update the published schedule information.

[0271] Step 6:

[0272] Acquiring and matching lending requests

[0273] The server receives rental requests from demand users and matches the requests with the optimal rental schedule. The input to this step is the request data from the demand users, and the output is the optimal matching result. Specifically, when a request is sent, the data is imported into the server in real time, and the AI ​​model automatically matches the optimal rental time with the request.

[0274] Step 7:

[0275] Notification and confirmation

[0276] If a match is made, the server sends a notification to the user and the demand user. Details of the confirmed reservation are sent and can be viewed by both parties in real time. The input to this step is the matching result obtained in step 6, and the output is a notification and reservation details sent to the user and the demand user. Specifically, the notification function is used to send detailed information via push notification or email.

[0277] Step 8:

[0278] Remote control of autonomous vehicles

[0279] The server moves the autonomous vehicle to the specified time and location based on the approved vehicle rental schedule. This allows for smooth rental and return. The input for this step is the approved schedule data, and the output is the movement of the autonomous vehicle or the completion status of remote control. Specifically, the server sends remote control commands for the vehicle using an API, and the vehicle moves as instructed.

[0280] 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.

[0281] This invention is a system for efficiently using privately owned vehicles for car sharing, and by combining it with an emotion engine that recognizes users' emotions, it provides an optimal rental schedule. This system uses an AI model and emotion engine to analyze the user's vehicle usage history data and external schedule data, predict and adjust the vehicle rental schedule, and propose it to the user. The following describes the overall operation flow of the system and a specific example.

[0282] Overall system overview

[0283] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these data into an AI model and emotion engine for analysis. The AI ​​model predicts the time periods when the vehicle is available for rental, and the emotion engine makes adjustments based on the user's emotional state. An optimal rental schedule is proposed to the user, who can then review, approve, or modify it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[0284] Server Operation

[0285] 1. Data collection and analysis

[0286] The server retrieves the user's vehicle usage history data from the database, which includes information such as past mileage, usage time, and usage location.

[0287] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[0288] The server inputs this data into an AI model to learn the user's vehicle usage patterns.

[0289] In addition, an emotion engine is used to collect user emotion data, which is also used for analysis.

[0290] 2. Anticipation and emotion regulation

[0291] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and then the emotion engine adjusts the schedule based on the user's emotional state.

[0292] The predicted schedule is sent by the server to the user's terminal and proposed to the user.

[0293] 3. Reservation management and matching

[0294] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[0295] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[0296] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[0297] Device behavior

[0298] 1. Receiving and checking the schedule

[0299] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[0300] Users can check the proposed schedule on their devices and make corrections as necessary.

[0301] 2. Receiving Notifications

[0302] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[0303] User Actions

[0304] 1. Check and approve the schedule

[0305] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[0306] 2. Loan Management

[0307] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[0308] Specific examples

[0309] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip (for example, the user is likely to be relaxed after the trip). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who can confirm and approve it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs the optimal match and sends notifications to the user and the demand-side user.

[0310] In this way, this system significantly reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[0311] The processing flow will be explained below.

[0312] Program processing flow

[0313] Step 1:

[0314] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[0315] Step 2:

[0316] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[0317] Step 3:

[0318] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[0319] Step 4:

[0320] The server collects user emotion data using an emotion engine, which analyzes the user's emotional state (e.g., stress level, satisfaction level, etc.) obtained from a smartphone or wearable device.

[0321] Step 5:

[0322] The server retrieves the predicted vehicle rental schedule from the AI ​​model, and the emotion engine then adjusts the schedule based on the user's emotional state, optimizing the schedule to accommodate rentals at times that are least stressful for the user.

[0323] Step 6:

[0324] The server sends the adjusted proposed schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[0325] Step 7:

[0326] The user checks the proposed lending schedule on the terminal, modifies the schedule as necessary, and finally approves it. This operation is performed on the terminal.

[0327] Step 8:

[0328] The server receives the schedule that the user has approved or modified, records it as an approved schedule, and reflects this information in the reservation system.

[0329] Step 9:

[0330] The server updates the reservation system with the confirmed available rental times, reflecting the available rental schedule in real time. This information is also made public to users on the demand side.

[0331] Step 10:

[0332] When a rental request arrives at the server from a demand-side user, the server retrieves it and performs optimal matching. The server finds the best match between the request and the schedule.

[0333] Step 11:

[0334] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[0335] Step 12:

[0336] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[0337] Specific examples

[0338] For example, the server retrieves the user's vehicle usage history data (such as past mileage, usage time, and location) from a database. The server then uses an API to extract the user's schedule data from Google Calendar and Time Tree. This data is input into an AI model to learn the user's vehicle usage patterns. The emotion engine collects user emotion data from smartphones and wearable devices and adds this to the analysis.

[0339] The server uses the AI ​​model to predict a vehicle rental schedule and adjusts it based on the user's emotional state through an emotion engine. For example, the schedule may be adjusted to avoid times when the user is likely to feel stressed. The server then sends the adjusted rental schedule to the user's device and notifies them. The user can then check the schedule on their device, modify it as necessary, and approve it.

[0340] The approved schedule is received by the server and updated in the reservation system. When a rental request comes from a demand user, the server performs optimal matching, and if successful, sends a notification to both the user and the demand user to confirm the reservation. In this way, efficient car sharing that takes into account the user's emotional state is realized.

[0341] Example 2

[0342] 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."

[0343] In conventional car sharing systems, vehicle rental schedules are set without taking into account the user's emotional state, which can be inconvenient for users. Furthermore, it is difficult to provide an optimal rental schedule simply by analyzing vehicle usage history data and external schedule data. Therefore, there is a need to improve user satisfaction with vehicle usage.

[0344] 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 acquiring vehicle usage history data of the user, means for acquiring external schedule data of the user, means for analyzing the vehicle usage history data and the external schedule data using an AI model to learn the user's vehicle usage pattern, means for collecting user emotion data using an emotion engine and using the collected data for analysis, means for predicting a vehicle rental schedule and adjusting it based on the user's emotional state, means for proposing the predicted and adjusted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in the reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, and means for confirming the reservation and sharing detailed information. This makes it possible to provide an optimal vehicle rental schedule that takes the user's emotional state into consideration.

[0345] "Vehicle usage history data" is data about how a user has used a vehicle in the past, and includes information such as mileage, usage time, and usage location.

[0346] "External schedule data" is data obtained from an external schedule management system that manages the user's schedule, and includes information obtained from Google Calendar, Time Tree, etc.

[0347] An "AI model" is software that uses machine learning algorithms to analyze data and identify patterns and predictions.

[0348] An "emotion engine" is a system or software for analyzing a user's emotional state, collecting and analyzing emotional data from social media posts, biometric data, etc.

[0349] The "vehicle rental schedule" is a schedule indicating the time periods during which a vehicle can be rented, and is predicted based on the user's vehicle usage history data and external schedule data.

[0350] "Prediction" is the act of estimating future vehicle usage patterns and rental availability times based on collected data.

[0351] "Adjustment" is the process of optimizing a predicted schedule by taking into account the user's emotional state and other factors.

[0352] "Proposal" is the act of presenting a predicted and adjusted vehicle rental schedule to a user.

[0353] "Approval" is an action in which the user agrees with the proposed vehicle rental schedule, and the result is reflected in the system.

[0354] The "reservation system" is a system that manages vehicle rental reservations, updates schedules, and confirms reservations.

[0355] A "demand user" is a user who wishes to rent a vehicle for use.

[0356] "Matching" is the act of optimally matching the demand user's request with the vehicle's available rental time.

[0357] "Notifications" are messages that inform users of information such as reservations and schedule changes.

[0358] "Detailed information" indicates specific information about the reservation contents and schedule.

[0359] This invention is a system for efficiently using privately owned vehicles for car sharing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides an optimal rental schedule. The overall operation flow of this system and a specific example are shown below.

[0360] System Overview

[0361] This system acquires historical usage data for vehicles owned by users and external schedule data for the users. These data are input into a generative AI model and emotion engine for analysis. The generative AI model uses TensorFlow and PyTorch to learn the user's vehicle usage patterns and predict the time periods when the vehicle is available for rental. The emotion engine uses, for example, IBM Watson (registered trademark) emotion analysis API to collect user emotion data and use it for analysis. The resulting predicted schedule is proposed to the user, who then approves it. The approved schedule is updated in the reservation system, where it is matched with rental requests from demand users. If the rental is confirmed, the server sends a notification to the user and the demand user, and the reservation is confirmed.

[0362] Server Operation

[0363] 1. The server retrieves the user's vehicle usage history data from the database. The data indicates how the user has used the vehicle in the past, including the mileage, usage time, and location of use.

[0364] 2. The server then retrieves external schedule data, such as Google Calendar or Time Tree, through an API. The external schedule data contains the user's upcoming events.

[0365] 3. The server inputs this data into a generative AI model, which uses TensorFlow and PyTorch to learn the user's vehicle usage patterns.

[0366] 4. The server uses an emotion engine to collect and analyze the user's emotion data. The emotion engine uses, for example, IBM Watson's emotion analysis API. This allows it to analyze emotions from the user's social media posts and other biometric sensor data.

[0367] 5. The generative AI model predicts the user's vehicle rental schedule, taking into account the user's historical usage patterns and external schedule data.

[0368] 6. The emotion engine adjusts the predicted schedule based on the user's emotional state, for example, avoiding rentals during times when the user is feeling stressed.

[0369] 7. The server sends the predicted and adjusted schedule to the user's device, allowing the user to review the proposed schedule.

[0370] 8. Once approval is received from the user, the server updates this schedule into the reservation system, which reflects available rental times in real time.

[0371] 9. The server receives the rental request from the demand user and matches it with the schedule. When the optimal match is found, the rental is completed.

[0372] 10. If the rental is successful, the server sends a notification to the user and the demand user and confirms the reservation.

[0373] Device behavior

[0374] 1. The terminal receives the proposed schedule sent from the server. The user can check the proposed schedule on the terminal and modify it if necessary.

[0375] 2. If the rental is successful, the device receives a notification from the server and displays the reservation details.

[0376] User Actions

[0377] 1. The user checks the proposed schedule on the device and modifies it if necessary. When the user finally approves the schedule, the information is sent to the server.

[0378] 2. The user receives a notification sent from the server and checks the details of the confirmed reservation, enabling smooth rental management.

[0379] Examples and prompts

[0380] Specific examples

[0381] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip. Based on this information, the server uses the emotion engine to adjust the schedule predicted by the generative AI model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs optimal matching and sends notifications to the user and the demand-side user.

[0382] Prompt Sentence Examples

[0383] Create optimal rental schedules based on user vehicle usage history data and external schedule data. Also take into account emotion engine data. For example:

[0384] Usage data: mileage, usage time, and location for the past month

[0385] External schedule data: Google Calendar, TimeTree events

[0386] Emotion Engine Data: High stress before travel, relaxed after travel

[0387] As a result, suggest a post-trip loan schedule.

[0388] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[0389] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0390] Step 1:

[0391] The server retrieves the user's vehicle usage history data from the database. Input includes mileage, usage time, and usage location. By retrieving this data, basic information can be obtained to understand the user's past vehicle usage patterns. The output is the retrieved vehicle usage history data.

[0392] Step 2:

[0393] The server retrieves the user's external schedule data from Google Calendar or TimeTree through an API. The input includes the user's authentication information and the calendar service's API endpoint, allowing you to leverage the user's upcoming events. The output is the retrieved external schedule data.

[0394] Step 3:

[0395] The server inputs vehicle usage history data and external schedule data into the generative AI model. The input includes the data obtained in Step 1 and Step 2. This allows the AI ​​model to learn the user's vehicle usage patterns. As a specific example, TensorFlow or PyTorch can be used. The output is the result of analyzing the user's vehicle usage patterns.

[0396] Step 4:

[0397] The server uses an emotion engine to collect and analyze user emotion data. Inputs include social media posts and biometric sensor data. For example, IBM Watson's emotion analysis API can be used. The output is user emotion data.

[0398] Step 5:

[0399] The generative AI model predicts the user's vehicle rental schedule. The input includes the user's vehicle usage pattern obtained in step 3 and the emotion data obtained in step 4. This creates the user's vehicle rental schedule. The output is the predicted vehicle rental schedule.

[0400] Step 6:

[0401] The emotion engine adjusts the predicted schedule based on the user's emotional state. The input includes the schedule predicted in step 5 and emotion data. This creates a schedule that takes the user's emotional state into account. The output is the adjusted vehicle rental schedule.

[0402] Step 7:

[0403] The server sends the adjusted schedule to the user's terminal. The input includes the vehicle rental schedule adjusted in step 6. The terminal displays the proposed schedule. The output is the schedule proposal to the user.

[0404] Step 8:

[0405] The user reviews the proposed schedule on the terminal and modifies it if necessary. The input includes the vehicle rental schedule received in step 7, which allows the user to approve or modify the schedule. The output is the schedule approved or modified by the user.

[0406] Step 9:

[0407] The server receives approval from the user and updates this schedule to the reservation system. The input includes the approved or modified schedule from step 8. The reservation system updates the available rental slots in real time. The output is the updated reservation information.

[0408] Step 10:

[0409] The server receives the rental request from the demand user and matches it with the schedule. The input includes the demand user's request and the reservation information updated in step 9. When the best match is found, the rental is established. The output is the matching result.

[0410] Step 11:

[0411] If the rental is successful, the server sends a notification to the user and the demand user to confirm the reservation. The input includes the matching result determined in step 10. The terminal receives the notification and displays the reservation details. The output is the confirmed reservation information and notification.

[0412] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[0413] (Application example 2)

[0414] 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."

[0415] Conventional car sharing systems have a problem in that efficient matching between vehicle users and those seeking to rent a vehicle is difficult because the vehicle rental schedule is not sufficiently optimized. In addition, because the system does not take into account the user's emotional state, there is a high possibility that schedules that cause stress to the user are proposed. This may result in a decrease in satisfaction with the car sharing system.

[0416] The specific processing by the specific 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 acquiring the user's vehicle usage history data, means for acquiring the user's external schedule data, and means for acquiring the user's emotional data and adjusting the rental schedule based on the user's emotional state. This makes it possible to analyze the user's vehicle usage history data and external schedule data, predict an optimal vehicle rental schedule, and adjust the schedule according to the user's emotional state. This makes it possible to realize efficient vehicle rental and improve user satisfaction.

[0417] "User's vehicle usage history data" refers to historical information about the user's past use of their own vehicle, specifically data such as mileage, usage time, and usage location.

[0418] "User's external schedule data" refers to external schedule information that may affect the user's use of the vehicle, such as schedule and event information obtained from a calendar service.

[0419] "Emotion data" refers to information that indicates the user's internal emotional state, specifically data that has been acquired by digitizing emotions such as stress, relaxation, and happiness.

[0420] "Means for adjusting the rental schedule based on emotional state" refers to a method for optimizing the schedule based on the acquired emotional data to ensure the least stressful and comfortable vehicle rental experience for the user.

[0421] "Proposed vehicle rental schedule" refers to the predicted rental itinerary that the system presents to the user after analysis and sentiment adjustment has been performed.

[0422] "Reservation System" refers to the computer system used by Users and Demand-Side Users to manage and confirm reservations for vehicle rentals.

[0423] "Demand-side user" refers to a user who wishes to rent a vehicle through a car sharing service.

[0424] "Matching" refers to the process of optimally combining the schedule of a user who wants to rent a vehicle with the request of a demand-side user who wants to rent a vehicle.

[0425] "Means for sending notifications" refers to the method by which schedule and reservation confirmation information is sent electronically to users and demand users, typically via a smartphone or PC application.

[0426] "Means for sharing detailed information" refers to a method for providing specific information about the vehicle rental to both the user and the demand-side user after the reservation is confirmed.

[0427] System Overview

[0428] This invention is a system for food delivery services that provides optimal delivery plans that take into account delivery personnel's schedule management and emotional state. This system collects delivery personnel's past delivery performance data and external schedule data, analyzes them using an AI model and an emotion engine, and predicts and adjusts delivery schedules and proposes them to delivery personnel.

[0429] Server Operation

[0430] 1. Data collection and analysis

[0431] The server retrieves the delivery personnel's past delivery performance data from the database. This data includes past delivery times, distances, delivery destinations, etc. It also uses an API to retrieve external schedule data. This allows the server to understand what the delivery personnel have scheduled at what time.

[0432] Furthermore, an emotion engine is used to collect emotional data from delivery personnel, and the emotional data is used for analysis, for example, to detect whether the emotional state is stressed or relaxed.

[0433] 2. Anticipation and emotion regulation

[0434] The AI ​​model predicts delivery schedules based on collected data, and an emotion engine then adjusts the schedule based on the driver's emotional state. For example, if a driver is stressed, the system may increase their break time.

[0435] The predicted and adjusted schedule is sent by the server to the delivery person's terminal and proposed to the delivery person.

[0436] 3. Reservation management and matching

[0437] Once the delivery person approves the schedule, this information is sent to the server and reflected in the reservation system, which updates available delivery times in real time.

[0438] Upon receiving a delivery request from a demand user, the server performs optimal matching to find the best match between the schedule and the request.

[0439] If a match is made, the server sends a notification to the delivery person and the demand user and confirms the reservation.

[0440] Device behavior

[0441] 1. Receiving and checking the schedule

[0442] The delivery person's device (smartphone or PC) receives the proposed delivery schedule sent from the server. The delivery person can check the proposed schedule on the device and modify it as necessary.

[0443] 2. Receiving Notifications

[0444] When a match is made and a delivery is confirmed, a notification is sent to the delivery person's device, which displays the delivery details and allows them to act according to the confirmed schedule.

[0445] User Actions

[0446] 1. Check and approve the schedule

[0447] The delivery person can review the proposed schedule on their device, modify it if necessary, and finally approve the schedule, which is then sent to the server.

[0448] 2. Managing deliveries

[0449] The delivery person receives the notification sent from the server and checks the details of the confirmed delivery, which allows the delivery person to smoothly manage their delivery work.

[0450] Specific examples

[0451] For example, if a delivery person has a meeting at 9:00 AM, the system retrieves that schedule information from the API. At the same time, the emotion engine recognizes the person's current stress level (they are likely nervous before the meeting). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determine that deliveries are possible at 10:00 AM after the meeting and at 3:00 PM. This predicted and adjusted schedule is proposed to the delivery person, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is made available to demand-side users.

[0452] When a request is sent from a demand user, the server performs optimal matching and sends a notification to the delivery person and the demand user.

[0453] Example prompt sentence:

[0454] We provide schedule and sentiment data, including: Use this to predict optimal delivery schedules and adjust them based on sentiment.

[0455] Schedule data: [{'date': '2023-01-01', 'event': 'meeting', 'time': '10:00'}, {'date': '2023-01-02', 'event': 'shopping', 'time': '12:00'}]

[0456] Emotion data: ['neutral', 'stress']

[0457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0458] Step 1:

[0459] Data Collection

[0460] The server first retrieves the delivery person's past delivery performance data from the database. Here, it uses a database query to obtain information such as past delivery times, distances, and delivery destinations. It also uses an API to obtain the delivery person's external schedule data and retrieves appointment and event information from a calendar service. The inputs are the delivery person's ID and query conditions, and the output is delivery performance data and schedule data.

[0461] Step 2:

[0462] Acquiring emotion data

[0463] The server uses an emotion engine to obtain the delivery person's emotional data. Specifically, the server inputs the delivery person's recent activities and feedback into the emotion analysis API to obtain data on their emotional state (stress, relaxation, happiness, etc.). The input is the delivery person's recent activity information, and the output is emotional data.

[0464] Step 3:

[0465] Prediction by AI model

[0466] The server inputs the delivery performance data and schedule data acquired in step 1 into the AI ​​model and predicts the optimal delivery schedule. The AI ​​model learns delivery patterns from past data and predicts future available delivery times. The inputs are delivery performance data and schedule data, and the output is a predicted delivery schedule.

[0467] Step 4:

[0468] emotional regulation

[0469] The server adjusts the predicted delivery schedule in step 3 based on the emotional data acquired in step 2. The emotion engine analyzes the emotional state of the delivery person and makes adjustments such as extending the interval between deliveries if the person is under high stress. The inputs are the predicted delivery schedule and emotional data, and the output is an adjusted delivery schedule.

[0470] Step 5:

[0471] Schedule proposal

[0472] The server sends the adjusted delivery schedule from step 4 to the delivery person's terminal and proposes it. The terminal receives the schedule sent from the server and presents it to the delivery person. The user checks the proposed schedule through the terminal and makes any necessary corrections. The input is the adjusted delivery schedule, and the output is the proposed schedule for the delivery person.

[0473] Step 6:

[0474] Schedule Approval

[0475] The user reviews the proposed schedule on the device and gives final approval. The device then sends the information to the server. The input is the delivery driver's feedback, and the output is the final approved schedule.

[0476] Step 7:

[0477] Updates to the reservation system

[0478] The server updates the reservation system with the approved delivery schedule, which reflects available delivery times in real time. The input is the final approved schedule, and the output is the updated schedule in the reservation system.

[0479] Step 8:

[0480] matching

[0481] The server receives delivery requests from users on the demand side and performs optimal matching. The AI ​​model analyzes demand and supply data and combines the most suitable schedule with the request. The inputs are the delivery request and available delivery schedule, and the output is the matching result.

[0482] Step 9:

[0483] Sending notifications

[0484] If a match is made, the server sends a notification to the delivery person and the demand user. The terminal receives the notification sent from the server and displays detailed information. The input is the matching result, and the output is the notification sent to the delivery person and the demand user.

[0485] Step 10:

[0486] Share details

[0487] After the reservation is confirmed, the server shares detailed information about the delivery with the delivery person and the demand user. The terminal receives the detailed information sent from the server and displays the delivery contents, time, etc. The input is the reservation confirmation information, and the output is the detailed information shared between the delivery person and the demand user.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 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.

[0494] 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).

[0495] 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.

[0496] 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.

[0497] 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).

[0498] 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. 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] 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."

[0504] This invention is a system for efficiently using privately owned vehicles for car sharing. This system uses an AI model to predict vehicle rental schedules based on vehicle usage history data and external schedule data, and proposes them to users. The following describes the overall operation flow of the system and a specific example.

[0505] Overall system overview

[0506] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these into an AI model for analysis. The AI ​​model predicts the time periods when the vehicle can be rented and proposes them to the user. The user confirms and modifies the proposed schedule, and finally approves it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[0507] Server Operation

[0508] 1. Data collection and analysis

[0509] The server retrieves the user's vehicle usage history data from the database, including information such as mileage, usage time, and usage location.

[0510] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[0511] The server inputs the collected data into an AI model to learn the user's vehicle usage patterns.

[0512] 2. Predictions and proposals

[0513] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and this predicted schedule is sent to the user's device by the server and proposed to the user.

[0514] 3. Reservation management and matching

[0515] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[0516] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[0517] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[0518] Device behavior

[0519] 1. Receiving and checking the schedule

[0520] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[0521] Users can check the proposed schedule on their devices and make corrections as necessary.

[0522] 2. Receiving Notifications

[0523] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[0524] User Actions

[0525] 1. Check and approve the schedule

[0526] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[0527] 2. Loan Management

[0528] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[0529] Specific examples

[0530] For example, if a user has travel plans for the weekend, the schedule information is registered in Google Calendar or Time Tree. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to demand users. When the demand user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand user.

[0531] In this way, this system significantly reduces the user's workload and realizes efficient car sharing.

[0532] The processing flow will be explained below.

[0533] Program processing flow

[0534] Step 1:

[0535] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[0536] Step 2:

[0537] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[0538] Step 3:

[0539] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[0540] Step 4:

[0541] The server retrieves the vehicle rental schedule predicted by the AI ​​model, which includes the dates, times, and times when the vehicle is available for rental.

[0542] Step 5:

[0543] The server then performs optimization based on the predicted schedule and generates an optimal lending schedule. It also combines lending demand data to create a schedule tailored to times of high demand.

[0544] Step 6:

[0545] The server sends the proposed rental schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[0546] Step 7:

[0547] The user checks the proposed lending schedule on the terminal and makes any necessary corrections. The user then checks the details of the schedule and approves or corrects it.

[0548] Step 8:

[0549] The server receives the schedule that the user has approved or modified, records it as the final approved schedule, and reflects it in the reservation system.

[0550] Step 9:

[0551] The server updates the confirmed available rental time in the reservation system, and reflects the available rental schedule in real time.

[0552] Step 10:

[0553] When a rental request arrives at the server from a user on the demand side, the server retrieves it and performs optimal matching, finding the best match between the request and the schedule.

[0554] Step 11:

[0555] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[0556] Step 12:

[0557] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[0558] The above are the specific steps in the processing flow of the system.

[0559] Example 1

[0560] 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."

[0561] In modern society, improving the utilization efficiency of mobility (e.g., vehicles) is an important issue. Sharing privately owned mobility can reduce the burden on the environment and increase economic efficiency. However, if schedules are created without taking into account users' mobility usage patterns and external timetable data, utilization efficiency may decrease. In addition, it is a significant effort for users to manually adjust their own schedules. Therefore, automatic prediction and matching of mobility rental schedules is required.

[0562] 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.

[0563] In this invention, the server includes means for acquiring user's mobile device usage history data, means for acquiring user's external timetable data, means for analyzing the mobile device usage history data and the external timetable data and learning the user's mobile device usage patterns, means for using a generative AI model to predict a mobile device rental schedule, means for proposing the predicted mobile device rental schedule to the user, means for receiving approval of the proposed mobile device rental schedule from the user, means for updating the approved mobile device rental schedule in a reservation system, means for acquiring rental requests from demand-side users and matching them with rental schedules, means for sending notifications to the user and demand-side users when rental is confirmed, and means for confirming reservations and sharing detailed information. This eliminates the need for users to manually adjust their schedules and enables automatic optimization of mobile device rental schedules.

[0564] "User" means an individual or legal entity that owns a vehicle and provides that vehicle to the car sharing system.

[0565] "Mobile object" refers to a means of transportation, such as a vehicle, that is owned and available for rent by a User.

[0566] "Usage history data" refers to information about how a user has used a vehicle in the past, including data such as distance traveled, time of use, and location of use.

[0567] "External Timetable Data" refers to data about a user's schedule and event information obtained through Google Calendar or other schedule management tools.

[0568] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and predict future mobility usage patterns.

[0569] "Proposal" is an operation in which the server sends the predicted rental schedule of the mobile object to the user terminal and asks the user to confirm or modify it.

[0570] "Approval" means that the user reviews and ultimately agrees to the proposed lending schedule.

[0571] "Reservation System" means a system for recording approved vehicle rental schedules and managing rental status.

[0572] A "demand user" is an individual or a corporation that wishes to use a mobile unit on a rental basis.

[0573] "Matching" refers to the process of matching the demand user's lending request with the lending schedule approved by the user to find the optimal combination.

[0574] "Notification" is a message to convey important information such as the completion of a loan or a schedule change to users and demand-side users.

[0575] "Detailed information" refers to specific details regarding the rental status and schedule, and is information shared with users and demand-side users.

[0576] An "information terminal" is a device used by a user to check the proposed lending schedule and approve or modify it, and includes a smartphone, PC, etc.

[0577] This invention is a system for efficiently sharing privately owned vehicles (e.g., cars). The system uses an AI model to predict vehicle rental schedules based on users' vehicle usage history data and external timetable data, and proposes them to users. After obtaining users' approval, the system matches the optimized schedule with users on the demand side, realizing efficient vehicle sharing.

[0578] Server Operation

[0579] 1. Data Collection

[0580] The server first retrieves the user's transportation usage history data from the database. This data consists of the vehicle's mileage, usage time, and usage location. Next, the server uses an API to collect external timetable data. This data includes the user's schedule and event information from Google Calendar and other schedule management tools.

[0581] 2. Data Analysis

[0582] The server preprocesses the collected data and inputs it into an AI model (using TensorFlow or PyTorch, for example), which learns the user's vehicle usage patterns and predicts the vehicle rental schedule based on this.

[0583] 3. Schedule proposal

[0584] The predicted schedule is sent from the server to the user's device, where the user can review the proposed schedule and make any necessary adjustments.

[0585] 4. Approval of forecast schedule

[0586] After the user approves the proposed schedule, it is sent to the server, which updates the reservation system with the approved schedule, reflecting available rental times in real time.

[0587] 5. Reservation management and matching

[0588] When a rental request is received from a demand user, the server performs optimal matching. The server selects the best match between the schedule and the request, and sends a notification to the user and the demand user if the rental is successful.

[0589] Device behavior

[0590] 1. Receiving and checking the schedule

[0591] The user's terminal receives and displays the mobile rental schedule sent from the server. The user can check the proposed schedule on the terminal and make corrections as necessary.

[0592] 2. Receiving Notifications

[0593] If the rental is successful, a notification is sent to the user's terminal and the reservation details are displayed.

[0594] User Actions

[0595] 1. Check and approve the schedule

[0596] The user can check the proposed schedule on the terminal and make any necessary corrections. When the user finally approves the schedule, the information is sent to the server.

[0597] 2. Loan Management

[0598] The user can receive a notification sent from the server and check the details of the confirmed reservation, which allows the user to smoothly manage the rental of the mobile object.

[0599] Specific examples

[0600] For example, if a user has a trip planned for the weekend, the schedule information is registered in Google Calendar. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time period after the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When the demand-side user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand-side user.

[0601] Prompt Sentence Examples

[0602] "If a user has scheduled this weekend in their Google Calendar, predict the available rental times based on past vehicle usage data and output the suggested schedule."

[0603] This system saves users the trouble of manually adjusting their schedules and enables efficient vehicle rental.

[0604] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0605] Step 1: Data collection

[0606] input

[0607] User mobility usage data

[0608] External timetable data (e.g. Google Calendar)

[0609] Server Operation

[0610] The server retrieves the user's vehicle usage history data from the database, including information such as the distance traveled, the time of use, and the location of use.

[0611] The server obtains the user's external timetable data using the API of Google Calendar or other schedule management tools.

[0612] output

[0613] Acquired mobility usage data and external timetable data

[0614] Specific actions

[0615] For example, the server retrieves vehicle usage data for the past six months from "User A's" database and retrieves future schedule information from "User A's calendar" via an API.

[0616] Step 2: Data analysis

[0617] input

[0618] Acquired mobile usage data

[0619] External timetable data

[0620] Server Operation

[0621] The server preprocesses both sets of data into an input format for the AI ​​model, for example by normalizing the data and extracting features.

[0622] The processed data is input into a generative AI model (e.g., TensorFlow or PyTorch) to learn the user's mobility usage patterns.

[0623] output

[0624] Pre-trained AI model

[0625] Mobile rental schedule forecast results

[0626] Specific actions

[0627] The server preprocesses usage data and schedule data, generates input data such as "Tuesday, 9:00 AM to 12:00 PM patterns," and analyzes it using an AI model.

[0628] Step 3: Schedule proposal

[0629] input

[0630] Mobile rental schedule forecast results

[0631] Server Operation

[0632] Based on the prediction results, a lending schedule suitable for the user is created.

[0633] The server transmits this predicted schedule to the user's terminal.

[0634] Device behavior

[0635] The user's device (smartphone or PC) receives and displays the proposed schedule sent from the server.

[0636] output

[0637] Proposed Lending Schedule

[0638] Specific actions

[0639] The user's smartphone app displays "Next available rental time: Wednesday from 2:00 PM to 5:00 PM."

[0640] Step 4: Review and approve the proposed schedule

[0641] input

[0642] Proposed Lending Schedule

[0643] User Actions

[0644] The user checks the proposed schedule on the terminal and makes corrections as necessary.

[0645] Once the user approves the schedule, the information is sent to the server.

[0646] output

[0647] Revised or approved schedule

[0648] Specific actions

[0649] The user changes the time on their smartphone from "Wednesday 2pm to 5pm" to "Thursday 10am to 1pm" and approves it.

[0650] Step 5: Update your booking management

[0651] input

[0652] Approved Schedule

[0653] Server Operation

[0654] The server updates the reservation system with the approved schedule and updates the database with available rental times.

[0655] output

[0656] Updated booking information

[0657] Specific actions

[0658] The server updates the database information to record that "User A can rent a vehicle from 10:00 AM to 1:00 PM on Thursdays."

[0659] Step 6: Matching the Lending Request

[0660] input

[0661] Lending request from demand side user

[0662] Updated booking information

[0663] Server Operation

[0664] The server receives the demand user's rental request and matches it with the approved schedule.

[0665] Find the best match and schedule to accommodate your request.

[0666] output

[0667] Matching results

[0668] Specific actions

[0669] The server receives a request from user B on the demand side and checks it against the information in the reservation system.

[0670] Step 7: Sending notifications

[0671] input

[0672] Matching results

[0673] Server Operation

[0674] If a match is made, the server sends a notification to the user and the demand user. Notification services such as Firebase and Twilio are used for this process.

[0675] Device behavior

[0676] The user's terminal receives the notification and confirms that the loan has been made.

[0677] output

[0678] Notification of loan completion

[0679] Specific actions

[0680] For example, the server notifies user A and demand user B that a match has been made via Firebase Cloud Messaging, and the device displays the message "Loan confirmed."

[0681] This processing flow enables users to efficiently share vehicles and optimize operations.

[0682] (Application example 1)

[0683] 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."

[0684] To efficiently utilize privately owned vehicles for car sharing using smartphones and other devices, it is essential to predict usage schedules and operate them optimally. However, conventional systems require a great deal of time and effort to manage schedules and operate vehicles. Furthermore, as the use of autonomous vehicles continues to increase, there is a significant lack of systems to properly manage and operate them. Therefore, there is a need for a system that allows privately owned vehicles, especially autonomous vehicles, to be efficiently used for car sharing.

[0685] 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.

[0686] In this invention, the server includes means for acquiring a user's vehicle usage history data, means for acquiring the user's external schedule data, means for analyzing the vehicle usage history data and the external schedule data and learning the user's vehicle usage patterns, means for predicting a vehicle rental schedule, means for proposing the predicted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in a reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, means for confirming the reservation and sharing detailed information, means for moving an autonomous vehicle to a specified time and place based on the approved vehicle rental schedule, and means for remotely operating the autonomous vehicle via a user terminal. This allows efficient management of rental schedules for autonomous vehicles owned by individuals, enabling smooth rental and return to users.

[0687] "User's vehicle usage history data" refers to information such as the time, distance, and location when the user uses the vehicle.

[0688] "External schedule data" is data about the user's schedules and appointments obtained from the calendar or schedule management service used by the user.

[0689] The "vehicle usage pattern" indicates the vehicle usage tendencies and habits analyzed based on the user's past vehicle usage record data and external schedule data.

[0690] The "vehicle rental schedule" is a schedule indicating the dates and times and periods during which a vehicle can be rented.

[0691] A "reservation system" is a system for managing vehicle rental schedules and matching with demand-side users.

[0692] A "demand user" refers to a user who wishes to rent a vehicle.

[0693] An "autonomous vehicle" is a vehicle that can autonomously perform driving operations by itself.

[0694] "Remote control" means controlling the operation and functions of a vehicle using a device such as a smartphone without being physically near the vehicle.

[0695] This invention relates to a system for efficiently using privately owned self-driving vehicles for car sharing. Specific embodiments of this system will be described below.

[0696] System configuration

[0697] The system consists of the following main components: a server, a user terminal, a demand-side user terminal, and an autonomous vehicle.

[0698] 1. Server

[0699] The server is equipped with the following software and data processing means:

[0700] Data collection module: Uses databases and APIs (for external schedules) to obtain user vehicle usage data and external schedule data. Examples include the Google Calendar API and the Time Tree API.

[0701] Analysis and prediction module: Analyzes data using machine learning libraries such as TensorFlow and predicts vehicle rental schedules.

[0702] Reservation management module: Based on the predictions made by the AI ​​model, the module proposes rental schedules to users and updates approved schedules in a cloud-based reservation system, using cloud services such as Firebase and AWS.

[0703] Autonomous driving collaboration module: Uses the autonomous vehicle API to remotely control and move vehicles based on approved schedules.

[0704] 2. User Device

[0705] Notification and schedule management: The smartphone app displays the proposed vehicle rental schedule received from the server and allows the user to confirm and modify it. For example, this applies to iOS and Android apps.

[0706] Remote control: Equipped with the ability to move and remotely control the vehicle.

[0707] 3. Demand-side user terminal

[0708] Request and confirmation: The demand-side user sends a request to rent a vehicle and receives a confirmation of the rental from the server.

[0709] 4. Self-driving vehicles

[0710] Transmission of vehicle operation data: The vehicle itself transmits driving data (e.g., GPS data, usage status) to the server.

[0711] Autonomous driving and remote control: Based on instructions received from the server via API, the autonomous driving function is used to move or return the vehicle.

[0712] Data processing and calculation

[0713] Data collection: The server collects the user's vehicle usage history data and external schedule data via API, which stores past usage history and future schedules in a database.

[0714] Data analysis: TensorFlow is used to analyze collected data and learn vehicle usage patterns, which then predicts the best times and dates for when the vehicle will be available for rental.

[0715] Schedule management: The predicted rental schedule is sent to the user's device, where the user can confirm and modify it, and the final rental schedule is determined. The determined schedule is then reflected in the cloud reservation system and updated as needed.

[0716] Autonomous driving collaboration: Based on the approved rental schedule, an autonomous vehicle will travel to the designated time and location, enabling users and demand users to share vehicles smoothly.

[0717] Specific examples

[0718] If a user has travel plans for the weekend, the plan is registered in advance in the schedule management service. The server retrieves this information and analyzes it along with past usage records. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this prediction to the user, who confirms and approves it. The approved schedule is reflected in the cloud reservation system and is also made public to demand users. When the demand user sends a request, the server performs optimal matching, and ultimately notifies both the user and the demand user.

[0719] Prompt Sentence Examples

[0720] "This app analyzes your vehicle usage data and schedule to suggest the optimal car sharing schedule. What features do you need?"

[0721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0722] Step 1:

[0723] Data collection

[0724] The server retrieves the user's vehicle usage history data from the database and also retrieves external schedule data via an API. Specifically, it uses the Google Calendar API and Time Tree API to collect the user's schedule information. The input at this stage is the vehicle usage history data and external schedule data, and the output is structured data that includes these data.

[0725] Step 2:

[0726] Data analysis

[0727] The server analyzes the collected vehicle usage history data and external schedule data. Using a generative AI model such as TensorFlow, it analyzes this data and learns the user's vehicle usage patterns. The input is the structured data collected in step 1, and the output is the vehicle usage pattern obtained through the analysis and the predicted rental availability time. Specifically, it identifies usage frequency and patterns from past data and predicts the optimal future rental schedule.

[0728] Step 3:

[0729] Schedule proposal

[0730] The server generates an optimal rental schedule based on the analysis results and sends it to the user's device. The user is notified via a smartphone app. A GUI (Graphical User Interface) is displayed on the app, allowing the user to confirm and modify the schedule. The input to this step is the analysis results obtained in step 2, and the output is a proposed schedule sent to the user's device. Specifically, the user confirms the proposed schedule and modifies it as necessary.

[0731] Step 4:

[0732] Schedule Approval

[0733] The user checks the proposed schedule on the terminal, makes any necessary corrections, and then gives final approval. The user's input is the action of checking, correcting, and approving the proposed lending schedule, and the output is the approved lending schedule that is sent to the server. Specifically, when the user clicks the "Approve" button in the application, the changes are uploaded to the server in real time.

[0734] Step 5:

[0735] Schedule updates and booking management

[0736] The server updates the approved rental schedule to the cloud-based reservation system, which updates and publishes the available rental time slots in real time. The input to this step is the approved schedule sent in step 4, and the output is the updated rental schedule in the reservation system. Specifically, the system updates the database in real time to update the published schedule information.

[0737] Step 6:

[0738] Acquiring and matching lending requests

[0739] The server receives rental requests from demand users and matches the requests with the optimal rental schedule. The input to this step is the request data from the demand users, and the output is the optimal matching result. Specifically, when a request is sent, the data is imported into the server in real time, and the AI ​​model automatically matches the optimal rental time with the request.

[0740] Step 7:

[0741] Notification and confirmation

[0742] If a match is made, the server sends a notification to the user and the demand user. Details of the confirmed reservation are sent and can be viewed by both parties in real time. The input to this step is the matching result obtained in step 6, and the output is a notification and reservation details sent to the user and the demand user. Specifically, the notification function is used to send detailed information via push notification or email.

[0743] Step 8:

[0744] Remote control of autonomous vehicles

[0745] The server moves the autonomous vehicle to the specified time and location based on the approved vehicle rental schedule. This allows for smooth rental and return. The input for this step is the approved schedule data, and the output is the movement of the autonomous vehicle or the completion status of remote control. Specifically, the server sends remote control commands for the vehicle using an API, and the vehicle moves as instructed.

[0746] 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.

[0747] This invention is a system for efficiently using privately owned vehicles for car sharing, and by combining it with an emotion engine that recognizes users' emotions, it provides an optimal rental schedule. This system uses an AI model and emotion engine to analyze the user's vehicle usage history data and external schedule data, predict and adjust the vehicle rental schedule, and propose it to the user. The following describes the overall operation flow of the system and a specific example.

[0748] Overall system overview

[0749] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these data into an AI model and emotion engine for analysis. The AI ​​model predicts the time periods when the vehicle is available for rental, and the emotion engine makes adjustments based on the user's emotional state. An optimal rental schedule is proposed to the user, who can then review, approve, or modify it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[0750] Server Operation

[0751] 1. Data collection and analysis

[0752] The server retrieves the user's vehicle usage history data from the database, which includes information such as past mileage, usage time, and usage location.

[0753] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[0754] The server inputs this data into an AI model to learn the user's vehicle usage patterns.

[0755] In addition, an emotion engine is used to collect user emotion data, which is also used for analysis.

[0756] 2. Anticipation and emotion regulation

[0757] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and then the emotion engine adjusts the schedule based on the user's emotional state.

[0758] The predicted schedule is sent by the server to the user's terminal and proposed to the user.

[0759] 3. Reservation management and matching

[0760] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[0761] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[0762] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[0763] Device behavior

[0764] 1. Receiving and checking the schedule

[0765] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[0766] Users can check the proposed schedule on their devices and make corrections as necessary.

[0767] 2. Receiving Notifications

[0768] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[0769] User Actions

[0770] 1. Check and approve the schedule

[0771] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[0772] 2. Loan Management

[0773] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[0774] Specific examples

[0775] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip (for example, the user is likely to be relaxed after the trip). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who can confirm and approve it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs the optimal match and sends notifications to the user and the demand-side user.

[0776] In this way, this system significantly reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[0777] The processing flow will be explained below.

[0778] Program processing flow

[0779] Step 1:

[0780] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[0781] Step 2:

[0782] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[0783] Step 3:

[0784] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[0785] Step 4:

[0786] The server collects user emotion data using an emotion engine, which analyzes the user's emotional state (e.g., stress level, satisfaction level, etc.) obtained from a smartphone or wearable device.

[0787] Step 5:

[0788] The server retrieves the predicted vehicle rental schedule from the AI ​​model, and the emotion engine then adjusts the schedule based on the user's emotional state, optimizing the schedule to accommodate rentals at times that are least stressful for the user.

[0789] Step 6:

[0790] The server sends the adjusted proposed schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[0791] Step 7:

[0792] The user checks the proposed lending schedule on the terminal, modifies the schedule as necessary, and finally approves it. This operation is performed on the terminal.

[0793] Step 8:

[0794] The server receives the schedule that the user has approved or modified, records it as an approved schedule, and reflects this information in the reservation system.

[0795] Step 9:

[0796] The server updates the reservation system with the confirmed available rental times, reflecting the available rental schedule in real time. This information is also made public to users on the demand side.

[0797] Step 10:

[0798] When a rental request arrives at the server from a demand-side user, the server retrieves it and performs optimal matching. The server finds the best match between the request and the schedule.

[0799] Step 11:

[0800] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[0801] Step 12:

[0802] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[0803] Specific examples

[0804] For example, the server retrieves the user's vehicle usage history data (such as past mileage, usage time, and location) from a database. The server then uses an API to extract the user's schedule data from Google Calendar and Time Tree. This data is input into an AI model to learn the user's vehicle usage patterns. The emotion engine collects user emotion data from smartphones and wearable devices and adds this to the analysis.

[0805] The server uses the AI ​​model to predict a vehicle rental schedule and adjusts it based on the user's emotional state through an emotion engine. For example, the schedule may be adjusted to avoid times when the user is likely to feel stressed. The server then sends the adjusted rental schedule to the user's device and notifies them. The user can then check the schedule on their device, modify it as necessary, and approve it.

[0806] The approved schedule is received by the server and updated in the reservation system. When a rental request comes from a demand user, the server performs optimal matching, and if successful, sends a notification to both the user and the demand user to confirm the reservation. In this way, efficient car sharing that takes into account the user's emotional state is realized.

[0807] Example 2

[0808] 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."

[0809] In conventional car sharing systems, vehicle rental schedules are set without taking into account the user's emotional state, which can be inconvenient for users. Furthermore, it is difficult to provide an optimal rental schedule simply by analyzing vehicle usage history data and external schedule data. Therefore, there is a need to improve user satisfaction with vehicle usage.

[0810] 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 acquiring vehicle usage history data of the user, means for acquiring external schedule data of the user, means for analyzing the vehicle usage history data and the external schedule data using an AI model to learn the user's vehicle usage pattern, means for collecting user emotion data using an emotion engine and using the collected data for analysis, means for predicting a vehicle rental schedule and adjusting it based on the user's emotional state, means for proposing the predicted and adjusted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in the reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, and means for confirming the reservation and sharing detailed information. This makes it possible to provide an optimal vehicle rental schedule that takes the user's emotional state into consideration.

[0811] "Vehicle usage history data" is data about how a user has used a vehicle in the past, and includes information such as mileage, usage time, and usage location.

[0812] "External schedule data" is data obtained from an external schedule management system that manages the user's schedule, and includes information obtained from Google Calendar, Time Tree, etc.

[0813] An "AI model" is software that uses machine learning algorithms to analyze data and identify patterns and predictions.

[0814] An "emotion engine" is a system or software for analyzing a user's emotional state, collecting and analyzing emotional data from social media posts, biometric data, etc.

[0815] The "vehicle rental schedule" is a schedule indicating the time periods during which a vehicle can be rented, and is predicted based on the user's vehicle usage history data and external schedule data.

[0816] "Prediction" is the act of estimating future vehicle usage patterns and rental availability times based on collected data.

[0817] "Adjustment" is the process of optimizing a predicted schedule by taking into account the user's emotional state and other factors.

[0818] "Proposal" is the act of presenting a predicted and adjusted vehicle rental schedule to a user.

[0819] "Approval" is an action in which the user agrees with the proposed vehicle rental schedule, and the result is reflected in the system.

[0820] The "reservation system" is a system that manages vehicle rental reservations, updates schedules, and confirms reservations.

[0821] A "demand user" is a user who wishes to rent a vehicle for use.

[0822] "Matching" is the act of optimally matching the demand user's request with the vehicle's available rental time.

[0823] "Notifications" are messages that inform users of information such as reservations and schedule changes.

[0824] "Detailed information" indicates specific information about the reservation contents and schedule.

[0825] This invention is a system for efficiently using privately owned vehicles for car sharing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides an optimal rental schedule. The overall operation flow of this system and a specific example are shown below.

[0826] System Overview

[0827] This system acquires historical vehicle usage data for users and their external schedule data. These data are input into a generative AI model and emotion engine for analysis. The generative AI model uses TensorFlow and PyTorch to learn users' vehicle usage patterns and predict the time periods when vehicles are available for rental. The emotion engine uses, for example, IBM Watson's emotion analysis API to collect user emotion data and use it for analysis. The resulting predicted schedule is proposed to the user, who then approves it. The approved schedule is updated in the reservation system and matched with rental requests from demand users. If the rental is confirmed, the server sends a notification to the user and the demand user, and the reservation is confirmed.

[0828] Server Operation

[0829] 1. The server retrieves the user's vehicle usage history data from the database. The data indicates how the user has used the vehicle in the past, including the mileage, usage time, and location of use.

[0830] 2. The server then retrieves external schedule data, such as Google Calendar or Time Tree, through an API. The external schedule data contains the user's upcoming events.

[0831] 3. The server inputs this data into a generative AI model, which uses TensorFlow and PyTorch to learn the user's vehicle usage patterns.

[0832] 4. The server uses an emotion engine to collect and analyze the user's emotion data. The emotion engine uses, for example, IBM Watson's emotion analysis API. This allows it to analyze emotions from the user's social media posts and other biometric sensor data.

[0833] 5. The generative AI model predicts the user's vehicle rental schedule, taking into account the user's historical usage patterns and external schedule data.

[0834] 6. The emotion engine adjusts the predicted schedule based on the user's emotional state, for example, avoiding rentals during times when the user is feeling stressed.

[0835] 7. The server sends the predicted and adjusted schedule to the user's device, allowing the user to review the proposed schedule.

[0836] 8. Once approval is received from the user, the server updates this schedule into the reservation system, which reflects available rental times in real time.

[0837] 9. The server receives the rental request from the demand user and matches it with the schedule. When the optimal match is found, the rental is completed.

[0838] 10. If the rental is successful, the server sends a notification to the user and the demand user and confirms the reservation.

[0839] Device behavior

[0840] 1. The terminal receives the proposed schedule sent from the server. The user can check the proposed schedule on the terminal and modify it if necessary.

[0841] 2. If the rental is successful, the device receives a notification from the server and displays the reservation details.

[0842] User Actions

[0843] 1. The user checks the proposed schedule on the device and modifies it if necessary. When the user finally approves the schedule, the information is sent to the server.

[0844] 2. The user receives a notification sent from the server and checks the details of the confirmed reservation, enabling smooth rental management.

[0845] Examples and prompts

[0846] Specific examples

[0847] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip. Based on this information, the server uses the emotion engine to adjust the schedule predicted by the generative AI model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs optimal matching and sends notifications to the user and the demand-side user.

[0848] Prompt Sentence Examples

[0849] Create optimal rental schedules based on user vehicle usage history data and external schedule data. Also take into account emotion engine data. For example:

[0850] Usage data: mileage, usage time, and location for the past month

[0851] External schedule data: Google Calendar, TimeTree events

[0852] Emotion Engine Data: High stress before travel, relaxed after travel

[0853] As a result, suggest a post-trip loan schedule.

[0854] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[0855] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0856] Step 1:

[0857] The server retrieves the user's vehicle usage history data from the database. Input includes mileage, usage time, and usage location. By retrieving this data, basic information can be obtained to understand the user's past vehicle usage patterns. The output is the retrieved vehicle usage history data.

[0858] Step 2:

[0859] The server retrieves the user's external schedule data from Google Calendar or TimeTree through an API. The input includes the user's authentication information and the calendar service's API endpoint, allowing you to leverage the user's upcoming events. The output is the retrieved external schedule data.

[0860] Step 3:

[0861] The server inputs vehicle usage history data and external schedule data into the generative AI model. The input includes the data obtained in Step 1 and Step 2. This allows the AI ​​model to learn the user's vehicle usage patterns. As a specific example, TensorFlow or PyTorch can be used. The output is the result of analyzing the user's vehicle usage patterns.

[0862] Step 4:

[0863] The server uses an emotion engine to collect and analyze user emotion data. Inputs include social media posts and biometric sensor data. For example, IBM Watson's emotion analysis API can be used. The output is user emotion data.

[0864] Step 5:

[0865] The generative AI model predicts the user's vehicle rental schedule. The input includes the user's vehicle usage pattern obtained in step 3 and the emotion data obtained in step 4. This creates the user's vehicle rental schedule. The output is the predicted vehicle rental schedule.

[0866] Step 6:

[0867] The emotion engine adjusts the predicted schedule based on the user's emotional state. The input includes the schedule predicted in step 5 and emotion data. This creates a schedule that takes the user's emotional state into account. The output is the adjusted vehicle rental schedule.

[0868] Step 7:

[0869] The server sends the adjusted schedule to the user's terminal. The input includes the vehicle rental schedule adjusted in step 6. The terminal displays the proposed schedule. The output is the schedule proposal to the user.

[0870] Step 8:

[0871] The user reviews the proposed schedule on the terminal and modifies it if necessary. The input includes the vehicle rental schedule received in step 7, which allows the user to approve or modify the schedule. The output is the schedule approved or modified by the user.

[0872] Step 9:

[0873] The server receives approval from the user and updates this schedule to the reservation system. The input includes the approved or modified schedule from step 8. The reservation system updates the available rental slots in real time. The output is the updated reservation information.

[0874] Step 10:

[0875] The server receives the rental request from the demand user and matches it with the schedule. The input includes the demand user's request and the reservation information updated in step 9. When the best match is found, the rental is established. The output is the matching result.

[0876] Step 11:

[0877] If the rental is successful, the server sends a notification to the user and the demand user to confirm the reservation. The input includes the matching result determined in step 10. The terminal receives the notification and displays the reservation details. The output is the confirmed reservation information and notification.

[0878] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[0879] (Application example 2)

[0880] 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."

[0881] Conventional car sharing systems have a problem in that efficient matching between vehicle users and those seeking to rent a vehicle is difficult because the vehicle rental schedule is not sufficiently optimized. In addition, because the system does not take into account the user's emotional state, there is a high possibility that schedules that cause stress to the user are proposed. This may result in a decrease in satisfaction with the car sharing system.

[0882] The specific processing by the specific 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 acquiring the user's vehicle usage history data, means for acquiring the user's external schedule data, and means for acquiring the user's emotional data and adjusting the rental schedule based on the user's emotional state. This makes it possible to analyze the user's vehicle usage history data and external schedule data, predict an optimal vehicle rental schedule, and adjust the schedule according to the user's emotional state. This makes it possible to realize efficient vehicle rental and improve user satisfaction.

[0883] "User's vehicle usage history data" refers to historical information about the user's past use of their own vehicle, specifically data such as mileage, usage time, and usage location.

[0884] "User's external schedule data" refers to external schedule information that may affect the user's use of the vehicle, such as schedule and event information obtained from a calendar service.

[0885] "Emotion data" refers to information that indicates the user's internal emotional state, specifically data that has been acquired by digitizing emotions such as stress, relaxation, and happiness.

[0886] "Means for adjusting the rental schedule based on emotional state" refers to a method for optimizing the schedule based on the acquired emotional data to ensure the least stressful and comfortable vehicle rental experience for the user.

[0887] "Proposed vehicle rental schedule" refers to the predicted rental itinerary that the system presents to the user after analysis and sentiment adjustment has been performed.

[0888] "Reservation System" refers to the computer system used by Users and Demand-Side Users to manage and confirm reservations for vehicle rentals.

[0889] "Demand-side user" refers to a user who wishes to rent a vehicle through a car sharing service.

[0890] "Matching" refers to the process of optimally combining the schedule of a user who wants to rent a vehicle with the request of a demand-side user who wants to rent a vehicle.

[0891] "Means for sending notifications" refers to the method by which schedule and reservation confirmation information is sent electronically to users and demand users, typically via a smartphone or PC application.

[0892] "Means for sharing detailed information" refers to a method for providing specific information about the vehicle rental to both the user and the demand-side user after the reservation is confirmed.

[0893] System Overview

[0894] This invention is a system for food delivery services that provides optimal delivery plans that take into account delivery personnel's schedule management and emotional state. This system collects delivery personnel's past delivery performance data and external schedule data, analyzes them using an AI model and an emotion engine, and predicts and adjusts delivery schedules and proposes them to delivery personnel.

[0895] Server Operation

[0896] 1. Data collection and analysis

[0897] The server retrieves the delivery personnel's past delivery performance data from the database. This data includes past delivery times, distances, delivery destinations, etc. It also uses an API to retrieve external schedule data. This allows the server to understand what the delivery personnel have scheduled at what time.

[0898] Furthermore, an emotion engine is used to collect emotional data from delivery personnel, and the emotional data is used for analysis, for example, to detect whether the emotional state is stressed or relaxed.

[0899] 2. Anticipation and emotion regulation

[0900] The AI ​​model predicts delivery schedules based on collected data, and an emotion engine then adjusts the schedule based on the driver's emotional state. For example, if a driver is stressed, the system may increase their break time.

[0901] The predicted and adjusted schedule is sent by the server to the delivery person's terminal and proposed to the delivery person.

[0902] 3. Reservation management and matching

[0903] Once the delivery person approves the schedule, this information is sent to the server and reflected in the reservation system, which updates available delivery times in real time.

[0904] Upon receiving a delivery request from a demand user, the server performs optimal matching to find the best match between the schedule and the request.

[0905] If a match is made, the server sends a notification to the delivery person and the demand user and confirms the reservation.

[0906] Device behavior

[0907] 1. Receiving and checking the schedule

[0908] The delivery person's device (smartphone or PC) receives the proposed delivery schedule sent from the server. The delivery person can check the proposed schedule on the device and modify it as necessary.

[0909] 2. Receiving Notifications

[0910] When a match is made and a delivery is confirmed, a notification is sent to the delivery person's device, which displays the delivery details and allows them to act according to the confirmed schedule.

[0911] User Actions

[0912] 1. Check and approve the schedule

[0913] The delivery person can review the proposed schedule on their device, modify it if necessary, and finally approve the schedule, which is then sent to the server.

[0914] 2. Managing deliveries

[0915] The delivery person receives the notification sent from the server and checks the details of the confirmed delivery, which allows the delivery person to smoothly manage their delivery work.

[0916] Specific examples

[0917] For example, if a delivery person has a meeting at 9:00 AM, the system retrieves that schedule information from the API. At the same time, the emotion engine recognizes the person's current stress level (they are likely nervous before the meeting). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determine that deliveries are possible at 10:00 AM after the meeting and at 3:00 PM. This predicted and adjusted schedule is proposed to the delivery person, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is made available to demand-side users.

[0918] When a request is sent from a demand user, the server performs optimal matching and sends a notification to the delivery person and the demand user.

[0919] Example prompt sentence:

[0920] We provide schedule and sentiment data, including: Use this to predict optimal delivery schedules and adjust them based on sentiment.

[0921] Schedule data: [{'date': '2023-01-01', 'event': 'meeting', 'time': '10:00'}, {'date': '2023-01-02', 'event': 'shopping', 'time': '12:00'}]

[0922] Emotion data: ['neutral', 'stress']

[0923] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0924] Step 1:

[0925] Data Collection

[0926] The server first retrieves the delivery person's past delivery performance data from the database. Here, it uses a database query to obtain information such as past delivery times, distances, and delivery destinations. It also uses an API to obtain the delivery person's external schedule data and retrieves appointment and event information from a calendar service. The inputs are the delivery person's ID and query conditions, and the output is delivery performance data and schedule data.

[0927] Step 2:

[0928] Acquiring emotion data

[0929] The server uses an emotion engine to obtain the delivery person's emotional data. Specifically, the server inputs the delivery person's recent activities and feedback into the emotion analysis API to obtain data on their emotional state (stress, relaxation, happiness, etc.). The input is the delivery person's recent activity information, and the output is emotional data.

[0930] Step 3:

[0931] Prediction by AI model

[0932] The server inputs the delivery performance data and schedule data acquired in step 1 into the AI ​​model and predicts the optimal delivery schedule. The AI ​​model learns delivery patterns from past data and predicts future available delivery times. The inputs are delivery performance data and schedule data, and the output is a predicted delivery schedule.

[0933] Step 4:

[0934] emotional regulation

[0935] The server adjusts the predicted delivery schedule in step 3 based on the emotional data acquired in step 2. The emotion engine analyzes the emotional state of the delivery person and makes adjustments such as extending the interval between deliveries if the person is under high stress. The inputs are the predicted delivery schedule and emotional data, and the output is an adjusted delivery schedule.

[0936] Step 5:

[0937] Schedule proposal

[0938] The server sends the adjusted delivery schedule from step 4 to the delivery person's terminal and proposes it. The terminal receives the schedule sent from the server and presents it to the delivery person. The user checks the proposed schedule through the terminal and makes any necessary corrections. The input is the adjusted delivery schedule, and the output is the proposed schedule for the delivery person.

[0939] Step 6:

[0940] Schedule Approval

[0941] The user reviews the proposed schedule on the device and gives final approval. The device then sends the information to the server. The input is the delivery driver's feedback, and the output is the final approved schedule.

[0942] Step 7:

[0943] Updates to the reservation system

[0944] The server updates the reservation system with the approved delivery schedule, which reflects available delivery times in real time. The input is the final approved schedule, and the output is the updated schedule in the reservation system.

[0945] Step 8:

[0946] matching

[0947] The server receives delivery requests from users on the demand side and performs optimal matching. The AI ​​model analyzes demand and supply data and combines the most suitable schedule with the request. The inputs are the delivery request and available delivery schedule, and the output is the matching result.

[0948] Step 9:

[0949] Sending notifications

[0950] If a match is made, the server sends a notification to the delivery person and the demand user. The terminal receives the notification sent from the server and displays detailed information. The input is the matching result, and the output is the notification sent to the delivery person and the demand user.

[0951] Step 10:

[0952] Share details

[0953] After the reservation is confirmed, the server shares detailed information about the delivery with the delivery person and the demand user. The terminal receives the detailed information sent from the server and displays the delivery contents, time, etc. The input is the reservation confirmation information, and the output is the detailed information shared between the delivery person and the demand user.

[0954] 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.

[0955] 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.

[0956] 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.

[0957] [Third embodiment]

[0958] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0959] 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.

[0960] 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).

[0961] 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.

[0962] 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.

[0963] 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).

[0964] 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. 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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."

[0970] This invention is a system for efficiently using privately owned vehicles for car sharing. This system uses an AI model to predict vehicle rental schedules based on vehicle usage history data and external schedule data, and proposes them to users. The following describes the overall operation flow of the system and a specific example.

[0971] Overall system overview

[0972] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these into an AI model for analysis. The AI ​​model predicts the time periods when the vehicle can be rented and proposes them to the user. The user confirms and modifies the proposed schedule, and finally approves it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[0973] Server Operation

[0974] 1. Data collection and analysis

[0975] The server retrieves the user's vehicle usage history data from the database, including information such as mileage, usage time, and usage location.

[0976] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[0977] The server inputs the collected data into an AI model to learn the user's vehicle usage patterns.

[0978] 2. Predictions and proposals

[0979] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and this predicted schedule is sent to the user's device by the server and proposed to the user.

[0980] 3. Reservation management and matching

[0981] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[0982] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[0983] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[0984] Device behavior

[0985] 1. Receiving and checking the schedule

[0986] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[0987] Users can check the proposed schedule on their devices and make corrections as necessary.

[0988] 2. Receiving Notifications

[0989] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[0990] User Actions

[0991] 1. Check and approve the schedule

[0992] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[0993] 2. Loan Management

[0994] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[0995] Specific examples

[0996] For example, if a user has travel plans for the weekend, the schedule information is registered in Google Calendar or Time Tree. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to demand users. When the demand user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand user.

[0997] In this way, this system significantly reduces the user's workload and realizes efficient car sharing.

[0998] The processing flow will be explained below.

[0999] Program processing flow

[1000] Step 1:

[1001] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[1002] Step 2:

[1003] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[1004] Step 3:

[1005] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[1006] Step 4:

[1007] The server retrieves the vehicle rental schedule predicted by the AI ​​model, which includes the dates, times, and times when the vehicle is available for rental.

[1008] Step 5:

[1009] The server then performs optimization based on the predicted schedule and generates an optimal lending schedule. It also combines lending demand data to create a schedule tailored to times of high demand.

[1010] Step 6:

[1011] The server sends the proposed rental schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[1012] Step 7:

[1013] The user checks the proposed lending schedule on the terminal and makes any necessary corrections. The user then checks the details of the schedule and approves or corrects it.

[1014] Step 8:

[1015] The server receives the schedule that the user has approved or modified, records it as the final approved schedule, and reflects it in the reservation system.

[1016] Step 9:

[1017] The server updates the confirmed available rental time in the reservation system, and reflects the available rental schedule in real time.

[1018] Step 10:

[1019] When a rental request arrives at the server from a user on the demand side, the server retrieves it and performs optimal matching, finding the best match between the request and the schedule.

[1020] Step 11:

[1021] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[1022] Step 12:

[1023] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[1024] The above are the specific steps in the processing flow of the system.

[1025] Example 1

[1026] 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."

[1027] In modern society, improving the utilization efficiency of mobility (e.g., vehicles) is an important issue. Sharing privately owned mobility can reduce the burden on the environment and increase economic efficiency. However, if schedules are created without taking into account users' mobility usage patterns and external timetable data, utilization efficiency may decrease. In addition, it is a significant effort for users to manually adjust their own schedules. Therefore, automatic prediction and matching of mobility rental schedules is required.

[1028] 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.

[1029] In this invention, the server includes means for acquiring user's mobile device usage history data, means for acquiring user's external timetable data, means for analyzing the mobile device usage history data and the external timetable data and learning the user's mobile device usage patterns, means for using a generative AI model to predict a mobile device rental schedule, means for proposing the predicted mobile device rental schedule to the user, means for receiving approval of the proposed mobile device rental schedule from the user, means for updating the approved mobile device rental schedule in a reservation system, means for acquiring rental requests from demand-side users and matching them with rental schedules, means for sending notifications to the user and demand-side users when rental is confirmed, and means for confirming reservations and sharing detailed information. This eliminates the need for users to manually adjust their schedules and enables automatic optimization of mobile device rental schedules.

[1030] "User" means an individual or legal entity that owns a vehicle and provides that vehicle to the car sharing system.

[1031] "Mobile object" refers to a means of transportation, such as a vehicle, that is owned and available for rent by a User.

[1032] "Usage history data" refers to information about how a user has used a vehicle in the past, including data such as distance traveled, time of use, and location of use.

[1033] "External Timetable Data" refers to data about a user's schedule and event information obtained through Google Calendar or other schedule management tools.

[1034] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and predict future mobility usage patterns.

[1035] "Proposal" is an operation in which the server sends the predicted rental schedule of the mobile object to the user terminal and asks the user to confirm or modify it.

[1036] "Approval" means that the user reviews and ultimately agrees to the proposed lending schedule.

[1037] "Reservation System" means a system for recording approved vehicle rental schedules and managing rental status.

[1038] A "demand user" is an individual or a corporation that wishes to use a mobile unit on a rental basis.

[1039] "Matching" refers to the process of matching the demand user's lending request with the lending schedule approved by the user to find the optimal combination.

[1040] "Notification" is a message to convey important information such as the completion of a loan or a schedule change to users and demand-side users.

[1041] "Detailed information" refers to specific details regarding the rental status and schedule, and is information shared with users and demand-side users.

[1042] An "information terminal" is a device used by a user to check the proposed lending schedule and approve or modify it, and includes a smartphone, PC, etc.

[1043] This invention is a system for efficiently sharing privately owned vehicles (e.g., cars). The system uses an AI model to predict vehicle rental schedules based on users' vehicle usage history data and external timetable data, and proposes them to users. After obtaining users' approval, the system matches the optimized schedule with users on the demand side, realizing efficient vehicle sharing.

[1044] Server Operation

[1045] 1. Data Collection

[1046] The server first retrieves the user's transportation usage history data from the database. This data consists of the vehicle's mileage, usage time, and usage location. Next, the server uses an API to collect external timetable data. This data includes the user's schedule and event information from Google Calendar and other schedule management tools.

[1047] 2. Data Analysis

[1048] The server preprocesses the collected data and inputs it into an AI model (using TensorFlow or PyTorch, for example), which learns the user's vehicle usage patterns and predicts the vehicle rental schedule based on this.

[1049] 3. Schedule proposal

[1050] The predicted schedule is sent from the server to the user's device, where the user can review the proposed schedule and make any necessary adjustments.

[1051] 4. Approval of forecast schedule

[1052] After the user approves the proposed schedule, it is sent to the server, which updates the reservation system with the approved schedule, reflecting available rental times in real time.

[1053] 5. Reservation management and matching

[1054] When a rental request is received from a demand user, the server performs optimal matching. The server selects the best match between the schedule and the request, and sends a notification to the user and the demand user if the rental is successful.

[1055] Device behavior

[1056] 1. Receiving and checking the schedule

[1057] The user's terminal receives and displays the mobile rental schedule sent from the server. The user can check the proposed schedule on the terminal and make corrections as necessary.

[1058] 2. Receiving Notifications

[1059] If the rental is successful, a notification is sent to the user's terminal and the reservation details are displayed.

[1060] User Actions

[1061] 1. Check and approve the schedule

[1062] The user can check the proposed schedule on the terminal and make any necessary corrections. When the user finally approves the schedule, the information is sent to the server.

[1063] 2. Loan Management

[1064] The user can receive a notification sent from the server and check the details of the confirmed reservation, which allows the user to smoothly manage the rental of the mobile object.

[1065] Specific examples

[1066] For example, if a user has a trip planned for the weekend, the schedule information is registered in Google Calendar. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time period after the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When the demand-side user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand-side user.

[1067] Prompt Sentence Examples

[1068] "If a user has scheduled this weekend in their Google Calendar, predict the available rental times based on past vehicle usage data and output the suggested schedule."

[1069] This system saves users the trouble of manually adjusting their schedules and enables efficient vehicle rental.

[1070] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1071] Step 1: Data collection

[1072] input

[1073] User mobility usage data

[1074] External timetable data (e.g. Google Calendar)

[1075] Server Operation

[1076] The server retrieves the user's vehicle usage history data from the database, including information such as the distance traveled, the time of use, and the location of use.

[1077] The server obtains the user's external timetable data using the API of Google Calendar or other schedule management tools.

[1078] output

[1079] Acquired mobility usage data and external timetable data

[1080] Specific actions

[1081] For example, the server retrieves vehicle usage data for the past six months from "User A's" database and retrieves future schedule information from "User A's calendar" via an API.

[1082] Step 2: Data analysis

[1083] input

[1084] Acquired mobile usage data

[1085] External timetable data

[1086] Server Operation

[1087] The server preprocesses both sets of data into an input format for the AI ​​model, for example by normalizing the data and extracting features.

[1088] The processed data is input into a generative AI model (e.g., TensorFlow or PyTorch) to learn the user's mobility usage patterns.

[1089] output

[1090] Pre-trained AI model

[1091] Mobile rental schedule forecast results

[1092] Specific actions

[1093] The server preprocesses usage data and schedule data, generates input data such as "Tuesday, 9:00 AM to 12:00 PM patterns," and analyzes it using an AI model.

[1094] Step 3: Schedule proposal

[1095] input

[1096] Mobile rental schedule forecast results

[1097] Server Operation

[1098] Based on the prediction results, a lending schedule suitable for the user is created.

[1099] The server transmits this predicted schedule to the user's terminal.

[1100] Device behavior

[1101] The user's device (smartphone or PC) receives and displays the proposed schedule sent from the server.

[1102] output

[1103] Proposed Lending Schedule

[1104] Specific actions

[1105] The user's smartphone app displays "Next available rental time: Wednesday from 2:00 PM to 5:00 PM."

[1106] Step 4: Review and approve the proposed schedule

[1107] input

[1108] Proposed Lending Schedule

[1109] User Actions

[1110] The user checks the proposed schedule on the terminal and makes corrections as necessary.

[1111] Once the user approves the schedule, the information is sent to the server.

[1112] output

[1113] Revised or approved schedule

[1114] Specific actions

[1115] The user changes the time on their smartphone from "Wednesday 2pm to 5pm" to "Thursday 10am to 1pm" and approves it.

[1116] Step 5: Update your booking management

[1117] input

[1118] Approved Schedule

[1119] Server Operation

[1120] The server updates the reservation system with the approved schedule and updates the database with available rental times.

[1121] output

[1122] Updated booking information

[1123] Specific actions

[1124] The server updates the database information to record that "User A can rent a vehicle from 10:00 AM to 1:00 PM on Thursdays."

[1125] Step 6: Matching the Lending Request

[1126] input

[1127] Lending request from demand side user

[1128] Updated booking information

[1129] Server Operation

[1130] The server receives the demand user's rental request and matches it with the approved schedule.

[1131] Find the best match and schedule to accommodate your request.

[1132] output

[1133] Matching results

[1134] Specific actions

[1135] The server receives a request from user B on the demand side and checks it against the information in the reservation system.

[1136] Step 7: Sending notifications

[1137] input

[1138] Matching results

[1139] Server Operation

[1140] If a match is made, the server sends a notification to the user and the demand user. Notification services such as Firebase and Twilio are used for this process.

[1141] Device behavior

[1142] The user's terminal receives the notification and confirms that the loan has been made.

[1143] output

[1144] Notification of loan completion

[1145] Specific actions

[1146] For example, the server notifies user A and demand user B that a match has been made via Firebase Cloud Messaging, and the device displays the message "Loan confirmed."

[1147] This processing flow enables users to efficiently share vehicles and optimize operations.

[1148] (Application example 1)

[1149] 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."

[1150] To efficiently utilize privately owned vehicles for car sharing using smartphones and other devices, it is essential to predict usage schedules and operate them optimally. However, conventional systems require a great deal of time and effort to manage schedules and operate vehicles. Furthermore, as the use of autonomous vehicles continues to increase, there is a significant lack of systems to properly manage and operate them. Therefore, there is a need for a system that allows privately owned vehicles, especially autonomous vehicles, to be efficiently used for car sharing.

[1151] 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.

[1152] In this invention, the server includes means for acquiring a user's vehicle usage history data, means for acquiring the user's external schedule data, means for analyzing the vehicle usage history data and the external schedule data and learning the user's vehicle usage patterns, means for predicting a vehicle rental schedule, means for proposing the predicted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in a reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, means for confirming the reservation and sharing detailed information, means for moving an autonomous vehicle to a specified time and place based on the approved vehicle rental schedule, and means for remotely operating the autonomous vehicle via a user terminal. This allows efficient management of rental schedules for autonomous vehicles owned by individuals, enabling smooth rental and return to users.

[1153] "User's vehicle usage history data" refers to information such as the time, distance, and location when the user uses the vehicle.

[1154] "External schedule data" is data about the user's schedules and appointments obtained from the calendar or schedule management service used by the user.

[1155] The "vehicle usage pattern" indicates the vehicle usage tendencies and habits analyzed based on the user's past vehicle usage record data and external schedule data.

[1156] The "vehicle rental schedule" is a schedule indicating the dates and times and periods during which a vehicle can be rented.

[1157] A "reservation system" is a system for managing vehicle rental schedules and matching with demand-side users.

[1158] A "demand user" refers to a user who wishes to rent a vehicle.

[1159] An "autonomous vehicle" is a vehicle that can autonomously perform driving operations by itself.

[1160] "Remote control" means controlling the operation and functions of a vehicle using a device such as a smartphone without being physically near the vehicle.

[1161] This invention relates to a system for efficiently using privately owned self-driving vehicles for car sharing. Specific embodiments of this system will be described below.

[1162] System configuration

[1163] The system consists of the following main components: a server, a user terminal, a demand-side user terminal, and an autonomous vehicle.

[1164] 1. Server

[1165] The server is equipped with the following software and data processing means:

[1166] Data collection module: Uses databases and APIs (for external schedules) to obtain user vehicle usage data and external schedule data. Examples include the Google Calendar API and the Time Tree API.

[1167] Analysis and prediction module: Analyzes data using machine learning libraries such as TensorFlow and predicts vehicle rental schedules.

[1168] Reservation management module: Based on the predictions made by the AI ​​model, the module proposes rental schedules to users and updates approved schedules in a cloud-based reservation system, using cloud services such as Firebase and AWS.

[1169] Autonomous driving collaboration module: Uses the autonomous vehicle API to remotely control and move vehicles based on approved schedules.

[1170] 2. User Device

[1171] Notification and schedule management: The smartphone app displays the proposed vehicle rental schedule received from the server and allows the user to confirm and modify it. For example, this applies to iOS and Android apps.

[1172] Remote control: Equipped with the ability to move and remotely control the vehicle.

[1173] 3. Demand-side user terminal

[1174] Request and confirmation: The demand-side user sends a request to rent a vehicle and receives a confirmation of the rental from the server.

[1175] 4. Self-driving vehicles

[1176] Transmission of vehicle operation data: The vehicle itself transmits driving data (e.g., GPS data, usage status) to the server.

[1177] Autonomous driving and remote control: Based on instructions received from the server via API, the autonomous driving function is used to move or return the vehicle.

[1178] Data processing and calculation

[1179] Data collection: The server collects the user's vehicle usage history data and external schedule data via API, which stores past usage history and future schedules in a database.

[1180] Data analysis: TensorFlow is used to analyze collected data and learn vehicle usage patterns, which then predicts the best times and dates for when the vehicle will be available for rental.

[1181] Schedule management: The predicted rental schedule is sent to the user's device, where the user can confirm and modify it, and the final rental schedule is determined. The determined schedule is then reflected in the cloud reservation system and updated as needed.

[1182] Autonomous driving collaboration: Based on the approved rental schedule, an autonomous vehicle will travel to the designated time and location, enabling users and demand users to share vehicles smoothly.

[1183] Specific examples

[1184] If a user has travel plans for the weekend, the plan is registered in advance in the schedule management service. The server retrieves this information and analyzes it along with past usage records. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this prediction to the user, who confirms and approves it. The approved schedule is reflected in the cloud reservation system and is also made public to demand users. When the demand user sends a request, the server performs optimal matching, and ultimately notifies both the user and the demand user.

[1185] Prompt Sentence Examples

[1186] "This app analyzes your vehicle usage data and schedule to suggest the optimal car sharing schedule. What features do you need?"

[1187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1188] Step 1:

[1189] Data collection

[1190] The server retrieves the user's vehicle usage history data from the database and also retrieves external schedule data via an API. Specifically, it uses the Google Calendar API and Time Tree API to collect the user's schedule information. The input at this stage is the vehicle usage history data and external schedule data, and the output is structured data that includes these data.

[1191] Step 2:

[1192] Data analysis

[1193] The server analyzes the collected vehicle usage history data and external schedule data. Using a generative AI model such as TensorFlow, it analyzes this data and learns the user's vehicle usage patterns. The input is the structured data collected in step 1, and the output is the vehicle usage pattern obtained through the analysis and the predicted rental availability time. Specifically, it identifies usage frequency and patterns from past data and predicts the optimal future rental schedule.

[1194] Step 3:

[1195] Schedule proposal

[1196] The server generates an optimal rental schedule based on the analysis results and sends it to the user's device. The user is notified via a smartphone app. A GUI (Graphical User Interface) is displayed on the app, allowing the user to confirm and modify the schedule. The input to this step is the analysis results obtained in step 2, and the output is a proposed schedule sent to the user's device. Specifically, the user confirms the proposed schedule and modifies it as necessary.

[1197] Step 4:

[1198] Schedule Approval

[1199] The user checks the proposed schedule on the terminal, makes any necessary corrections, and then gives final approval. The user's input is the action of checking, correcting, and approving the proposed lending schedule, and the output is the approved lending schedule that is sent to the server. Specifically, when the user clicks the "Approve" button in the application, the changes are uploaded to the server in real time.

[1200] Step 5:

[1201] Schedule updates and booking management

[1202] The server updates the approved rental schedule to the cloud-based reservation system, which updates and publishes the available rental time slots in real time. The input to this step is the approved schedule sent in step 4, and the output is the updated rental schedule in the reservation system. Specifically, the system updates the database in real time to update the published schedule information.

[1203] Step 6:

[1204] Acquiring and matching lending requests

[1205] The server receives rental requests from demand users and matches the requests with the optimal rental schedule. The input to this step is the request data from the demand users, and the output is the optimal matching result. Specifically, when a request is sent, the data is imported into the server in real time, and the AI ​​model automatically matches the optimal rental time with the request.

[1206] Step 7:

[1207] Notification and confirmation

[1208] If a match is made, the server sends a notification to the user and the demand user. Details of the confirmed reservation are sent and can be viewed by both parties in real time. The input to this step is the matching result obtained in step 6, and the output is a notification and reservation details sent to the user and the demand user. Specifically, the notification function is used to send detailed information via push notification or email.

[1209] Step 8:

[1210] Remote control of autonomous vehicles

[1211] The server moves the autonomous vehicle to the specified time and location based on the approved vehicle rental schedule. This allows for smooth rental and return. The input for this step is the approved schedule data, and the output is the movement of the autonomous vehicle or the completion status of remote control. Specifically, the server sends remote control commands for the vehicle using an API, and the vehicle moves as instructed.

[1212] 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.

[1213] This invention is a system for efficiently using privately owned vehicles for car sharing, and by combining it with an emotion engine that recognizes users' emotions, it provides an optimal rental schedule. This system uses an AI model and emotion engine to analyze the user's vehicle usage history data and external schedule data, predict and adjust the vehicle rental schedule, and propose it to the user. The following describes the overall operation flow of the system and a specific example.

[1214] Overall system overview

[1215] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these data into an AI model and emotion engine for analysis. The AI ​​model predicts the time periods when the vehicle is available for rental, and the emotion engine makes adjustments based on the user's emotional state. An optimal rental schedule is proposed to the user, who can then review, approve, or modify it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[1216] Server Operation

[1217] 1. Data collection and analysis

[1218] The server retrieves the user's vehicle usage history data from the database, which includes information such as past mileage, usage time, and usage location.

[1219] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[1220] The server inputs this data into an AI model to learn the user's vehicle usage patterns.

[1221] In addition, an emotion engine is used to collect user emotion data, which is also used for analysis.

[1222] 2. Anticipation and emotion regulation

[1223] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and then the emotion engine adjusts the schedule based on the user's emotional state.

[1224] The predicted schedule is sent by the server to the user's terminal and proposed to the user.

[1225] 3. Reservation management and matching

[1226] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[1227] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[1228] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[1229] Device behavior

[1230] 1. Receiving and checking the schedule

[1231] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[1232] Users can check the proposed schedule on their devices and make corrections as necessary.

[1233] 2. Receiving Notifications

[1234] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[1235] User Actions

[1236] 1. Check and approve the schedule

[1237] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[1238] 2. Loan Management

[1239] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[1240] Specific examples

[1241] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip (for example, the user is likely to be relaxed after the trip). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who can confirm and approve it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs the optimal match and sends notifications to the user and the demand-side user.

[1242] In this way, this system significantly reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[1243] The processing flow will be explained below.

[1244] Program processing flow

[1245] Step 1:

[1246] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[1247] Step 2:

[1248] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[1249] Step 3:

[1250] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[1251] Step 4:

[1252] The server collects user emotion data using an emotion engine, which analyzes the user's emotional state (e.g., stress level, satisfaction level, etc.) obtained from a smartphone or wearable device.

[1253] Step 5:

[1254] The server retrieves the predicted vehicle rental schedule from the AI ​​model, and the emotion engine then adjusts the schedule based on the user's emotional state, optimizing the schedule to accommodate rentals at times that are least stressful for the user.

[1255] Step 6:

[1256] The server sends the adjusted proposed schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[1257] Step 7:

[1258] The user checks the proposed lending schedule on the terminal, modifies the schedule as necessary, and finally approves it. This operation is performed on the terminal.

[1259] Step 8:

[1260] The server receives the schedule that the user has approved or modified, records it as an approved schedule, and reflects this information in the reservation system.

[1261] Step 9:

[1262] The server updates the reservation system with the confirmed available rental times, reflecting the available rental schedule in real time. This information is also made public to users on the demand side.

[1263] Step 10:

[1264] When a rental request arrives at the server from a demand-side user, the server retrieves it and performs optimal matching. The server finds the best match between the request and the schedule.

[1265] Step 11:

[1266] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[1267] Step 12:

[1268] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[1269] Specific examples

[1270] For example, the server retrieves the user's vehicle usage history data (such as past mileage, usage time, and location) from a database. The server then uses an API to extract the user's schedule data from Google Calendar and Time Tree. This data is input into an AI model to learn the user's vehicle usage patterns. The emotion engine collects user emotion data from smartphones and wearable devices and adds this to the analysis.

[1271] The server uses the AI ​​model to predict a vehicle rental schedule and adjusts it based on the user's emotional state through an emotion engine. For example, the schedule may be adjusted to avoid times when the user is likely to feel stressed. The server then sends the adjusted rental schedule to the user's device and notifies them. The user can then check the schedule on their device, modify it as necessary, and approve it.

[1272] The approved schedule is received by the server and updated in the reservation system. When a rental request comes from a demand user, the server performs optimal matching, and if successful, sends a notification to both the user and the demand user to confirm the reservation. In this way, efficient car sharing that takes into account the user's emotional state is realized.

[1273] Example 2

[1274] 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."

[1275] In conventional car sharing systems, vehicle rental schedules are set without taking into account the user's emotional state, which can be inconvenient for users. Furthermore, it is difficult to provide an optimal rental schedule simply by analyzing vehicle usage history data and external schedule data. Therefore, there is a need to improve user satisfaction with vehicle usage.

[1276] 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 acquiring vehicle usage history data of the user, means for acquiring external schedule data of the user, means for analyzing the vehicle usage history data and the external schedule data using an AI model to learn the user's vehicle usage pattern, means for collecting user emotion data using an emotion engine and using the collected data for analysis, means for predicting a vehicle rental schedule and adjusting it based on the user's emotional state, means for proposing the predicted and adjusted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in the reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, and means for confirming the reservation and sharing detailed information. This makes it possible to provide an optimal vehicle rental schedule that takes the user's emotional state into consideration.

[1277] "Vehicle usage history data" is data about how a user has used a vehicle in the past, and includes information such as mileage, usage time, and usage location.

[1278] "External schedule data" is data obtained from an external schedule management system that manages the user's schedule, and includes information obtained from Google Calendar, Time Tree, etc.

[1279] An "AI model" is software that uses machine learning algorithms to analyze data and identify patterns and predictions.

[1280] An "emotion engine" is a system or software for analyzing a user's emotional state, collecting and analyzing emotional data from social media posts, biometric data, etc.

[1281] The "vehicle rental schedule" is a schedule indicating the time periods during which a vehicle can be rented, and is predicted based on the user's vehicle usage history data and external schedule data.

[1282] "Prediction" is the act of estimating future vehicle usage patterns and rental availability times based on collected data.

[1283] "Adjustment" is the process of optimizing a predicted schedule by taking into account the user's emotional state and other factors.

[1284] "Proposal" is the act of presenting a predicted and adjusted vehicle rental schedule to a user.

[1285] "Approval" is an action in which the user agrees with the proposed vehicle rental schedule, and the result is reflected in the system.

[1286] The "reservation system" is a system that manages vehicle rental reservations, updates schedules, and confirms reservations.

[1287] A "demand user" is a user who wishes to rent a vehicle for use.

[1288] "Matching" is the act of optimally matching the demand user's request with the vehicle's available rental time.

[1289] "Notifications" are messages that inform users of information such as reservations and schedule changes.

[1290] "Detailed information" indicates specific information about the reservation contents and schedule.

[1291] This invention is a system for efficiently using privately owned vehicles for car sharing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides an optimal rental schedule. The overall operation flow of this system and a specific example are shown below.

[1292] System Overview

[1293] This system acquires historical vehicle usage data for users and their external schedule data. These data are input into a generative AI model and emotion engine for analysis. The generative AI model uses TensorFlow and PyTorch to learn users' vehicle usage patterns and predict the time periods when vehicles are available for rental. The emotion engine uses, for example, IBM Watson's emotion analysis API to collect user emotion data and use it for analysis. The resulting predicted schedule is proposed to the user, who then approves it. The approved schedule is updated in the reservation system and matched with rental requests from demand users. If the rental is confirmed, the server sends a notification to the user and the demand user, and the reservation is confirmed.

[1294] Server Operation

[1295] 1. The server retrieves the user's vehicle usage history data from the database. The data indicates how the user has used the vehicle in the past, including the mileage, usage time, and location of use.

[1296] 2. The server then retrieves external schedule data, such as Google Calendar or Time Tree, through an API. The external schedule data contains the user's upcoming events.

[1297] 3. The server inputs this data into a generative AI model, which uses TensorFlow and PyTorch to learn the user's vehicle usage patterns.

[1298] 4. The server uses an emotion engine to collect and analyze the user's emotion data. The emotion engine uses, for example, IBM Watson's emotion analysis API. This allows it to analyze emotions from the user's social media posts and other biometric sensor data.

[1299] 5. The generative AI model predicts the user's vehicle rental schedule, taking into account the user's historical usage patterns and external schedule data.

[1300] 6. The emotion engine adjusts the predicted schedule based on the user's emotional state, for example, avoiding rentals during times when the user is feeling stressed.

[1301] 7. The server sends the predicted and adjusted schedule to the user's device, allowing the user to review the proposed schedule.

[1302] 8. Once approval is received from the user, the server updates this schedule into the reservation system, which reflects available rental times in real time.

[1303] 9. The server receives the rental request from the demand user and matches it with the schedule. When the optimal match is found, the rental is completed.

[1304] 10. If the rental is successful, the server sends a notification to the user and the demand user and confirms the reservation.

[1305] Device behavior

[1306] 1. The terminal receives the proposed schedule sent from the server. The user can check the proposed schedule on the terminal and modify it if necessary.

[1307] 2. If the rental is successful, the device receives a notification from the server and displays the reservation details.

[1308] User Actions

[1309] 1. The user checks the proposed schedule on the device and modifies it if necessary. When the user finally approves the schedule, the information is sent to the server.

[1310] 2. The user receives a notification sent from the server and checks the details of the confirmed reservation, enabling smooth rental management.

[1311] Examples and prompts

[1312] Specific examples

[1313] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip. Based on this information, the server uses the emotion engine to adjust the schedule predicted by the generative AI model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs optimal matching and sends notifications to the user and the demand-side user.

[1314] Prompt Sentence Examples

[1315] Create optimal rental schedules based on user vehicle usage history data and external schedule data. Also take into account emotion engine data. For example:

[1316] Usage data: mileage, usage time, and location for the past month

[1317] External schedule data: Google Calendar, TimeTree events

[1318] Emotion Engine Data: High stress before travel, relaxed after travel

[1319] As a result, suggest a post-trip loan schedule.

[1320] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[1321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1322] Step 1:

[1323] The server retrieves the user's vehicle usage history data from the database. Input includes mileage, usage time, and usage location. By retrieving this data, basic information can be obtained to understand the user's past vehicle usage patterns. The output is the retrieved vehicle usage history data.

[1324] Step 2:

[1325] The server retrieves the user's external schedule data from Google Calendar or TimeTree through an API. The input includes the user's authentication information and the calendar service's API endpoint, allowing you to leverage the user's upcoming events. The output is the retrieved external schedule data.

[1326] Step 3:

[1327] The server inputs vehicle usage history data and external schedule data into the generative AI model. The input includes the data obtained in Step 1 and Step 2. This allows the AI ​​model to learn the user's vehicle usage patterns. As a specific example, TensorFlow or PyTorch can be used. The output is the result of analyzing the user's vehicle usage patterns.

[1328] Step 4:

[1329] The server uses an emotion engine to collect and analyze user emotion data. Inputs include social media posts and biometric sensor data. For example, IBM Watson's emotion analysis API can be used. The output is user emotion data.

[1330] Step 5:

[1331] The generative AI model predicts the user's vehicle rental schedule. The input includes the user's vehicle usage pattern obtained in step 3 and the emotion data obtained in step 4. This creates the user's vehicle rental schedule. The output is the predicted vehicle rental schedule.

[1332] Step 6:

[1333] The emotion engine adjusts the predicted schedule based on the user's emotional state. The input includes the schedule predicted in step 5 and emotion data. This creates a schedule that takes the user's emotional state into account. The output is the adjusted vehicle rental schedule.

[1334] Step 7:

[1335] The server sends the adjusted schedule to the user's terminal. The input includes the vehicle rental schedule adjusted in step 6. The terminal displays the proposed schedule. The output is the schedule proposal to the user.

[1336] Step 8:

[1337] The user reviews the proposed schedule on the terminal and modifies it if necessary. The input includes the vehicle rental schedule received in step 7, which allows the user to approve or modify the schedule. The output is the schedule approved or modified by the user.

[1338] Step 9:

[1339] The server receives approval from the user and updates this schedule to the reservation system. The input includes the approved or modified schedule from step 8. The reservation system updates the available rental slots in real time. The output is the updated reservation information.

[1340] Step 10:

[1341] The server receives the rental request from the demand user and matches it with the schedule. The input includes the demand user's request and the reservation information updated in step 9. When the best match is found, the rental is established. The output is the matching result.

[1342] Step 11:

[1343] If the rental is successful, the server sends a notification to the user and the demand user to confirm the reservation. The input includes the matching result determined in step 10. The terminal receives the notification and displays the reservation details. The output is the confirmed reservation information and notification.

[1344] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[1345] (Application example 2)

[1346] 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."

[1347] Conventional car sharing systems have a problem in that efficient matching between vehicle users and those seeking to rent a vehicle is difficult because the vehicle rental schedule is not sufficiently optimized. In addition, because the system does not take into account the user's emotional state, there is a high possibility that schedules that cause stress to the user are proposed. This may result in a decrease in satisfaction with the car sharing system.

[1348] The specific processing by the specific 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 acquiring the user's vehicle usage history data, means for acquiring the user's external schedule data, and means for acquiring the user's emotional data and adjusting the rental schedule based on the user's emotional state. This makes it possible to analyze the user's vehicle usage history data and external schedule data, predict an optimal vehicle rental schedule, and adjust the schedule according to the user's emotional state. This makes it possible to realize efficient vehicle rental and improve user satisfaction.

[1349] "User's vehicle usage history data" refers to historical information about the user's past use of their own vehicle, specifically data such as mileage, usage time, and usage location.

[1350] "User's external schedule data" refers to external schedule information that may affect the user's use of the vehicle, such as schedule and event information obtained from a calendar service.

[1351] "Emotion data" refers to information that indicates the user's internal emotional state, specifically data that has been acquired by digitizing emotions such as stress, relaxation, and happiness.

[1352] "Means for adjusting the rental schedule based on emotional state" refers to a method for optimizing the schedule based on the acquired emotional data to ensure the least stressful and comfortable vehicle rental experience for the user.

[1353] "Proposed vehicle rental schedule" refers to the predicted rental itinerary that the system presents to the user after analysis and sentiment adjustment has been performed.

[1354] "Reservation System" refers to the computer system used by Users and Demand-Side Users to manage and confirm reservations for vehicle rentals.

[1355] "Demand-side user" refers to a user who wishes to rent a vehicle through a car sharing service.

[1356] "Matching" refers to the process of optimally combining the schedule of a user who wants to rent a vehicle with the request of a demand-side user who wants to rent a vehicle.

[1357] "Means for sending notifications" refers to the method by which schedule and reservation confirmation information is sent electronically to users and demand users, typically via a smartphone or PC application.

[1358] "Means for sharing detailed information" refers to a method for providing specific information about the vehicle rental to both the user and the demand-side user after the reservation is confirmed.

[1359] System Overview

[1360] This invention is a system for food delivery services that provides optimal delivery plans that take into account delivery personnel's schedule management and emotional state. This system collects delivery personnel's past delivery performance data and external schedule data, analyzes them using an AI model and an emotion engine, and predicts and adjusts delivery schedules and proposes them to delivery personnel.

[1361] Server Operation

[1362] 1. Data collection and analysis

[1363] The server retrieves the delivery personnel's past delivery performance data from the database. This data includes past delivery times, distances, delivery destinations, etc. It also uses an API to retrieve external schedule data. This allows the server to understand what the delivery personnel have scheduled at what time.

[1364] Furthermore, an emotion engine is used to collect emotional data from delivery personnel, and the emotional data is used for analysis, for example, to detect whether the emotional state is stressed or relaxed.

[1365] 2. Anticipation and emotion regulation

[1366] The AI ​​model predicts delivery schedules based on collected data, and an emotion engine then adjusts the schedule based on the driver's emotional state. For example, if a driver is stressed, the system may increase their break time.

[1367] The predicted and adjusted schedule is sent by the server to the delivery person's terminal and proposed to the delivery person.

[1368] 3. Reservation management and matching

[1369] Once the delivery person approves the schedule, this information is sent to the server and reflected in the reservation system, which updates available delivery times in real time.

[1370] Upon receiving a delivery request from a demand user, the server performs optimal matching to find the best match between the schedule and the request.

[1371] If a match is made, the server sends a notification to the delivery person and the demand user and confirms the reservation.

[1372] Device behavior

[1373] 1. Receiving and checking the schedule

[1374] The delivery person's device (smartphone or PC) receives the proposed delivery schedule sent from the server. The delivery person can check the proposed schedule on the device and modify it as necessary.

[1375] 2. Receiving Notifications

[1376] When a match is made and a delivery is confirmed, a notification is sent to the delivery person's device, which displays the delivery details and allows them to act according to the confirmed schedule.

[1377] User Actions

[1378] 1. Check and approve the schedule

[1379] The delivery person can review the proposed schedule on their device, modify it if necessary, and finally approve the schedule, which is then sent to the server.

[1380] 2. Managing deliveries

[1381] The delivery person receives the notification sent from the server and checks the details of the confirmed delivery, which allows the delivery person to smoothly manage their delivery work.

[1382] Specific examples

[1383] For example, if a delivery person has a meeting at 9:00 AM, the system retrieves that schedule information from the API. At the same time, the emotion engine recognizes the person's current stress level (they are likely nervous before the meeting). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determine that deliveries are possible at 10:00 AM after the meeting and at 3:00 PM. This predicted and adjusted schedule is proposed to the delivery person, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is made available to demand-side users.

[1384] When a request is sent from a demand user, the server performs optimal matching and sends a notification to the delivery person and the demand user.

[1385] Example prompt sentence:

[1386] We provide schedule and sentiment data, including: Use this to predict optimal delivery schedules and adjust them based on sentiment.

[1387] Schedule data: [{'date': '2023-01-01', 'event': 'meeting', 'time': '10:00'}, {'date': '2023-01-02', 'event': 'shopping', 'time': '12:00'}]

[1388] Emotion data: ['neutral', 'stress']

[1389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1390] Step 1:

[1391] Data Collection

[1392] The server first retrieves the delivery person's past delivery performance data from the database. Here, it uses a database query to obtain information such as past delivery times, distances, and delivery destinations. It also uses an API to obtain the delivery person's external schedule data and retrieves appointment and event information from a calendar service. The inputs are the delivery person's ID and query conditions, and the output is delivery performance data and schedule data.

[1393] Step 2:

[1394] Acquiring emotion data

[1395] The server uses an emotion engine to obtain the delivery person's emotional data. Specifically, the server inputs the delivery person's recent activities and feedback into the emotion analysis API to obtain data on their emotional state (stress, relaxation, happiness, etc.). The input is the delivery person's recent activity information, and the output is emotional data.

[1396] Step 3:

[1397] Prediction by AI model

[1398] The server inputs the delivery performance data and schedule data acquired in step 1 into the AI ​​model and predicts the optimal delivery schedule. The AI ​​model learns delivery patterns from past data and predicts future available delivery times. The inputs are delivery performance data and schedule data, and the output is a predicted delivery schedule.

[1399] Step 4:

[1400] emotional regulation

[1401] The server adjusts the predicted delivery schedule in step 3 based on the emotional data acquired in step 2. The emotion engine analyzes the emotional state of the delivery person and makes adjustments such as extending the interval between deliveries if the person is under high stress. The inputs are the predicted delivery schedule and emotional data, and the output is an adjusted delivery schedule.

[1402] Step 5:

[1403] Schedule proposal

[1404] The server sends the adjusted delivery schedule from step 4 to the delivery person's terminal and proposes it. The terminal receives the schedule sent from the server and presents it to the delivery person. The user checks the proposed schedule through the terminal and makes any necessary corrections. The input is the adjusted delivery schedule, and the output is the proposed schedule for the delivery person.

[1405] Step 6:

[1406] Schedule Approval

[1407] The user reviews the proposed schedule on the device and gives final approval. The device then sends the information to the server. The input is the delivery driver's feedback, and the output is the final approved schedule.

[1408] Step 7:

[1409] Updates to the reservation system

[1410] The server updates the reservation system with the approved delivery schedule, which reflects available delivery times in real time. The input is the final approved schedule, and the output is the updated schedule in the reservation system.

[1411] Step 8:

[1412] matching

[1413] The server receives delivery requests from users on the demand side and performs optimal matching. The AI ​​model analyzes demand and supply data and combines the most suitable schedule with the request. The inputs are the delivery request and available delivery schedule, and the output is the matching result.

[1414] Step 9:

[1415] Sending notifications

[1416] If a match is made, the server sends a notification to the delivery person and the demand user. The terminal receives the notification sent from the server and displays detailed information. The input is the matching result, and the output is the notification sent to the delivery person and the demand user.

[1417] Step 10:

[1418] Share details

[1419] After the reservation is confirmed, the server shares detailed information about the delivery with the delivery person and the demand user. The terminal receives the detailed information sent from the server and displays the delivery contents, time, etc. The input is the reservation confirmation information, and the output is the detailed information shared between the delivery person and the demand user.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] [Fourth embodiment]

[1424] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1425] 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.

[1426] 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).

[1427] 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.

[1428] 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.

[1429] 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).

[1430] 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. 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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."

[1437] This invention is a system for efficiently using privately owned vehicles for car sharing. This system uses an AI model to predict vehicle rental schedules based on vehicle usage history data and external schedule data, and proposes them to users. The following describes the overall operation flow of the system and a specific example.

[1438] Overall system overview

[1439] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these into an AI model for analysis. The AI ​​model predicts the time periods when the vehicle can be rented and proposes them to the user. The user confirms and modifies the proposed schedule, and finally approves it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[1440] Server Operation

[1441] 1. Data collection and analysis

[1442] The server retrieves the user's vehicle usage history data from the database, including information such as mileage, usage time, and usage location.

[1443] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[1444] The server inputs the collected data into an AI model to learn the user's vehicle usage patterns.

[1445] 2. Predictions and proposals

[1446] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and this predicted schedule is sent to the user's device by the server and proposed to the user.

[1447] 3. Reservation management and matching

[1448] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[1449] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[1450] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[1451] Device behavior

[1452] 1. Receiving and checking the schedule

[1453] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[1454] Users can check the proposed schedule on their devices and make corrections as necessary.

[1455] 2. Receiving Notifications

[1456] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[1457] User Actions

[1458] 1. Check and approve the schedule

[1459] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[1460] 2. Loan Management

[1461] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[1462] Specific examples

[1463] For example, if a user has travel plans for the weekend, the schedule information is registered in Google Calendar or Time Tree. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to demand users. When the demand user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand user.

[1464] In this way, this system significantly reduces the user's workload and realizes efficient car sharing.

[1465] The processing flow will be explained below.

[1466] Program processing flow

[1467] Step 1:

[1468] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[1469] Step 2:

[1470] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[1471] Step 3:

[1472] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[1473] Step 4:

[1474] The server retrieves the vehicle rental schedule predicted by the AI ​​model, which includes the dates, times, and times when the vehicle is available for rental.

[1475] Step 5:

[1476] The server then performs optimization based on the predicted schedule and generates an optimal lending schedule. It also combines lending demand data to create a schedule tailored to times of high demand.

[1477] Step 6:

[1478] The server sends the proposed rental schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[1479] Step 7:

[1480] The user checks the proposed lending schedule on the terminal and makes any necessary corrections. The user then checks the details of the schedule and approves or corrects it.

[1481] Step 8:

[1482] The server receives the schedule that the user has approved or modified, records it as the final approved schedule, and reflects it in the reservation system.

[1483] Step 9:

[1484] The server updates the confirmed available rental time in the reservation system, and reflects the available rental schedule in real time.

[1485] Step 10:

[1486] When a rental request arrives at the server from a user on the demand side, the server retrieves it and performs optimal matching, finding the best match between the request and the schedule.

[1487] Step 11:

[1488] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[1489] Step 12:

[1490] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[1491] The above are the specific steps in the processing flow of the system.

[1492] Example 1

[1493] 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."

[1494] In modern society, improving the utilization efficiency of mobility (e.g., vehicles) is an important issue. Sharing privately owned mobility can reduce the burden on the environment and increase economic efficiency. However, if schedules are created without taking into account users' mobility usage patterns and external timetable data, utilization efficiency may decrease. In addition, it is a significant effort for users to manually adjust their own schedules. Therefore, automatic prediction and matching of mobility rental schedules is required.

[1495] 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.

[1496] In this invention, the server includes means for acquiring user's mobile device usage history data, means for acquiring user's external timetable data, means for analyzing the mobile device usage history data and the external timetable data and learning the user's mobile device usage patterns, means for using a generative AI model to predict a mobile device rental schedule, means for proposing the predicted mobile device rental schedule to the user, means for receiving approval of the proposed mobile device rental schedule from the user, means for updating the approved mobile device rental schedule in a reservation system, means for acquiring rental requests from demand-side users and matching them with rental schedules, means for sending notifications to the user and demand-side users when rental is confirmed, and means for confirming reservations and sharing detailed information. This eliminates the need for users to manually adjust their schedules and enables automatic optimization of mobile device rental schedules.

[1497] "User" means an individual or legal entity that owns a vehicle and provides that vehicle to the car sharing system.

[1498] "Mobile object" refers to a means of transportation, such as a vehicle, that is owned and available for rent by a User.

[1499] "Usage history data" refers to information about how a user has used a vehicle in the past, including data such as distance traveled, time of use, and location of use.

[1500] "External Timetable Data" refers to data about a user's schedule and event information obtained through Google Calendar or other schedule management tools.

[1501] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and predict future mobility usage patterns.

[1502] "Proposal" is an operation in which the server sends the predicted rental schedule of the mobile object to the user terminal and asks the user to confirm or modify it.

[1503] "Approval" means that the user reviews and ultimately agrees to the proposed lending schedule.

[1504] "Reservation System" means a system for recording approved vehicle rental schedules and managing rental status.

[1505] A "demand user" is an individual or a corporation that wishes to use a mobile unit on a rental basis.

[1506] "Matching" refers to the process of matching the demand user's lending request with the lending schedule approved by the user to find the optimal combination.

[1507] "Notification" is a message to convey important information such as the completion of a loan or a schedule change to users and demand-side users.

[1508] "Detailed information" refers to specific details regarding the rental status and schedule, and is information shared with users and demand-side users.

[1509] An "information terminal" is a device used by a user to check the proposed lending schedule and approve or modify it, and includes a smartphone, PC, etc.

[1510] This invention is a system for efficiently sharing privately owned vehicles (e.g., cars). The system uses an AI model to predict vehicle rental schedules based on users' vehicle usage history data and external timetable data, and proposes them to users. After obtaining users' approval, the system matches the optimized schedule with users on the demand side, realizing efficient vehicle sharing.

[1511] Server Operation

[1512] 1. Data Collection

[1513] The server first retrieves the user's transportation usage history data from the database. This data consists of the vehicle's mileage, usage time, and usage location. Next, the server uses an API to collect external timetable data. This data includes the user's schedule and event information from Google Calendar and other schedule management tools.

[1514] 2. Data Analysis

[1515] The server preprocesses the collected data and inputs it into an AI model (using TensorFlow or PyTorch, for example), which learns the user's vehicle usage patterns and predicts the vehicle rental schedule based on this.

[1516] 3. Schedule proposal

[1517] The predicted schedule is sent from the server to the user's device, where the user can review the proposed schedule and make any necessary adjustments.

[1518] 4. Approval of forecast schedule

[1519] After the user approves the proposed schedule, it is sent to the server, which updates the reservation system with the approved schedule, reflecting available rental times in real time.

[1520] 5. Reservation management and matching

[1521] When a rental request is received from a demand user, the server performs optimal matching. The server selects the best match between the schedule and the request, and sends a notification to the user and the demand user if the rental is successful.

[1522] Device behavior

[1523] 1. Receiving and checking the schedule

[1524] The user's terminal receives and displays the mobile rental schedule sent from the server. The user can check the proposed schedule on the terminal and make corrections as necessary.

[1525] 2. Receiving Notifications

[1526] If the rental is successful, a notification is sent to the user's terminal and the reservation details are displayed.

[1527] User Actions

[1528] 1. Check and approve the schedule

[1529] The user can check the proposed schedule on the terminal and make any necessary corrections. When the user finally approves the schedule, the information is sent to the server.

[1530] 2. Loan Management

[1531] The user can receive a notification sent from the server and check the details of the confirmed reservation, which allows the user to smoothly manage the rental of the mobile object.

[1532] Specific examples

[1533] For example, if a user has a trip planned for the weekend, the schedule information is registered in Google Calendar. The server obtains this information and analyzes it using an AI model along with past usage data. As a result of this analysis, it predicts that a vehicle will be available for rental during the time period after the trip ends. The server proposes this predicted schedule to the user, who then confirms and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When the demand-side user sends a request, the server performs the optimal match, and ultimately notifies both the user and the demand-side user.

[1534] Prompt Sentence Examples

[1535] "If a user has scheduled this weekend in their Google Calendar, predict the available rental times based on past vehicle usage data and output the suggested schedule."

[1536] This system saves users the trouble of manually adjusting their schedules and enables efficient vehicle rental.

[1537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1538] Step 1: Data collection

[1539] input

[1540] User mobility usage data

[1541] External timetable data (e.g. Google Calendar)

[1542] Server Operation

[1543] The server retrieves the user's vehicle usage history data from the database, including information such as the distance traveled, the time of use, and the location of use.

[1544] The server obtains the user's external timetable data using the API of Google Calendar or other schedule management tools.

[1545] output

[1546] Acquired mobility usage data and external timetable data

[1547] Specific actions

[1548] For example, the server retrieves vehicle usage data for the past six months from "User A's" database and retrieves future schedule information from "User A's calendar" via an API.

[1549] Step 2: Data analysis

[1550] input

[1551] Acquired mobile usage data

[1552] External timetable data

[1553] Server Operation

[1554] The server preprocesses both sets of data into an input format for the AI ​​model, for example by normalizing the data and extracting features.

[1555] The processed data is input into a generative AI model (e.g., TensorFlow or PyTorch) to learn the user's mobility usage patterns.

[1556] output

[1557] Pre-trained AI model

[1558] Mobile rental schedule forecast results

[1559] Specific actions

[1560] The server preprocesses usage data and schedule data, generates input data such as "Tuesday, 9:00 AM to 12:00 PM patterns," and analyzes it using an AI model.

[1561] Step 3: Schedule proposal

[1562] input

[1563] Mobile rental schedule forecast results

[1564] Server Operation

[1565] Based on the prediction results, a lending schedule suitable for the user is created.

[1566] The server transmits this predicted schedule to the user's terminal.

[1567] Device behavior

[1568] The user's device (smartphone or PC) receives and displays the proposed schedule sent from the server.

[1569] output

[1570] Proposed Lending Schedule

[1571] Specific actions

[1572] The user's smartphone app displays "Next available rental time: Wednesday from 2:00 PM to 5:00 PM."

[1573] Step 4: Review and approve the proposed schedule

[1574] input

[1575] Proposed Lending Schedule

[1576] User Actions

[1577] The user checks the proposed schedule on the terminal and makes corrections as necessary.

[1578] Once the user approves the schedule, the information is sent to the server.

[1579] output

[1580] Revised or approved schedule

[1581] Specific actions

[1582] The user changes the time on their smartphone from "Wednesday 2pm to 5pm" to "Thursday 10am to 1pm" and approves it.

[1583] Step 5: Update your booking management

[1584] input

[1585] Approved Schedule

[1586] Server Operation

[1587] The server updates the reservation system with the approved schedule and updates the database with available rental times.

[1588] output

[1589] Updated booking information

[1590] Specific actions

[1591] The server updates the database information to record that "User A can rent a vehicle from 10:00 AM to 1:00 PM on Thursdays."

[1592] Step 6: Matching the Lending Request

[1593] input

[1594] Lending request from demand side user

[1595] Updated booking information

[1596] Server Operation

[1597] The server receives the demand user's rental request and matches it with the approved schedule.

[1598] Find the best match and schedule to accommodate your request.

[1599] output

[1600] Matching results

[1601] Specific actions

[1602] The server receives a request from user B on the demand side and checks it against the information in the reservation system.

[1603] Step 7: Sending notifications

[1604] input

[1605] Matching results

[1606] Server Operation

[1607] If a match is made, the server sends a notification to the user and the demand user. Notification services such as Firebase and Twilio are used for this process.

[1608] Device behavior

[1609] The user's terminal receives the notification and confirms that the loan has been made.

[1610] output

[1611] Notification of loan completion

[1612] Specific actions

[1613] For example, the server notifies user A and demand user B that a match has been made via Firebase Cloud Messaging, and the device displays the message "Loan confirmed."

[1614] This processing flow enables users to efficiently share vehicles and optimize operations.

[1615] (Application example 1)

[1616] 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."

[1617] To efficiently utilize privately owned vehicles for car sharing using smartphones and other devices, it is essential to predict usage schedules and operate them optimally. However, conventional systems require a great deal of time and effort to manage schedules and operate vehicles. Furthermore, as the use of autonomous vehicles continues to increase, there is a significant lack of systems to properly manage and operate them. Therefore, there is a need for a system that allows privately owned vehicles, especially autonomous vehicles, to be efficiently used for car sharing.

[1618] 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.

[1619] In this invention, the server includes means for acquiring a user's vehicle usage history data, means for acquiring the user's external schedule data, means for analyzing the vehicle usage history data and the external schedule data and learning the user's vehicle usage patterns, means for predicting a vehicle rental schedule, means for proposing the predicted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in a reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, means for confirming the reservation and sharing detailed information, means for moving an autonomous vehicle to a specified time and place based on the approved vehicle rental schedule, and means for remotely operating the autonomous vehicle via a user terminal. This allows efficient management of rental schedules for autonomous vehicles owned by individuals, enabling smooth rental and return to users.

[1620] "User's vehicle usage history data" refers to information such as the time, distance, and location when the user uses the vehicle.

[1621] "External schedule data" is data about the user's schedules and appointments obtained from the calendar or schedule management service used by the user.

[1622] The "vehicle usage pattern" indicates the vehicle usage tendencies and habits analyzed based on the user's past vehicle usage record data and external schedule data.

[1623] The "vehicle rental schedule" is a schedule indicating the dates and times and periods during which a vehicle can be rented.

[1624] A "reservation system" is a system for managing vehicle rental schedules and matching with demand-side users.

[1625] A "demand user" refers to a user who wishes to rent a vehicle.

[1626] An "autonomous vehicle" is a vehicle that can autonomously perform driving operations by itself.

[1627] "Remote control" means controlling the operation and functions of a vehicle using a device such as a smartphone without being physically near the vehicle.

[1628] This invention relates to a system for efficiently using privately owned self-driving vehicles for car sharing. Specific embodiments of this system will be described below.

[1629] System configuration

[1630] The system consists of the following main components: a server, a user terminal, a demand-side user terminal, and an autonomous vehicle.

[1631] 1. Server

[1632] The server is equipped with the following software and data processing means:

[1633] Data collection module: Uses databases and APIs (for external schedules) to obtain user vehicle usage data and external schedule data. Examples include the Google Calendar API and the Time Tree API.

[1634] Analysis and prediction module: Analyzes data using machine learning libraries such as TensorFlow and predicts vehicle rental schedules.

[1635] Reservation management module: Based on the predictions made by the AI ​​model, the module proposes rental schedules to users and updates approved schedules in a cloud-based reservation system, using cloud services such as Firebase and AWS.

[1636] Autonomous driving collaboration module: Uses the autonomous vehicle API to remotely control and move vehicles based on approved schedules.

[1637] 2. User Device

[1638] Notification and schedule management: The smartphone app displays the proposed vehicle rental schedule received from the server and allows the user to confirm and modify it. For example, this applies to iOS and Android apps.

[1639] Remote control: Equipped with the ability to move and remotely control the vehicle.

[1640] 3. Demand-side user terminal

[1641] Request and confirmation: The demand-side user sends a request to rent a vehicle and receives a confirmation of the rental from the server.

[1642] 4. Self-driving vehicles

[1643] Transmission of vehicle operation data: The vehicle itself transmits driving data (e.g., GPS data, usage status) to the server.

[1644] Autonomous driving and remote control: Based on instructions received from the server via API, the autonomous driving function is used to move or return the vehicle.

[1645] Data processing and calculation

[1646] Data collection: The server collects the user's vehicle usage history data and external schedule data via API, which stores past usage history and future schedules in a database.

[1647] Data analysis: TensorFlow is used to analyze collected data and learn vehicle usage patterns, which then predicts the best times and dates for when the vehicle will be available for rental.

[1648] Schedule management: The predicted rental schedule is sent to the user's device, where the user can confirm and modify it, and the final rental schedule is determined. The determined schedule is then reflected in the cloud reservation system and updated as needed.

[1649] Autonomous driving collaboration: Based on the approved rental schedule, an autonomous vehicle will travel to the designated time and location, enabling users and demand users to share vehicles smoothly.

[1650] Specific examples

[1651] If a user has travel plans for the weekend, the plan is registered in advance in the schedule management service. The server retrieves this information and analyzes it along with past usage records. As a result of this analysis, it predicts that a vehicle will be available for rental during the time the trip ends. The server proposes this prediction to the user, who confirms and approves it. The approved schedule is reflected in the cloud reservation system and is also made public to demand users. When the demand user sends a request, the server performs optimal matching, and ultimately notifies both the user and the demand user.

[1652] Prompt Sentence Examples

[1653] "This app analyzes your vehicle usage data and schedule to suggest the optimal car sharing schedule. What features do you need?"

[1654] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1655] Step 1:

[1656] Data collection

[1657] The server retrieves the user's vehicle usage history data from the database and also retrieves external schedule data via an API. Specifically, it uses the Google Calendar API and Time Tree API to collect the user's schedule information. The input at this stage is the vehicle usage history data and external schedule data, and the output is structured data that includes these data.

[1658] Step 2:

[1659] Data analysis

[1660] The server analyzes the collected vehicle usage history data and external schedule data. Using a generative AI model such as TensorFlow, it analyzes this data and learns the user's vehicle usage patterns. The input is the structured data collected in step 1, and the output is the vehicle usage pattern obtained through the analysis and the predicted rental availability time. Specifically, it identifies usage frequency and patterns from past data and predicts the optimal future rental schedule.

[1661] Step 3:

[1662] Schedule proposal

[1663] The server generates an optimal rental schedule based on the analysis results and sends it to the user's device. The user is notified via a smartphone app. A GUI (Graphical User Interface) is displayed on the app, allowing the user to confirm and modify the schedule. The input to this step is the analysis results obtained in step 2, and the output is a proposed schedule sent to the user's device. Specifically, the user confirms the proposed schedule and modifies it as necessary.

[1664] Step 4:

[1665] Schedule Approval

[1666] The user checks the proposed schedule on the terminal, makes any necessary corrections, and then gives final approval. The user's input is the action of checking, correcting, and approving the proposed lending schedule, and the output is the approved lending schedule that is sent to the server. Specifically, when the user clicks the "Approve" button in the application, the changes are uploaded to the server in real time.

[1667] Step 5:

[1668] Schedule updates and booking management

[1669] The server updates the approved rental schedule to the cloud-based reservation system, which updates and publishes the available rental time slots in real time. The input to this step is the approved schedule sent in step 4, and the output is the updated rental schedule in the reservation system. Specifically, the system updates the database in real time to update the published schedule information.

[1670] Step 6:

[1671] Acquiring and matching lending requests

[1672] The server receives rental requests from demand users and matches the requests with the optimal rental schedule. The input to this step is the request data from the demand users, and the output is the optimal matching result. Specifically, when a request is sent, the data is imported into the server in real time, and the AI ​​model automatically matches the optimal rental time with the request.

[1673] Step 7:

[1674] Notification and confirmation

[1675] If a match is made, the server sends a notification to the user and the demand user. Details of the confirmed reservation are sent and can be viewed by both parties in real time. The input to this step is the matching result obtained in step 6, and the output is a notification and reservation details sent to the user and the demand user. Specifically, the notification function is used to send detailed information via push notification or email.

[1676] Step 8:

[1677] Remote control of autonomous vehicles

[1678] The server moves the autonomous vehicle to the specified time and location based on the approved vehicle rental schedule. This allows for smooth rental and return. The input for this step is the approved schedule data, and the output is the movement of the autonomous vehicle or the completion status of remote control. Specifically, the server sends remote control commands for the vehicle using an API, and the vehicle moves as instructed.

[1679] 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.

[1680] This invention is a system for efficiently using privately owned vehicles for car sharing, and by combining it with an emotion engine that recognizes users' emotions, it provides an optimal rental schedule. This system uses an AI model and emotion engine to analyze the user's vehicle usage history data and external schedule data, predict and adjust the vehicle rental schedule, and propose it to the user. The following describes the overall operation flow of the system and a specific example.

[1681] Overall system overview

[1682] This system acquires historical usage data for vehicles owned by users and their external schedule data, and inputs these data into an AI model and emotion engine for analysis. The AI ​​model predicts the time periods when the vehicle is available for rental, and the emotion engine makes adjustments based on the user's emotional state. An optimal rental schedule is proposed to the user, who can then review, approve, or modify it. This approved schedule is then reflected in the reservation system, and is matched with rental requests from demand-side users. If the rental is successful, the server sends a notification to the user and the demand-side user, and the reservation is confirmed.

[1683] Server Operation

[1684] 1. Data collection and analysis

[1685] The server retrieves the user's vehicle usage history data from the database, which includes information such as past mileage, usage time, and usage location.

[1686] The server then uses APIs to retrieve the user's external schedule data from Google Calendar or Time Tree.

[1687] The server inputs this data into an AI model to learn the user's vehicle usage patterns.

[1688] In addition, an emotion engine is used to collect user emotion data, which is also used for analysis.

[1689] 2. Anticipation and emotion regulation

[1690] The AI ​​model predicts the vehicle rental schedule based on the analysis results, and then the emotion engine adjusts the schedule based on the user's emotional state.

[1691] The predicted schedule is sent by the server to the user's terminal and proposed to the user.

[1692] 3. Reservation management and matching

[1693] The server receives the schedule approved by the user and updates the reservation system, which reflects the available rental times in real time.

[1694] Upon receiving a rental request from a demand-side user, the server performs optimal matching to find the best match between the schedule and the request.

[1695] If a match is made, the server sends a notification to the user and the demand-side user and confirms the reservation.

[1696] Device behavior

[1697] 1. Receiving and checking the schedule

[1698] The user's terminal (smartphone or PC) receives the proposed vehicle rental schedule sent from the server.

[1699] Users can check the proposed schedule on their devices and make corrections as necessary.

[1700] 2. Receiving Notifications

[1701] If the rental is successful, a notification is sent to the user's device and the reservation details are displayed.

[1702] User Actions

[1703] 1. Check and approve the schedule

[1704] The user can review the proposed schedule on their device and modify it if necessary. Once the user finally approves the schedule, the information is sent to the server.

[1705] 2. Loan Management

[1706] The user receives a notification sent from the server and checks the details of the confirmed reservation, allowing the user to smoothly manage the rental.

[1707] Specific examples

[1708] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip (for example, the user is likely to be relaxed after the trip). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who can confirm and approve it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs the optimal match and sends notifications to the user and the demand-side user.

[1709] In this way, this system significantly reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[1710] The processing flow will be explained below.

[1711] Program processing flow

[1712] Step 1:

[1713] The server retrieves the user's vehicle usage history data from the database, including information such as past mileage, usage time, and usage location. The server collects this data and prepares it for analysis.

[1714] Step 2:

[1715] The server uses APIs to retrieve external schedule data from the user's Google Calendar and Time Tree, which aggregates the user's event information for subsequent analysis.

[1716] Step 3:

[1717] The server inputs the acquired vehicle usage history data and external schedule data into the AI ​​model to learn the user's vehicle usage patterns. During this learning process, the AI ​​analyzes the data and identifies usable patterns.

[1718] Step 4:

[1719] The server collects user emotion data using an emotion engine, which analyzes the user's emotional state (e.g., stress level, satisfaction level, etc.) obtained from a smartphone or wearable device.

[1720] Step 5:

[1721] The server retrieves the predicted vehicle rental schedule from the AI ​​model, and the emotion engine then adjusts the schedule based on the user's emotional state, optimizing the schedule to accommodate rentals at times that are least stressful for the user.

[1722] Step 6:

[1723] The server sends the adjusted proposed schedule to the user's device and notifies them, allowing the user to check the proposal on their smartphone or PC.

[1724] Step 7:

[1725] The user checks the proposed lending schedule on the terminal, modifies the schedule as necessary, and finally approves it. This operation is performed on the terminal.

[1726] Step 8:

[1727] The server receives the schedule that the user has approved or modified, records it as an approved schedule, and reflects this information in the reservation system.

[1728] Step 9:

[1729] The server updates the reservation system with the confirmed available rental times, reflecting the available rental schedule in real time. This information is also made public to users on the demand side.

[1730] Step 10:

[1731] When a rental request arrives at the server from a demand-side user, the server retrieves it and performs optimal matching. The server finds the best match between the request and the schedule.

[1732] Step 11:

[1733] If a match is made, the server sends a notification to the user and the demanding user, informing both parties of the loan details.

[1734] Step 12:

[1735] The server finalizes the booking and saves the details in the booking system, making the booking official and available for future reference.

[1736] Specific examples

[1737] For example, the server retrieves the user's vehicle usage history data (such as past mileage, usage time, and location) from a database. The server then uses an API to extract the user's schedule data from Google Calendar and Time Tree. This data is input into an AI model to learn the user's vehicle usage patterns. The emotion engine collects user emotion data from smartphones and wearable devices and adds this to the analysis.

[1738] The server uses the AI ​​model to predict a vehicle rental schedule and adjusts it based on the user's emotional state through an emotion engine. For example, the schedule may be adjusted to avoid times when the user is likely to feel stressed. The server then sends the adjusted rental schedule to the user's device and notifies them. The user can then check the schedule on their device, modify it as necessary, and approve it.

[1739] The approved schedule is received by the server and updated in the reservation system. When a rental request comes from a demand user, the server performs optimal matching, and if successful, sends a notification to both the user and the demand user to confirm the reservation. In this way, efficient car sharing that takes into account the user's emotional state is realized.

[1740] Example 2

[1741] 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."

[1742] In conventional car sharing systems, vehicle rental schedules are set without taking into account the user's emotional state, which can be inconvenient for users. Furthermore, it is difficult to provide an optimal rental schedule simply by analyzing vehicle usage history data and external schedule data. Therefore, there is a need to improve user satisfaction with vehicle usage.

[1743] 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 acquiring vehicle usage history data of the user, means for acquiring external schedule data of the user, means for analyzing the vehicle usage history data and the external schedule data using an AI model to learn the user's vehicle usage pattern, means for collecting user emotion data using an emotion engine and using the collected data for analysis, means for predicting a vehicle rental schedule and adjusting it based on the user's emotional state, means for proposing the predicted and adjusted vehicle rental schedule to the user, means for receiving approval of the proposed vehicle rental schedule from the user, means for updating the approved vehicle rental schedule in the reservation system, means for acquiring a rental request from a demand-side user and matching it with a schedule, means for sending a notification to the user and the demand-side user when the rental is confirmed, and means for confirming the reservation and sharing detailed information. This makes it possible to provide an optimal vehicle rental schedule that takes the user's emotional state into consideration.

[1744] "Vehicle usage history data" is data about how a user has used a vehicle in the past, and includes information such as mileage, usage time, and usage location.

[1745] "External schedule data" is data obtained from an external schedule management system that manages the user's schedule, and includes information obtained from Google Calendar, Time Tree, etc.

[1746] An "AI model" is software that uses machine learning algorithms to analyze data and identify patterns and predictions.

[1747] An "emotion engine" is a system or software for analyzing a user's emotional state, collecting and analyzing emotional data from social media posts, biometric data, etc.

[1748] The "vehicle rental schedule" is a schedule indicating the time periods during which a vehicle can be rented, and is predicted based on the user's vehicle usage history data and external schedule data.

[1749] "Prediction" is the act of estimating future vehicle usage patterns and rental availability times based on collected data.

[1750] "Adjustment" is the process of optimizing a predicted schedule by taking into account the user's emotional state and other factors.

[1751] "Proposal" is the act of presenting a predicted and adjusted vehicle rental schedule to a user.

[1752] "Approval" is an action in which the user agrees with the proposed vehicle rental schedule, and the result is reflected in the system.

[1753] The "reservation system" is a system that manages vehicle rental reservations, updates schedules, and confirms reservations.

[1754] A "demand user" is a user who wishes to rent a vehicle for use.

[1755] "Matching" is the act of optimally matching the demand user's request with the vehicle's available rental time.

[1756] "Notifications" are messages that inform users of information such as reservations and schedule changes.

[1757] "Detailed information" indicates specific information about the reservation contents and schedule.

[1758] This invention is a system for efficiently using privately owned vehicles for car sharing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides an optimal rental schedule. The overall operation flow of this system and a specific example are shown below.

[1759] System Overview

[1760] This system acquires historical vehicle usage data for users and their external schedule data. These data are input into a generative AI model and emotion engine for analysis. The generative AI model uses TensorFlow and PyTorch to learn users' vehicle usage patterns and predict the time periods when vehicles are available for rental. The emotion engine uses, for example, IBM Watson's emotion analysis API to collect user emotion data and use it for analysis. The resulting predicted schedule is proposed to the user, who then approves it. The approved schedule is updated in the reservation system and matched with rental requests from demand users. If the rental is confirmed, the server sends a notification to the user and the demand user, and the reservation is confirmed.

[1761] Server Operation

[1762] 1. The server retrieves the user's vehicle usage history data from the database. The data indicates how the user has used the vehicle in the past, including the mileage, usage time, and location of use.

[1763] 2. The server then retrieves external schedule data, such as Google Calendar or Time Tree, through an API. The external schedule data contains the user's upcoming events.

[1764] 3. The server inputs this data into a generative AI model, which uses TensorFlow and PyTorch to learn the user's vehicle usage patterns.

[1765] 4. The server uses an emotion engine to collect and analyze the user's emotion data. The emotion engine uses, for example, IBM Watson's emotion analysis API. This allows it to analyze emotions from the user's social media posts and other biometric sensor data.

[1766] 5. The generative AI model predicts the user's vehicle rental schedule, taking into account the user's historical usage patterns and external schedule data.

[1767] 6. The emotion engine adjusts the predicted schedule based on the user's emotional state, for example, avoiding rentals during times when the user is feeling stressed.

[1768] 7. The server sends the predicted and adjusted schedule to the user's device, allowing the user to review the proposed schedule.

[1769] 8. Once approval is received from the user, the server updates this schedule into the reservation system, which reflects available rental times in real time.

[1770] 9. The server receives the rental request from the demand user and matches it with the schedule. When the optimal match is found, the rental is completed.

[1771] 10. If the rental is successful, the server sends a notification to the user and the demand user and confirms the reservation.

[1772] Device behavior

[1773] 1. The terminal receives the proposed schedule sent from the server. The user can check the proposed schedule on the terminal and modify it if necessary.

[1774] 2. If the rental is successful, the device receives a notification from the server and displays the reservation details.

[1775] User Actions

[1776] 1. The user checks the proposed schedule on the device and modifies it if necessary. When the user finally approves the schedule, the information is sent to the server.

[1777] 2. The user receives a notification sent from the server and checks the details of the confirmed reservation, enabling smooth rental management.

[1778] Examples and prompts

[1779] Specific examples

[1780] For example, for a user who has a weekend trip planned, the system retrieves the schedule information from Google Calendar and Time Tree. At the same time, the emotion engine recognizes the user's emotional state before and after the trip. Based on this information, the server uses the emotion engine to adjust the schedule predicted by the generative AI model and determines whether a vehicle will be available for rental after the trip. This predicted schedule is proposed to the user, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is also made public to the demand-side user. When a request is sent from the demand-side user, the server performs optimal matching and sends notifications to the user and the demand-side user.

[1781] Prompt Sentence Examples

[1782] Create optimal rental schedules based on user vehicle usage history data and external schedule data. Also take into account emotion engine data. For example:

[1783] Usage data: mileage, usage time, and location for the past month

[1784] External schedule data: Google Calendar, TimeTree events

[1785] Emotion Engine Data: High stress before travel, relaxed after travel

[1786] As a result, suggest a post-trip loan schedule.

[1787] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[1788] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1789] Step 1:

[1790] The server retrieves the user's vehicle usage history data from the database. Input includes mileage, usage time, and usage location. By retrieving this data, basic information can be obtained to understand the user's past vehicle usage patterns. The output is the retrieved vehicle usage history data.

[1791] Step 2:

[1792] The server retrieves the user's external schedule data from Google Calendar or TimeTree through an API. The input includes the user's authentication information and the calendar service's API endpoint, allowing you to leverage the user's upcoming events. The output is the retrieved external schedule data.

[1793] Step 3:

[1794] The server inputs vehicle usage history data and external schedule data into the generative AI model. The input includes the data obtained in Step 1 and Step 2. This allows the AI ​​model to learn the user's vehicle usage patterns. As a specific example, TensorFlow or PyTorch can be used. The output is the result of analyzing the user's vehicle usage patterns.

[1795] Step 4:

[1796] The server uses an emotion engine to collect and analyze user emotion data. Inputs include social media posts and biometric sensor data. For example, IBM Watson's emotion analysis API can be used. The output is user emotion data.

[1797] Step 5:

[1798] The generative AI model predicts the user's vehicle rental schedule. The input includes the user's vehicle usage pattern obtained in step 3 and the emotion data obtained in step 4. This creates the user's vehicle rental schedule. The output is the predicted vehicle rental schedule.

[1799] Step 6:

[1800] The emotion engine adjusts the predicted schedule based on the user's emotional state. The input includes the schedule predicted in step 5 and emotion data. This creates a schedule that takes the user's emotional state into account. The output is the adjusted vehicle rental schedule.

[1801] Step 7:

[1802] The server sends the adjusted schedule to the user's terminal. The input includes the vehicle rental schedule adjusted in step 6. The terminal displays the proposed schedule. The output is the schedule proposal to the user.

[1803] Step 8:

[1804] The user reviews the proposed schedule on the terminal and modifies it if necessary. The input includes the vehicle rental schedule received in step 7, which allows the user to approve or modify the schedule. The output is the schedule approved or modified by the user.

[1805] Step 9:

[1806] The server receives approval from the user and updates this schedule to the reservation system. The input includes the approved or modified schedule from step 8. The reservation system updates the available rental slots in real time. The output is the updated reservation information.

[1807] Step 10:

[1808] The server receives the rental request from the demand user and matches it with the schedule. The input includes the demand user's request and the reservation information updated in step 9. When the best match is found, the rental is established. The output is the matching result.

[1809] Step 11:

[1810] If the rental is successful, the server sends a notification to the user and the demand user to confirm the reservation. The input includes the matching result determined in step 10. The terminal receives the notification and displays the reservation details. The output is the confirmed reservation information and notification.

[1811] In this way, this system reduces the user's effort and realizes efficient car sharing that takes into account the user's emotional state.

[1812] (Application example 2)

[1813] 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."

[1814] Conventional car sharing systems have a problem in that efficient matching between vehicle users and those seeking to rent a vehicle is difficult because the vehicle rental schedule is not sufficiently optimized. In addition, because the system does not take into account the user's emotional state, there is a high possibility that schedules that cause stress to the user are proposed. This may result in a decrease in satisfaction with the car sharing system.

[1815] The specific processing by the specific 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 acquiring the user's vehicle usage history data, means for acquiring the user's external schedule data, and means for acquiring the user's emotional data and adjusting the rental schedule based on the user's emotional state. This makes it possible to analyze the user's vehicle usage history data and external schedule data, predict an optimal vehicle rental schedule, and adjust the schedule according to the user's emotional state. This makes it possible to realize efficient vehicle rental and improve user satisfaction.

[1816] "User's vehicle usage history data" refers to historical information about the user's past use of their own vehicle, specifically data such as mileage, usage time, and usage location.

[1817] "User's external schedule data" refers to external schedule information that may affect the user's use of the vehicle, such as schedule and event information obtained from a calendar service.

[1818] "Emotion data" refers to information that indicates the user's internal emotional state, specifically data that has been acquired by digitizing emotions such as stress, relaxation, and happiness.

[1819] "Means for adjusting the rental schedule based on emotional state" refers to a method for optimizing the schedule based on the acquired emotional data to ensure the least stressful and comfortable vehicle rental experience for the user.

[1820] "Proposed vehicle rental schedule" refers to the predicted rental itinerary that the system presents to the user after analysis and sentiment adjustment has been performed.

[1821] "Reservation System" refers to the computer system used by Users and Demand-Side Users to manage and confirm reservations for vehicle rentals.

[1822] "Demand-side user" refers to a user who wishes to rent a vehicle through a car sharing service.

[1823] "Matching" refers to the process of optimally combining the schedule of a user who wants to rent a vehicle with the request of a demand-side user who wants to rent a vehicle.

[1824] "Means for sending notifications" refers to the method by which schedule and reservation confirmation information is sent electronically to users and demand users, typically via a smartphone or PC application.

[1825] "Means for sharing detailed information" refers to a method for providing specific information about the vehicle rental to both the user and the demand-side user after the reservation is confirmed.

[1826] System Overview

[1827] This invention is a system for food delivery services that provides optimal delivery plans that take into account delivery personnel's schedule management and emotional state. This system collects delivery personnel's past delivery performance data and external schedule data, analyzes them using an AI model and an emotion engine, and predicts and adjusts delivery schedules and proposes them to delivery personnel.

[1828] Server Operation

[1829] 1. Data collection and analysis

[1830] The server retrieves the delivery personnel's past delivery performance data from the database. This data includes past delivery times, distances, delivery destinations, etc. It also uses an API to retrieve external schedule data. This allows the server to understand what the delivery personnel have scheduled at what time.

[1831] Furthermore, an emotion engine is used to collect emotional data from delivery personnel, and the emotional data is used for analysis, for example, to detect whether the emotional state is stressed or relaxed.

[1832] 2. Anticipation and emotion regulation

[1833] The AI ​​model predicts delivery schedules based on collected data, and an emotion engine then adjusts the schedule based on the driver's emotional state. For example, if a driver is stressed, the system may increase their break time.

[1834] The predicted and adjusted schedule is sent by the server to the delivery person's terminal and proposed to the delivery person.

[1835] 3. Reservation management and matching

[1836] Once the delivery person approves the schedule, this information is sent to the server and reflected in the reservation system, which updates available delivery times in real time.

[1837] Upon receiving a delivery request from a demand user, the server performs optimal matching to find the best match between the schedule and the request.

[1838] If a match is made, the server sends a notification to the delivery person and the demand user and confirms the reservation.

[1839] Device behavior

[1840] 1. Receiving and checking the schedule

[1841] The delivery person's device (smartphone or PC) receives the proposed delivery schedule sent from the server. The delivery person can check the proposed schedule on the device and modify it as necessary.

[1842] 2. Receiving Notifications

[1843] When a match is made and a delivery is confirmed, a notification is sent to the delivery person's device, which displays the delivery details and allows them to act according to the confirmed schedule.

[1844] User Actions

[1845] 1. Check and approve the schedule

[1846] The delivery person can review the proposed schedule on their device, modify it if necessary, and finally approve the schedule, which is then sent to the server.

[1847] 2. Managing deliveries

[1848] The delivery person receives the notification sent from the server and checks the details of the confirmed delivery, which allows the delivery person to smoothly manage their delivery work.

[1849] Specific examples

[1850] For example, if a delivery person has a meeting at 9:00 AM, the system retrieves that schedule information from the API. At the same time, the emotion engine recognizes the person's current stress level (they are likely nervous before the meeting). Based on this information, the server uses the emotion engine to adjust the schedule predicted by the AI ​​model and determine that deliveries are possible at 10:00 AM after the meeting and at 3:00 PM. This predicted and adjusted schedule is proposed to the delivery person, who then reviews and approves it. The approved schedule is updated in the reservation system, and the information is made available to demand-side users.

[1851] When a request is sent from a demand user, the server performs optimal matching and sends a notification to the delivery person and the demand user.

[1852] Example prompt sentence:

[1853] We provide schedule and sentiment data, including: Use this to predict optimal delivery schedules and adjust them based on sentiment.

[1854] Schedule data: [{'date': '2023-01-01', 'event': 'meeting', 'time': '10:00'}, {'date': '2023-01-02', 'event': 'shopping', 'time': '12:00'}]

[1855] Emotion data: ['neutral', 'stress']

[1856] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1857] Step 1:

[1858] Data Collection

[1859] The server first retrieves the delivery person's past delivery performance data from the database. Here, it uses a database query to obtain information such as past delivery times, distances, and delivery destinations. It also uses an API to obtain the delivery person's external schedule data and retrieves appointment and event information from a calendar service. The inputs are the delivery person's ID and query conditions, and the output is delivery performance data and schedule data.

[1860] Step 2:

[1861] Acquiring emotion data

[1862] The server uses an emotion engine to obtain the delivery person's emotional data. Specifically, the server inputs the delivery person's recent activities and feedback into the emotion analysis API to obtain data on their emotional state (stress, relaxation, happiness, etc.). The input is the delivery person's recent activity information, and the output is emotional data.

[1863] Step 3:

[1864] Prediction by AI model

[1865] The server inputs the delivery performance data and schedule data acquired in step 1 into the AI ​​model and predicts the optimal delivery schedule. The AI ​​model learns delivery patterns from past data and predicts future available delivery times. The inputs are delivery performance data and schedule data, and the output is a predicted delivery schedule.

[1866] Step 4:

[1867] emotional regulation

[1868] The server adjusts the predicted delivery schedule in step 3 based on the emotional data acquired in step 2. The emotion engine analyzes the emotional state of the delivery person and makes adjustments such as extending the interval between deliveries if the person is under high stress. The inputs are the predicted delivery schedule and emotional data, and the output is an adjusted delivery schedule.

[1869] Step 5:

[1870] Schedule proposal

[1871] The server sends the adjusted delivery schedule from step 4 to the delivery person's terminal and proposes it. The terminal receives the schedule sent from the server and presents it to the delivery person. The user checks the proposed schedule through the terminal and makes any necessary corrections. The input is the adjusted delivery schedule, and the output is the proposed schedule for the delivery person.

[1872] Step 6:

[1873] Schedule Approval

[1874] The user reviews the proposed schedule on the device and gives final approval. The device then sends the information to the server. The input is the delivery driver's feedback, and the output is the final approved schedule.

[1875] Step 7:

[1876] Updates to the reservation system

[1877] The server updates the reservation system with the approved delivery schedule, which reflects available delivery times in real time. The input is the final approved schedule, and the output is the updated schedule in the reservation system.

[1878] Step 8:

[1879] matching

[1880] The server receives delivery requests from users on the demand side and performs optimal matching. The AI ​​model analyzes demand and supply data and combines the most suitable schedule with the request. The inputs are the delivery request and available delivery schedule, and the output is the matching result.

[1881] Step 9:

[1882] Sending notifications

[1883] If a match is made, the server sends a notification to the delivery person and the demand user. The terminal receives the notification sent from the server and displays detailed information. The input is the matching result, and the output is the notification sent to the delivery person and the demand user.

[1884] Step 10:

[1885] Share details

[1886] After the reservation is confirmed, the server shares detailed information about the delivery with the delivery person and the demand user. The terminal receives the detailed information sent from the server and displays the delivery contents, time, etc. The input is the reservation confirmation information, and the output is the detailed information shared between the delivery person and the demand user.

[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 discl...

Claims

1. A means for acquiring vehicle usage history data of a user; means for obtaining external schedule data for a user; means for analyzing the vehicle usage record data and external schedule data to learn a user's vehicle usage pattern; a means for predicting vehicle rental schedules; means for proposing the predicted vehicle rental schedule to a user; means for receiving approval of the proposed vehicle rental schedule from a user; means for updating the approved vehicle rental schedule in a reservation system; A means for acquiring a lending request from a demand-side user and matching it with a schedule; means for sending a notification to the user and the demand-side user when the loan is established; A way to confirm your booking and share details, A system including:

2. 10. The system of claim 1, further comprising means for optimizing based on the predicted vehicle rental schedule and demand data.

3. 2. The system of claim 1, further comprising means for transmitting notifications to said user and demand users through terminals.

Images