System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting location information of transportation vehicles; means for collecting traffic information; means for analyzing the collected location information and traffic information using a generative AI to calculate an optimal transportation route; means for calculating an estimated delivery time based on the calculated transportation route; means for notifying a recipient of the calculated estimated delivery time; and means for increasing a user's stay-at-home ratio based on the notified estimated delivery time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, there have been concerns about a decrease in transportation volume due to a shortage of truck drivers and work style reforms. One of the causes of this problem is the increase in redelivery due to missed deliveries. Missed deliveries reduce delivery efficiency and increase driver working hours. In addition, it is difficult for users to predict delivery timing, making it difficult to arrange time for pickup. To solve these issues, there is a need for technology that optimizes delivery efficiency and increases the rate at which users are at home. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means for collecting location information of transport vehicles is provided. Next, a means for collecting traffic condition data in real time is used, and the generated AI analyzes this data to calculate the optimal transport route. Then, a means for calculating the estimated delivery time of each package with high accuracy based on the calculated transport route is used. Furthermore, a means for notifying the recipient of the calculated estimated delivery time is used to increase the rate at which users are at home, thereby reducing the number of missed deliveries. Furthermore, by adding a means for recording the actual delivery time after delivery is completed and training the generated AI using the collected data as feedback, the accuracy of predictions for future deliveries is improved. Furthermore, by incorporating a means for optimizing the delivery order, even more efficient deliveries are achieved. These means make it possible to significantly improve delivery efficiency while effectively resolving the problems caused by missed deliveries.

[0006] "Transport vehicle" is a general term for cars and trucks used to transport goods to their destination.

[0007] "Location information" is data that indicates the latitude and longitude of a specific location or object through technology such as GPS.

[0008] "Traffic condition data" is information indicating road congestion, accidents, construction, and other road conditions.

[0009] "Generative AI" is artificial intelligence that analyzes large amounts of data using machine learning technology to make predictions and optimizations.

[0010] A "transportation route" refers to the route or path taken by a transport vehicle when transporting goods.

[0011] "Estimated delivery time" is the time when the package is expected to be delivered to the recipient.

[0012] "Notification method" refers to the process of sending information to users using methods such as email, SMS, app notifications, etc.

[0013] "Recipient" means the person or organization that is to receive the delivered item.

[0014] "User" refers to a person who receives an item to be delivered or checks the delivery schedule.

[0015] "At-home rate" refers to the probability that the recipient will be at home when the item is delivered.

[0016] "Optimization" is the process of making calculations and adjustments to obtain the best results under given conditions.

[0017] "Feedback" refers to collecting information about the results and performance of a system and using it to make improvements.

[0018] "Learning" is the process by which AI improves its performance and predictive accuracy based on newly acquired data. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0027] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0040] This invention is a system that optimizes specific transport routes and notifies users of highly accurate scheduled delivery times, taking into account traffic conditions. This system achieves efficient delivery by collecting transport vehicle location information and traffic condition data and optimizing transport routes using generative AI.

[0041] Overview of the embodiment

[0042] This system consists of three main elements: a server, a terminal, and a user.

[0043] server

[0044] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[0045] 1. Data Collection

[0046] The server collects real-time location information sent from the GPS devices of the transport vehicles, as well as traffic condition data such as traffic congestion and road closure information through a traffic condition API.

[0047] 2. Data analysis and route optimization

[0048] The collected location and traffic data is analyzed and generative AI is used to calculate the optimal transportation route, taking into account real-time traffic congestion information and other factors.

[0049] 3. Calculating the estimated delivery time

[0050] Based on the optimized transportation route, the estimated delivery time at each delivery point is calculated.

[0051] 4. Notification System

[0052] The calculated estimated delivery time is notified to the user's device via email, SMS, etc.

[0053] 5. Feedback and learning

[0054] After the delivery is completed, the actual delivery time is recorded, and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[0055] Terminal

[0056] The terminal is used to notify the user of the estimated delivery time. Specifically, it receives the notification sent from the server and displays it to the user, allowing the user to check the estimated delivery time in advance.

[0057] User

[0058] By being at home based on the notified scheduled delivery time, users can easily receive deliveries. By checking the notification, deliveries without being present can be reduced, and efficient delivery can be supported.

[0059] Specific examples

[0060] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0061] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0062] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0063] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0064] 4. The server selects the fastest and most efficient delivery route while taking costs into account.

[0065] 5. The server notifies each user of the estimated delivery time. For example, user A receives an email saying, "Delivery will be at 10:00 today."

[0066] 6. The user checks the notification and adjusts their schedule so that they will be at home at the scheduled delivery time.

[0067] 7. After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[0068] In this way, the present invention achieves improved delivery efficiency and user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[0072] Step 2:

[0073] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[0074] Step 3:

[0075] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[0076] Step 4:

[0077] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[0078] Step 5:

[0079] The server optimizes the calculated estimated delivery time as necessary and confirms the estimated delivery time for each recipient, which is then stored in a database.

[0080] Step 6:

[0081] The server generates a notification message for each recipient and sends it via email or SMS via the API, including the estimated delivery time, in a user-viewable format.

[0082] Step 7:

[0083] The terminal displays the received notification message to the user, who can then check the estimated delivery time via the terminal.

[0084] Step 8:

[0085] The user makes a plan to be at home based on the notified scheduled delivery time. By being at home, the user can smoothly receive the delivery.

[0086] Step 9:

[0087] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[0088] Step 10:

[0089] The server provides the collected actual delivery time data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[0090] Example 1

[0091] 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."

[0092] Conventional delivery systems are unable to properly reflect the current location of delivery vehicles or real-time traffic conditions, resulting in inaccurate delivery schedules and a low rate of users being at home, leading to frequent missed deliveries. This in turn reduces delivery efficiency and increases costs. Furthermore, delivery plans are not optimized due to a lack of a feedback function that uses data from completed deliveries to retrain the generative AI to improve the accuracy of future predictions.

[0093] 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.

[0094] In this invention, the server includes means for collecting vehicle location information, means for collecting traffic data, means for using a generating AI to analyze the collected location information and traffic data and calculate an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for increasing the user's chance of being at home based on the notified estimated delivery time, and means for recording the time after delivery is completed and retraining the generating AI to improve the accuracy of the next delivery prediction. This improves the accuracy of the estimated delivery time, increases the user's chance of being at home, and reduces missed deliveries. Furthermore, the generating AI can be retrained based on feedback to further optimize the next delivery plan.

[0095] "Means for collecting transport vehicle location information" refers to equipment or technology that obtains the current location of a transport vehicle in real time from a GPS device.

[0096] "Means of collecting traffic condition data" refers to technology that uses APIs and data provision services to obtain real-time traffic information such as traffic congestion information and road closure information.

[0097] "Means of using generative AI to analyze collected location information and traffic condition data and calculate the optimal transportation route" refers to a technology that analyzes collected location information and traffic condition data and uses a generative AI model to calculate the most efficient transportation route.

[0098] The "means for calculating the estimated delivery time based on the calculated transportation route" refers to an algorithm or technology that calculates the estimated arrival time at each delivery point based on the optimal transportation route.

[0099] "Means for notifying the recipient of the calculated estimated delivery time" refers to technology that sends the estimated delivery time to the user's device via email, SMS, application notification, etc.

[0100] "Means for increasing the rate at which users are at home based on the notified scheduled delivery time" refers to techniques or methods for encouraging users to adjust their schedules based on the notified scheduled delivery time and be at home.

[0101] "Means for recording the time after delivery completion and retraining the generating AI to improve the accuracy of the next delivery prediction" refers to a technology that records the time when delivery is completed in a database and uses this data to retrain the generating AI model to improve the accuracy of future delivery predictions.

[0102] This system optimizes specific transportation routes and notifies users of highly accurate estimated delivery times, taking into account traffic conditions. This system consists of three main components: a server, a terminal, and a user.

[0103] server

[0104] The server is responsible for the main data processing and analysis. Specifically, it uses GPS devices to collect vehicle location information and traffic situation APIs (e.g., Google Maps API and Here API) to collect traffic situation data. The server collects the data and records it in an internal database.

[0105] The server then uses a generative AI model (e.g., Google Cloud AI, AWS SageMaker) to analyze the collected location and traffic data, generates prompts, and sends API requests to the generative AI model to calculate the optimal transportation route, taking into account real-time traffic congestion and road closure information.

[0106] Once the optimal delivery route is determined, the server calculates the estimated time of arrival at each delivery point using an algorithm that calculates the travel time to each delivery point based on the optimal route.

[0107] The server uses an SMTP server or SMS sending API (e.g., Twilio API) to notify the user's device of the calculated estimated delivery time, allowing the user to check the estimated delivery time in advance.

[0108] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving the accuracy of future delivery predictions.

[0109] Terminal

[0110] The terminal receives the notification sent from the server and displays the estimated delivery time to the user, allowing the user to know the estimated delivery time in advance and making it easier for the user to receive the delivery.

[0111] User

[0112] Users can check the estimated delivery time displayed on their device and adjust their schedule to be at home at the specified time, which reduces missed deliveries and improves delivery efficiency.

[0113] Specific examples

[0114] For example, consider a scenario where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0115] 1. The server obtains the current location of the transport vehicle from the GPS device and collects traffic condition data in real time from the traffic condition API.

[0116] Specific API examples: Google Maps API, Here API

[0117] 2. The server analyzes the data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0118] Generative AI model examples: Google Cloud AI, AWS SageMaker

[0119] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0120] 4. The server notifies each user of the calculated estimated delivery time. For example, user A receives an email saying "Delivery will be at 10:00 today."

[0121] Notification method: SMTP server, Twilio API, etc.

[0122] 5. The user checks the estimated delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time.

[0123] 6. After the delivery is completed, the server records the actual delivery time and uses this information to retrain the generative AI model. This feedback improves prediction accuracy in future deliveries.

[0124] Prompt Sentence Examples

[0125] For example, you could input the following prompts into a generative AI model:

[0126] "A transport vehicle with current location 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic data."

[0127] In this way, the present invention achieves efficient delivery and improved user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The server collects location information of the transport vehicle. The input for this step is real-time location information sent from the GPS device of the transport vehicle. The server receives this location information and stores it in a database. Specifically, the server periodically polls for data from the GPS device and records the received information in the database.

[0131] Step 2:

[0132] The server collects traffic condition data. The input for this step is real-time traffic congestion and road closure information provided by the traffic condition API. The server calls the API and stores the acquired data in an internal database. Specifically, the server periodically acquires the necessary traffic information using the Google Maps API, Here API, etc., and stores it in the database.

[0133] Step 3:

[0134] The server inputs the collected location information and traffic condition data into the generative AI model. The input data includes the current location of the transport vehicle and the latest traffic conditions. The server creates a prompt based on this data and sends an API request to the generative AI model. Specifically, the server generates a prompt that reads, "A transport vehicle with a current location of 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic condition data," and sends it to the generative AI.

[0135] Step 4:

[0136] The server receives the optimal transportation route and estimated delivery time provided by the generative AI model. The output of the generative AI model includes multiple delivery points and their estimated arrival times. The server receives this information, stores it in a database, and checks the accuracy of each delivery route. Specifically, the server analyzes the response from the generative AI and stores the transportation route in a database.

[0137] Step 5:

[0138] The server notifies the user's device of the optimized estimated delivery time. The input for this step is the calculated estimated delivery time, and the server sends a notification to the user using an SMTP server or SMS sending API. Specifically, the server generates a message saying "Delivery will be at 10:00 today" and sends it to the user via email or SMS. For example, the SMS can be sent using the Twilio API.

[0139] Step 6:

[0140] The user checks the scheduled delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time. The input for this step is the scheduled delivery time notified by the server, and the output is an improvement in the user's rate of being at home. Specifically, the user checks the notification and adjusts their schedule so that they will be at home at the specified time.

[0141] Step 7:

[0142] After the delivery is completed, the server records the actual delivery time. The input for this step is the actual time of delivery, and the server stores this information in a database. Specifically, when the delivery is completed, the server obtains information from the GPS device of the transport vehicle and records the time.

[0143] Step 8:

[0144] The server uses the recorded delivery time to retrain the generative AI model and improve the accuracy of the next prediction. The input for this step is the data at the time of delivery completion, which the server provides to the generative AI model for retraining. Specifically, the server periodically inputs the delivery history recorded in the database into the generative AI model to promote retraining.

[0145] (Application example 1)

[0146] 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."

[0147] Conventional food delivery services have struggled to accurately predict scheduled delivery times while taking into full account changes in traffic conditions and the impact of delivery destination order. This has led to problems such as users being unable to be at home at the scheduled delivery time, resulting in reduced delivery efficiency. Another issue is that information after delivery completion is not provided as feedback, preventing future delivery predictions from improving. Furthermore, there is a lack of a mechanism for notifying users in real time, reducing user convenience.

[0148] 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.

[0149] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generation AI and calculating an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for recording the actual delivery time after delivery completion as feedback and for learning using the generation AI, means for acquiring traffic conditions in real time, and means for sending a push notification to the user. This enables a food delivery service to calculate an optimal delivery route that takes changes in traffic conditions into account, and to provide users with highly accurate estimated delivery times, thereby improving delivery efficiency and user convenience.

[0150] "Means for collecting location information of transport vehicles" refers to devices or software that have the function of obtaining the current location of transport vehicles from a location information system such as GPS and transmitting it to a server.

[0151] "Means for collecting traffic condition data" refers to devices or software that have the function of obtaining traffic condition data such as road congestion information and road closure information from the Internet or external APIs.

[0152] "Generative AI" is an artificial intelligence algorithm that analyzes large amounts of data, learns patterns and trends, and makes predictions and classifications.

[0153] The "means for calculating the optimal transport route" refers to a device or software that has the function of calculating the most efficient route for transport vehicles based on the collected location information and traffic condition data.

[0154] The "means for calculating the estimated delivery time" is a device or software that has the function of calculating the predicted delivery time at each delivery point based on the optimal transportation route.

[0155] "Means for notifying the recipient of the estimated delivery time" refers to devices or software that have the function of notifying the recipient of the calculated estimated delivery time via email, SMS, push notification within the app, etc.

[0156] "Means for recording the actual delivery time after delivery is completed as feedback" refers to a device or software that has the function of recording the actual delivery time as data after delivery is completed and using it to improve prediction accuracy in future deliveries.

[0157] "Means for obtaining traffic conditions in real time" refers to devices or software that have the function of continuously monitoring current traffic conditions and providing the latest data to a server.

[0158] A "means for sending push notifications" is a device or software that has the function of sending messages directly from a server to a user's device such as a smartphone or tablet.

[0159] MODE FOR CARRYING OUT THE INVENTION

[0160] This invention is a system that optimizes specific delivery routes and notifies users of highly accurate estimated delivery times, taking traffic conditions into account. This system achieves efficient delivery by collecting vehicle location information and traffic condition data and optimizing delivery routes using generative AI. The system consists of three main components: a server, a terminal, and a user.

[0161] server

[0162] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[0163] 1. Data Collection

[0164] The server collects real-time location information from the GPS devices of the transport vehicles, as well as traffic data such as traffic congestion and road closures through a traffic API. The software used includes the Google Maps API and an API for GPS data collection.

[0165] 2. Data analysis and route optimization

[0166] The collected location information and traffic situation data are analyzed, and the optimal transportation route is calculated using generative AI. Real-time traffic congestion information and other factors are also taken into account. A generative AI model is used to predict the most efficient route. For example, a generative AI model using TensorFlow is applied.

[0167] 3. Calculating the estimated delivery time

[0168] Based on the optimized transportation route, the system calculates the estimated delivery time at each delivery point, thereby providing highly accurate delivery times.

[0169] 4. Notification System

[0170] The calculated estimated delivery time is notified to the user's device via email, SMS, in-app notification, etc. Firebase is used to send push notifications.

[0171] 5. Feedback and learning

[0172] After the delivery is completed, the actual delivery time is recorded and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[0173] Terminal

[0174] The terminal is used to notify the user of the scheduled delivery time. Specifically, it receives the notification sent from the server and displays it to the user. This allows the user to check the scheduled delivery time in advance, increasing the chance of the user being at home. The terminal can be a smartphone or tablet.

[0175] User

[0176] The user can easily receive the delivery by being at home based on the notified scheduled delivery time. By checking the notification, the number of missed deliveries can be reduced, supporting efficient delivery. The user can adjust their schedule based on the received notification.

[0177] Specific examples

[0178] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In that case, it operates as follows:

[0179] The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0180] The server analyzes the collected location information and traffic condition data using a generative AI model to calculate the optimal transportation route. For example, if road A is congested, detour route B will be selected.

[0181] The server calculates the estimated time of arrival at each delivery point based on the optimal transportation route.

[0182] The server notifies each user of the estimated delivery time. For example, user A receives a notification that "the delivery will be made at 12:15 today."

[0183] After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[0184] Example prompt sentence:

[0185] "The transport vehicle's location is latitude 35.6895, longitude 139.6917."

[0186] "High traffic congestion is expected."

[0187] "Delivery addresses are 123, 456, and 789 in Tokyo."

[0188] This system and method will enable food delivery services to notify highly accurate scheduled delivery times that take into account changes in traffic conditions, significantly improving delivery efficiency and user convenience.

[0189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0190] Program processing steps

[0191] Step 1:

[0192] The server collects the location information of the transport vehicle in real time from the GPS device. The input is the transport vehicle ID, and the output is the latitude and longitude information. This allows the current vehicle location to be accurately determined.

[0193] Step 2:

[0194] The server collects traffic data from the Internet or external APIs (e.g., Google Maps API). The input is a specific area name or coordinate range, and the output is traffic congestion and road closure information for that area. This allows the server to obtain the latest traffic conditions.

[0195] Step 3:

[0196] Based on the collected location information and traffic data, the server uses a generative AI model to calculate the optimal delivery route. The input is location information, traffic data, and a list of delivery addresses, and the output is an optimized route and estimated arrival time at each delivery point. TensorFlow is used to process the data and calculate the optimal route based on real-time traffic conditions.

[0197] Step 4:

[0198] The server calculates the estimated delivery time based on the calculated transportation route. The input is the optimized route information, and the output is the predicted arrival time at each delivery point. This results in an efficient delivery schedule.

[0199] Step 5:

[0200] The server notifies the user of the calculated estimated delivery time via email, SMS, and push notification. The input is the user's contact information and the estimated delivery time, and the output is a notification message that arrives on the user's device. The notification system uses Firebase.

[0201] Step 6:

[0202] Based on the notification, the user can decide whether to be at home or not and prepare for the scheduled delivery time, making it easier for the user to receive the delivery.

[0203] Step 7:

[0204] After the delivery is completed, the server records the actual delivery time. The input is the delivery completion time, and the output is the recorded history data. This stores the actual delivery time in the database.

[0205] Step 8:

[0206] The server uses the accumulated historical data to retrain the generative AI model and improve the accuracy of future predictions. The input is past delivery data, and the output is an improved predictive model. This improves the accuracy of the next prediction.

[0207] The above are the specific processing steps of the system that realizes the application example, and by following these steps, delivery efficiency and user convenience can be greatly improved.

[0208] 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.

[0209] This invention is a system that uses generative AI to calculate the optimal delivery route based on the location information of the delivery vehicle and traffic condition data, and notifies the user of a highly accurate estimated delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[0210] Overview of the embodiment

[0211] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[0212] server

[0213] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[0214] 1. Data Collection

[0215] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[0216] 2. Data analysis and route optimization

[0217] The server inputs the collected location information and traffic data into the AI ​​generator to calculate the optimal transportation route, taking real-time traffic conditions into account.

[0218] 3. Calculating the estimated delivery time

[0219] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0220] 4. Notification System

[0221] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[0222] 5. Emotion Engine

[0223] The server uses an emotion engine to analyze the user's emotions. It can recognize emotions based on the user's text messages, voice, or facial expression data, and can suggest changes to delivery times based on the results. This emotion data is also used as feedback for the generative AI.

[0224] 6. Feedback and Learning

[0225] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI, improving prediction accuracy in future runs.

[0226] Terminal

[0227] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[0228] 1. Receives notification messages sent by the server and displays them to the user.

[0229] 2. Use an emotion engine to provide notification content based on the user's emotions.

[0230] User

[0231] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[0232] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[0233] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[0234] Specific examples

[0235] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0236] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0237] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0238] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0239] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[0240] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[0241] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[0242] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI, improving the accuracy of the next prediction.

[0243] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[0244] The processing flow will be explained below.

[0245] Step 1:

[0246] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[0247] Step 2:

[0248] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[0249] Step 3:

[0250] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[0251] Step 4:

[0252] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[0253] Step 5:

[0254] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via the API. This notification includes the specific estimated delivery time.

[0255] Step 6:

[0256] The emotion engine analyzes the user's text message, voice, or facial expression data to recognize emotions. For example, if the user feels that the delivery time is slow, the emotion engine analyzes the emotion and provides it to the server.

[0257] Step 7:

[0258] The server can suggest changes to the delivery time based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, the server can add a suggestion to the notification to "advance the delivery time."

[0259] Step 8:

[0260] The terminal displays the received notification message to the user, who can then check the estimated delivery time and suggestions from the server via the terminal.

[0261] Step 9:

[0262] The user can plan their stay at home based on the estimated delivery time. They can also request a change in the delivery time based on the analysis results of the emotion engine. For example, they can send a request to the server such as "Please deliver a little later."

[0263] Step 10:

[0264] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[0265] Step 11:

[0266] The server provides the collected actual delivery time data and emotion data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[0267] In this way, efficient delivery can be achieved while taking into consideration the user's feelings.

[0268] Example 2

[0269] 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."

[0270] In modern logistics systems, efficient route selection for transport vehicles and prediction of scheduled delivery times are important issues. However, conventional systems cannot fully consider fluctuations in traffic conditions or the rate at which users are at home, making it difficult to select optimal routes or accurately calculate scheduled delivery times. Furthermore, frequent missed deliveries lead to reduced delivery efficiency and lower customer satisfaction.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0272] In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using generative artificial intelligence and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the recipient's emotional data and adjusting the notification content based on the results, and means for increasing the rate at which the user will be at home based on the estimated delivery time. This makes it possible to select an optimal route taking traffic conditions into consideration in real time and to predict the estimated delivery time with high accuracy, and further to increase the rate at which the user will be at home by analyzing the user's emotions, thereby reducing missed deliveries and improving customer satisfaction.

[0273] "Transport vehicle location information" indicates coordinate data of the location where the transport vehicle is currently located.

[0274] "Traffic condition data" refers to current traffic data relating to the movement of transport vehicles, such as road congestion information and road closure information.

[0275] "Generative artificial intelligence" refers to advanced computational models used to analyze data and make predictions, particularly those that utilize machine learning and deep learning.

[0276] "Analysis" refers to the process of extracting information from collected data and making understanding or predictions.

[0277] The "optimal transportation route" is a route selected for efficient delivery, and is calculated taking into account traffic conditions, distance, time, etc.

[0278] "Scheduled delivery time" refers to the time when a transport vehicle is scheduled to arrive at a particular location.

[0279] "Recipient" means the person or entity intended to receive the delivery.

[0280] "Notification" refers to a message or signal that conveys information to a specific recipient.

[0281] "Emotion data" is information that indicates the user's emotional state, and is extracted from text, voice, facial expressions, and the like.

[0282] The "at-home rate" indicates the probability that a user is at home during a particular time period.

[0283] MODE FOR CARRYING OUT THE INVENTION

[0284] This invention is a system that uses generative artificial intelligence to calculate the optimal transportation route based on the location information of the transportation vehicle and traffic condition data, and notifies the user of a highly accurate scheduled delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[0285] System configuration

[0286] Server Roles

[0287] The server is responsible for the main data processing and analysis, specifically fulfilling the following roles:

[0288] 1. Data Collection

[0289] The server collects real-time location information sent from the GPS devices of transport vehicles, and also collects traffic congestion information, road closure information, etc. using traffic condition APIs, and stores this data in a database.

[0290] 2. Data analysis and route optimization

[0291] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal delivery route, taking real-time traffic conditions into consideration. For example, a prompt might be used: "Based on the current location information and traffic situation data of the delivery vehicle, please calculate the optimal delivery route and estimated delivery time."

[0292] 3. Calculating the estimated delivery time

[0293] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0294] 4. Notification System

[0295] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[0296] 5. Emotion Engine

[0297] The server analyzes the user's text message, voice, or facial expression data to recognize the user's emotions. Based on the analysis results, the server can suggest changes to the delivery time. For example, the prompt could read, "Analyze the user's latest emotional data and suggest changes to the delivery time based on the results."

[0298] 6. Feedback and Learning

[0299] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[0300] Device Role

[0301] The terminal's main role is to notify the user of the estimated delivery time.

[0302] 1. Notification display

[0303] Receives notification messages sent from the server and displays them to the user. For example, it displays a message saying "Delivery will be made at 10:00 today."

[0304] 2. Emotional Engine Support

[0305] It works in conjunction with the server's emotion engine to provide notifications based on the user's emotions. For example, if the user is feeling stressed, it will suggest flexible delivery times.

[0306] User Roles

[0307] The user acts based on the notified estimated delivery time.

[0308] 1. Notification Confirmation and Action Plan

[0309] Check the notification message you received and plan to be at home at the scheduled delivery time. For example, you can plan to be at home at 10:00 today.

[0310] 2. Adjustments based on the emotion engine's suggestions

[0311] Accept the suggestions provided based on the sentiment engine and adjust the delivery time, for example, request a different delivery time.

[0312] Specific examples

[0313] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0314] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0315] 2. The server uses a generation AI to analyze the collected data and calculate the optimal transportation route. For example, "Road A is congested, so select detour route B."

[0316] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0317] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[0318] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[0319] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[0320] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as learning data for the generative AI, improving the accuracy of the next prediction.

[0321] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[0322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0323] Step 1: Data collection

[0324] The server collects real-time location information from the GPS devices of the transport vehicles, and also obtains traffic congestion and road closure information using the traffic situation API, which is then stored in a database.

[0325] Input: GPS data of transport vehicles, traffic information from traffic situation API

[0326] Output: Location and traffic data stored in a database

[0327] Specific operation: The server obtains location information from the GPS device every second and accesses the traffic situation API via HTTP request to obtain traffic information. This information is stored in a database.

[0328] Step 2: Data analysis and route optimization

[0329] The server inputs the collected location and traffic data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account.

[0330] Input: location information, traffic data

[0331] Output: Optimal transportation route

[0332] Specific operation: The server sends a prompt to the generative AI model saying, "Calculate the optimal route using the current location, destination, and traffic information as input," and determines the next movement step based on the route information returned by the generative AI model.

[0333] Step 3: Calculate the estimated delivery time

[0334] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0335] Input: Optimal transport route, traffic situation data

[0336] Output: Estimated delivery time for each delivery point

[0337] Specific operation: The server calculates the travel time and stop time for each delivery point, and calculates the estimated arrival time at point 1 as 10:00, point 2 as 11:00, and the final point as 12:30.

[0338] Step 4: Notification System

[0339] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[0340] Input: Estimated delivery time

[0341] Output: Notification message to the user terminal

[0342] Specific operation: The server creates a message stating "Delivery will be made at 10:00 today" and sends a notification to the user's device using an email sending API or SMS sending API.

[0343] Step 5: Emotion Engine

[0344] The server analyzes the user's text messages, voice, or facial expression data to recognize their emotions, and then suggests changes to the delivery time based on the results.

[0345] Input: User text messages, voice, and facial expression data

[0346] Output: Sentiment analysis results, suggestion to change delivery time

[0347] Specific operation: When a user sends a message or voice message, the server analyzes it using an emotion engine, and if it determines that the user is "stressed," it takes the action of "suggesting to change the delivery time to 15 minutes later."

[0348] Step 6: Feedback and learning

[0349] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[0350] Input: Actual delivery time

[0351] Output: Retrained generative AI model

[0352] Specific operation: When a delivery is completed, the server saves the actual delivery time in a database and inputs it into the generative AI model with the prompt "Relearn to improve prediction accuracy next time."

[0353] Step 7: User Behavior

[0354] The user acts based on the notified estimated delivery time.

[0355] Input: Notification message

[0356] Output: User action plan, increase in at-home rate

[0357] Specific operation: The user checks the notification message displayed on the device and adds a schedule such as "I'll be at home at 10:00 today" to their calendar. They can also request a change in delivery time based on suggestions from the emotion engine.

[0358] (Application example 2)

[0359] 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."

[0360] Conventional food delivery systems have difficulty calculating the optimal delivery route based on the delivery person's current location information and traffic condition data, and notifying the user of a highly accurate estimated delivery time. Furthermore, since delivery times are notified unilaterally without considering the user's feelings, there is a high possibility of user satisfaction decreasing. Furthermore, frequent missed deliveries lead to inefficiencies and increased costs.

[0361] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generative AI model and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the user's emotions, and means for flexibly changing the delivery time based on the user's emotions. This enables highly accurate notification of the estimated delivery time and flexible delivery response that takes the user's emotions into consideration.

[0362] "Transport vehicle location information" is data indicating the current geographical location of the transport vehicle.

[0363] "Traffic condition data" refers to data that includes information about roads and traffic, such as road congestion and closure information, and the status of traffic signals.

[0364] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to calculate optimal routes and arrival times based on collected data.

[0365] The "optimal transportation route" is the most efficient and quickest route to reach the destination based on collected location information and traffic data.

[0366] The "estimated delivery time" is the arrival time at each delivery point calculated based on the optimal transportation route.

[0367] "Means of notifying recipient" refers to the method or function for notifying the recipient of the calculated estimated delivery time, and mainly includes email, SMS, and in-app notifications.

[0368] "Means for analyzing user emotions" refers to technology for determining a user's emotional state based on voice, text messages, facial expression data, etc.

[0369] The "means for flexibly changing delivery time based on user's emotions" is a method for proposing and executing changes to delivery time in accordance with the analyzed user's emotions.

[0370] "Data collected as feedback" refers to data used as training data for the generative AI model to improve future prediction accuracy, such as delivery time and emotional data recorded after a delivery is completed.

[0371] This invention is a food delivery system that uses a generative AI model to calculate the optimal delivery route based on vehicle location information and traffic condition data, and notifies users of highly accurate estimated delivery times. Furthermore, by combining it with an emotion engine that analyzes user emotions, it is possible to further increase the rate at which users are at home and reduce missed deliveries.

[0372] System configuration

[0373] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[0374] server

[0375] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[0376] 1. Data Collection

[0377] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[0378] 2. Data analysis and route optimization

[0379] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account. The generative AI model is implemented using TensorFlow, PyTorch, and other tools.

[0380] 3. Calculating the estimated delivery time

[0381] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0382] 4. Notification System

[0383] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via an API, using a mail server or SMS gateway.

[0384] 5. Emotion Engine

[0385] The server uses an emotion engine to analyze the user's emotions. It recognizes emotions based on the user's text message, voice, or facial expression data, and can suggest changes to the delivery time based on the results. The emotion engine uses NLTK and Google Cloud Natural Language API. This emotion data is also used as feedback and training data for the generative AI.

[0386] 6. Feedback and Learning

[0387] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[0388] Terminal

[0389] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[0390] 1. Receives notification messages sent from the server and displays them to the user. This applies to smartphone apps and web notifications.

[0391] 2. Use an emotion engine to provide notification content based on the user's emotions.

[0392] User

[0393] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[0394] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[0395] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[0396] Specific examples

[0397] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In this case, the system operates as follows:

[0398] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0399] 2. The server analyzes the collected data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, it selects detour route B.

[0400] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0401] 4. The server notifies the recipient of the calculated estimated delivery time. User A receives a message saying "Delivery will be at 10:00 today."

[0402] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[0403] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[0404] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI model, improving the accuracy of the next prediction.

[0405] Prompt Sentence Examples

[0406] "Current location: {current_location}, Estimated delivery time: {estimated_delivery_times}, User emotion: {user_emotion}"

[0407] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[0408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0409] Step 1:

[0410] The server collects the location information of the transport vehicle in real time from the GPS device. Specifically, it obtains the GPS information indicating the current location of the transport vehicle via API and stores it in a database. The input is the location information from the GPS device. The output is the location information stored in the database.

[0411] Step 2:

[0412] The server collects traffic condition data in real time from the traffic API. Specifically, it obtains traffic signal status, road congestion information, and road closure information via the API and stores it in a database. The input is traffic condition data from the traffic API. The output is the traffic condition data stored in the database.

[0413] Step 3:

[0414] The server inputs the collected location information and traffic condition data into a generative AI model to calculate the optimal transportation route. Specifically, the data is passed to a generative AI model built with TensorFlow and PyTorch to calculate the optimal route. The input is location information and traffic condition data. The output is an optimized transportation route.

[0415] Step 4:

[0416] The server calculates the estimated delivery time for each delivery point based on the optimal transportation route. Specifically, it calculates the estimated arrival time for each point, taking into account expected stop times and other traffic conditions. The input is the optimized transportation route. The output is the estimated delivery time for each delivery point.

[0417] Step 5:

[0418] The server generates a notification message with the calculated estimated delivery time and sends it to the device via an API, using a mail server or SMS gateway. The input is the calculated estimated delivery time, and the output is the notification message sent to the user's device.

[0419] Step 6:

[0420] The server inputs the user's text message, voice, or facial expression data into the emotion engine and analyzes the emotions. Specifically, it uses NLTK or Google Cloud Natural Language API to determine the user's emotional state. The input is the text message or voice data sent by the user. The output is the analyzed emotion data.

[0421] Step 7:

[0422] The server proposes a change in delivery time based on the analyzed emotion data. Specifically, if the user is feeling stressed, it proposes a flexible delivery time. The input is emotion data, and the output is a proposal to change the delivery time.

[0423] Step 8:

[0424] The terminal receives the notification message sent from the server and displays it to the user. Specifically, it notifies the user of the estimated delivery time through a smartphone app or web notification. The input is the notification message from the server, and the output is the notification displayed to the user.

[0425] Step 9:

[0426] The user checks the notified estimated delivery time and adjusts their schedule, such as planning when they will be at home. The input is the notification message, and the output is the user's adjusted schedule.

[0427] Step 10:

[0428] After the delivery is completed, the server records the actual delivery time and emotion data and uses this data to retrain the generative AI model. Specifically, the delivery time information and emotion data stored in the database are used to retrain the generative AI model. The input is the actual delivery time and emotion data, and the output is an updated generative AI model.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Second embodiment]

[0433] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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."

[0445] This invention is a system that optimizes specific transport routes and notifies users of highly accurate scheduled delivery times, taking into account traffic conditions. This system achieves efficient delivery by collecting transport vehicle location information and traffic condition data and optimizing transport routes using generative AI.

[0446] Overview of the embodiment

[0447] This system consists of three main elements: a server, a terminal, and a user.

[0448] server

[0449] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[0450] 1. Data Collection

[0451] The server collects real-time location information sent from the GPS devices of the transport vehicles, as well as traffic condition data such as traffic congestion and road closure information through a traffic condition API.

[0452] 2. Data analysis and route optimization

[0453] The collected location and traffic data is analyzed and generative AI is used to calculate the optimal transportation route, taking into account real-time traffic congestion information and other factors.

[0454] 3. Calculating the estimated delivery time

[0455] Based on the optimized transportation route, the estimated delivery time at each delivery point is calculated.

[0456] 4. Notification System

[0457] The calculated estimated delivery time is notified to the user's device via email, SMS, etc.

[0458] 5. Feedback and learning

[0459] After the delivery is completed, the actual delivery time is recorded, and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[0460] Terminal

[0461] The terminal is used to notify the user of the estimated delivery time. Specifically, it receives the notification sent from the server and displays it to the user, allowing the user to check the estimated delivery time in advance.

[0462] User

[0463] By being at home based on the notified scheduled delivery time, users can easily receive deliveries. By checking the notification, deliveries without being present can be reduced, and efficient delivery can be supported.

[0464] Specific examples

[0465] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0466] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0467] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0468] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0469] 4. The server selects the fastest and most efficient delivery route while taking costs into account.

[0470] 5. The server notifies each user of the estimated delivery time. For example, user A receives an email saying, "Delivery will be at 10:00 today."

[0471] 6. The user checks the notification and adjusts their schedule so that they will be at home at the scheduled delivery time.

[0472] 7. After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[0473] In this way, the present invention achieves improved delivery efficiency and user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[0474] The processing flow will be explained below.

[0475] Step 1:

[0476] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[0477] Step 2:

[0478] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[0479] Step 3:

[0480] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[0481] Step 4:

[0482] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[0483] Step 5:

[0484] The server optimizes the calculated estimated delivery time as necessary and confirms the estimated delivery time for each recipient, which is then stored in a database.

[0485] Step 6:

[0486] The server generates a notification message for each recipient and sends it via email or SMS via the API, including the estimated delivery time, in a user-viewable format.

[0487] Step 7:

[0488] The terminal displays the received notification message to the user, who can then check the estimated delivery time via the terminal.

[0489] Step 8:

[0490] The user makes a plan to be at home based on the notified scheduled delivery time. By being at home, the user can smoothly receive the delivery.

[0491] Step 9:

[0492] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[0493] Step 10:

[0494] The server provides the collected actual delivery time data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[0495] Example 1

[0496] 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."

[0497] Conventional delivery systems are unable to properly reflect the current location of delivery vehicles or real-time traffic conditions, resulting in inaccurate delivery schedules and a low rate of users being at home, leading to frequent missed deliveries. This in turn reduces delivery efficiency and increases costs. Furthermore, delivery plans are not optimized due to a lack of a feedback function that uses data from completed deliveries to retrain the generative AI to improve the accuracy of future predictions.

[0498] 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.

[0499] In this invention, the server includes means for collecting vehicle location information, means for collecting traffic data, means for using a generating AI to analyze the collected location information and traffic data and calculate an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for increasing the user's chance of being at home based on the notified estimated delivery time, and means for recording the time after delivery is completed and retraining the generating AI to improve the accuracy of the next delivery prediction. This improves the accuracy of the estimated delivery time, increases the user's chance of being at home, and reduces missed deliveries. Furthermore, the generating AI can be retrained based on feedback to further optimize the next delivery plan.

[0500] "Means for collecting transport vehicle location information" refers to equipment or technology that obtains the current location of a transport vehicle in real time from a GPS device.

[0501] "Means of collecting traffic condition data" refers to technology that uses APIs and data provision services to obtain real-time traffic information such as traffic congestion information and road closure information.

[0502] "Means of using generative AI to analyze collected location information and traffic condition data and calculate the optimal transportation route" refers to a technology that analyzes collected location information and traffic condition data and uses a generative AI model to calculate the most efficient transportation route.

[0503] The "means for calculating the estimated delivery time based on the calculated transportation route" refers to an algorithm or technology that calculates the estimated arrival time at each delivery point based on the optimal transportation route.

[0504] "Means for notifying the recipient of the calculated estimated delivery time" refers to technology that sends the estimated delivery time to the user's device via email, SMS, application notification, etc.

[0505] "Means for increasing the rate at which users are at home based on the notified scheduled delivery time" refers to techniques or methods for encouraging users to adjust their schedules based on the notified scheduled delivery time and be at home.

[0506] "Means for recording the time after delivery completion and retraining the generating AI to improve the accuracy of the next delivery prediction" refers to a technology that records the time when delivery is completed in a database and uses this data to retrain the generating AI model to improve the accuracy of future delivery predictions.

[0507] This system optimizes specific transportation routes and notifies users of highly accurate estimated delivery times, taking into account traffic conditions. This system consists of three main components: a server, a terminal, and a user.

[0508] server

[0509] The server is responsible for the main data processing and analysis. Specifically, it uses GPS devices to collect vehicle location information and traffic situation APIs (e.g., Google Maps API and Here API) to collect traffic situation data. The server collects the data and records it in an internal database.

[0510] The server then uses a generative AI model (e.g., Google Cloud AI, AWS SageMaker) to analyze the collected location and traffic data, generates prompts, and sends API requests to the generative AI model to calculate the optimal transportation route, taking into account real-time traffic congestion and road closure information.

[0511] Once the optimal delivery route is determined, the server calculates the estimated time of arrival at each delivery point using an algorithm that calculates the travel time to each delivery point based on the optimal route.

[0512] The server uses an SMTP server or SMS sending API (e.g., Twilio API) to notify the user's device of the calculated estimated delivery time, allowing the user to check the estimated delivery time in advance.

[0513] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving the accuracy of future delivery predictions.

[0514] Terminal

[0515] The terminal receives the notification sent from the server and displays the estimated delivery time to the user, allowing the user to know the estimated delivery time in advance and making it easier for the user to receive the delivery.

[0516] User

[0517] Users can check the estimated delivery time displayed on their device and adjust their schedule to be at home at the specified time, which reduces missed deliveries and improves delivery efficiency.

[0518] Specific examples

[0519] For example, consider a scenario where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0520] 1. The server obtains the current location of the transport vehicle from the GPS device and collects traffic condition data in real time from the traffic condition API.

[0521] Specific API examples: Google Maps API, Here API

[0522] 2. The server analyzes the data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0523] Generative AI model examples: Google Cloud AI, AWS SageMaker

[0524] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0525] 4. The server notifies each user of the calculated estimated delivery time. For example, user A receives an email saying "Delivery will be at 10:00 today."

[0526] Notification method: SMTP server, Twilio API, etc.

[0527] 5. The user checks the estimated delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time.

[0528] 6. After the delivery is completed, the server records the actual delivery time and uses this information to retrain the generative AI model. This feedback improves prediction accuracy in future deliveries.

[0529] Prompt Sentence Examples

[0530] For example, you could input the following prompts into a generative AI model:

[0531] "A transport vehicle with current location 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic data."

[0532] In this way, the present invention achieves efficient delivery and improved user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[0533] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0534] Step 1:

[0535] The server collects location information of the transport vehicle. The input for this step is real-time location information sent from the GPS device of the transport vehicle. The server receives this location information and stores it in a database. Specifically, the server periodically polls for data from the GPS device and records the received information in the database.

[0536] Step 2:

[0537] The server collects traffic condition data. The input for this step is real-time traffic congestion and road closure information provided by the traffic condition API. The server calls the API and stores the acquired data in an internal database. Specifically, the server periodically acquires the necessary traffic information using the Google Maps API, Here API, etc., and stores it in the database.

[0538] Step 3:

[0539] The server inputs the collected location information and traffic condition data into the generative AI model. The input data includes the current location of the transport vehicle and the latest traffic conditions. The server creates a prompt based on this data and sends an API request to the generative AI model. Specifically, the server generates a prompt that reads, "A transport vehicle with a current location of 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic condition data," and sends it to the generative AI.

[0540] Step 4:

[0541] The server receives the optimal transportation route and estimated delivery time provided by the generative AI model. The output of the generative AI model includes multiple delivery points and their estimated arrival times. The server receives this information, stores it in a database, and checks the accuracy of each delivery route. Specifically, the server analyzes the response from the generative AI and stores the transportation route in a database.

[0542] Step 5:

[0543] The server notifies the user's device of the optimized estimated delivery time. The input for this step is the calculated estimated delivery time, and the server sends a notification to the user using an SMTP server or SMS sending API. Specifically, the server generates a message saying "Delivery will be at 10:00 today" and sends it to the user via email or SMS. For example, the SMS can be sent using the Twilio API.

[0544] Step 6:

[0545] The user checks the scheduled delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time. The input for this step is the scheduled delivery time notified by the server, and the output is an improvement in the user's rate of being at home. Specifically, the user checks the notification and adjusts their schedule so that they will be at home at the specified time.

[0546] Step 7:

[0547] After the delivery is completed, the server records the actual delivery time. The input for this step is the actual time of delivery, and the server stores this information in a database. Specifically, when the delivery is completed, the server obtains information from the GPS device of the transport vehicle and records the time.

[0548] Step 8:

[0549] The server uses the recorded delivery time to retrain the generative AI model and improve the accuracy of the next prediction. The input for this step is the data at the time of delivery completion, which the server provides to the generative AI model for retraining. Specifically, the server periodically inputs the delivery history recorded in the database into the generative AI model to promote retraining.

[0550] (Application example 1)

[0551] 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."

[0552] Conventional food delivery services have struggled to accurately predict scheduled delivery times while taking into full account changes in traffic conditions and the impact of delivery destination order. This has led to problems such as users being unable to be at home at the scheduled delivery time, resulting in reduced delivery efficiency. Another issue is that information after delivery completion is not provided as feedback, preventing future delivery predictions from improving. Furthermore, there is a lack of a mechanism for notifying users in real time, reducing user convenience.

[0553] 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.

[0554] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generation AI and calculating an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for recording the actual delivery time after delivery completion as feedback and for learning using the generation AI, means for acquiring traffic conditions in real time, and means for sending a push notification to the user. This enables a food delivery service to calculate an optimal delivery route that takes changes in traffic conditions into account, and to provide users with highly accurate estimated delivery times, thereby improving delivery efficiency and user convenience.

[0555] "Means for collecting location information of transport vehicles" refers to devices or software that have the function of obtaining the current location of transport vehicles from a location information system such as GPS and transmitting it to a server.

[0556] "Means for collecting traffic condition data" refers to devices or software that have the function of obtaining traffic condition data such as road congestion information and road closure information from the Internet or external APIs.

[0557] "Generative AI" is an artificial intelligence algorithm that analyzes large amounts of data, learns patterns and trends, and makes predictions and classifications.

[0558] The "means for calculating the optimal transport route" refers to a device or software that has the function of calculating the most efficient route for transport vehicles based on the collected location information and traffic condition data.

[0559] The "means for calculating the estimated delivery time" is a device or software that has the function of calculating the predicted delivery time at each delivery point based on the optimal transportation route.

[0560] "Means for notifying the recipient of the estimated delivery time" refers to devices or software that have the function of notifying the recipient of the calculated estimated delivery time via email, SMS, push notification within the app, etc.

[0561] "Means for recording the actual delivery time after delivery is completed as feedback" refers to a device or software that has the function of recording the actual delivery time as data after delivery is completed and using it to improve prediction accuracy in future deliveries.

[0562] "Means for obtaining traffic conditions in real time" refers to devices or software that have the function of continuously monitoring current traffic conditions and providing the latest data to a server.

[0563] A "means for sending push notifications" is a device or software that has the function of sending messages directly from a server to a user's device such as a smartphone or tablet.

[0564] MODE FOR CARRYING OUT THE INVENTION

[0565] This invention is a system that optimizes specific delivery routes and notifies users of highly accurate estimated delivery times, taking traffic conditions into account. This system achieves efficient delivery by collecting vehicle location information and traffic condition data and optimizing delivery routes using generative AI. The system consists of three main components: a server, a terminal, and a user.

[0566] server

[0567] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[0568] 1. Data Collection

[0569] The server collects real-time location information from the GPS devices of the transport vehicles, as well as traffic data such as traffic congestion and road closures through a traffic API. The software used includes the Google Maps API and an API for GPS data collection.

[0570] 2. Data analysis and route optimization

[0571] The collected location information and traffic situation data are analyzed, and the optimal transportation route is calculated using generative AI. Real-time traffic congestion information and other factors are also taken into account. A generative AI model is used to predict the most efficient route. For example, a generative AI model using TensorFlow is applied.

[0572] 3. Calculating the estimated delivery time

[0573] Based on the optimized transportation route, the system calculates the estimated delivery time at each delivery point, thereby providing highly accurate delivery times.

[0574] 4. Notification System

[0575] The calculated estimated delivery time is notified to the user's device via email, SMS, in-app notification, etc. Firebase is used to send push notifications.

[0576] 5. Feedback and learning

[0577] After the delivery is completed, the actual delivery time is recorded and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[0578] Terminal

[0579] The terminal is used to notify the user of the scheduled delivery time. Specifically, it receives the notification sent from the server and displays it to the user. This allows the user to check the scheduled delivery time in advance, increasing the chance of the user being at home. The terminal can be a smartphone or tablet.

[0580] User

[0581] The user can easily receive the delivery by being at home based on the notified scheduled delivery time. By checking the notification, the number of missed deliveries can be reduced, supporting efficient delivery. The user can adjust their schedule based on the received notification.

[0582] Specific examples

[0583] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In that case, it operates as follows:

[0584] The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0585] The server analyzes the collected location information and traffic condition data using a generative AI model to calculate the optimal transportation route. For example, if road A is congested, detour route B will be selected.

[0586] The server calculates the estimated time of arrival at each delivery point based on the optimal transportation route.

[0587] The server notifies each user of the estimated delivery time. For example, user A receives a notification that "the delivery will be made at 12:15 today."

[0588] After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[0589] Example prompt sentence:

[0590] "The transport vehicle's location is latitude 35.6895, longitude 139.6917."

[0591] "High traffic congestion is expected."

[0592] "Delivery addresses are 123, 456, and 789 in Tokyo."

[0593] This system and method will enable food delivery services to notify highly accurate scheduled delivery times that take into account changes in traffic conditions, significantly improving delivery efficiency and user convenience.

[0594] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0595] Program processing steps

[0596] Step 1:

[0597] The server collects the location information of the transport vehicle in real time from the GPS device. The input is the transport vehicle ID, and the output is the latitude and longitude information. This allows the current vehicle location to be accurately determined.

[0598] Step 2:

[0599] The server collects traffic data from the Internet or external APIs (e.g., Google Maps API). The input is a specific area name or coordinate range, and the output is traffic congestion and road closure information for that area. This allows the server to obtain the latest traffic conditions.

[0600] Step 3:

[0601] Based on the collected location information and traffic data, the server uses a generative AI model to calculate the optimal delivery route. The input is location information, traffic data, and a list of delivery addresses, and the output is an optimized route and estimated arrival time at each delivery point. TensorFlow is used to process the data and calculate the optimal route based on real-time traffic conditions.

[0602] Step 4:

[0603] The server calculates the estimated delivery time based on the calculated transportation route. The input is the optimized route information, and the output is the predicted arrival time at each delivery point. This results in an efficient delivery schedule.

[0604] Step 5:

[0605] The server notifies the user of the calculated estimated delivery time via email, SMS, and push notification. The input is the user's contact information and the estimated delivery time, and the output is a notification message that arrives on the user's device. The notification system uses Firebase.

[0606] Step 6:

[0607] Based on the notification, the user can decide whether to be at home or not and prepare for the scheduled delivery time, making it easier for the user to receive the delivery.

[0608] Step 7:

[0609] After the delivery is completed, the server records the actual delivery time. The input is the delivery completion time, and the output is the recorded history data. This stores the actual delivery time in the database.

[0610] Step 8:

[0611] The server uses the accumulated historical data to retrain the generative AI model and improve the accuracy of future predictions. The input is past delivery data, and the output is an improved predictive model. This improves the accuracy of the next prediction.

[0612] The above are the specific processing steps of the system that realizes the application example, and by following these steps, delivery efficiency and user convenience can be greatly improved.

[0613] 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.

[0614] This invention is a system that uses generative AI to calculate the optimal delivery route based on the location information of the delivery vehicle and traffic condition data, and notifies the user of a highly accurate estimated delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[0615] Overview of the embodiment

[0616] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[0617] server

[0618] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[0619] 1. Data Collection

[0620] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[0621] 2. Data analysis and route optimization

[0622] The server inputs the collected location information and traffic data into the AI ​​generator to calculate the optimal transportation route, taking real-time traffic conditions into account.

[0623] 3. Calculating the estimated delivery time

[0624] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0625] 4. Notification System

[0626] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[0627] 5. Emotion Engine

[0628] The server uses an emotion engine to analyze the user's emotions. It can recognize emotions based on the user's text messages, voice, or facial expression data, and can suggest changes to delivery times based on the results. This emotion data is also used as feedback for the generative AI.

[0629] 6. Feedback and Learning

[0630] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI, improving prediction accuracy in future runs.

[0631] Terminal

[0632] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[0633] 1. Receives notification messages sent by the server and displays them to the user.

[0634] 2. Use an emotion engine to provide notification content based on the user's emotions.

[0635] User

[0636] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[0637] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[0638] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[0639] Specific examples

[0640] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0641] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0642] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0643] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0644] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[0645] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[0646] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[0647] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI, improving the accuracy of the next prediction.

[0648] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[0649] The processing flow will be explained below.

[0650] Step 1:

[0651] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[0652] Step 2:

[0653] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[0654] Step 3:

[0655] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[0656] Step 4:

[0657] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[0658] Step 5:

[0659] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via the API. This notification includes the specific estimated delivery time.

[0660] Step 6:

[0661] The emotion engine analyzes the user's text message, voice, or facial expression data to recognize emotions. For example, if the user feels that the delivery time is slow, the emotion engine analyzes the emotion and provides it to the server.

[0662] Step 7:

[0663] The server can suggest changes to the delivery time based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, the server can add a suggestion to the notification to "advance the delivery time."

[0664] Step 8:

[0665] The terminal displays the received notification message to the user, who can then check the estimated delivery time and suggestions from the server via the terminal.

[0666] Step 9:

[0667] The user can plan their stay at home based on the estimated delivery time. They can also request a change in the delivery time based on the analysis results of the emotion engine. For example, they can send a request to the server such as "Please deliver a little later."

[0668] Step 10:

[0669] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[0670] Step 11:

[0671] The server provides the collected actual delivery time data and emotion data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[0672] In this way, efficient delivery can be achieved while taking into consideration the user's feelings.

[0673] Example 2

[0674] 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."

[0675] In modern logistics systems, efficient route selection for transport vehicles and prediction of scheduled delivery times are important issues. However, conventional systems cannot fully consider fluctuations in traffic conditions or the rate at which users are at home, making it difficult to select optimal routes or accurately calculate scheduled delivery times. Furthermore, frequent missed deliveries lead to reduced delivery efficiency and lower customer satisfaction.

[0676] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0677] In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using generative artificial intelligence and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the recipient's emotional data and adjusting the notification content based on the results, and means for increasing the rate at which the user will be at home based on the estimated delivery time. This makes it possible to select an optimal route taking traffic conditions into consideration in real time and to predict the estimated delivery time with high accuracy, and further to increase the rate at which the user will be at home by analyzing the user's emotions, thereby reducing missed deliveries and improving customer satisfaction.

[0678] "Transport vehicle location information" indicates coordinate data of the location where the transport vehicle is currently located.

[0679] "Traffic condition data" refers to current traffic data relating to the movement of transport vehicles, such as road congestion information and road closure information.

[0680] "Generative artificial intelligence" refers to advanced computational models used to analyze data and make predictions, particularly those that utilize machine learning and deep learning.

[0681] "Analysis" refers to the process of extracting information from collected data and making understanding or predictions.

[0682] The "optimal transportation route" is a route selected for efficient delivery, and is calculated taking into account traffic conditions, distance, time, etc.

[0683] "Scheduled delivery time" refers to the time when a transport vehicle is scheduled to arrive at a particular location.

[0684] "Recipient" means the person or entity intended to receive the delivery.

[0685] "Notification" refers to a message or signal that conveys information to a specific recipient.

[0686] "Emotion data" is information that indicates the user's emotional state, and is extracted from text, voice, facial expressions, and the like.

[0687] The "at-home rate" indicates the probability that a user is at home during a particular time period.

[0688] MODE FOR CARRYING OUT THE INVENTION

[0689] This invention is a system that uses generative artificial intelligence to calculate the optimal transportation route based on the location information of the transportation vehicle and traffic condition data, and notifies the user of a highly accurate scheduled delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[0690] System configuration

[0691] Server Roles

[0692] The server is responsible for the main data processing and analysis, specifically fulfilling the following roles:

[0693] 1. Data Collection

[0694] The server collects real-time location information sent from the GPS devices of transport vehicles, and also collects traffic congestion information, road closure information, etc. using traffic condition APIs, and stores this data in a database.

[0695] 2. Data analysis and route optimization

[0696] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal delivery route, taking real-time traffic conditions into consideration. For example, a prompt might be used: "Based on the current location information and traffic situation data of the delivery vehicle, please calculate the optimal delivery route and estimated delivery time."

[0697] 3. Calculating the estimated delivery time

[0698] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0699] 4. Notification System

[0700] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[0701] 5. Emotion Engine

[0702] The server analyzes the user's text message, voice, or facial expression data to recognize the user's emotions. Based on the analysis results, the server can suggest changes to the delivery time. For example, the prompt could read, "Analyze the user's latest emotional data and suggest changes to the delivery time based on the results."

[0703] 6. Feedback and Learning

[0704] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[0705] Device Role

[0706] The terminal's main role is to notify the user of the estimated delivery time.

[0707] 1. Notification display

[0708] Receives notification messages sent from the server and displays them to the user. For example, it displays a message saying "Delivery will be made at 10:00 today."

[0709] 2. Emotional Engine Support

[0710] It works in conjunction with the server's emotion engine to provide notifications based on the user's emotions. For example, if the user is feeling stressed, it will suggest flexible delivery times.

[0711] User Roles

[0712] The user acts based on the notified estimated delivery time.

[0713] 1. Notification Confirmation and Action Plan

[0714] Check the notification message you received and plan to be at home at the scheduled delivery time. For example, you can plan to be at home at 10:00 today.

[0715] 2. Adjustments based on the emotion engine's suggestions

[0716] Accept the suggestions provided based on the sentiment engine and adjust the delivery time, for example, request a different delivery time.

[0717] Specific examples

[0718] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0719] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0720] 2. The server uses a generation AI to analyze the collected data and calculate the optimal transportation route. For example, "Road A is congested, so select detour route B."

[0721] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0722] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[0723] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[0724] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[0725] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as learning data for the generative AI, improving the accuracy of the next prediction.

[0726] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[0727] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0728] Step 1: Data collection

[0729] The server collects real-time location information from the GPS devices of the transport vehicles, and also obtains traffic congestion and road closure information using the traffic situation API, which is then stored in a database.

[0730] Input: GPS data of transport vehicles, traffic information from traffic situation API

[0731] Output: Location and traffic data stored in a database

[0732] Specific operation: The server obtains location information from the GPS device every second and accesses the traffic situation API via HTTP request to obtain traffic information. This information is stored in a database.

[0733] Step 2: Data analysis and route optimization

[0734] The server inputs the collected location and traffic data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account.

[0735] Input: location information, traffic data

[0736] Output: Optimal transportation route

[0737] Specific operation: The server sends a prompt to the generative AI model saying, "Calculate the optimal route using the current location, destination, and traffic information as input," and determines the next movement step based on the route information returned by the generative AI model.

[0738] Step 3: Calculate the estimated delivery time

[0739] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0740] Input: Optimal transport route, traffic situation data

[0741] Output: Estimated delivery time for each delivery point

[0742] Specific operation: The server calculates the travel time and stop time for each delivery point, and calculates the estimated arrival time at point 1 as 10:00, point 2 as 11:00, and the final point as 12:30.

[0743] Step 4: Notification System

[0744] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[0745] Input: Estimated delivery time

[0746] Output: Notification message to the user terminal

[0747] Specific operation: The server creates a message stating "Delivery will be made at 10:00 today" and sends a notification to the user's device using an email sending API or SMS sending API.

[0748] Step 5: Emotion Engine

[0749] The server analyzes the user's text messages, voice, or facial expression data to recognize their emotions, and then suggests changes to the delivery time based on the results.

[0750] Input: User text messages, voice, and facial expression data

[0751] Output: Sentiment analysis results, suggestion to change delivery time

[0752] Specific operation: When a user sends a message or voice message, the server analyzes it using an emotion engine, and if it determines that the user is "stressed," it takes the action of "suggesting to change the delivery time to 15 minutes later."

[0753] Step 6: Feedback and learning

[0754] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[0755] Input: Actual delivery time

[0756] Output: Retrained generative AI model

[0757] Specific operation: When a delivery is completed, the server saves the actual delivery time in a database and inputs it into the generative AI model with the prompt "Relearn to improve prediction accuracy next time."

[0758] Step 7: User Behavior

[0759] The user acts based on the notified estimated delivery time.

[0760] Input: Notification message

[0761] Output: User action plan, increase in at-home rate

[0762] Specific operation: The user checks the notification message displayed on the device and adds a schedule such as "I'll be at home at 10:00 today" to their calendar. They can also request a change in delivery time based on suggestions from the emotion engine.

[0763] (Application example 2)

[0764] 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."

[0765] Conventional food delivery systems have difficulty calculating the optimal delivery route based on the delivery person's current location information and traffic condition data, and notifying the user of a highly accurate estimated delivery time. Furthermore, since delivery times are notified unilaterally without considering the user's feelings, there is a high possibility of user satisfaction decreasing. Furthermore, frequent missed deliveries lead to inefficiencies and increased costs.

[0766] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generative AI model and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the user's emotions, and means for flexibly changing the delivery time based on the user's emotions. This enables highly accurate notification of the estimated delivery time and flexible delivery response that takes the user's emotions into consideration.

[0767] "Transport vehicle location information" is data indicating the current geographical location of the transport vehicle.

[0768] "Traffic condition data" refers to data that includes information about roads and traffic, such as road congestion and closure information, and the status of traffic signals.

[0769] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to calculate optimal routes and arrival times based on collected data.

[0770] The "optimal transportation route" is the most efficient and quickest route to reach the destination based on collected location information and traffic data.

[0771] The "estimated delivery time" is the arrival time at each delivery point calculated based on the optimal transportation route.

[0772] "Means of notifying recipient" refers to the method or function for notifying the recipient of the calculated estimated delivery time, and mainly includes email, SMS, and in-app notifications.

[0773] "Means for analyzing user emotions" refers to technology for determining a user's emotional state based on voice, text messages, facial expression data, etc.

[0774] The "means for flexibly changing delivery time based on user's emotions" is a method for proposing and executing changes to delivery time in accordance with the analyzed user's emotions.

[0775] "Data collected as feedback" refers to data used as training data for the generative AI model to improve future prediction accuracy, such as delivery time and emotional data recorded after a delivery is completed.

[0776] This invention is a food delivery system that uses a generative AI model to calculate the optimal delivery route based on vehicle location information and traffic condition data, and notifies users of highly accurate estimated delivery times. Furthermore, by combining it with an emotion engine that analyzes user emotions, it is possible to further increase the rate at which users are at home and reduce missed deliveries.

[0777] System configuration

[0778] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[0779] server

[0780] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[0781] 1. Data Collection

[0782] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[0783] 2. Data analysis and route optimization

[0784] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account. The generative AI model is implemented using TensorFlow, PyTorch, and other tools.

[0785] 3. Calculating the estimated delivery time

[0786] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[0787] 4. Notification System

[0788] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via an API, using a mail server or SMS gateway.

[0789] 5. Emotion Engine

[0790] The server uses an emotion engine to analyze the user's emotions. It recognizes emotions based on the user's text message, voice, or facial expression data, and can suggest changes to the delivery time based on the results. The emotion engine uses NLTK and Google Cloud Natural Language API. This emotion data is also used as feedback and training data for the generative AI.

[0791] 6. Feedback and Learning

[0792] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[0793] Terminal

[0794] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[0795] 1. Receives notification messages sent from the server and displays them to the user. This applies to smartphone apps and web notifications.

[0796] 2. Use an emotion engine to provide notification content based on the user's emotions.

[0797] User

[0798] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[0799] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[0800] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[0801] Specific examples

[0802] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In this case, the system operates as follows:

[0803] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0804] 2. The server analyzes the collected data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, it selects detour route B.

[0805] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0806] 4. The server notifies the recipient of the calculated estimated delivery time. User A receives a message saying "Delivery will be at 10:00 today."

[0807] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[0808] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[0809] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI model, improving the accuracy of the next prediction.

[0810] Prompt Sentence Examples

[0811] "Current location: {current_location}, Estimated delivery time: {estimated_delivery_times}, User emotion: {user_emotion}"

[0812] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[0813] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0814] Step 1:

[0815] The server collects the location information of the transport vehicle in real time from the GPS device. Specifically, it obtains the GPS information indicating the current location of the transport vehicle via API and stores it in a database. The input is the location information from the GPS device. The output is the location information stored in the database.

[0816] Step 2:

[0817] The server collects traffic condition data in real time from the traffic API. Specifically, it obtains traffic signal status, road congestion information, and road closure information via the API and stores it in a database. The input is traffic condition data from the traffic API. The output is the traffic condition data stored in the database.

[0818] Step 3:

[0819] The server inputs the collected location information and traffic condition data into a generative AI model to calculate the optimal transportation route. Specifically, the data is passed to a generative AI model built with TensorFlow and PyTorch to calculate the optimal route. The input is location information and traffic condition data. The output is an optimized transportation route.

[0820] Step 4:

[0821] The server calculates the estimated delivery time for each delivery point based on the optimal transportation route. Specifically, it calculates the estimated arrival time for each point, taking into account expected stop times and other traffic conditions. The input is the optimized transportation route. The output is the estimated delivery time for each delivery point.

[0822] Step 5:

[0823] The server generates a notification message with the calculated estimated delivery time and sends it to the device via an API, using a mail server or SMS gateway. The input is the calculated estimated delivery time, and the output is the notification message sent to the user's device.

[0824] Step 6:

[0825] The server inputs the user's text message, voice, or facial expression data into the emotion engine and analyzes the emotions. Specifically, it uses NLTK or Google Cloud Natural Language API to determine the user's emotional state. The input is the text message or voice data sent by the user. The output is the analyzed emotion data.

[0826] Step 7:

[0827] The server proposes a change in delivery time based on the analyzed emotion data. Specifically, if the user is feeling stressed, it proposes a flexible delivery time. The input is emotion data, and the output is a proposal to change the delivery time.

[0828] Step 8:

[0829] The terminal receives the notification message sent from the server and displays it to the user. Specifically, it notifies the user of the estimated delivery time through a smartphone app or web notification. The input is the notification message from the server, and the output is the notification displayed to the user.

[0830] Step 9:

[0831] The user checks the notified estimated delivery time and adjusts their schedule, such as planning when they will be at home. The input is the notification message, and the output is the user's adjusted schedule.

[0832] Step 10:

[0833] After the delivery is completed, the server records the actual delivery time and emotion data and uses this data to retrain the generative AI model. Specifically, the delivery time information and emotion data stored in the database are used to retrain the generative AI model. The input is the actual delivery time and emotion data, and the output is an updated generative AI model.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] [Third embodiment]

[0838] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0839] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0840] 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).

[0841] 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.

[0842] 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.

[0843] 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).

[0844] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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."

[0850] This invention is a system that optimizes specific transport routes and notifies users of highly accurate scheduled delivery times, taking into account traffic conditions. This system achieves efficient delivery by collecting transport vehicle location information and traffic condition data and optimizing transport routes using generative AI.

[0851] Overview of the embodiment

[0852] This system consists of three main elements: a server, a terminal, and a user.

[0853] server

[0854] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[0855] 1. Data Collection

[0856] The server collects real-time location information sent from the GPS devices of the transport vehicles, as well as traffic condition data such as traffic congestion and road closure information through a traffic condition API.

[0857] 2. Data analysis and route optimization

[0858] The collected location and traffic data is analyzed and generative AI is used to calculate the optimal transportation route, taking into account real-time traffic congestion information and other factors.

[0859] 3. Calculating the estimated delivery time

[0860] Based on the optimized transportation route, the estimated delivery time at each delivery point is calculated.

[0861] 4. Notification System

[0862] The calculated estimated delivery time is notified to the user's device via email, SMS, etc.

[0863] 5. Feedback and learning

[0864] After the delivery is completed, the actual delivery time is recorded, and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[0865] Terminal

[0866] The terminal is used to notify the user of the estimated delivery time. Specifically, it receives the notification sent from the server and displays it to the user, allowing the user to check the estimated delivery time in advance.

[0867] User

[0868] By being at home based on the notified scheduled delivery time, users can easily receive deliveries. By checking the notification, deliveries without being present can be reduced, and efficient delivery can be supported.

[0869] Specific examples

[0870] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0871] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0872] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0873] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0874] 4. The server selects the fastest and most efficient delivery route while taking costs into account.

[0875] 5. The server notifies each user of the estimated delivery time. For example, user A receives an email saying, "Delivery will be at 10:00 today."

[0876] 6. The user checks the notification and adjusts their schedule so that they will be at home at the scheduled delivery time.

[0877] 7. After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[0878] In this way, the present invention achieves improved delivery efficiency and user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[0879] The processing flow will be explained below.

[0880] Step 1:

[0881] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[0882] Step 2:

[0883] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[0884] Step 3:

[0885] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[0886] Step 4:

[0887] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[0888] Step 5:

[0889] The server optimizes the calculated estimated delivery time as necessary and confirms the estimated delivery time for each recipient, which is then stored in a database.

[0890] Step 6:

[0891] The server generates a notification message for each recipient and sends it via email or SMS via the API, including the estimated delivery time, in a user-viewable format.

[0892] Step 7:

[0893] The terminal displays the received notification message to the user, who can then check the estimated delivery time via the terminal.

[0894] Step 8:

[0895] The user makes a plan to be at home based on the notified scheduled delivery time. By being at home, the user can smoothly receive the delivery.

[0896] Step 9:

[0897] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[0898] Step 10:

[0899] The server provides the collected actual delivery time data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[0900] Example 1

[0901] 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."

[0902] Conventional delivery systems are unable to properly reflect the current location of delivery vehicles or real-time traffic conditions, resulting in inaccurate delivery schedules and a low rate of users being at home, leading to frequent missed deliveries. This in turn reduces delivery efficiency and increases costs. Furthermore, delivery plans are not optimized due to a lack of a feedback function that uses data from completed deliveries to retrain the generative AI to improve the accuracy of future predictions.

[0903] 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.

[0904] In this invention, the server includes means for collecting vehicle location information, means for collecting traffic data, means for using a generating AI to analyze the collected location information and traffic data and calculate an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for increasing the user's chance of being at home based on the notified estimated delivery time, and means for recording the time after delivery is completed and retraining the generating AI to improve the accuracy of the next delivery prediction. This improves the accuracy of the estimated delivery time, increases the user's chance of being at home, and reduces missed deliveries. Furthermore, the generating AI can be retrained based on feedback to further optimize the next delivery plan.

[0905] "Means for collecting transport vehicle location information" refers to equipment or technology that obtains the current location of a transport vehicle in real time from a GPS device.

[0906] "Means of collecting traffic condition data" refers to technology that uses APIs and data provision services to obtain real-time traffic information such as traffic congestion information and road closure information.

[0907] "Means of using generative AI to analyze collected location information and traffic condition data and calculate the optimal transportation route" refers to a technology that analyzes collected location information and traffic condition data and uses a generative AI model to calculate the most efficient transportation route.

[0908] The "means for calculating the estimated delivery time based on the calculated transportation route" refers to an algorithm or technology that calculates the estimated arrival time at each delivery point based on the optimal transportation route.

[0909] "Means for notifying the recipient of the calculated estimated delivery time" refers to technology that sends the estimated delivery time to the user's device via email, SMS, application notification, etc.

[0910] "Means for increasing the rate at which users are at home based on the notified scheduled delivery time" refers to techniques or methods for encouraging users to adjust their schedules based on the notified scheduled delivery time and be at home.

[0911] "Means for recording the time after delivery completion and retraining the generating AI to improve the accuracy of the next delivery prediction" refers to a technology that records the time when delivery is completed in a database and uses this data to retrain the generating AI model to improve the accuracy of future delivery predictions.

[0912] This system optimizes specific transportation routes and notifies users of highly accurate estimated delivery times, taking into account traffic conditions. This system consists of three main components: a server, a terminal, and a user.

[0913] server

[0914] The server is responsible for the main data processing and analysis. Specifically, it uses GPS devices to collect vehicle location information and traffic situation APIs (e.g., Google Maps API and Here API) to collect traffic situation data. The server collects the data and records it in an internal database.

[0915] The server then uses a generative AI model (e.g., Google Cloud AI, AWS SageMaker) to analyze the collected location and traffic data, generates prompts, and sends API requests to the generative AI model to calculate the optimal transportation route, taking into account real-time traffic congestion and road closure information.

[0916] Once the optimal delivery route is determined, the server calculates the estimated time of arrival at each delivery point using an algorithm that calculates the travel time to each delivery point based on the optimal route.

[0917] The server uses an SMTP server or SMS sending API (e.g., Twilio API) to notify the user's device of the calculated estimated delivery time, allowing the user to check the estimated delivery time in advance.

[0918] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving the accuracy of future delivery predictions.

[0919] Terminal

[0920] The terminal receives the notification sent from the server and displays the estimated delivery time to the user, allowing the user to know the estimated delivery time in advance and making it easier for the user to receive the delivery.

[0921] User

[0922] Users can check the estimated delivery time displayed on their device and adjust their schedule to be at home at the specified time, which reduces missed deliveries and improves delivery efficiency.

[0923] Specific examples

[0924] For example, consider a scenario where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[0925] 1. The server obtains the current location of the transport vehicle from the GPS device and collects traffic condition data in real time from the traffic condition API.

[0926] Specific API examples: Google Maps API, Here API

[0927] 2. The server analyzes the data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, detour route B is selected.

[0928] Generative AI model examples: Google Cloud AI, AWS SageMaker

[0929] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[0930] 4. The server notifies each user of the calculated estimated delivery time. For example, user A receives an email saying "Delivery will be at 10:00 today."

[0931] Notification method: SMTP server, Twilio API, etc.

[0932] 5. The user checks the estimated delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time.

[0933] 6. After the delivery is completed, the server records the actual delivery time and uses this information to retrain the generative AI model. This feedback improves prediction accuracy in future deliveries.

[0934] Prompt Sentence Examples

[0935] For example, you could input the following prompts into a generative AI model:

[0936] "A transport vehicle with current location 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic data."

[0937] In this way, the present invention achieves efficient delivery and improved user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[0938] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0939] Step 1:

[0940] The server collects location information of the transport vehicle. The input for this step is real-time location information sent from the GPS device of the transport vehicle. The server receives this location information and stores it in a database. Specifically, the server periodically polls for data from the GPS device and records the received information in the database.

[0941] Step 2:

[0942] The server collects traffic condition data. The input for this step is real-time traffic congestion and road closure information provided by the traffic condition API. The server calls the API and stores the acquired data in an internal database. Specifically, the server periodically acquires the necessary traffic information using the Google Maps API, Here API, etc., and stores it in the database.

[0943] Step 3:

[0944] The server inputs the collected location information and traffic condition data into the generative AI model. The input data includes the current location of the transport vehicle and the latest traffic conditions. The server creates a prompt based on this data and sends an API request to the generative AI model. Specifically, the server generates a prompt that reads, "A transport vehicle with a current location of 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic condition data," and sends it to the generative AI.

[0945] Step 4:

[0946] The server receives the optimal transportation route and estimated delivery time provided by the generative AI model. The output of the generative AI model includes multiple delivery points and their estimated arrival times. The server receives this information, stores it in a database, and checks the accuracy of each delivery route. Specifically, the server analyzes the response from the generative AI and stores the transportation route in a database.

[0947] Step 5:

[0948] The server notifies the user's device of the optimized estimated delivery time. The input for this step is the calculated estimated delivery time, and the server sends a notification to the user using an SMTP server or SMS sending API. Specifically, the server generates a message saying "Delivery will be at 10:00 today" and sends it to the user via email or SMS. For example, the SMS can be sent using the Twilio API.

[0949] Step 6:

[0950] The user checks the scheduled delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time. The input for this step is the scheduled delivery time notified by the server, and the output is an improvement in the user's rate of being at home. Specifically, the user checks the notification and adjusts their schedule so that they will be at home at the specified time.

[0951] Step 7:

[0952] After the delivery is completed, the server records the actual delivery time. The input for this step is the actual time of delivery, and the server stores this information in a database. Specifically, when the delivery is completed, the server obtains information from the GPS device of the transport vehicle and records the time.

[0953] Step 8:

[0954] The server uses the recorded delivery time to retrain the generative AI model and improve the accuracy of the next prediction. The input for this step is the data at the time of delivery completion, which the server provides to the generative AI model for retraining. Specifically, the server periodically inputs the delivery history recorded in the database into the generative AI model to promote retraining.

[0955] (Application example 1)

[0956] 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."

[0957] Conventional food delivery services have struggled to accurately predict scheduled delivery times while taking into full account changes in traffic conditions and the impact of delivery destination order. This has led to problems such as users being unable to be at home at the scheduled delivery time, resulting in reduced delivery efficiency. Another issue is that information after delivery completion is not provided as feedback, preventing future delivery predictions from improving. Furthermore, there is a lack of a mechanism for notifying users in real time, reducing user convenience.

[0958] 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.

[0959] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generation AI and calculating an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for recording the actual delivery time after delivery completion as feedback and for learning using the generation AI, means for acquiring traffic conditions in real time, and means for sending a push notification to the user. This enables a food delivery service to calculate an optimal delivery route that takes changes in traffic conditions into account, and to provide users with highly accurate estimated delivery times, thereby improving delivery efficiency and user convenience.

[0960] "Means for collecting location information of transport vehicles" refers to devices or software that have the function of obtaining the current location of transport vehicles from a location information system such as GPS and transmitting it to a server.

[0961] "Means for collecting traffic condition data" refers to devices or software that have the function of obtaining traffic condition data such as road congestion information and road closure information from the Internet or external APIs.

[0962] "Generative AI" is an artificial intelligence algorithm that analyzes large amounts of data, learns patterns and trends, and makes predictions and classifications.

[0963] The "means for calculating the optimal transport route" refers to a device or software that has the function of calculating the most efficient route for transport vehicles based on the collected location information and traffic condition data.

[0964] The "means for calculating the estimated delivery time" is a device or software that has the function of calculating the predicted delivery time at each delivery point based on the optimal transportation route.

[0965] "Means for notifying the recipient of the estimated delivery time" refers to devices or software that have the function of notifying the recipient of the calculated estimated delivery time via email, SMS, push notification within the app, etc.

[0966] "Means for recording the actual delivery time after delivery is completed as feedback" refers to a device or software that has the function of recording the actual delivery time as data after delivery is completed and using it to improve prediction accuracy in future deliveries.

[0967] "Means for obtaining traffic conditions in real time" refers to devices or software that have the function of continuously monitoring current traffic conditions and providing the latest data to a server.

[0968] A "means for sending push notifications" is a device or software that has the function of sending messages directly from a server to a user's device such as a smartphone or tablet.

[0969] MODE FOR CARRYING OUT THE INVENTION

[0970] This invention is a system that optimizes specific delivery routes and notifies users of highly accurate estimated delivery times, taking traffic conditions into account. This system achieves efficient delivery by collecting vehicle location information and traffic condition data and optimizing delivery routes using generative AI. The system consists of three main components: a server, a terminal, and a user.

[0971] server

[0972] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[0973] 1. Data Collection

[0974] The server collects real-time location information from the GPS devices of the transport vehicles, as well as traffic data such as traffic congestion and road closures through a traffic API. The software used includes the Google Maps API and an API for GPS data collection.

[0975] 2. Data analysis and route optimization

[0976] The collected location information and traffic situation data are analyzed, and the optimal transportation route is calculated using generative AI. Real-time traffic congestion information and other factors are also taken into account. A generative AI model is used to predict the most efficient route. For example, a generative AI model using TensorFlow is applied.

[0977] 3. Calculating the estimated delivery time

[0978] Based on the optimized transportation route, the system calculates the estimated delivery time at each delivery point, thereby providing highly accurate delivery times.

[0979] 4. Notification System

[0980] The calculated estimated delivery time is notified to the user's device via email, SMS, in-app notification, etc. Firebase is used to send push notifications.

[0981] 5. Feedback and learning

[0982] After the delivery is completed, the actual delivery time is recorded and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[0983] Terminal

[0984] The terminal is used to notify the user of the scheduled delivery time. Specifically, it receives the notification sent from the server and displays it to the user. This allows the user to check the scheduled delivery time in advance, increasing the chance of the user being at home. The terminal can be a smartphone or tablet.

[0985] User

[0986] The user can easily receive the delivery by being at home based on the notified scheduled delivery time. By checking the notification, the number of missed deliveries can be reduced, supporting efficient delivery. The user can adjust their schedule based on the received notification.

[0987] Specific examples

[0988] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In that case, it operates as follows:

[0989] The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[0990] The server analyzes the collected location information and traffic condition data using a generative AI model to calculate the optimal transportation route. For example, if road A is congested, detour route B will be selected.

[0991] The server calculates the estimated time of arrival at each delivery point based on the optimal transportation route.

[0992] The server notifies each user of the estimated delivery time. For example, user A receives a notification that "the delivery will be made at 12:15 today."

[0993] After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[0994] Example prompt sentence:

[0995] "The transport vehicle's location is latitude 35.6895, longitude 139.6917."

[0996] "High traffic congestion is expected."

[0997] "Delivery addresses are 123, 456, and 789 in Tokyo."

[0998] This system and method will enable food delivery services to notify highly accurate scheduled delivery times that take into account changes in traffic conditions, significantly improving delivery efficiency and user convenience.

[0999] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1000] Program processing steps

[1001] Step 1:

[1002] The server collects the location information of the transport vehicle in real time from the GPS device. The input is the transport vehicle ID, and the output is the latitude and longitude information. This allows the current vehicle location to be accurately determined.

[1003] Step 2:

[1004] The server collects traffic data from the Internet or external APIs (e.g., Google Maps API). The input is a specific area name or coordinate range, and the output is traffic congestion and road closure information for that area. This allows the server to obtain the latest traffic conditions.

[1005] Step 3:

[1006] Based on the collected location information and traffic data, the server uses a generative AI model to calculate the optimal delivery route. The input is location information, traffic data, and a list of delivery addresses, and the output is an optimized route and estimated arrival time at each delivery point. TensorFlow is used to process the data and calculate the optimal route based on real-time traffic conditions.

[1007] Step 4:

[1008] The server calculates the estimated delivery time based on the calculated transportation route. The input is the optimized route information, and the output is the predicted arrival time at each delivery point. This results in an efficient delivery schedule.

[1009] Step 5:

[1010] The server notifies the user of the calculated estimated delivery time via email, SMS, and push notification. The input is the user's contact information and the estimated delivery time, and the output is a notification message that arrives on the user's device. The notification system uses Firebase.

[1011] Step 6:

[1012] Based on the notification, the user can decide whether to be at home or not and prepare for the scheduled delivery time, making it easier for the user to receive the delivery.

[1013] Step 7:

[1014] After the delivery is completed, the server records the actual delivery time. The input is the delivery completion time, and the output is the recorded history data. This stores the actual delivery time in the database.

[1015] Step 8:

[1016] The server uses the accumulated historical data to retrain the generative AI model and improve the accuracy of future predictions. The input is past delivery data, and the output is an improved predictive model. This improves the accuracy of the next prediction.

[1017] The above are the specific processing steps of the system that realizes the application example, and by following these steps, delivery efficiency and user convenience can be greatly improved.

[1018] 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.

[1019] This invention is a system that uses generative AI to calculate the optimal delivery route based on the location information of the delivery vehicle and traffic condition data, and notifies the user of a highly accurate estimated delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[1020] Overview of the embodiment

[1021] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[1022] server

[1023] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[1024] 1. Data Collection

[1025] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[1026] 2. Data analysis and route optimization

[1027] The server inputs the collected location information and traffic data into the AI ​​generator to calculate the optimal transportation route, taking real-time traffic conditions into account.

[1028] 3. Calculating the estimated delivery time

[1029] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1030] 4. Notification System

[1031] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[1032] 5. Emotion Engine

[1033] The server uses an emotion engine to analyze the user's emotions. It can recognize emotions based on the user's text messages, voice, or facial expression data, and can suggest changes to delivery times based on the results. This emotion data is also used as feedback for the generative AI.

[1034] 6. Feedback and Learning

[1035] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI, improving prediction accuracy in future runs.

[1036] Terminal

[1037] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[1038] 1. Receives notification messages sent by the server and displays them to the user.

[1039] 2. Use an emotion engine to provide notification content based on the user's emotions.

[1040] User

[1041] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[1042] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[1043] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[1044] Specific examples

[1045] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[1046] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1047] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[1048] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1049] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[1050] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[1051] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[1052] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI, improving the accuracy of the next prediction.

[1053] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[1057] Step 2:

[1058] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[1059] Step 3:

[1060] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[1061] Step 4:

[1062] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[1063] Step 5:

[1064] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via the API. This notification includes the specific estimated delivery time.

[1065] Step 6:

[1066] The emotion engine analyzes the user's text message, voice, or facial expression data to recognize emotions. For example, if the user feels that the delivery time is slow, the emotion engine analyzes the emotion and provides it to the server.

[1067] Step 7:

[1068] The server can suggest changes to the delivery time based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, the server can add a suggestion to the notification to "advance the delivery time."

[1069] Step 8:

[1070] The terminal displays the received notification message to the user, who can then check the estimated delivery time and suggestions from the server via the terminal.

[1071] Step 9:

[1072] The user can plan their stay at home based on the estimated delivery time. They can also request a change in the delivery time based on the analysis results of the emotion engine. For example, they can send a request to the server such as "Please deliver a little later."

[1073] Step 10:

[1074] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[1075] Step 11:

[1076] The server provides the collected actual delivery time data and emotion data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[1077] In this way, efficient delivery can be achieved while taking into consideration the user's feelings.

[1078] Example 2

[1079] 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."

[1080] In modern logistics systems, efficient route selection for transport vehicles and prediction of scheduled delivery times are important issues. However, conventional systems cannot fully consider fluctuations in traffic conditions or the rate at which users are at home, making it difficult to select optimal routes or accurately calculate scheduled delivery times. Furthermore, frequent missed deliveries lead to reduced delivery efficiency and lower customer satisfaction.

[1081] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1082] In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using generative artificial intelligence and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the recipient's emotional data and adjusting the notification content based on the results, and means for increasing the rate at which the user will be at home based on the estimated delivery time. This makes it possible to select an optimal route taking traffic conditions into consideration in real time and to predict the estimated delivery time with high accuracy, and further to increase the rate at which the user will be at home by analyzing the user's emotions, thereby reducing missed deliveries and improving customer satisfaction.

[1083] "Transport vehicle location information" indicates coordinate data of the location where the transport vehicle is currently located.

[1084] "Traffic condition data" refers to current traffic data relating to the movement of transport vehicles, such as road congestion information and road closure information.

[1085] "Generative artificial intelligence" refers to advanced computational models used to analyze data and make predictions, particularly those that utilize machine learning and deep learning.

[1086] "Analysis" refers to the process of extracting information from collected data and making understanding or predictions.

[1087] The "optimal transportation route" is a route selected for efficient delivery, and is calculated taking into account traffic conditions, distance, time, etc.

[1088] "Scheduled delivery time" refers to the time when a transport vehicle is scheduled to arrive at a particular location.

[1089] "Recipient" means the person or entity intended to receive the delivery.

[1090] "Notification" refers to a message or signal that conveys information to a specific recipient.

[1091] "Emotion data" is information that indicates the user's emotional state, and is extracted from text, voice, facial expressions, and the like.

[1092] The "at-home rate" indicates the probability that a user is at home during a particular time period.

[1093] MODE FOR CARRYING OUT THE INVENTION

[1094] This invention is a system that uses generative artificial intelligence to calculate the optimal transportation route based on the location information of the transportation vehicle and traffic condition data, and notifies the user of a highly accurate scheduled delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[1095] System configuration

[1096] Server Roles

[1097] The server is responsible for the main data processing and analysis, specifically fulfilling the following roles:

[1098] 1. Data Collection

[1099] The server collects real-time location information sent from the GPS devices of transport vehicles, and also collects traffic congestion information, road closure information, etc. using traffic condition APIs, and stores this data in a database.

[1100] 2. Data analysis and route optimization

[1101] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal delivery route, taking real-time traffic conditions into consideration. For example, a prompt might be used: "Based on the current location information and traffic situation data of the delivery vehicle, please calculate the optimal delivery route and estimated delivery time."

[1102] 3. Calculating the estimated delivery time

[1103] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1104] 4. Notification System

[1105] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[1106] 5. Emotion Engine

[1107] The server analyzes the user's text message, voice, or facial expression data to recognize the user's emotions. Based on the analysis results, the server can suggest changes to the delivery time. For example, the prompt could read, "Analyze the user's latest emotional data and suggest changes to the delivery time based on the results."

[1108] 6. Feedback and Learning

[1109] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[1110] Device Role

[1111] The terminal's main role is to notify the user of the estimated delivery time.

[1112] 1. Notification display

[1113] Receives notification messages sent from the server and displays them to the user. For example, it displays a message saying "Delivery will be made at 10:00 today."

[1114] 2. Emotional Engine Support

[1115] It works in conjunction with the server's emotion engine to provide notifications based on the user's emotions. For example, if the user is feeling stressed, it will suggest flexible delivery times.

[1116] User Roles

[1117] The user acts based on the notified estimated delivery time.

[1118] 1. Notification Confirmation and Action Plan

[1119] Check the notification message you received and plan to be at home at the scheduled delivery time. For example, you can plan to be at home at 10:00 today.

[1120] 2. Adjustments based on the emotion engine's suggestions

[1121] Accept the suggestions provided based on the sentiment engine and adjust the delivery time, for example, request a different delivery time.

[1122] Specific examples

[1123] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[1124] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1125] 2. The server uses a generation AI to analyze the collected data and calculate the optimal transportation route. For example, "Road A is congested, so select detour route B."

[1126] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1127] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[1128] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[1129] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[1130] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as learning data for the generative AI, improving the accuracy of the next prediction.

[1131] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[1132] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1133] Step 1: Data collection

[1134] The server collects real-time location information from the GPS devices of the transport vehicles, and also obtains traffic congestion and road closure information using the traffic situation API, which is then stored in a database.

[1135] Input: GPS data of transport vehicles, traffic information from traffic situation API

[1136] Output: Location and traffic data stored in a database

[1137] Specific operation: The server obtains location information from the GPS device every second and accesses the traffic situation API via HTTP request to obtain traffic information. This information is stored in a database.

[1138] Step 2: Data analysis and route optimization

[1139] The server inputs the collected location and traffic data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account.

[1140] Input: location information, traffic data

[1141] Output: Optimal transportation route

[1142] Specific operation: The server sends a prompt to the generative AI model saying, "Calculate the optimal route using the current location, destination, and traffic information as input," and determines the next movement step based on the route information returned by the generative AI model.

[1143] Step 3: Calculate the estimated delivery time

[1144] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1145] Input: Optimal transport route, traffic situation data

[1146] Output: Estimated delivery time for each delivery point

[1147] Specific operation: The server calculates the travel time and stop time for each delivery point, and calculates the estimated arrival time at point 1 as 10:00, point 2 as 11:00, and the final point as 12:30.

[1148] Step 4: Notification System

[1149] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[1150] Input: Estimated delivery time

[1151] Output: Notification message to the user terminal

[1152] Specific operation: The server creates a message stating "Delivery will be made at 10:00 today" and sends a notification to the user's device using an email sending API or SMS sending API.

[1153] Step 5: Emotion Engine

[1154] The server analyzes the user's text messages, voice, or facial expression data to recognize their emotions, and then suggests changes to the delivery time based on the results.

[1155] Input: User text messages, voice, and facial expression data

[1156] Output: Sentiment analysis results, suggestion to change delivery time

[1157] Specific operation: When a user sends a message or voice message, the server analyzes it using an emotion engine, and if it determines that the user is "stressed," it takes the action of "suggesting to change the delivery time to 15 minutes later."

[1158] Step 6: Feedback and learning

[1159] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[1160] Input: Actual delivery time

[1161] Output: Retrained generative AI model

[1162] Specific operation: When a delivery is completed, the server saves the actual delivery time in a database and inputs it into the generative AI model with the prompt "Relearn to improve prediction accuracy next time."

[1163] Step 7: User Behavior

[1164] The user acts based on the notified estimated delivery time.

[1165] Input: Notification message

[1166] Output: User action plan, increase in at-home rate

[1167] Specific operation: The user checks the notification message displayed on the device and adds a schedule such as "I'll be at home at 10:00 today" to their calendar. They can also request a change in delivery time based on suggestions from the emotion engine.

[1168] (Application example 2)

[1169] 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."

[1170] Conventional food delivery systems have difficulty calculating the optimal delivery route based on the delivery person's current location information and traffic condition data, and notifying the user of a highly accurate estimated delivery time. Furthermore, since delivery times are notified unilaterally without considering the user's feelings, there is a high possibility of user satisfaction decreasing. Furthermore, frequent missed deliveries lead to inefficiencies and increased costs.

[1171] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generative AI model and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the user's emotions, and means for flexibly changing the delivery time based on the user's emotions. This enables highly accurate notification of the estimated delivery time and flexible delivery response that takes the user's emotions into consideration.

[1172] "Transport vehicle location information" is data indicating the current geographical location of the transport vehicle.

[1173] "Traffic condition data" refers to data that includes information about roads and traffic, such as road congestion and closure information, and the status of traffic signals.

[1174] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to calculate optimal routes and arrival times based on collected data.

[1175] The "optimal transportation route" is the most efficient and quickest route to reach the destination based on collected location information and traffic data.

[1176] The "estimated delivery time" is the arrival time at each delivery point calculated based on the optimal transportation route.

[1177] "Means of notifying recipient" refers to the method or function for notifying the recipient of the calculated estimated delivery time, and mainly includes email, SMS, and in-app notifications.

[1178] "Means for analyzing user emotions" refers to technology for determining a user's emotional state based on voice, text messages, facial expression data, etc.

[1179] The "means for flexibly changing delivery time based on user's emotions" is a method for proposing and executing changes to delivery time in accordance with the analyzed user's emotions.

[1180] "Data collected as feedback" refers to data used as training data for the generative AI model to improve future prediction accuracy, such as delivery time and emotional data recorded after a delivery is completed.

[1181] This invention is a food delivery system that uses a generative AI model to calculate the optimal delivery route based on vehicle location information and traffic condition data, and notifies users of highly accurate estimated delivery times. Furthermore, by combining it with an emotion engine that analyzes user emotions, it is possible to further increase the rate at which users are at home and reduce missed deliveries.

[1182] System configuration

[1183] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[1184] server

[1185] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[1186] 1. Data Collection

[1187] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[1188] 2. Data analysis and route optimization

[1189] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account. The generative AI model is implemented using TensorFlow, PyTorch, and other tools.

[1190] 3. Calculating the estimated delivery time

[1191] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1192] 4. Notification System

[1193] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via an API, using a mail server or SMS gateway.

[1194] 5. Emotion Engine

[1195] The server uses an emotion engine to analyze the user's emotions. It recognizes emotions based on the user's text message, voice, or facial expression data, and can suggest changes to the delivery time based on the results. The emotion engine uses NLTK and Google Cloud Natural Language API. This emotion data is also used as feedback and training data for the generative AI.

[1196] 6. Feedback and Learning

[1197] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[1198] Terminal

[1199] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[1200] 1. Receives notification messages sent from the server and displays them to the user. This applies to smartphone apps and web notifications.

[1201] 2. Use an emotion engine to provide notification content based on the user's emotions.

[1202] User

[1203] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[1204] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[1205] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[1206] Specific examples

[1207] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In this case, the system operates as follows:

[1208] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1209] 2. The server analyzes the collected data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, it selects detour route B.

[1210] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1211] 4. The server notifies the recipient of the calculated estimated delivery time. User A receives a message saying "Delivery will be at 10:00 today."

[1212] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[1213] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[1214] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI model, improving the accuracy of the next prediction.

[1215] Prompt Sentence Examples

[1216] "Current location: {current_location}, Estimated delivery time: {estimated_delivery_times}, User emotion: {user_emotion}"

[1217] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[1218] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1219] Step 1:

[1220] The server collects the location information of the transport vehicle in real time from the GPS device. Specifically, it obtains the GPS information indicating the current location of the transport vehicle via API and stores it in a database. The input is the location information from the GPS device. The output is the location information stored in the database.

[1221] Step 2:

[1222] The server collects traffic condition data in real time from the traffic API. Specifically, it obtains traffic signal status, road congestion information, and road closure information via the API and stores it in a database. The input is traffic condition data from the traffic API. The output is the traffic condition data stored in the database.

[1223] Step 3:

[1224] The server inputs the collected location information and traffic condition data into a generative AI model to calculate the optimal transportation route. Specifically, the data is passed to a generative AI model built with TensorFlow and PyTorch to calculate the optimal route. The input is location information and traffic condition data. The output is an optimized transportation route.

[1225] Step 4:

[1226] The server calculates the estimated delivery time for each delivery point based on the optimal transportation route. Specifically, it calculates the estimated arrival time for each point, taking into account expected stop times and other traffic conditions. The input is the optimized transportation route. The output is the estimated delivery time for each delivery point.

[1227] Step 5:

[1228] The server generates a notification message with the calculated estimated delivery time and sends it to the device via an API, using a mail server or SMS gateway. The input is the calculated estimated delivery time, and the output is the notification message sent to the user's device.

[1229] Step 6:

[1230] The server inputs the user's text message, voice, or facial expression data into the emotion engine and analyzes the emotions. Specifically, it uses NLTK or Google Cloud Natural Language API to determine the user's emotional state. The input is the text message or voice data sent by the user. The output is the analyzed emotion data.

[1231] Step 7:

[1232] The server proposes a change in delivery time based on the analyzed emotion data. Specifically, if the user is feeling stressed, it proposes a flexible delivery time. The input is emotion data, and the output is a proposal to change the delivery time.

[1233] Step 8:

[1234] The terminal receives the notification message sent from the server and displays it to the user. Specifically, it notifies the user of the estimated delivery time through a smartphone app or web notification. The input is the notification message from the server, and the output is the notification displayed to the user.

[1235] Step 9:

[1236] The user checks the notified estimated delivery time and adjusts their schedule, such as planning when they will be at home. The input is the notification message, and the output is the user's adjusted schedule.

[1237] Step 10:

[1238] After the delivery is completed, the server records the actual delivery time and emotion data and uses this data to retrain the generative AI model. Specifically, the delivery time information and emotion data stored in the database are used to retrain the generative AI model. The input is the actual delivery time and emotion data, and the output is an updated generative AI model.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] [Fourth embodiment]

[1243] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1244] 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.

[1245] 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).

[1246] 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.

[1247] 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.

[1248] 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).

[1249] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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."

[1256] This invention is a system that optimizes specific transport routes and notifies users of highly accurate scheduled delivery times, taking into account traffic conditions. This system achieves efficient delivery by collecting transport vehicle location information and traffic condition data and optimizing transport routes using generative AI.

[1257] Overview of the embodiment

[1258] This system consists of three main elements: a server, a terminal, and a user.

[1259] server

[1260] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[1261] 1. Data Collection

[1262] The server collects real-time location information sent from the GPS devices of the transport vehicles, as well as traffic condition data such as traffic congestion and road closure information through a traffic condition API.

[1263] 2. Data analysis and route optimization

[1264] The collected location and traffic data is analyzed and generative AI is used to calculate the optimal transportation route, taking into account real-time traffic congestion information and other factors.

[1265] 3. Calculating the estimated delivery time

[1266] Based on the optimized transportation route, the estimated delivery time at each delivery point is calculated.

[1267] 4. Notification System

[1268] The calculated estimated delivery time is notified to the user's device via email, SMS, etc.

[1269] 5. Feedback and learning

[1270] After the delivery is completed, the actual delivery time is recorded, and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[1271] Terminal

[1272] The terminal is used to notify the user of the estimated delivery time. Specifically, it receives the notification sent from the server and displays it to the user, allowing the user to check the estimated delivery time in advance.

[1273] User

[1274] By being at home based on the notified scheduled delivery time, users can easily receive deliveries. By checking the notification, deliveries without being present can be reduced, and efficient delivery can be supported.

[1275] Specific examples

[1276] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[1277] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1278] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[1279] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1280] 4. The server selects the fastest and most efficient delivery route while taking costs into account.

[1281] 5. The server notifies each user of the estimated delivery time. For example, user A receives an email saying, "Delivery will be at 10:00 today."

[1282] 6. The user checks the notification and adjusts their schedule so that they will be at home at the scheduled delivery time.

[1283] 7. After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[1284] In this way, the present invention achieves improved delivery efficiency and user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[1285] The processing flow will be explained below.

[1286] Step 1:

[1287] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[1288] Step 2:

[1289] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[1290] Step 3:

[1291] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[1292] Step 4:

[1293] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[1294] Step 5:

[1295] The server optimizes the calculated estimated delivery time as necessary and confirms the estimated delivery time for each recipient, which is then stored in a database.

[1296] Step 6:

[1297] The server generates a notification message for each recipient and sends it via email or SMS via the API, including the estimated delivery time, in a user-viewable format.

[1298] Step 7:

[1299] The terminal displays the received notification message to the user, who can then check the estimated delivery time via the terminal.

[1300] Step 8:

[1301] The user makes a plan to be at home based on the notified scheduled delivery time. By being at home, the user can smoothly receive the delivery.

[1302] Step 9:

[1303] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[1304] Step 10:

[1305] The server provides the collected actual delivery time data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[1306] Example 1

[1307] 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."

[1308] Conventional delivery systems are unable to properly reflect the current location of delivery vehicles or real-time traffic conditions, resulting in inaccurate delivery schedules and a low rate of users being at home, leading to frequent missed deliveries. This in turn reduces delivery efficiency and increases costs. Furthermore, delivery plans are not optimized due to a lack of a feedback function that uses data from completed deliveries to retrain the generative AI to improve the accuracy of future predictions.

[1309] 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.

[1310] In this invention, the server includes means for collecting vehicle location information, means for collecting traffic data, means for using a generating AI to analyze the collected location information and traffic data and calculate an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for increasing the user's chance of being at home based on the notified estimated delivery time, and means for recording the time after delivery is completed and retraining the generating AI to improve the accuracy of the next delivery prediction. This improves the accuracy of the estimated delivery time, increases the user's chance of being at home, and reduces missed deliveries. Furthermore, the generating AI can be retrained based on feedback to further optimize the next delivery plan.

[1311] "Means for collecting transport vehicle location information" refers to equipment or technology that obtains the current location of a transport vehicle in real time from a GPS device.

[1312] "Means of collecting traffic condition data" refers to technology that uses APIs and data provision services to obtain real-time traffic information such as traffic congestion information and road closure information.

[1313] "Means of using generative AI to analyze collected location information and traffic condition data and calculate the optimal transportation route" refers to a technology that analyzes collected location information and traffic condition data and uses a generative AI model to calculate the most efficient transportation route.

[1314] The "means for calculating the estimated delivery time based on the calculated transportation route" refers to an algorithm or technology that calculates the estimated arrival time at each delivery point based on the optimal transportation route.

[1315] "Means for notifying the recipient of the calculated estimated delivery time" refers to technology that sends the estimated delivery time to the user's device via email, SMS, application notification, etc.

[1316] "Means for increasing the rate at which users are at home based on the notified scheduled delivery time" refers to techniques or methods for encouraging users to adjust their schedules based on the notified scheduled delivery time and be at home.

[1317] "Means for recording the time after delivery completion and retraining the generating AI to improve the accuracy of the next delivery prediction" refers to a technology that records the time when delivery is completed in a database and uses this data to retrain the generating AI model to improve the accuracy of future delivery predictions.

[1318] This system optimizes specific transportation routes and notifies users of highly accurate estimated delivery times, taking into account traffic conditions. This system consists of three main components: a server, a terminal, and a user.

[1319] server

[1320] The server is responsible for the main data processing and analysis. Specifically, it uses GPS devices to collect vehicle location information and traffic situation APIs (e.g., Google Maps API and Here API) to collect traffic situation data. The server collects the data and records it in an internal database.

[1321] The server then uses a generative AI model (e.g., Google Cloud AI, AWS SageMaker) to analyze the collected location and traffic data, generates prompts, and sends API requests to the generative AI model to calculate the optimal transportation route, taking into account real-time traffic congestion and road closure information.

[1322] Once the optimal delivery route is determined, the server calculates the estimated time of arrival at each delivery point using an algorithm that calculates the travel time to each delivery point based on the optimal route.

[1323] The server uses an SMTP server or SMS sending API (e.g., Twilio API) to notify the user's device of the calculated estimated delivery time, allowing the user to check the estimated delivery time in advance.

[1324] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving the accuracy of future delivery predictions.

[1325] Terminal

[1326] The terminal receives the notification sent from the server and displays the estimated delivery time to the user, allowing the user to know the estimated delivery time in advance and making it easier for the user to receive the delivery.

[1327] User

[1328] Users can check the estimated delivery time displayed on their device and adjust their schedule to be at home at the specified time, which reduces missed deliveries and improves delivery efficiency.

[1329] Specific examples

[1330] For example, consider a scenario where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[1331] 1. The server obtains the current location of the transport vehicle from the GPS device and collects traffic condition data in real time from the traffic condition API.

[1332] Specific API examples: Google Maps API, Here API

[1333] 2. The server analyzes the data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, detour route B is selected.

[1334] Generative AI model examples: Google Cloud AI, AWS SageMaker

[1335] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1336] 4. The server notifies each user of the calculated estimated delivery time. For example, user A receives an email saying "Delivery will be at 10:00 today."

[1337] Notification method: SMTP server, Twilio API, etc.

[1338] 5. The user checks the estimated delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time.

[1339] 6. After the delivery is completed, the server records the actual delivery time and uses this information to retrain the generative AI model. This feedback improves prediction accuracy in future deliveries.

[1340] Prompt Sentence Examples

[1341] For example, you could input the following prompts into a generative AI model:

[1342] "A transport vehicle with current location 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic data."

[1343] In this way, the present invention achieves efficient delivery and improved user convenience through optimization of transportation routes and calculation of highly accurate scheduled delivery times.

[1344] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1345] Step 1:

[1346] The server collects location information of the transport vehicle. The input for this step is real-time location information sent from the GPS device of the transport vehicle. The server receives this location information and stores it in a database. Specifically, the server periodically polls for data from the GPS device and records the received information in the database.

[1347] Step 2:

[1348] The server collects traffic condition data. The input for this step is real-time traffic congestion and road closure information provided by the traffic condition API. The server calls the API and stores the acquired data in an internal database. Specifically, the server periodically acquires the necessary traffic information using the Google Maps API, Here API, etc., and stores it in the database.

[1349] Step 3:

[1350] The server inputs the collected location information and traffic condition data into the generative AI model. The input data includes the current location of the transport vehicle and the latest traffic conditions. The server creates a prompt based on this data and sends an API request to the generative AI model. Specifically, the server generates a prompt that reads, "A transport vehicle with a current location of 35.6895, 139.6917 is heading to Shibuya. Please calculate the optimal route and estimated arrival time taking into account the latest traffic condition data," and sends it to the generative AI.

[1351] Step 4:

[1352] The server receives the optimal transportation route and estimated delivery time provided by the generative AI model. The output of the generative AI model includes multiple delivery points and their estimated arrival times. The server receives this information, stores it in a database, and checks the accuracy of each delivery route. Specifically, the server analyzes the response from the generative AI and stores the transportation route in a database.

[1353] Step 5:

[1354] The server notifies the user's device of the optimized estimated delivery time. The input for this step is the calculated estimated delivery time, and the server sends a notification to the user using an SMTP server or SMS sending API. Specifically, the server generates a message saying "Delivery will be at 10:00 today" and sends it to the user via email or SMS. For example, the SMS can be sent using the Twilio API.

[1355] Step 6:

[1356] The user checks the scheduled delivery time displayed on the terminal and adjusts their schedule so that they will be at home at the specified time. The input for this step is the scheduled delivery time notified by the server, and the output is an improvement in the user's rate of being at home. Specifically, the user checks the notification and adjusts their schedule so that they will be at home at the specified time.

[1357] Step 7:

[1358] After the delivery is completed, the server records the actual delivery time. The input for this step is the actual time of delivery, and the server stores this information in a database. Specifically, when the delivery is completed, the server obtains information from the GPS device of the transport vehicle and records the time.

[1359] Step 8:

[1360] The server uses the recorded delivery time to retrain the generative AI model and improve the accuracy of the next prediction. The input for this step is the data at the time of delivery completion, which the server provides to the generative AI model for retraining. Specifically, the server periodically inputs the delivery history recorded in the database into the generative AI model to promote retraining.

[1361] (Application example 1)

[1362] 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."

[1363] Conventional food delivery services have struggled to accurately predict scheduled delivery times while taking into full account changes in traffic conditions and the impact of delivery destination order. This has led to problems such as users being unable to be at home at the scheduled delivery time, resulting in reduced delivery efficiency. Another issue is that information after delivery completion is not provided as feedback, preventing future delivery predictions from improving. Furthermore, there is a lack of a mechanism for notifying users in real time, reducing user convenience.

[1364] 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.

[1365] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generation AI and calculating an optimal delivery route, means for calculating an estimated delivery time based on the calculated delivery route, means for notifying the recipient of the calculated estimated delivery time, means for recording the actual delivery time after delivery completion as feedback and for learning using the generation AI, means for acquiring traffic conditions in real time, and means for sending a push notification to the user. This enables a food delivery service to calculate an optimal delivery route that takes changes in traffic conditions into account, and to provide users with highly accurate estimated delivery times, thereby improving delivery efficiency and user convenience.

[1366] "Means for collecting location information of transport vehicles" refers to devices or software that have the function of obtaining the current location of transport vehicles from a location information system such as GPS and transmitting it to a server.

[1367] "Means for collecting traffic condition data" refers to devices or software that have the function of obtaining traffic condition data such as road congestion information and road closure information from the Internet or external APIs.

[1368] "Generative AI" is an artificial intelligence algorithm that analyzes large amounts of data, learns patterns and trends, and makes predictions and classifications.

[1369] The "means for calculating the optimal transport route" refers to a device or software that has the function of calculating the most efficient route for transport vehicles based on the collected location information and traffic condition data.

[1370] The "means for calculating the estimated delivery time" is a device or software that has the function of calculating the predicted delivery time at each delivery point based on the optimal transportation route.

[1371] "Means for notifying the recipient of the estimated delivery time" refers to devices or software that have the function of notifying the recipient of the calculated estimated delivery time via email, SMS, push notification within the app, etc.

[1372] "Means for recording the actual delivery time after delivery is completed as feedback" refers to a device or software that has the function of recording the actual delivery time as data after delivery is completed and using it to improve prediction accuracy in future deliveries.

[1373] "Means for obtaining traffic conditions in real time" refers to devices or software that have the function of continuously monitoring current traffic conditions and providing the latest data to a server.

[1374] A "means for sending push notifications" is a device or software that has the function of sending messages directly from a server to a user's device such as a smartphone or tablet.

[1375] MODE FOR CARRYING OUT THE INVENTION

[1376] This invention is a system that optimizes specific delivery routes and notifies users of highly accurate estimated delivery times, taking traffic conditions into account. This system achieves efficient delivery by collecting vehicle location information and traffic condition data and optimizing delivery routes using generative AI. The system consists of three main components: a server, a terminal, and a user.

[1377] server

[1378] The server is responsible for the main data processing and analysis. Specifically, it performs the following operations:

[1379] 1. Data Collection

[1380] The server collects real-time location information from the GPS devices of the transport vehicles, as well as traffic data such as traffic congestion and road closures through a traffic API. The software used includes the Google Maps API and an API for GPS data collection.

[1381] 2. Data analysis and route optimization

[1382] The collected location information and traffic situation data are analyzed, and the optimal transportation route is calculated using generative AI. Real-time traffic congestion information and other factors are also taken into account. A generative AI model is used to predict the most efficient route. For example, a generative AI model using TensorFlow is applied.

[1383] 3. Calculating the estimated delivery time

[1384] Based on the optimized transportation route, the system calculates the estimated delivery time at each delivery point, thereby providing highly accurate delivery times.

[1385] 4. Notification System

[1386] The calculated estimated delivery time is notified to the user's device via email, SMS, in-app notification, etc. Firebase is used to send push notifications.

[1387] 5. Feedback and learning

[1388] After the delivery is completed, the actual delivery time is recorded and this data is used to retrain the generating AI, improving prediction accuracy for future deliveries.

[1389] Terminal

[1390] The terminal is used to notify the user of the scheduled delivery time. Specifically, it receives the notification sent from the server and displays it to the user. This allows the user to check the scheduled delivery time in advance, increasing the chance of the user being at home. The terminal can be a smartphone or tablet.

[1391] User

[1392] The user can easily receive the delivery by being at home based on the notified scheduled delivery time. By checking the notification, the number of missed deliveries can be reduced, supporting efficient delivery. The user can adjust their schedule based on the received notification.

[1393] Specific examples

[1394] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In that case, it operates as follows:

[1395] The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1396] The server analyzes the collected location information and traffic condition data using a generative AI model to calculate the optimal transportation route. For example, if road A is congested, detour route B will be selected.

[1397] The server calculates the estimated time of arrival at each delivery point based on the optimal transportation route.

[1398] The server notifies each user of the estimated delivery time. For example, user A receives a notification that "the delivery will be made at 12:15 today."

[1399] After the delivery is completed, the server records the actual delivery time and uses it as training data for the generative AI. This feedback improves the accuracy of future predictions.

[1400] Example prompt sentence:

[1401] "The transport vehicle's location is latitude 35.6895, longitude 139.6917."

[1402] "High traffic congestion is expected."

[1403] "Delivery addresses are 123, 456, and 789 in Tokyo."

[1404] This system and method will enable food delivery services to notify highly accurate scheduled delivery times that take into account changes in traffic conditions, significantly improving delivery efficiency and user convenience.

[1405] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1406] Program processing steps

[1407] Step 1:

[1408] The server collects the location information of the transport vehicle in real time from the GPS device. The input is the transport vehicle ID, and the output is the latitude and longitude information. This allows the current vehicle location to be accurately determined.

[1409] Step 2:

[1410] The server collects traffic data from the Internet or external APIs (e.g., Google Maps API). The input is a specific area name or coordinate range, and the output is traffic congestion and road closure information for that area. This allows the server to obtain the latest traffic conditions.

[1411] Step 3:

[1412] Based on the collected location information and traffic data, the server uses a generative AI model to calculate the optimal delivery route. The input is location information, traffic data, and a list of delivery addresses, and the output is an optimized route and estimated arrival time at each delivery point. TensorFlow is used to process the data and calculate the optimal route based on real-time traffic conditions.

[1413] Step 4:

[1414] The server calculates the estimated delivery time based on the calculated transportation route. The input is the optimized route information, and the output is the predicted arrival time at each delivery point. This results in an efficient delivery schedule.

[1415] Step 5:

[1416] The server notifies the user of the calculated estimated delivery time via email, SMS, and push notification. The input is the user's contact information and the estimated delivery time, and the output is a notification message that arrives on the user's device. The notification system uses Firebase.

[1417] Step 6:

[1418] Based on the notification, the user can decide whether to be at home or not and prepare for the scheduled delivery time, making it easier for the user to receive the delivery.

[1419] Step 7:

[1420] After the delivery is completed, the server records the actual delivery time. The input is the delivery completion time, and the output is the recorded history data. This stores the actual delivery time in the database.

[1421] Step 8:

[1422] The server uses the accumulated historical data to retrain the generative AI model and improve the accuracy of future predictions. The input is past delivery data, and the output is an improved predictive model. This improves the accuracy of the next prediction.

[1423] The above are the specific processing steps of the system that realizes the application example, and by following these steps, delivery efficiency and user convenience can be greatly improved.

[1424] 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.

[1425] This invention is a system that uses generative AI to calculate the optimal delivery route based on the location information of the delivery vehicle and traffic condition data, and notifies the user of a highly accurate estimated delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[1426] Overview of the embodiment

[1427] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[1428] server

[1429] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[1430] 1. Data Collection

[1431] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[1432] 2. Data analysis and route optimization

[1433] The server inputs the collected location information and traffic data into the AI ​​generator to calculate the optimal transportation route, taking real-time traffic conditions into account.

[1434] 3. Calculating the estimated delivery time

[1435] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1436] 4. Notification System

[1437] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[1438] 5. Emotion Engine

[1439] The server uses an emotion engine to analyze the user's emotions. It can recognize emotions based on the user's text messages, voice, or facial expression data, and can suggest changes to delivery times based on the results. This emotion data is also used as feedback for the generative AI.

[1440] 6. Feedback and Learning

[1441] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI, improving prediction accuracy in future runs.

[1442] Terminal

[1443] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[1444] 1. Receives notification messages sent by the server and displays them to the user.

[1445] 2. Use an emotion engine to provide notification content based on the user's emotions.

[1446] User

[1447] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[1448] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[1449] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[1450] Specific examples

[1451] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[1452] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1453] 2. The server uses the generation AI to analyze the collected data and calculate the optimal transportation route. For example, if road A is congested, detour route B is selected.

[1454] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1455] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[1456] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[1457] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[1458] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI, improving the accuracy of the next prediction.

[1459] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[1460] The processing flow will be explained below.

[1461] Step 1:

[1462] The server obtains real-time location information from the GPS devices of the transport vehicles. Specifically, it collects latitude and longitude data indicating the current location of each transport vehicle every minute and stores it in a database.

[1463] Step 2:

[1464] The server uses the traffic API to collect traffic data, such as current traffic congestion and road closure information, and stores the collected data in a database for immediate analysis.

[1465] Step 3:

[1466] The server inputs the collected location information and traffic data into the generation AI to calculate the optimal transportation route. The generation AI takes real-time traffic conditions into account, evaluates multiple route options, and selects the most efficient route.

[1467] Step 4:

[1468] The server calculates the estimated delivery time for each delivery point based on the selected optimal route, taking into account the expected stop time and traffic conditions at each point.

[1469] Step 5:

[1470] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via the API. This notification includes the specific estimated delivery time.

[1471] Step 6:

[1472] The emotion engine analyzes the user's text message, voice, or facial expression data to recognize emotions. For example, if the user feels that the delivery time is slow, the emotion engine analyzes the emotion and provides it to the server.

[1473] Step 7:

[1474] The server can suggest changes to the delivery time based on the emotion data received from the emotion engine. For example, if the user is feeling stressed, the server can add a suggestion to the notification to "advance the delivery time."

[1475] Step 8:

[1476] The terminal displays the received notification message to the user, who can then check the estimated delivery time and suggestions from the server via the terminal.

[1477] Step 9:

[1478] The user can plan their stay at home based on the estimated delivery time. They can also request a change in the delivery time based on the analysis results of the emotion engine. For example, they can send a request to the server such as "Please deliver a little later."

[1479] Step 10:

[1480] The delivery is executed and the server records the delivery progress and the actual delivery time. After the delivery is completed, the server receives a report from the driver and stores the actual delivery time in the database.

[1481] Step 11:

[1482] The server provides the collected actual delivery time data and emotion data as feedback to the generation AI, allowing it to retrain the prediction model. Based on this training data, the accuracy of future delivery predictions will be improved.

[1483] In this way, efficient delivery can be achieved while taking into consideration the user's feelings.

[1484] Example 2

[1485] 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."

[1486] In modern logistics systems, efficient route selection for transport vehicles and prediction of scheduled delivery times are important issues. However, conventional systems cannot fully consider fluctuations in traffic conditions or the rate at which users are at home, making it difficult to select optimal routes or accurately calculate scheduled delivery times. Furthermore, frequent missed deliveries lead to reduced delivery efficiency and lower customer satisfaction.

[1487] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1488] In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using generative artificial intelligence and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the recipient's emotional data and adjusting the notification content based on the results, and means for increasing the rate at which the user will be at home based on the estimated delivery time. This makes it possible to select an optimal route taking traffic conditions into consideration in real time and to predict the estimated delivery time with high accuracy, and further to increase the rate at which the user will be at home by analyzing the user's emotions, thereby reducing missed deliveries and improving customer satisfaction.

[1489] "Transport vehicle location information" indicates coordinate data of the location where the transport vehicle is currently located.

[1490] "Traffic condition data" refers to current traffic data relating to the movement of transport vehicles, such as road congestion information and road closure information.

[1491] "Generative artificial intelligence" refers to advanced computational models used to analyze data and make predictions, particularly those that utilize machine learning and deep learning.

[1492] "Analysis" refers to the process of extracting information from collected data and making understanding or predictions.

[1493] The "optimal transportation route" is a route selected for efficient delivery, and is calculated taking into account traffic conditions, distance, time, etc.

[1494] "Scheduled delivery time" refers to the time when a transport vehicle is scheduled to arrive at a particular location.

[1495] "Recipient" means the person or entity intended to receive the delivery.

[1496] "Notification" refers to a message or signal that conveys information to a specific recipient.

[1497] "Emotion data" is information that indicates the user's emotional state, and is extracted from text, voice, facial expressions, and the like.

[1498] The "at-home rate" indicates the probability that a user is at home during a particular time period.

[1499] MODE FOR CARRYING OUT THE INVENTION

[1500] This invention is a system that uses generative artificial intelligence to calculate the optimal transportation route based on the location information of the transportation vehicle and traffic condition data, and notifies the user of a highly accurate scheduled delivery time. A feature of this invention is that by combining it with an emotion engine that recognizes the user's emotions, it can further increase the rate at which users are at home and reduce the number of missed deliveries.

[1501] System configuration

[1502] Server Roles

[1503] The server is responsible for the main data processing and analysis, specifically fulfilling the following roles:

[1504] 1. Data Collection

[1505] The server collects real-time location information sent from the GPS devices of transport vehicles, and also collects traffic congestion information, road closure information, etc. using traffic condition APIs, and stores this data in a database.

[1506] 2. Data analysis and route optimization

[1507] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal delivery route, taking real-time traffic conditions into consideration. For example, a prompt might be used: "Based on the current location information and traffic situation data of the delivery vehicle, please calculate the optimal delivery route and estimated delivery time."

[1508] 3. Calculating the estimated delivery time

[1509] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1510] 4. Notification System

[1511] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[1512] 5. Emotion Engine

[1513] The server analyzes the user's text message, voice, or facial expression data to recognize the user's emotions. Based on the analysis results, the server can suggest changes to the delivery time. For example, the prompt could read, "Analyze the user's latest emotional data and suggest changes to the delivery time based on the results."

[1514] 6. Feedback and Learning

[1515] After a delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[1516] Device Role

[1517] The terminal's main role is to notify the user of the estimated delivery time.

[1518] 1. Notification display

[1519] Receives notification messages sent from the server and displays them to the user. For example, it displays a message saying "Delivery will be made at 10:00 today."

[1520] 2. Emotional Engine Support

[1521] It works in conjunction with the server's emotion engine to provide notifications based on the user's emotions. For example, if the user is feeling stressed, it will suggest flexible delivery times.

[1522] User Roles

[1523] The user acts based on the notified estimated delivery time.

[1524] 1. Notification Confirmation and Action Plan

[1525] Check the notification message you received and plan to be at home at the scheduled delivery time. For example, you can plan to be at home at 10:00 today.

[1526] 2. Adjustments based on the emotion engine's suggestions

[1527] Accept the suggestions provided based on the sentiment engine and adjust the delivery time, for example, request a different delivery time.

[1528] Specific examples

[1529] For example, consider a situation where a transport vehicle delivers multiple packages to different addresses. In this case, the system operates as follows:

[1530] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1531] 2. The server uses a generation AI to analyze the collected data and calculate the optimal transportation route. For example, "Road A is congested, so select detour route B."

[1532] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1533] 4. The server notifies the recipient of the calculated estimated delivery time. For example, User A receives a message saying, "The parcel will be delivered at 10:00 today."

[1534] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[1535] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[1536] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as learning data for the generative AI, improving the accuracy of the next prediction.

[1537] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[1538] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1539] Step 1: Data collection

[1540] The server collects real-time location information from the GPS devices of the transport vehicles, and also obtains traffic congestion and road closure information using the traffic situation API, which is then stored in a database.

[1541] Input: GPS data of transport vehicles, traffic information from traffic situation API

[1542] Output: Location and traffic data stored in a database

[1543] Specific operation: The server obtains location information from the GPS device every second and accesses the traffic situation API via HTTP request to obtain traffic information. This information is stored in a database.

[1544] Step 2: Data analysis and route optimization

[1545] The server inputs the collected location and traffic data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account.

[1546] Input: location information, traffic data

[1547] Output: Optimal transportation route

[1548] Specific operation: The server sends a prompt to the generative AI model saying, "Calculate the optimal route using the current location, destination, and traffic information as input," and determines the next movement step based on the route information returned by the generative AI model.

[1549] Step 3: Calculate the estimated delivery time

[1550] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1551] Input: Optimal transport route, traffic situation data

[1552] Output: Estimated delivery time for each delivery point

[1553] Specific operation: The server calculates the travel time and stop time for each delivery point, and calculates the estimated arrival time at point 1 as 10:00, point 2 as 11:00, and the final point as 12:30.

[1554] Step 4: Notification System

[1555] The server generates a notification message with the calculated estimated delivery time and notifies the user's device via email or SMS via the API.

[1556] Input: Estimated delivery time

[1557] Output: Notification message to the user terminal

[1558] Specific operation: The server creates a message stating "Delivery will be made at 10:00 today" and sends a notification to the user's device using an email sending API or SMS sending API.

[1559] Step 5: Emotion Engine

[1560] The server analyzes the user's text messages, voice, or facial expression data to recognize their emotions, and then suggests changes to the delivery time based on the results.

[1561] Input: User text messages, voice, and facial expression data

[1562] Output: Sentiment analysis results, suggestion to change delivery time

[1563] Specific operation: When a user sends a message or voice message, the server analyzes it using an emotion engine, and if it determines that the user is "stressed," it takes the action of "suggesting to change the delivery time to 15 minutes later."

[1564] Step 6: Feedback and learning

[1565] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[1566] Input: Actual delivery time

[1567] Output: Retrained generative AI model

[1568] Specific operation: When a delivery is completed, the server saves the actual delivery time in a database and inputs it into the generative AI model with the prompt "Relearn to improve prediction accuracy next time."

[1569] Step 7: User Behavior

[1570] The user acts based on the notified estimated delivery time.

[1571] Input: Notification message

[1572] Output: User action plan, increase in at-home rate

[1573] Specific operation: The user checks the notification message displayed on the device and adds a schedule such as "I'll be at home at 10:00 today" to their calendar. They can also request a change in delivery time based on suggestions from the emotion engine.

[1574] (Application example 2)

[1575] 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."

[1576] Conventional food delivery systems have difficulty calculating the optimal delivery route based on the delivery person's current location information and traffic condition data, and notifying the user of a highly accurate estimated delivery time. Furthermore, since delivery times are notified unilaterally without considering the user's feelings, there is a high possibility of user satisfaction decreasing. Furthermore, frequent missed deliveries lead to inefficiencies and increased costs.

[1577] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting location information of transport vehicles, means for collecting traffic condition data, means for analyzing the collected location information and traffic condition data using a generative AI model and calculating an optimal transport route, means for calculating an estimated delivery time based on the calculated transport route, means for notifying the recipient of the calculated estimated delivery time, means for analyzing the user's emotions, and means for flexibly changing the delivery time based on the user's emotions. This enables highly accurate notification of the estimated delivery time and flexible delivery response that takes the user's emotions into consideration.

[1578] "Transport vehicle location information" is data indicating the current geographical location of the transport vehicle.

[1579] "Traffic condition data" refers to data that includes information about roads and traffic, such as road congestion and closure information, and the status of traffic signals.

[1580] A "generative AI model" is a type of artificial intelligence that uses machine learning algorithms to calculate optimal routes and arrival times based on collected data.

[1581] The "optimal transportation route" is the most efficient and quickest route to reach the destination based on collected location information and traffic data.

[1582] The "estimated delivery time" is the arrival time at each delivery point calculated based on the optimal transportation route.

[1583] "Means of notifying recipient" refers to the method or function for notifying the recipient of the calculated estimated delivery time, and mainly includes email, SMS, and in-app notifications.

[1584] "Means for analyzing user emotions" refers to technology for determining a user's emotional state based on voice, text messages, facial expression data, etc.

[1585] The "means for flexibly changing delivery time based on user's emotions" is a method for proposing and executing changes to delivery time in accordance with the analyzed user's emotions.

[1586] "Data collected as feedback" refers to data used as training data for the generative AI model to improve future prediction accuracy, such as delivery time and emotional data recorded after a delivery is completed.

[1587] This invention is a food delivery system that uses a generative AI model to calculate the optimal delivery route based on vehicle location information and traffic condition data, and notifies users of highly accurate estimated delivery times. Furthermore, by combining it with an emotion engine that analyzes user emotions, it is possible to further increase the rate at which users are at home and reduce missed deliveries.

[1588] System configuration

[1589] This system consists of three main components: a server, a terminal, and a user. It also includes a new emotion engine.

[1590] server

[1591] The server is responsible for the main data processing and analysis. The specific operations are as follows:

[1592] 1. Data Collection

[1593] The server collects real-time location information sent from the GPS devices of transport vehicles, as well as traffic congestion and road closure information from the traffic situation API, and stores this data in a database.

[1594] 2. Data analysis and route optimization

[1595] The server inputs the collected location information and traffic situation data into a generative AI model to calculate the optimal transportation route, taking real-time traffic conditions into account. The generative AI model is implemented using TensorFlow, PyTorch, and other tools.

[1596] 3. Calculating the estimated delivery time

[1597] The server calculates the estimated delivery time for each delivery point based on the optimized transportation route, taking into account expected stop times and traffic conditions at each point.

[1598] 4. Notification System

[1599] The server generates a notification message with the calculated estimated delivery time and sends it to the user's device via email or SMS via an API, using a mail server or SMS gateway.

[1600] 5. Emotion Engine

[1601] The server uses an emotion engine to analyze the user's emotions. It recognizes emotions based on the user's text message, voice, or facial expression data, and can suggest changes to the delivery time based on the results. The emotion engine uses NLTK and Google Cloud Natural Language API. This emotion data is also used as feedback and training data for the generative AI.

[1602] 6. Feedback and Learning

[1603] After the delivery is completed, the server records the actual delivery time and uses this data to retrain the generative AI model, improving prediction accuracy in future deliveries.

[1604] Terminal

[1605] The terminal is responsible for notifying the user of the estimated delivery time. The specific operation is as follows:

[1606] 1. Receives notification messages sent from the server and displays them to the user. This applies to smartphone apps and web notifications.

[1607] 2. Use an emotion engine to provide notification content based on the user's emotions.

[1608] User

[1609] The user acts based on the notified estimated delivery time. The specific operation is as follows.

[1610] 1. Check the notification message you receive and plan to be at home at the scheduled delivery time.

[1611] 2. Adjust delivery times according to suggestions provided based on the sentiment engine.

[1612] Specific examples

[1613] For example, consider a situation where a delivery vehicle delivers multiple meals to different addresses. In this case, the system operates as follows:

[1614] 1. The server obtains the current location and destination address of the transport vehicle and collects traffic situation data in real time.

[1615] 2. The server analyzes the collected data using a generative AI model and calculates the optimal transportation route. For example, if road A is congested, it selects detour route B.

[1616] 3. The server calculates the estimated time of arrival for each delivery point. For example, the estimated time of delivery to point 1 is calculated as 10:00, point 2 is calculated as 11:00, and the final point is calculated as 12:30.

[1617] 4. The server notifies the recipient of the calculated estimated delivery time. User A receives a message saying "Delivery will be at 10:00 today."

[1618] 5. The emotion engine analyzes User A's emotions from his / her text messages and voice, and if the user is feeling stressed, it will respond by suggesting a flexible delivery time.

[1619] 6. The user can review the notification and adjust their schedule to be at home for the scheduled delivery time, or request a different delivery time based on suggestions from the emotion engine.

[1620] 7. After the delivery is completed, the server records the actual delivery time and emotion data, which are used as training data for the generative AI model, improving the accuracy of the next prediction.

[1621] Prompt Sentence Examples

[1622] "Current location: {current_location}, Estimated delivery time: {estimated_delivery_times}, User emotion: {user_emotion}"

[1623] In this way, the present invention can improve delivery efficiency and user satisfaction through optimization of transportation routes, calculation of highly accurate scheduled delivery times, and flexible responses that take user emotions into consideration.

[1624] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1625] Step 1:

[1626] The server collects the location information of the transport vehicle in real time from the GPS device. Specifically, it obtains the GPS information indicating the current location of the transport vehicle via API and stores it in a database. The input is the location information from the GPS device. The output is the location information stored in the database.

[1627] Step 2:

[1628] The server collects traffic condition data in real time from the traffic API. Specifically, it obtains traffic signal status, road congestion information, and road closure information via the API and stores it in a database. The input is traffic condition data from the traffic API. The output is the traffic condition data stored in the database.

[1629] Step 3:

[1630] The server inputs the collected location information and traffic condition data into a generative AI model to calculate the optimal transportation route. Specifically, the data is passed to a generative AI model built with TensorFlow and PyTorch to calculate the optimal route. The input is location information and traffic condition data. The output is an optimized transportation route.

[1631] Step 4:

[1632] The server calculates the estimated delivery time for each delivery point based on the optimal transportation route. Specifically, it calculates the estimated arrival time for each point, taking into account expected stop times and other traffic conditions. The input is the optimized transportation route. The output is the estimated delivery time for each delivery point.

[1633] Step 5:

[1634] The server generates a notification message with the calculated estimated delivery time and sends it to the device via an API, using a mail server or SMS gateway. The input is the calculated estimated delivery time, and the output is the notification message sent to the user's device.

[1635] Step 6:

[1636] The server inputs the user's text message, voice, or facial expression data into the emotion engine and analyzes the emotions. Specifically, it uses NLTK or Google Cloud Natural Language API to determine the user's emotional state. The input is the text message or voice data sent by the user. The output is the analyzed emotion data.

[1637] Step 7:

[1638] The server proposes a change in delivery time based on the analyzed emotion data. Specifically, if the user is feeling stressed, it proposes a flexible delivery time. The input is emotion data, and the output is a proposal to change the delivery time.

[1639] Step 8:

[1640] The terminal receives the notification message sent from the server and displays it to the user. Specifically, it notifies the user of the estimated delivery time through a smartphone app or web notification. The input is the notification message from the server, and the output is the notification displayed to the user.

[1641] Step 9:

[1642] The user checks the notified estimated delivery time and adjusts their schedule, such as planning when they will be at home. The input is the notification message, and the output is the user's adjusted schedule.

[1643] Step 10:

[1644] After the delivery is completed, the server records the actual delivery time and emotion data and uses this data to retrain the generative AI model. Specifically, the delivery time information and emotion data stored in the database are used to retrain the generative AI model. The input is the actual delivery time and emotion data, and the output is an updated generative AI model.

[1645] 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.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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).

[1652] 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.

[1653] 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."

[1654] 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.

[1655] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1656] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1657] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1658] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1659] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1660] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1661] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1662] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1663] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1664] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1665] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1666] The following is further disclosed regarding the above embodiment.

[1667] (Claim 1)

[1668] means for collecting location information of the transport vehicle;

[1669] a means for collecting traffic condition data;

[1670] A means of analyzing the location information and traffic situation data collected using generative AI and calculating the optimal transportation route;

[1671] means for calculating an estimated delivery time based on the calculated transportation route;

[1672] means for notifying the recipient of the calculated estimated delivery time;

[1673] A means for increasing the rate at which the user is at home based on the notified scheduled delivery time;

[1674] A system including:

[1675] (Claim 2)

[1676] 10. The system of claim 1, further comprising means for recording the actual delivery time after the delivery is completed and training the generative AI using the collected data as feedback.

[1677] (Claim 3)

[1678] 3. The system of claim 1 or 2, further comprising means for optimizing the delivery sequence.

[1679] "Example 1"

[1680] (Claim 1)

[1681] means for collecting location information of the transport vehicle;

[1682] a means for collecting traffic condit...

Claims

1. means for collecting location information of the transport vehicle; a means for collecting traffic condition data; A means of analyzing the location information and traffic situation data collected using generative AI and calculating the optimal transportation route; means for calculating an estimated delivery time based on the calculated transportation route; means for notifying the recipient of the calculated estimated delivery time; A means for increasing the rate at which the user is at home based on the notified scheduled delivery time; A system including:

2. 10. The system of claim 1, further comprising means for recording the actual delivery time after the delivery is completed and training the generative AI using the collected data as feedback.

3. 3. The system of claim 1 or 2, further comprising means for optimizing the delivery sequence.

Images