system

Abstract

We provide the system. [Solution] A means for collecting location information of delivery vehicles, Means of collecting order information from shippers, A means of collecting information on the status of receiving goods, A means for integrating and preprocessing this data, A means of generating the optimal delivery route and schedule using an AI algorithm, A means of distributing the generated schedule to the delivery vehicle drivers and shippers, A means to receive real-time feedback on delivery status and problems, and to optimize the schedule again, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] The main problems in truck transportation are the high empty vehicle return rate and the long waiting time for loading. These problems lead to a decrease in transportation efficiency and an increase in the working hours and costs of drivers. With conventional operation management methods, it is difficult to efficiently match the orders from shippers with the loading status, leaving much room for improvement to significantly enhance the overall transportation efficiency. The present invention aims to solve these problems and provide a system for improving the efficiency of truck transportation.

Means for Solving the Problems

[0005] The present invention solves the above-mentioned problems by providing the following means. First, it includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, and means for collecting information on the status of receiving goods. By means for integrating and pre-processing this data, data without errors or omissions is provided. Subsequently, a means is provided to generate the optimal delivery route and schedule from the data of all vehicles and orders using an AI algorithm. This generated schedule is shared in real time by means for distributing it to the drivers of the delivery vehicles and shippers. Furthermore, efficient operation management is achieved by providing means for providing real-time feedback on congestion and other problems that occur during delivery, and by applying the AI ​​algorithm again to optimize the schedule.

[0006] "Means for collecting location information of delivery vehicles" refers to devices or software that use location information services such as GPS to obtain the current geographical location of delivery vehicles.

[0007] "Means for collecting order information from shippers" refers to interfaces and systems for obtaining delivery request information provided by shippers. This includes detailed information such as origin, destination, type of package, weight, and desired delivery time.

[0008] "Means for collecting information on the status of receiving packages" refers to means for obtaining information regarding the status of package acceptance, such as the preparation for receiving packages at the delivery destination and the available acceptance time.

[0009] "Means for integrating and preprocessing data" refers to devices or software that centrally manage data collected from different sources and perform processing such as supplementing missing data and removing outliers.

[0010] "Methods for generating optimal delivery routes and schedules using AI algorithms" refer to devices or software that utilize artificial intelligence technology to calculate and generate the most efficient delivery routes and schedules from all vehicle and order information.

[0011] "Means for distributing the generated schedule to delivery vehicle drivers and shippers" refers to communication devices and software for notifying and sharing optimized delivery plans with drivers and shippers.

[0012] "A means of receiving real-time feedback on delivery status and problems and re-optimizing the schedule" refers to a device or software that receives data in real time when the situation changes or problems occur during delivery, and reapplies AI algorithms to update and optimize the schedule. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system aimed at reducing the rate of empty return trips and shortening loading / unloading waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and loading / unloading status information, and generating and distributing the optimal route and schedule based on this information. The following describes in detail embodiments for specifically implementing this invention.

[0035] System Configuration

[0036] 1. Data collection methods

[0037] The server collects real-time location information for delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[0038] The server collects order information from shippers. To do this, shippers input order information (origin, destination, type of package, weight, desired delivery time, etc.) through an interface.

[0039] The server collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[0040] 2. Data integration and preprocessing means

[0041] The server integrates and preprocesses the collected location, order, and delivery information. By performing data interpolation and removing outliers, it generates a highly reliable dataset.

[0042] 3. Means for applying the matching algorithm

[0043] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[0044] Specifically, the system calculates the optimal combination based on data such as the truck's current location, load capacity, and the order's origin, destination, weight, and desired delivery time.

[0045] 4. Schedule distribution method

[0046] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The schedule is notified to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[0047] 5. Real-time feedback and optimization means

[0048] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0049] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0050] Explanation of the program's processing

[0051] The program for this system implements the above-mentioned methods to achieve efficient truck transportation. The following describes the processing details of the program.

[0052] 1. Data Collection

[0053] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[0054] The user (shipper) enters order information using a terminal and sends it to the server.

[0055] The server sets up a means to collect information on the status of receiving shipments and understands the acceptance time and preparation status.

[0056] 2. Data Integration and Preprocessing

[0057] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[0058] 3. Application of the matching algorithm

[0059] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it calculates that truck A can pick up two orders on its way from Tokyo to Yokohama.

[0060] 4. Scheduled distribution

[0061] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The driver's smartphone displays the specific route and loading / unloading instructions.

[0062] 5. Real-time feedback

[0063] Users (drivers) report real-time information such as traffic congestion and changes in delivery destinations from their terminals.

[0064] Based on this information, the server reapplies the AI ​​algorithm to recalculate the optimal route and schedule for delivery.

[0065] Specific example

[0066] As an example, consider the case where truck A travels from Tokyo to Yokohama. GPS data from the delivery vehicle is collected to determine that its current location is Tokyo. Two delivery requests (orders 1 and 2) from Tokyo to Yokohama are entered as order information from the shipper. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A accepts orders 1 and 2 via the optimal route. The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up the two packages at the Tokyo warehouse and deliver them to Yokohama. If traffic congestion occurs along the way, the driver reports it to the server in real time, and the server calculates a new route and delivers it again.

[0067] In this way, this system reduces the rate at which trucks are empty and shortens waiting times for loading and unloading, thereby achieving efficient delivery operation management.

[0068] The following describes the processing flow.

[0069] Step 1: Data Collection

[0070] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[0071] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[0072] The device sends the above data to the server.

[0073] Step 2: Data Integration and Preprocessing

[0074] The server stores the received data in a centrally managed database.

[0075] The server checks data integrity and fills in any missing data. For example, if there is a missing input, it will fill in the estimated value based on the previous data.

[0076] The server filters out abnormal values ​​(for example, delivery times exceeding the possible range) and sends a correction request to the user if an abnormality is found.

[0077] Step 3: Matching using AI algorithms

[0078] The server runs an AI algorithm based on the current location, order information, and planned route of all trucks.

[0079] The server performs optimal matching of each truck with an order. Specifically, it determines the best combination based on factors such as the distance and time from the dispatched vehicle's current location to the order's departure point, load capacity, and environmental impact.

[0080] Step 4: Generate Optimal Route and Schedule

[0081] The server generates the optimal route and schedule calculated by an AI algorithm. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[0082] Step 5: Scheduled distribution

[0083] The server sends the generated schedule to each truck driver's terminal. Specifically, it provides detailed instructions to the driver's terminal on where to pick up the cargo and where to deliver it.

[0084] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[0085] Step 6: Real-time feedback and reoptimization

[0086] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[0087] The server reapplies the AI ​​algorithm based on the received feedback (e.g., traffic information) to calculate a new, optimal route.

[0088] The server resends the updated schedule and route to the driver's terminal.

[0089] (Example 1)

[0090] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] There is a need to solve the problems of empty vehicle return rates and waiting times in truck transportation. Conventional systems have insufficient management of delivery vehicle location information and order information, making it difficult to optimize delivery routes efficiently. In addition, the inability to flexibly change schedules in response to real-time changes in circumstances led to problems with reduced operational efficiency.

[0092] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0093] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and re-optimizing the schedule, means for determining location information using a GPS device, means for inputting order information via a terminal, pre-processing means for data completion and removal of anomalies, and means for distributing schedule information using a notification system. This makes it possible to reduce the rate of empty return trips of trucks and shorten waiting times for loading and unloading.

[0094] "Delivery vehicles" refer to means of transport such as automobiles, trucks, and vans used to transport goods and products.

[0095] "Location information" refers to data that indicates the geographical location of a specific object or person, obtained by location measurement devices such as GPS devices.

[0096] "Order information" refers to data provided by shippers when requesting delivery services, including details such as the origin, destination, type of package, weight, and desired delivery time.

[0097] "Receiving information" refers to information such as the readiness status of the receiving location and the available receiving times for packages.

[0098] "Integration" is the process of bringing together different types of data and managing them comprehensively.

[0099] "Preprocessing" refers to the process of transforming collected raw data into a format that is easy to analyze, and includes data interpolation and removal of outliers.

[0100] An "AI algorithm" is a set of computational procedures that use artificial intelligence technology to analyze data and perform optimization and predictions.

[0101] A "schedule" is a plan of time and location, outlining when and where a delivery vehicle will pick up a package and where it will deliver it.

[0102] "Feedback" is the process of receiving information about the system's operation status and problems from the system and its users, and using that information to improve and adjust the system.

[0103] "Optimization" is the process of adjusting calculations and procedures to obtain the best possible result under given conditions and constraints.

[0104] A "GPS device" is a device that measures and reports a specific location on Earth, and it obtains location information using satellite signals.

[0105] A "terminal" is a device, such as a computer or smartphone, that a user uses to input information or receive information from a system.

[0106] A "notification system" is a communication method used to instantly deliver important information and updates to users and systems, and includes SMS and push notifications.

[0107] This invention is a system aimed at reducing the rate of empty return trips and shortening waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and cargo receiving status information, and generating and distributing the optimal route and schedule based on this information.

[0108] Hardware and software to be used

[0109] The hardware used includes GPS devices, user terminals (smartphones and PCs), and servers. The software includes data collection software, AI algorithms, data integration and preprocessing software, and notification systems.

[0110] Overall flow

[0111] 1. Data Collection

[0112] The server collects location information in real time from GPS devices attached to delivery vehicles. This information includes the vehicle's current location, speed, and direction of travel.

[0113] The user (shipper) enters order information (origin, destination, type of package, weight, desired delivery time, etc.) via a terminal and sends it to the server.

[0114] The server collects information on the status of receiving shipments (such as readiness for acceptance and available acceptance times). This information is either entered by the person in charge at the receiving location or automatically retrieved by the system.

[0115] 2. Data Integration and Preprocessing

[0116] The server integrates collected location information, order information, and delivery information, and manages them centrally in real time.

[0117] The server performs preprocessing to complete the data and remove outliers. This process fills in missing data and corrects outliers, resulting in a reliable dataset.

[0118] 3. Application of the matching algorithm

[0119] The server uses an AI algorithm to generate the optimal delivery route and schedule. This algorithm considers the current location, load capacity, origin, destination, weight, and desired delivery time of each delivery vehicle to calculate the most efficient route and schedule.

[0120] 4. Scheduled distribution

[0121] The server distributes the generated schedule to the delivery vehicle drivers and shippers. This distribution is done through a notification system, and the specific route and loading / unloading instructions are displayed on the drivers' smartphones or tablets.

[0122] 5. Real-time feedback and optimization

[0123] Users (drivers) report operational status and problems (such as traffic congestion or changes in delivery destinations) to the server in real time from their terminals.

[0124] The server reapplies the AI ​​algorithm based on this status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0125] Specific example

[0126] As an example, let's consider the case where truck A is traveling from Tokyo to Yokohama.

[0127] 1. Data Collection: The server obtains the current location of truck A (Tokyo) from a GPS device. The shipper also inputs order information, such as "I would like a 500kg package delivered from a warehouse in Tokyo to a warehouse in Yokohama," and sends it to the server.

[0128] 2. Data Integration and Preprocessing: The server integrates the collected data (location information of truck A, order information, and acceptance time information for the Yokohama warehouse) and supplements any missing data or outliers.

[0129] 3. Application of Matching Algorithm: The server uses an AI algorithm to generate the optimal schedule for truck A to pick up goods from a warehouse in Tokyo via the shortest route and deliver them to a warehouse in Yokohama.

[0130] 4. Schedule Distribution: The server distributes the generated schedule to the driver of truck A's smartphone. The smartphone displays instructions such as, "Pick up the cargo at the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[0131] 5. Real-time feedback and optimization: If traffic congestion occurs along the way, the user (driver) reports "traffic congestion" information from their device. The server then reapplies the AI ​​algorithm based on this information, calculates an alternative route, and redistributes it to the driver.

[0132] Example of a prompt:

[0133] "The system uses the current location data of trucks collected from GPS devices as input to calculate the optimal delivery route."

[0134] "Using multiple order details from shippers as input, an AI algorithm is applied to generate the optimal schedule."

[0135] "We will re-optimize the route and schedule based on real-time feedback from drivers."

[0136] This system will reduce the rate of empty truck return trips and waiting times for loading and unloading, enabling more efficient delivery operation management.

[0137] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0138] Step 1: Data Collection

[0139] The server collects location information in real time from GPS devices installed in delivery vehicles. The input data includes the current location, speed, and direction of movement of each vehicle, and this data is analyzed to output accurate location information.

[0140] The user (shipper) enters order information using a terminal. This information includes the origin, destination, type of package, weight, and desired delivery time. This information is then sent to the server via the terminal.

[0141] The server collects information on the status of receiving shipments (readiness for receiving, available time for receiving). This includes means of obtaining data entered by the person in charge at the receiving location. The server analyzes the input data and outputs the available time slots for receiving shipments.

[0142] Step 2: Data Integration and Preprocessing

[0143] The server centrally integrates the collected location information, order information, and delivery information. The input data consists of the above-mentioned collected items, and it outputs a manageable dataset by integrating these items.

[0144] The server performs preprocessing on the integrated data, including data imputation and outlier removal. The input data includes integrated raw data, and the server outputs a reliable dataset after imputing missing data and detecting and correcting outliers.

[0145] Step 3: Applying the Matching Algorithm

[0146] The server uses AI algorithms to generate the optimal delivery route and schedule. Input data includes the current location of the delivery vehicle, its load capacity, and order information (origin, destination, weight, desired delivery time). This data is analyzed to output an efficient route and schedule.

[0147] Specifically, the server calculates the optimal location and time for truck A to pick up two orders within Tokyo, and generates its route and schedule.

[0148] Step 4: Scheduled delivery

[0149] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The input data is the generated schedule information, which is distributed via the notification system. As a result of the distribution, the specific route and loading instructions are output to the driver's smartphone.

[0150] In terms of specific actions, the server distributes schedules such as "Pick up the package from the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[0151] Step 5: Real-time feedback and optimization

[0152] Users (drivers) report problems and situations during their journey (such as traffic congestion or changes in delivery destinations) in real time from their terminals. The input data includes the driver's reported information.

[0153] The server re-optimizes the schedule and route by applying the AI ​​algorithm again based on real-time feedback. The input data is feedback information from the driver, which is analyzed to output a new route and schedule.

[0154] Specifically, the server generates a new instruction stating, "There is currently traffic congestion, so take an alternative route," and redistributes it to the driver.

[0155] (Application Example 1)

[0156] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0157] This invention aims to reduce the rate of empty truck return trips and shorten loading / unloading waiting times in truck transportation, but existing systems have not been able to completely solve this problem. Specifically, real-time location information collection, optimal route generation, and rapid response to problems are not adequately performed, and efficient delivery operation management has not been achieved. Furthermore, even when using autonomous vehicles, there are still aspects that are difficult to address.

[0158] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0159] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and optimizing the schedule again, and an autonomous vehicle control system for comfortable delivery operation management. This makes it possible to reduce the rate of empty return trips, shorten waiting times for cargo, and improve the efficiency of autonomous vehicle operation management.

[0160] "Means for collecting location information of delivery vehicles" refers to a device that uses a GPS device to obtain the current location of delivery vehicles in real time.

[0161] "Means for collecting order information from shippers" refers to an interface and system on which shippers input order information such as origin, destination, type of goods, weight, and desired delivery time, and transmit it to a server.

[0162] "Means for collecting information on the status of receiving goods" refers to devices and systems that collect information from the receiving party regarding the status of preparation for receiving goods, the time when they can be received, etc.

[0163] "Means for integrating and preprocessing data" refers to devices and systems that centrally manage multiple collected data sets and perform processes to supplement and correct deficiencies and abnormal values.

[0164] "A method for generating optimal delivery routes and schedules using AI algorithms" refers to a software algorithm that uses artificial intelligence technology to calculate and generate optimal delivery routes and schedules based on collected data.

[0165] "Means for distributing the generated schedule to delivery vehicle drivers and shippers" refers to a system that notifies drivers' terminals and shippers' management systems of the calculated and generated schedule.

[0166] "A means of receiving real-time feedback on delivery status and problems and re-optimizing the schedule" refers to a system that receives real-time information on problems and delays from vehicles in operation, and then applies AI algorithms to calculate and distribute new routes and schedules.

[0167] The "Autonomous Vehicle Control System for Comfortable Delivery Operation Management" is a system that efficiently manages the operation of autonomous vehicles and distributes optimal routes and schedules to enable quick responses in the event of problems.

[0168] A "generative AI model" is an artificial intelligence model that has been trained to efficiently perform a specific task based on training data.

[0169] A "prompt statement" is an instruction given to a generative AI model to obtain a specific output.

[0170] This invention relates to a truck transportation management system that utilizes autonomous vehicles to maximize transportation efficiency. The configuration and operation of the system for specifically implementing this invention, including the hardware and software used, are described below.

[0171] System Configuration

[0172] 1. Data collection methods

[0173] The server collects real-time location information for delivery vehicles. For this purpose, each vehicle is equipped with a GPS device to collect location data.

[0174] The system also collects order information from shippers. This involves providing an interface for inputting data such as origin, destination, type of package, weight, and desired delivery time.

[0175] The server also collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[0176] 2. Data integration and preprocessing means

[0177] The server centrally manages the collected data. This includes a data cleansing process to supplement and correct any missing or outlier values.

[0178] 3. Means for applying the matching algorithm

[0179] The server uses AI algorithms to generate the optimal delivery route and schedule. Technologies such as TENSORFLOW® and PyTorch are used to calculate and generate the optimal route and schedule based on all collected data.

[0180] 4. Schedule distribution method

[0181] The generated schedule is distributed to the delivery vehicle drivers and the shippers. Notifications are sent to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[0182] 5. Real-time feedback and optimization means

[0183] The user (driver) reports the situation and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0184] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0185] Specific example

[0186] As an example, consider the case of truck B traveling from Osaka to Nagoya. Real-time location information collected from the delivery vehicle's GPS device determines that its current location is Osaka. The shipper inputs order information: departure point is Osaka, destination is Nagoya, large cargo, weight 500kg, desired delivery time 10:00-12:00. The server integrates and preprocesses this data and generates the optimal route and schedule for truck B using an AI algorithm (e.g., using TensorFlow or PyTorch). The generated schedule is delivered to the driver's smartphone, displaying instructions for departure time 08:00 and arrival time 11:30. If traffic congestion occurs near Kyoto along the way, the driver's terminal automatically detects this and provides feedback to the cloud server. The server recalculates and generates a new route (e.g., Kyoto – Shiga – Nagoya) and delivers that information again. In this way, a reduction in empty return trips and a reduction in waiting time for loading and unloading are achieved.

[0187] Example of a prompt:

[0188] "Departure point: Osaka, Arrival point: Nagoya, Departure time: 08:00, Desired arrival time: 10:00-12:00, Package type: Large, Weight: 500kg. Based on these conditions, please generate the optimal delivery route and schedule."

[0189] This will enable efficient truck transportation using autonomous vehicles.

[0190] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0191] Step 1:

[0192] The server collects location information in real time from the GPS devices of delivery vehicles. The input data is the current location of the delivery vehicle, and the output is the collected location data. This data is formatted into a predetermined format and saved.

[0193] Step 2:

[0194] The user (shipper) enters order information using the interface. The input data includes origin, destination, package type, weight, and desired delivery time. The output is a dataset that centrally manages this order information. This data is sent to and stored on the server.

[0195] Step 3:

[0196] The server collects information on the status of receiving shipments. The input data includes the preparation status and acceptance time for receiving shipments, and the output is integrated receiving information data. This data is also formatted and saved in a predetermined format.

[0197] Step 4:

[0198] The server integrates the collected location information, order information, and receiving information, and performs data preprocessing. The input data consists of location information, order information, and receiving information, and the output is integrated data with outliers removed and imputed. Specifically, it imputes missing data and removes outliers.

[0199] Step 5:

[0200] The server uses AI algorithms to generate optimal delivery routes and schedules. The input data is pre-processed, integrated data, and the output is optimal route and schedule information. Specifically, it applies AI algorithms using TensorFlow or PyTorch to calculate delivery routes and schedules.

[0201] Step 6:

[0202] The server distributes the generated schedule to the delivery vehicle drivers and the shippers. The input data consists of the generated route and schedule information, and the output is a notification to the driver's terminal and the shipper's management system. Specifically, it displays the detailed route and schedule on the driver's smartphone.

[0203] Step 7:

[0204] The user (driver) reports the status and problems encountered during operation to the server in real time from their terminal. The input data is information about problems that occurred during operation, such as traffic congestion or changes in delivery destinations, and the output is feedback data to the server.

[0205] Step 8:

[0206] The server reapplies the AI ​​algorithm based on the received situation data to re-optimize the schedule and route. The input data is real-time feedback of situation data, and the output is the re-optimized route and schedule. Specifically, it calculates the new route and schedule and redistributes them to the driver's terminal.

[0207] In this way, efficient truck transportation management using autonomous vehicles is realized by utilizing the generated AI model and prompt messages.

[0208] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0209] This invention combines a system that matches delivery vehicle location information with order information to generate and distribute efficient delivery routes and schedules, with an emotion engine that recognizes user emotions. This system enables the re-optimization of schedules that take into account the driver's stress and fatigue levels, and schedule updates based on real-time feedback.

[0210] System Configuration

[0211] 1. Data collection methods

[0212] The server collects real-time location information of delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[0213] The server collects order information from shippers, who input the order information through an interface.

[0214] The server provides a means to collect information on the status of receiving shipments, and to understand the readiness for receiving shipments and the available time for receiving them.

[0215] 2. Data integration and preprocessing means

[0216] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[0217] 3. Matching methods using AI algorithms

[0218] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[0219] Specifically, the system calculates the optimal combination based on the truck's current location, load capacity, and detailed order information.

[0220] 4. Schedule distribution method

[0221] The server sends the generated schedule to each truck driver's terminal and also distributes the schedule to the shipper.

[0222] 5. Real-time feedback and optimization means

[0223] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0224] The server reapplies the AI ​​algorithm based on the received status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0225] 6. Emotional Engine

[0226] The server uses an emotion engine to collect emotional information from users (drivers and shippers). This information is used to evaluate stress levels and satisfaction levels.

[0227] The emotional engine senses the driver's stress and fatigue levels and re-optimizes the schedule accordingly. For example, if the driver is highly fatigued while driving, it can incorporate break time into the schedule.

[0228] The server reapplies AI algorithms and updates schedules based on sentiment information collected in real time. It also evaluates user satisfaction and suggests ways to improve the service.

[0229] Explanation of the program's processing

[0230] The program for this system implements the above-mentioned methods to achieve efficient truck transportation while also taking user emotions into consideration. The following describes the program's processing details.

[0231] 1. Data Collection

[0232] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[0233] The user (shipper) enters order information using a terminal and sends it to the server.

[0234] The server uses means to collect information on the status of receiving shipments and to understand the readiness for acceptance.

[0235] 2. Data Integration and Preprocessing

[0236] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[0237] 3. Application of AI algorithms

[0238] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[0239] 4. Scheduled distribution

[0240] The server distributes the generated schedule to each truck driver's terminal. The driver's terminal provides detailed instructions on where to pick up the cargo and where to deliver it.

[0241] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[0242] 5. Real-time feedback

[0243] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[0244] Based on this information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and delivers it again.

[0245] 6. Application of the emotion engine

[0246] The server uses an emotion engine to collect emotional information from users (drivers and shippers). For example, it can sense a driver's stress level and suggest a break if stress levels are high.

[0247] The user (driver) reports emotional information through their device, and the server uses this information to re-optimize the schedule.

[0248] The server proposes service improvements based on emotional information, thereby improving overall delivery efficiency.

[0249] Specific example

[0250] For example, consider the case where truck A is traveling from Tokyo to Yokohama. This system collects GPS data from the delivery vehicle to determine its current location is Tokyo. Two delivery requests from the shipper (orders 1 and 2) from Tokyo to Yokohama are entered as order information. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A takes the optimal route to accept orders 1 and 2.

[0251] The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up two packages at the Tokyo warehouse and deliver them to Yokohama. If the driver encounters traffic congestion during the trip, they can report it to the server in real time using their device, and the server will calculate and redistribute a new route.

[0252] Furthermore, the emotion engine integrated into this system senses the driver's stress level and fatigue, and suggests breaks as needed. It also collects feedback from shippers and drivers in real time, and reapplies the AI ​​algorithm to update the schedule. In this way, it is possible to reduce the rate of empty trucks returning to port, shorten waiting times for loading and unloading, and improve user satisfaction.

[0253] The following describes the processing flow.

[0254] Step 1: Data Collection

[0255] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[0256] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[0257] The device sends the above data to the server.

[0258] The server integrates the collected location information, order information, and delivery status information.

[0259] Step 2: Data Integration and Preprocessing

[0260] The server stores the received data in the database.

[0261] The server checks data integrity, completes missing data, and removes outliers. If data is missing, it is completed using estimates or previous data.

[0262] The server filters out abnormal values ​​(for example, extremely long delivery times) and sends correction requests to users for data where abnormalities are detected.

[0263] Step 3: Matching using AI algorithms

[0264] The server runs an AI algorithm based on the current location of all delivery vehicles, order information, and planned routes.

[0265] The server performs optimal matching of each delivery vehicle with each order. Specifically, it calculates the best combination by considering factors such as the distance and time from each truck's current location to the order's departure point, load capacity, and environmental impact.

[0266] Step 4: Gathering emotional information

[0267] The user's (driver's) emotional state (stress level, fatigue level, etc.) is collected through an emotion engine.

[0268] The server integrates the collected sentiment information and performs data preprocessing based on it.

[0269] Step 5: Generate Optimal Route and Schedule

[0270] The server uses AI algorithms and collected data to generate the optimal delivery route and schedule. For example, it calculates a route where truck A can pick up two orders on its way from Tokyo to Yokohama.

[0271] Furthermore, the server generates a schedule that includes breaks and adjustments to the route based on the driver's emotional state (stress and fatigue levels).

[0272] Step 6: Scheduled delivery

[0273] The server sends the generated schedule to each driver's terminal. Specifically, it provides information such as where to pick up packages, where to deliver them, and even rest instructions based on the driver's emotional state.

[0274] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[0275] Step 7: Real-time feedback and re-optimization

[0276] The user (driver) reports the current traffic situation and the status of the truck in real time using a terminal. For example, the occurrence of traffic jams or accidents.

[0277] Based on the received feedback data, the server reapplies the AI algorithm and recalculates the optimal route and schedule.

[0278] The server redistributes the recalculated schedule and route to the driver's terminal.

[0279] Step 8: Evaluation and improvement by the emotion engine

[0280] The server evaluates the emotion information collected in real time and checks the driver's stress level and satisfaction.

[0281] Based on the emotion information, the server proposes improvement measures for the service and reflects them in the operation plan. For example, when the stress is high, more breaks are set or the route is changed to reduce the burden.

[0282] In this way, an efficient distribution operation management system is realized that reduces the empty vehicle return rate and shortens the waiting time for goods while considering the emotions of the user (driver) and the shipper.

[0283] (Example 2)

[0284] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0285] In the conventional distribution system, simple route optimization is performed based on the position information of the delivery vehicle and the order information, but it lacks the ability to respond to the emotions of users and sudden problems in real time. Therefore, there is a problem that the satisfaction of the driver and shipper of the delivery vehicle cannot be sufficiently improved and the burden on the driver cannot be sufficiently reduced. Furthermore, the conventional system also has a problem that it is difficult to respond flexibly when traffic jams or delivery obstacles occur.

[0286] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means.

[0287] In this invention, the server includes means for collecting the position information of the delivery vehicle, means for collecting order information from the shipper, means for collecting the receiving status information, means for integrating these data and performing preprocessing, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the driver of the delivery vehicle and the shipper, means for receiving real-time feedback on the delivery status and problems and optimizing the schedule again, and means for collecting the user's emotional information, analyzing this using an emotion engine, and re-optimizing the delivery schedule. As a result, it becomes possible to improve the satisfaction of the driver of the delivery vehicle and the shipper, reduce the burden on the driver, and further enable flexible real-time response.

[0288] A "delivery vehicle" is a vehicle used to transport goods or luggage from one location to another.

[0289] "Position information" is information indicating where a specific object or person is currently located, obtained using position measurement technologies such as GPS.

[0290] "Order information" is data including detailed information such as the type, quantity, and delivery destination of the goods to be shipped by the shipper.

[0291] "Receiving status information" is information regarding the preparation status of receiving goods at the delivery destination and the time zone when they can be received.

[0292] A "server" is a computer system for collecting, integrating, analyzing data, and distributing the results.

[0293] "Means for integrating data and performing preprocessing" is a technology for managing the collected position information, order information, and receiving status information in a unified manner and complementing and correcting deficiencies and outliers.

[0294] An "AI algorithm" is an algorithm that uses machine learning and artificial intelligence technologies to calculate the optimal delivery route and schedule.

[0295] "Methods for generating optimal delivery routes and schedules" refers to technologies that analyze collected data to create efficient delivery routes and schedules that meet user requirements.

[0296] "Means for distributing schedules to delivery vehicle drivers and shippers" refers to a function that transmits the generated delivery routes and schedules to the drivers' terminals and the shippers' terminals.

[0297] "A means of receiving real-time feedback on delivery status and problems, and re-optimizing the schedule" refers to a technology that receives feedback information from drivers and shippers during operations, and then reapplies an AI algorithm based on this information to update the schedule.

[0298] "Users" refer to people such as drivers and shippers who use the delivery system.

[0299] "Emotional information" refers to data about the user's emotional state, such as stress levels and satisfaction levels.

[0300] An "emotion engine" is a system that collects and analyzes user emotional information to provide appropriate responses and suggestions.

[0301] "Methods for re-optimizing delivery schedules" refer to technologies that generate more efficient delivery schedules based on user sentiment information and real-time feedback.

[0302] This invention is a system that combines an emotion engine for recognizing the emotions of users in addition to a system that matches the location information of delivery vehicles with order information and generates and distributes an efficient delivery route and schedule. This enables the re-optimization of schedules considering the stress and fatigue levels of drivers and the update of schedules based on real-time feedback.

[0303] This system can be implemented as follows.

[0304] 1. Data collection means

[0305] The server collects the location information of delivery vehicles in real time. For this purpose, a GPS device is installed in each vehicle, and data is collected through the driver's terminal. The user (shipper) uses the terminal to input order information and transmits it to the server. The server also collects the receiving status information from the systems of each delivery destination.

[0306] 2. Data integration and preprocessing means

[0307] The server manages all the collected data in a unified manner and complements and corrects deficiencies and outliers. For this purpose, a database management system (DBMS) is used. For example, past trends and machine learning models are used to complement missing location information.

[0308] 3. AI algorithm application means

[0309] The server analyzes the collected real-time data and preprocessed data and applies an AI algorithm to generate an optimal delivery route and schedule. For example, a machine learning algorithm is used to calculate the shortest route from delivery destination A to delivery destination B or the route to efficiently accept a specific order.

[0310] 4. Schedule distribution means

[0311] The server distributes the generated schedule to the delivery vehicle drivers and shippers. Specifically, the driver's terminal displays detailed information about the pickup point and delivery destination. Shippers are notified of the schedule and can understand the overall delivery status.

[0312] 5. Real-time feedback and optimization means

[0313] Users (drivers) report their driving status and problems to the server in real time via their terminals. For example, they send information such as traffic congestion or changes in delivery destinations. Based on this feedback information, the server reapplies an AI algorithm to calculate a new, optimal schedule and route, and delivers it to the driver's terminal.

[0314] 6. Means of applying the emotion engine

[0315] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). This information is used, for example, to evaluate the driver's stress level and fatigue level. If the server detects that the driver is highly stressed, it suggests a break. Users (drivers) report their emotional information through a terminal, and the server uses this information to re-optimize the schedule.

[0316] Specific example

[0317] For example, in the case where truck A is traveling from Tokyo to Yokohama, this system operates as follows:

[0318] 1. Data collection methods

[0319] The server confirms that truck A is currently in Tokyo using its GPS device. The user (shipper) enters orders (orders 1 and 2) for delivery from Tokyo to Yokohama.

[0320] 2. Data integration and preprocessing means

[0321] The server integrates location information, order information, and receiving information, and estimates and supplements any missing data.

[0322] 3. Methods for applying AI algorithms

[0323] The server uses an AI algorithm to calculate the optimal route based on the current location and order information of truck A. For example, it might pick up packages A and B from the Tokyo warehouse and head to the delivery destination in Yokohama.

[0324] 4. Schedule distribution method

[0325] The server delivers this schedule to the driver's smartphone. The device displays, "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama."

[0326] 5. Real-time feedback and optimization means

[0327] When a user (driver) encounters traffic congestion, they report it to the server from their device. The server receives this information, calculates a new route, and redistributes it.

[0328] 6. Means of applying the emotion engine

[0329] If the server detects that the driver is stressed, it will suggest a break. For example, a message might appear on the terminal saying, "Take a 15-minute break at the next service area."

[0330] Examples of prompts to input into a generative AI model

[0331] The following are examples of prompts to input into the generative AI model.

[0332] "Based on the current location information of the delivery vehicles, please generate the optimal delivery route and schedule."

[0333] "Please suggest countermeasures for situations where the driver's stress level is high."

[0334] "Please re-optimize the schedule in real time based on the following data: Track A's current location, load capacity, order information, and sentiment information."

[0335] This enables highly accurate scheduling and service improvements using generative AI models.

[0336] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0337] Step 1: Data Collection

[0338] The server collects real-time location information of delivery vehicles from GPS devices installed in the vehicles. Specifically, it receives signals from the GPS devices to determine the vehicle's current location. Users (shippers) use a terminal to input order information (e.g., delivery destination and package details) and send it to the server. The server collects information on the status of package receipt from the delivery destination, receiving data such as the time when the package can be received and the readiness status from the system. This data is aggregated on the server as GPS location information (input), order information (input), and package receipt information (input).

[0339] Step 2: Data Integration and Preprocessing

[0340] The server integrates and centrally manages all collected data. Specifically, it uses a database management system (DBMS) to organize the information and processes data to supplement and correct missing data and outliers. For example, it uses historical trend data and machine learning models to infer and fill in missing location information. As a result, a consistent dataset (output) is created.

[0341] Step 3: Applying the AI ​​algorithm

[0342] The server uses integrated data to apply AI algorithms to generate optimal delivery routes and schedules. Specifically, it analyzes the truck's current location, load capacity, and order details, and uses machine learning algorithms (e.g., route optimization algorithms) to calculate the shortest route and most efficient delivery sequence. This generates the optimal delivery route and schedule (output).

[0343] Step 4: Scheduled delivery

[0344] The server distributes the generated schedule to each driver's terminal and the shipper's terminal. Specifically, it sends detailed pickup and delivery instructions to the driver's terminal and notifies the shipper of the overall delivery status. On the driver's terminal, instructions such as "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama" will be displayed. As a result, the schedule is distributed (output) to each terminal.

[0345] Step 5: Real-time feedback and optimization

[0346] The user (driver) reports the status and problems during their journey (e.g., traffic congestion or changes in delivery destinations) to the server in real time using their terminal. Specifically, they input feedback information using the status reporting menu. Based on the received feedback information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and schedule, and redistributes it. The optimized schedule (output) is then delivered back to the driver's terminal.

[0347] Step 6: Apply the emotion engine

[0348] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). Specifically, it senses the driver's stress level using facial recognition and voice analysis technology. For example, if a high stress level is detected, it suggests taking a break. Users (drivers) report their emotional information from their terminals, and the server re-optimizes the schedule based on this information. The re-optimized schedule (output) based on the emotional information is delivered to the driver's terminal. The server also suggests service improvement measures to enhance user satisfaction.

[0349] The above describes the specific program processing flow of this system.

[0350] (Application Example 2)

[0351] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0352] Currently, delivery systems exist that generate efficient delivery routes based on the location and order information of delivery vehicles. However, they lack sufficient functionality to optimize schedules while considering driver stress and fatigue. This can lead to accumulated driver fatigue and decreased efficiency. Furthermore, the lack of smooth real-time feedback and schedule re-optimization can result in a decline in service quality.

[0353] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0354] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving goods, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle driver and shipper, means for detecting the driver's emotional state, means for re-optimizing the schedule based on the detected emotional state and fatigue level, and means for receiving real-time feedback on the delivery status and problems and re-optimizing the schedule. This enables efficient schedule generation that takes into account the driver's emotional state and fatigue level, and smooth schedule re-optimization based on real-time feedback.

[0355] A "delivery vehicle" is a vehicle used to transport orders from customers or shippers to their destination.

[0356] "Location information" refers to data that indicates the current geographical coordinates of the delivery vehicle.

[0357] "Order information" refers to information provided by the shipper that includes specific instructions and requirements regarding delivery.

[0358] "Delivery status information" refers to information regarding the location and time of delivery, the progress of preparation for delivery, and so on.

[0359] "Data integration" is the process of centrally combining data collected from different sources.

[0360] "Preprocessing" refers to the preparatory processes performed to ensure data quality and to prepare the data for analysis and application to algorithms.

[0361] An "AI algorithm" is a mathematical model or calculation method that uses artificial intelligence technology to generate the optimal delivery route and schedule.

[0362] A "delivery route" is the path that a delivery vehicle takes to reach its destination.

[0363] A "schedule" is a plan that outlines the specific time allocation and sequence of delivery operations.

[0364] "Emotional state" refers to the psychological and physiological state of the driver, such as their stress level and fatigue level.

[0365] "Real-time feedback" is a function that immediately reports any problems or situations that arise during delivery operations to the system.

[0366] A "break" refers to a short period of rest taken by a driver during work.

[0367] "Service improvement measures" refer to specific suggestions and strategies aimed at improving user satisfaction.

[0368] This invention is a system for efficiently carrying out delivery operations, and in particular, it generates and manages optimal delivery routes and schedules based on the location information and order information of delivery vehicles, as well as the emotional state of the drivers. This system enables the generation of efficient delivery routes and the re-optimization of schedules that take into account the stress and fatigue of drivers.

[0369] The system includes the following key technological elements:

[0370] 1. Data collection methods

[0371] The server has the functionality to collect real-time location information of delivery vehicles. GPS modules are installed in the vehicles, and the data is transmitted to the server. In addition, order information from shippers is collected via terminals and transmitted to the server. Information on the pickup location is also collected simultaneously, and all data is managed centrally.

[0372] 2. Data integration and preprocessing means

[0373] The server has the function of integrating the collected data and supplementing or correcting any deficiencies or anomalies. This allows subsequent processing to be carried out based on high-quality data.

[0374] 3. Optimal route generation method using AI algorithms

[0375] The server uses AI algorithms to generate the optimal delivery route and schedule based on the current location of the delivery vehicle, order information, and planned route. For example, it calculates the optimal route that allows a truck to efficiently handle multiple orders.

[0376] 4. Schedule distribution method

[0377] The server has the function of distributing the generated schedule to delivery vehicle drivers and shippers. The driver's terminal displays the current schedule and route in real time.

[0378] 5. Means for detecting the driver's emotional state

[0379] The server incorporates an emotion engine that collects driver emotional data and evaluates stress and fatigue levels. Based on this emotional data, it generates a schedule that takes the driver's health into consideration.

[0380] 6. Real-time feedback and re-optimization means

[0381] The server receives delivery status and issues collected in real time by drivers and systems, and then reapplies AI algorithms based on this information to update schedules and routes. For example, it instantly reflects traffic congestion and other obstacle information and recalculates the optimal route.

[0382] Explanation of specific examples

[0383] For example, consider a delivery vehicle making a food delivery from Tokyo to Yokohama. Using this system, the server collects the vehicle's GPS data and determines that its current location is Tokyo. Order information from the client is entered, and the order is to deliver sushi and ramen to Yokohama at 2:00 PM. Based on this data, the server applies an AI algorithm to generate a route that allows the truck to complete the order in the shortest possible time.

[0384] If a driver encounters traffic congestion during their journey, they use a terminal to report the information to the server in real time. The server immediately recalculates a new route and notifies the driver. In addition, an emotion engine built into the system senses the driver's stress level and fatigue level and suggests a break if necessary.

[0385] Example of a prompt

[0386] "For a food delivery from Tokyo to Yokohama, please collect GPS location data and emotional state to generate an efficient schedule and route. The current order is to deliver sushi and ramen to Yokohama at 2:00 PM. The driver's stress level is high, so please also suggest optimal rest times."

[0387] As described above, the present invention can simultaneously improve the efficiency of delivery operations and manage the health of drivers.

[0388] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0389] Step 1:

[0390] Data collection

[0391] Input: GPS information of delivery vehicles, order information from the consignor, and delivery status information.

[0392] Processing: The server collects GPS data from delivery vehicles in real time to obtain location information. It also sends order information entered by the shipper via a terminal to the server and simultaneously collects information on the status of receiving the goods.

[0393] Output: Integrated location information, order information, and delivery status information.

[0394] Step 2:

[0395] Data preprocessing

[0396] Input: All collected data (location information, order information, delivery status information)

[0397] Processing: The server centrally manages the collected data and imputes and corrects missing or outlier values. For example, if location information is missing, it is interpolated based on the previous data and the imputed information.

[0398] Output: Replicated and preprocessed dataset

[0399] Step 3:

[0400] Optimal route generation using AI algorithms

[0401] Input: Preprocessed dataset (location information, order information, delivery status information)

[0402] Processing: The server uses this data to apply AI algorithms to generate the optimal delivery route and schedule. For example, it considers the vehicle's current location, the order pickup location, and the delivery destination to calculate the shortest and most efficient route.

[0403] Output: Optimal route and schedule information

[0404] Step 4:

[0405] Scheduled distribution

[0406] Input: Optimal route and schedule information

[0407] Processing: The server distributes the generated schedule to the driver's terminal and the shipper's system. Detailed route information is displayed on the terminal.

[0408] Output: Schedule information distributed to the driver's terminal and the shipper's system.

[0409] Step 5:

[0410] Driver emotional state detection

[0411] Input: Prompt messages sent by the server and feedback data from the driver.

[0412] Processing: The terminal uses an emotion engine to detect the driver's emotional state and sends that data to the server. For example, it evaluates the stress level from the driver's facial expressions and voice.

[0413] Output: Driver's emotional state data

[0414] Step 6:

[0415] Schedule reoptimization based on the driver's emotional state

[0416] Input: Emotional state data (stress level, fatigue level)

[0417] Processing: The server adjusts the schedule as needed based on the driver's emotional state data. For example, if stress levels are high, it suggests a break and recalculates the schedule.

[0418] Output: Adjusted schedule information

[0419] Step 7:

[0420] Real-time feedback and optimization

[0421] Input: Delivery problem reports (traffic information, other disruption information), new order information

[0422] Processing: The driver reports the problem in real time via a terminal. The server receives this information, reapplies the AI ​​algorithm based on the new data, and recalculates the optimal route and schedule.

[0423] Output: Updated optimal route and schedule information

[0424] Each processing step works in conjunction with the entire system to improve the efficiency of delivery operations and ensure the health of drivers.

[0425] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0426] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0427] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0428] [Second Embodiment]

[0429] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0430] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0431] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0432] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0433] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0434] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0435] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0436] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0437] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0438] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0439] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0440] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0441] This invention is a system aimed at reducing the rate of empty return trips and shortening loading / unloading waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and loading / unloading status information, and generating and distributing the optimal route and schedule based on this information. The following describes in detail embodiments for specifically implementing this invention.

[0442] System Configuration

[0443] 1. Data collection methods

[0444] The server collects real-time location information for delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[0445] The server collects order information from shippers. To do this, shippers input order information (origin, destination, type of package, weight, desired delivery time, etc.) through an interface.

[0446] The server collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[0447] 2. Data integration and preprocessing means

[0448] The server integrates and preprocesses the collected location, order, and delivery information. By performing data interpolation and removing outliers, it generates a highly reliable dataset.

[0449] 3. Means for applying the matching algorithm

[0450] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[0451] Specifically, the system calculates the optimal combination based on data such as the truck's current location, load capacity, and the order's origin, destination, weight, and desired delivery time.

[0452] 4. Schedule distribution method

[0453] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The schedule is notified to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[0454] 5. Real-time feedback and optimization means

[0455] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0456] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0457] Explanation of the program's processing

[0458] The program for this system implements the above-mentioned methods to achieve efficient truck transportation. The following describes the processing details of the program.

[0459] 1. Data Collection

[0460] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[0461] The user (shipper) enters order information using a terminal and sends it to the server.

[0462] The server sets up a means to collect information on the status of receiving shipments and understands the acceptance time and preparation status.

[0463] 2. Data Integration and Preprocessing

[0464] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[0465] 3. Application of the matching algorithm

[0466] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it calculates that truck A can pick up two orders on its way from Tokyo to Yokohama.

[0467] 4. Scheduled distribution

[0468] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The driver's smartphone displays the specific route and loading / unloading instructions.

[0469] 5. Real-time feedback

[0470] Users (drivers) report real-time information such as traffic congestion and changes in delivery destinations from their terminals.

[0471] Based on this information, the server reapplies the AI ​​algorithm to recalculate the optimal route and schedule for delivery.

[0472] Specific example

[0473] As an example, consider the case where truck A travels from Tokyo to Yokohama. GPS data from the delivery vehicle is collected to determine that its current location is Tokyo. Two delivery requests (orders 1 and 2) from Tokyo to Yokohama are entered as order information from the shipper. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A accepts orders 1 and 2 via the optimal route. The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up the two packages at the Tokyo warehouse and deliver them to Yokohama. If traffic congestion occurs along the way, the driver reports it to the server in real time, and the server calculates a new route and delivers it again.

[0474] In this way, this system reduces the rate at which trucks are empty and shortens waiting times for loading and unloading, thereby achieving efficient delivery operation management.

[0475] The following describes the processing flow.

[0476] Step 1: Data Collection

[0477] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[0478] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[0479] The device sends the above data to the server.

[0480] Step 2: Data Integration and Preprocessing

[0481] The server stores the received data in a centrally managed database.

[0482] The server checks data integrity and fills in any missing data. For example, if there is a missing input, it will fill in the estimated value based on the previous data.

[0483] The server filters out abnormal values ​​(for example, delivery times exceeding the possible range) and sends a correction request to the user if an abnormality is found.

[0484] Step 3: Matching using AI algorithms

[0485] The server runs an AI algorithm based on the current location, order information, and planned route of all trucks.

[0486] The server performs optimal matching of each truck with an order. Specifically, it determines the best combination based on factors such as the distance and time from the dispatched vehicle's current location to the order's departure point, load capacity, and environmental impact.

[0487] Step 4: Generate Optimal Route and Schedule

[0488] The server generates the optimal route and schedule calculated by an AI algorithm. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[0489] Step 5: Scheduled distribution

[0490] The server sends the generated schedule to each truck driver's terminal. Specifically, it provides detailed instructions to the driver's terminal on where to pick up the cargo and where to deliver it.

[0491] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[0492] Step 6: Real-time feedback and reoptimization

[0493] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[0494] The server reapplies the AI ​​algorithm based on the received feedback (e.g., traffic information) to calculate a new, optimal route.

[0495] The server resends the updated schedule and route to the driver's terminal.

[0496] (Example 1)

[0497] Next, we will describe Example 1. 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."

[0498] There is a need to solve the problems of empty vehicle return rates and waiting times in truck transportation. Conventional systems have insufficient management of delivery vehicle location information and order information, making it difficult to optimize delivery routes efficiently. In addition, the inability to flexibly change schedules in response to real-time changes in circumstances led to problems with reduced operational efficiency.

[0499] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0500] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and re-optimizing the schedule, means for determining location information using a GPS device, means for inputting order information via a terminal, pre-processing means for data completion and removal of anomalies, and means for distributing schedule information using a notification system. This makes it possible to reduce the rate of empty return trips of trucks and shorten waiting times for loading and unloading.

[0501] "Delivery vehicles" refer to means of transport such as automobiles, trucks, and vans used to transport goods and products.

[0502] "Location information" refers to data that indicates the geographical location of a specific object or person, obtained by location measurement devices such as GPS devices.

[0503] "Order information" refers to data provided by shippers when requesting delivery services, including details such as the origin, destination, type of package, weight, and desired delivery time.

[0504] "Receiving information" refers to information such as the readiness status of the receiving location and the available receiving times for packages.

[0505] "Integration" is the process of bringing together different types of data and managing them comprehensively.

[0506] "Preprocessing" refers to the process of transforming collected raw data into a format that is easy to analyze, and includes data interpolation and removal of outliers.

[0507] An "AI algorithm" is a set of computational procedures that use artificial intelligence technology to analyze data and perform optimization and predictions.

[0508] A "schedule" is a plan of time and location, outlining when and where a delivery vehicle will pick up a package and where it will deliver it.

[0509] "Feedback" is the process of receiving information about the system's operation status and problems from the system and its users, and using that information to improve and adjust the system.

[0510] "Optimization" is the process of adjusting calculations and procedures to obtain the best possible result under given conditions and constraints.

[0511] A "GPS device" is a device that measures and reports a specific location on Earth, and it obtains location information using satellite signals.

[0512] A "terminal" is a device, such as a computer or smartphone, that a user uses to input information or receive information from a system.

[0513] A "notification system" is a communication method used to instantly deliver important information and updates to users and systems, and includes SMS and push notifications.

[0514] This invention is a system aimed at reducing the rate of empty return trips and shortening waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and cargo receiving status information, and generating and distributing the optimal route and schedule based on this information.

[0515] Hardware and software to be used

[0516] The hardware used includes GPS devices, user terminals (smartphones and PCs), and servers. The software includes data collection software, AI algorithms, data integration and preprocessing software, and notification systems.

[0517] Overall flow

[0518] 1. Data Collection

[0519] The server collects location information in real time from GPS devices attached to delivery vehicles. This information includes the vehicle's current location, speed, and direction of travel.

[0520] The user (shipper) enters order information (origin, destination, type of package, weight, desired delivery time, etc.) via a terminal and sends it to the server.

[0521] The server collects information on the status of receiving shipments (such as readiness for acceptance and available acceptance times). This information is either entered by the person in charge at the receiving location or automatically retrieved by the system.

[0522] 2. Data Integration and Preprocessing

[0523] The server integrates collected location information, order information, and delivery information, and manages them centrally in real time.

[0524] The server performs preprocessing to complete the data and remove outliers. This process fills in missing data and corrects outliers, resulting in a reliable dataset.

[0525] 3. Application of the matching algorithm

[0526] The server uses an AI algorithm to generate the optimal delivery route and schedule. This algorithm considers the current location, load capacity, origin, destination, weight, and desired delivery time of each delivery vehicle to calculate the most efficient route and schedule.

[0527] 4. Scheduled distribution

[0528] The server distributes the generated schedule to the delivery vehicle drivers and shippers. This distribution is done through a notification system, and the specific route and loading / unloading instructions are displayed on the drivers' smartphones or tablets.

[0529] 5. Real-time feedback and optimization

[0530] Users (drivers) report operational status and problems (such as traffic congestion or changes in delivery destinations) to the server in real time from their terminals.

[0531] The server reapplies the AI ​​algorithm based on this status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0532] Specific example

[0533] As an example, let's consider the case where truck A is traveling from Tokyo to Yokohama.

[0534] 1. Data Collection: The server obtains the current location of truck A (Tokyo) from a GPS device. The shipper also inputs order information, such as "I would like a 500kg package delivered from a warehouse in Tokyo to a warehouse in Yokohama," and sends it to the server.

[0535] 2. Data Integration and Preprocessing: The server integrates the collected data (location information of truck A, order information, and acceptance time information for the Yokohama warehouse) and supplements any missing data or outliers.

[0536] 3. Application of Matching Algorithm: The server uses an AI algorithm to generate the optimal schedule for truck A to pick up goods from a warehouse in Tokyo via the shortest route and deliver them to a warehouse in Yokohama.

[0537] 4. Schedule Distribution: The server distributes the generated schedule to the driver of truck A's smartphone. The smartphone displays instructions such as, "Pick up the cargo at the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[0538] 5. Real-time feedback and optimization: If traffic congestion occurs along the way, the user (driver) reports "traffic congestion" information from their device. The server then reapplies the AI ​​algorithm based on this information, calculates an alternative route, and redistributes it to the driver.

[0539] Example of a prompt:

[0540] "The system uses the current location data of trucks collected from GPS devices as input to calculate the optimal delivery route."

[0541] "Using multiple order details from shippers as input, an AI algorithm is applied to generate the optimal schedule."

[0542] "We will re-optimize the route and schedule based on real-time feedback from drivers."

[0543] This system will reduce the rate of empty truck return trips and waiting times for loading and unloading, enabling more efficient delivery operation management.

[0544] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0545] Step 1: Data Collection

[0546] The server collects location information in real time from GPS devices installed in delivery vehicles. The input data includes the current location, speed, and direction of movement of each vehicle, and this data is analyzed to output accurate location information.

[0547] The user (shipper) enters order information using a terminal. This information includes the origin, destination, type of package, weight, and desired delivery time. This information is then sent to the server via the terminal.

[0548] The server collects information on the status of receiving shipments (readiness for receiving, available time for receiving). This includes means of obtaining data entered by the person in charge at the receiving location. The server analyzes the input data and outputs the available time slots for receiving shipments.

[0549] Step 2: Data Integration and Preprocessing

[0550] The server centrally integrates the collected location information, order information, and delivery information. The input data consists of the above-mentioned collected items, and it outputs a manageable dataset by integrating these items.

[0551] The server performs preprocessing on the integrated data, including data imputation and outlier removal. The input data includes integrated raw data, and the server outputs a reliable dataset after imputing missing data and detecting and correcting outliers.

[0552] Step 3: Applying the Matching Algorithm

[0553] The server uses AI algorithms to generate the optimal delivery route and schedule. Input data includes the current location of the delivery vehicle, its load capacity, and order information (origin, destination, weight, desired delivery time). This data is analyzed to output an efficient route and schedule.

[0554] Specifically, the server calculates the optimal location and time for truck A to pick up two orders within Tokyo, and generates its route and schedule.

[0555] Step 4: Scheduled delivery

[0556] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The input data is the generated schedule information, which is distributed via the notification system. As a result of the distribution, the specific route and loading instructions are output to the driver's smartphone.

[0557] In terms of specific actions, the server distributes schedules such as "Pick up the package from the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[0558] Step 5: Real-time feedback and optimization

[0559] Users (drivers) report problems and situations during their journey (such as traffic congestion or changes in delivery destinations) in real time from their terminals. The input data includes the driver's reported information.

[0560] The server re-optimizes the schedule and route by applying the AI ​​algorithm again based on real-time feedback. The input data is feedback information from the driver, which is analyzed to output a new route and schedule.

[0561] Specifically, the server generates a new instruction stating, "There is currently traffic congestion, so take an alternative route," and redistributes it to the driver.

[0562] (Application Example 1)

[0563] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0564] This invention aims to reduce the rate of empty truck return trips and shorten loading / unloading waiting times in truck transportation, but existing systems have not been able to completely solve this problem. Specifically, real-time location information collection, optimal route generation, and rapid response to problems are not adequately performed, and efficient delivery operation management has not been achieved. Furthermore, even when using autonomous vehicles, there are still aspects that are difficult to address.

[0565] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0566] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and optimizing the schedule again, and an autonomous vehicle control system for comfortable delivery operation management. This makes it possible to reduce the rate of empty return trips, shorten waiting times for cargo, and improve the efficiency of autonomous vehicle operation management.

[0567] "Means for collecting location information of delivery vehicles" refers to a device that uses a GPS device to obtain the current location of delivery vehicles in real time.

[0568] "Means for collecting order information from shippers" refers to an interface and system on which shippers input order information such as origin, destination, type of goods, weight, and desired delivery time, and transmit it to a server.

[0569] "Means for collecting information on the status of receiving goods" refers to devices and systems that collect information from the receiving party regarding the status of preparation for receiving goods, the time when they can be received, etc.

[0570] "Means for integrating and preprocessing data" refers to devices and systems that centrally manage multiple collected data sets and perform processes to supplement and correct deficiencies and abnormal values.

[0571] "A method for generating optimal delivery routes and schedules using AI algorithms" refers to a software algorithm that uses artificial intelligence technology to calculate and generate optimal delivery routes and schedules based on collected data.

[0572] "Means for distributing the generated schedule to delivery vehicle drivers and shippers" refers to a system that notifies drivers' terminals and shippers' management systems of the calculated and generated schedule.

[0573] "A means of receiving real-time feedback on delivery status and problems and re-optimizing the schedule" refers to a system that receives real-time information on problems and delays from vehicles in operation, and then applies AI algorithms to calculate and distribute new routes and schedules.

[0574] The "Autonomous Vehicle Control System for Comfortable Delivery Operation Management" is a system that efficiently manages the operation of autonomous vehicles and distributes optimal routes and schedules to enable quick responses in the event of problems.

[0575] A "generative AI model" is an artificial intelligence model that has been trained to efficiently perform a specific task based on training data.

[0576] A "prompt statement" is an instruction given to a generative AI model to obtain a specific output.

[0577] This invention relates to a truck transportation management system that utilizes autonomous vehicles to maximize transportation efficiency. The configuration and operation of the system for specifically implementing this invention, including the hardware and software used, are described below.

[0578] System Configuration

[0579] 1. Data collection methods

[0580] The server collects real-time location information for delivery vehicles. For this purpose, each vehicle is equipped with a GPS device to collect location data.

[0581] The system also collects order information from shippers. This involves providing an interface for inputting data such as origin, destination, type of package, weight, and desired delivery time.

[0582] The server also collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[0583] 2. Data integration and preprocessing means

[0584] The server centrally manages the collected data. This includes a data cleansing process to supplement and correct any missing or outlier values.

[0585] 3. Means for applying the matching algorithm

[0586] The server uses AI algorithms to generate the optimal delivery route and schedule. It utilizes technologies such as TensorFlow and PyTorch to calculate and generate the optimal route and schedule based on all the collected data.

[0587] 4. Schedule distribution method

[0588] The generated schedule is distributed to the delivery vehicle drivers and the shippers. Notifications are sent to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[0589] 5. Real-time feedback and optimization means

[0590] The user (driver) reports the situation and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0591] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0592] Specific example

[0593] As an example, consider the case of truck B traveling from Osaka to Nagoya. Real-time location information collected from the delivery vehicle's GPS device determines that its current location is Osaka. The shipper inputs order information: departure point is Osaka, destination is Nagoya, large cargo, weight 500kg, desired delivery time 10:00-12:00. The server integrates and preprocesses this data and generates the optimal route and schedule for truck B using an AI algorithm (e.g., using TensorFlow or PyTorch). The generated schedule is delivered to the driver's smartphone, displaying instructions for departure time 08:00 and arrival time 11:30. If traffic congestion occurs near Kyoto along the way, the driver's terminal automatically detects this and provides feedback to the cloud server. The server recalculates and generates a new route (e.g., Kyoto – Shiga – Nagoya) and delivers that information again. In this way, a reduction in empty return trips and a reduction in waiting time for loading and unloading are achieved.

[0594] Example of a prompt:

[0595] "Departure point: Osaka, Arrival point: Nagoya, Departure time: 08:00, Desired arrival time: 10:00-12:00, Package type: Large, Weight: 500kg. Based on these conditions, please generate the optimal delivery route and schedule."

[0596] This will enable efficient truck transportation using autonomous vehicles.

[0597] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0598] Step 1:

[0599] The server collects location information in real time from the GPS devices of delivery vehicles. The input data is the current location of the delivery vehicle, and the output is the collected location data. This data is formatted into a predetermined format and saved.

[0600] Step 2:

[0601] The user (shipper) enters order information using the interface. The input data includes origin, destination, package type, weight, and desired delivery time. The output is a dataset that centrally manages this order information. This data is sent to and stored on the server.

[0602] Step 3:

[0603] The server collects information on the status of receiving shipments. The input data includes the preparation status and acceptance time for receiving shipments, and the output is integrated receiving information data. This data is also formatted and saved in a predetermined format.

[0604] Step 4:

[0605] The server integrates the collected location information, order information, and receiving information, and performs data preprocessing. The input data consists of location information, order information, and receiving information, and the output is integrated data with outliers removed and imputed. Specifically, it imputes missing data and removes outliers.

[0606] Step 5:

[0607] The server uses AI algorithms to generate optimal delivery routes and schedules. The input data is pre-processed, integrated data, and the output is optimal route and schedule information. Specifically, it applies AI algorithms using TensorFlow or PyTorch to calculate delivery routes and schedules.

[0608] Step 6:

[0609] The server distributes the generated schedule to the delivery vehicle drivers and the shippers. The input data consists of the generated route and schedule information, and the output is a notification to the driver's terminal and the shipper's management system. Specifically, it displays the detailed route and schedule on the driver's smartphone.

[0610] Step 7:

[0611] The user (driver) reports the status and problems encountered during operation to the server in real time from their terminal. The input data is information about problems that occurred during operation, such as traffic congestion or changes in delivery destinations, and the output is feedback data to the server.

[0612] Step 8:

[0613] The server reapplies the AI ​​algorithm based on the received situation data to re-optimize the schedule and route. The input data is real-time feedback of situation data, and the output is the re-optimized route and schedule. Specifically, it calculates the new route and schedule and redistributes them to the driver's terminal.

[0614] In this way, efficient truck transportation management using autonomous vehicles is realized by utilizing the generated AI model and prompt messages.

[0615] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0616] This invention combines a system that matches delivery vehicle location information with order information to generate and distribute efficient delivery routes and schedules, with an emotion engine that recognizes user emotions. This system enables the re-optimization of schedules that take into account the driver's stress and fatigue levels, and schedule updates based on real-time feedback.

[0617] System Configuration

[0618] 1. Data collection methods

[0619] The server collects real-time location information of delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[0620] The server collects order information from shippers, who input the order information through an interface.

[0621] The server provides a means to collect information on the status of receiving shipments, and to understand the readiness for receiving shipments and the available time for receiving them.

[0622] 2. Data integration and preprocessing means

[0623] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[0624] 3. Matching methods using AI algorithms

[0625] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[0626] Specifically, the system calculates the optimal combination based on the truck's current location, load capacity, and detailed order information.

[0627] 4. Schedule distribution method

[0628] The server sends the generated schedule to each truck driver's terminal and also distributes the schedule to the shipper.

[0629] 5. Real-time feedback and optimization means

[0630] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0631] The server reapplies the AI ​​algorithm based on the received status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0632] 6. Emotional Engine

[0633] The server uses an emotion engine to collect emotional information from users (drivers and shippers). This information is used to evaluate stress levels and satisfaction levels.

[0634] The emotional engine senses the driver's stress and fatigue levels and re-optimizes the schedule accordingly. For example, if the driver is highly fatigued while driving, it can incorporate break time into the schedule.

[0635] The server reapplies AI algorithms and updates schedules based on sentiment information collected in real time. It also evaluates user satisfaction and suggests ways to improve the service.

[0636] Explanation of the program's processing

[0637] The program for this system implements the above-mentioned methods to achieve efficient truck transportation while also taking user emotions into consideration. The following describes the program's processing details.

[0638] 1. Data Collection

[0639] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[0640] The user (shipper) enters order information using a terminal and sends it to the server.

[0641] The server uses means to collect information on the status of receiving shipments and to understand the readiness for acceptance.

[0642] 2. Data Integration and Preprocessing

[0643] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[0644] 3. Application of AI algorithms

[0645] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[0646] 4. Scheduled distribution

[0647] The server distributes the generated schedule to each truck driver's terminal. The driver's terminal provides detailed instructions on where to pick up the cargo and where to deliver it.

[0648] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[0649] 5. Real-time feedback

[0650] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[0651] Based on this information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and delivers it again.

[0652] 6. Application of the emotion engine

[0653] The server uses an emotion engine to collect emotional information from users (drivers and shippers). For example, it can sense a driver's stress level and suggest a break if stress levels are high.

[0654] The user (driver) reports emotional information through their device, and the server uses this information to re-optimize the schedule.

[0655] The server proposes service improvements based on emotional information, thereby improving overall delivery efficiency.

[0656] Specific example

[0657] For example, consider the case where truck A is traveling from Tokyo to Yokohama. This system collects GPS data from the delivery vehicle to determine its current location is Tokyo. Two delivery requests from the shipper (orders 1 and 2) from Tokyo to Yokohama are entered as order information. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A takes the optimal route to accept orders 1 and 2.

[0658] The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up two packages at the Tokyo warehouse and deliver them to Yokohama. If the driver encounters traffic congestion during the trip, they can report it to the server in real time using their device, and the server will calculate and redistribute a new route.

[0659] Furthermore, the emotion engine integrated into this system senses the driver's stress level and fatigue, and suggests breaks as needed. It also collects feedback from shippers and drivers in real time, and reapplies the AI ​​algorithm to update the schedule. In this way, it is possible to reduce the rate of empty trucks returning to port, shorten waiting times for loading and unloading, and improve user satisfaction.

[0660] The following describes the processing flow.

[0661] Step 1: Data Collection

[0662] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[0663] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[0664] The device sends the above data to the server.

[0665] The server integrates the collected location information, order information, and delivery status information.

[0666] Step 2: Data Integration and Preprocessing

[0667] The server stores the received data in the database.

[0668] The server checks data integrity, completes missing data, and removes outliers. If data is missing, it is completed using estimates or previous data.

[0669] The server filters out abnormal values ​​(for example, extremely long delivery times) and sends correction requests to users for data where abnormalities are detected.

[0670] Step 3: Matching using AI algorithms

[0671] The server runs an AI algorithm based on the current location of all delivery vehicles, order information, and planned routes.

[0672] The server performs optimal matching of each delivery vehicle with each order. Specifically, it calculates the best combination by considering factors such as the distance and time from each truck's current location to the order's departure point, load capacity, and environmental impact.

[0673] Step 4: Gathering emotional information

[0674] The user's (driver's) emotional state (stress level, fatigue level, etc.) is collected through an emotion engine.

[0675] The server integrates the collected sentiment information and performs data preprocessing based on it.

[0676] Step 5: Generate Optimal Route and Schedule

[0677] The server uses AI algorithms and collected data to generate the optimal delivery route and schedule. For example, it calculates a route where truck A can pick up two orders on its way from Tokyo to Yokohama.

[0678] Furthermore, the server generates a schedule that includes breaks and adjustments to the route based on the driver's emotional state (stress and fatigue levels).

[0679] Step 6: Scheduled delivery

[0680] The server sends the generated schedule to each driver's terminal. Specifically, it provides information such as where to pick up packages, where to deliver them, and even rest instructions based on the driver's emotional state.

[0681] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[0682] Step 7: Real-time feedback and re-optimization

[0683] Users (drivers) use a terminal to report traffic conditions and the status of their trucks in real time while they are driving. For example, they might report traffic jams or accidents.

[0684] The server reapplies the AI ​​algorithm based on the received feedback data and recalculates the optimal route and schedule.

[0685] The server redistributes the recalculated schedule and route to the driver's terminal.

[0686] Step 8: Evaluation and improvement using the emotional engine

[0687] The server evaluates emotional information collected in real time to check the driver's stress level and satisfaction level.

[0688] The server uses emotional information to suggest service improvements and incorporates them into the operational plan. For example, if stress levels are high, it may schedule more breaks or change the route to reduce the burden.

[0689] In this way, an efficient delivery operation management system is realized that reduces the rate of empty vehicle return trips and shortens waiting times for loading and unloading, while also taking into consideration the feelings of users (drivers) and shippers.

[0690] (Example 2)

[0691] Next, we will describe Example 2. 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".

[0692] Traditional delivery systems perform simple route optimization based on the location and order information of delivery vehicles, but they lack the ability to respond to user emotions and unexpected problems in real time. This has resulted in challenges such as insufficient improvement in driver and shipper satisfaction, and inadequate reduction of driver workload. Furthermore, traditional systems have difficulty responding flexibly to traffic congestion and delivery disruptions.

[0693] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0694] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving goods, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and re-optimizing the schedule, and means for collecting user sentiment information, analyzing it using a sentiment engine, and re-optimizing the delivery schedule. This makes it possible to improve the satisfaction of delivery vehicle drivers and shippers, reduce the burden on drivers, and enable flexible responses in real time.

[0695] A "delivery vehicle" is a vehicle used to transport goods or packages from one point to another.

[0696] "Location information" refers to information obtained using location measurement technologies such as GPS, which indicates the current location of a specific object or person.

[0697] "Order information" refers to data that includes detailed information such as the type, quantity, and destination of the goods being shipped by the shipper.

[0698] "Receiving status information" refers to information regarding the readiness of the delivery destination to receive the package and the available time slots for receiving it.

[0699] A "server" is a computer system used to collect, integrate, and analyze data, and to distribute the results.

[0700] "Methods for integrating and pre-processing data" refers to technologies that centrally manage collected location information, order information, and delivery status information, and supplement and correct any deficiencies or anomalies.

[0701] An "AI algorithm" is an algorithm that uses machine learning and artificial intelligence technologies to calculate the optimal delivery route and schedule.

[0702] "Methods for generating optimal delivery routes and schedules" refers to technologies that analyze collected data to create efficient delivery routes and schedules that meet user requirements.

[0703] "Means for distributing schedules to delivery vehicle drivers and shippers" refers to a function that transmits the generated delivery routes and schedules to the drivers' terminals and the shippers' terminals.

[0704] "A means of receiving real-time feedback on delivery status and problems, and re-optimizing the schedule" refers to a technology that receives feedback information from drivers and shippers during operations, and then reapplies an AI algorithm based on this information to update the schedule.

[0705] "Users" refer to people such as drivers and shippers who use the delivery system.

[0706] "Emotional information" refers to data about the user's emotional state, such as stress levels and satisfaction levels.

[0707] An "emotion engine" is a system that collects and analyzes user emotional information to provide appropriate responses and suggestions.

[0708] "Methods for re-optimizing delivery schedules" refer to technologies that generate more efficient delivery schedules based on user sentiment information and real-time feedback.

[0709] This invention combines a system that matches delivery vehicle location information with order information to generate and distribute efficient delivery routes and schedules, with an emotion engine that recognizes user emotions. This enables the re-optimization of schedules that take into account driver stress and fatigue levels, and schedule updates based on real-time feedback.

[0710] This system can be implemented as follows:

[0711] 1. Data collection methods

[0712] The server collects real-time location information for delivery vehicles. To achieve this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal. Users (shippers) use the terminal to enter order information and send it to the server. The server also collects delivery status information from the systems of each delivery destination.

[0713] 2. Data integration and preprocessing means

[0714] The server centrally manages all collected data and compensates for and corrects any omissions or anomalies. A database management system (DBMS) is used for this purpose. For example, historical trends and machine learning models are used to compensate for missing location data.

[0715] 3. Methods for applying AI algorithms

[0716] The server analyzes collected real-time and pre-processed data and applies AI algorithms to generate optimal delivery routes and schedules. For example, it uses machine learning algorithms to calculate the shortest route from delivery destination A to delivery destination B, or a route that efficiently handles specific orders.

[0717] 4. Schedule distribution method

[0718] The server distributes the generated schedule to the delivery vehicle drivers and shippers. Specifically, the driver's terminal displays detailed information about the pickup point and delivery destination. Shippers are notified of the schedule and can understand the overall delivery status.

[0719] 5. Real-time feedback and optimization means

[0720] Users (drivers) report their driving status and problems to the server in real time via their terminals. For example, they send information such as traffic congestion or changes in delivery destinations. Based on this feedback information, the server reapplies an AI algorithm to calculate a new, optimal schedule and route, and delivers it to the driver's terminal.

[0721] 6. Means of applying the emotion engine

[0722] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). This information is used, for example, to evaluate the driver's stress level and fatigue level. If the server detects that the driver is highly stressed, it suggests a break. Users (drivers) report their emotional information through a terminal, and the server uses this information to re-optimize the schedule.

[0723] Specific example

[0724] For example, in the case where truck A is traveling from Tokyo to Yokohama, this system operates as follows:

[0725] 1. Data collection methods

[0726] The server confirms that truck A is currently in Tokyo using its GPS device. The user (shipper) enters orders (orders 1 and 2) for delivery from Tokyo to Yokohama.

[0727] 2. Data integration and preprocessing means

[0728] The server integrates location information, order information, and receiving information, and estimates and supplements any missing data.

[0729] 3. Methods for applying AI algorithms

[0730] The server uses an AI algorithm to calculate the optimal route based on the current location and order information of truck A. For example, it might pick up packages A and B from the Tokyo warehouse and head to the delivery destination in Yokohama.

[0731] 4. Schedule distribution method

[0732] The server delivers this schedule to the driver's smartphone. The device displays, "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama."

[0733] 5. Real-time feedback and optimization means

[0734] When a user (driver) encounters traffic congestion, they report it to the server from their device. The server receives this information, calculates a new route, and redistributes it.

[0735] 6. Means of applying the emotion engine

[0736] If the server detects that the driver is stressed, it will suggest a break. For example, a message might appear on the terminal saying, "Take a 15-minute break at the next service area."

[0737] Examples of prompts to input into a generative AI model

[0738] The following are examples of prompts to input into the generative AI model.

[0739] "Based on the current location information of the delivery vehicles, please generate the optimal delivery route and schedule."

[0740] "Please suggest countermeasures for situations where the driver's stress level is high."

[0741] "Please re-optimize the schedule in real time based on the following data: Track A's current location, load capacity, order information, and sentiment information."

[0742] This enables highly accurate scheduling and service improvements using generative AI models.

[0743] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0744] Step 1: Data Collection

[0745] The server collects real-time location information of delivery vehicles from GPS devices installed in the vehicles. Specifically, it receives signals from the GPS devices to determine the vehicle's current location. Users (shippers) use a terminal to input order information (e.g., delivery destination and package details) and send it to the server. The server collects information on the status of package receipt from the delivery destination, receiving data such as the time when the package can be received and the readiness status from the system. This data is aggregated on the server as GPS location information (input), order information (input), and package receipt information (input).

[0746] Step 2: Data Integration and Preprocessing

[0747] The server integrates and centrally manages all collected data. Specifically, it uses a database management system (DBMS) to organize the information and processes data to supplement and correct missing data and outliers. For example, it uses historical trend data and machine learning models to infer and fill in missing location information. As a result, a consistent dataset (output) is created.

[0748] Step 3: Applying the AI ​​algorithm

[0749] The server uses integrated data to apply AI algorithms to generate optimal delivery routes and schedules. Specifically, it analyzes the truck's current location, load capacity, and order details, and uses machine learning algorithms (e.g., route optimization algorithms) to calculate the shortest route and most efficient delivery sequence. This generates the optimal delivery route and schedule (output).

[0750] Step 4: Scheduled delivery

[0751] The server distributes the generated schedule to each driver's terminal and the shipper's terminal. Specifically, it sends detailed pickup and delivery instructions to the driver's terminal and notifies the shipper of the overall delivery status. On the driver's terminal, instructions such as "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama" will be displayed. As a result, the schedule is distributed (output) to each terminal.

[0752] Step 5: Real-time feedback and optimization

[0753] The user (driver) reports the status and problems during their journey (e.g., traffic congestion or changes in delivery destinations) to the server in real time using their terminal. Specifically, they input feedback information using the status reporting menu. Based on the received feedback information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and schedule, and redistributes it. The optimized schedule (output) is then delivered back to the driver's terminal.

[0754] Step 6: Apply the emotion engine

[0755] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). Specifically, it senses the driver's stress level using facial recognition and voice analysis technology. For example, if a high stress level is detected, it suggests taking a break. Users (drivers) report their emotional information from their terminals, and the server re-optimizes the schedule based on this information. The re-optimized schedule (output) based on the emotional information is delivered to the driver's terminal. The server also suggests service improvement measures to enhance user satisfaction.

[0756] The above describes the specific program processing flow of this system.

[0757] (Application Example 2)

[0758] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0759] Currently, delivery systems exist that generate efficient delivery routes based on the location and order information of delivery vehicles. However, they lack sufficient functionality to optimize schedules while considering driver stress and fatigue. This can lead to accumulated driver fatigue and decreased efficiency. Furthermore, the lack of smooth real-time feedback and schedule re-optimization can result in a decline in service quality.

[0760] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0761] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving goods, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle driver and shipper, means for detecting the driver's emotional state, means for re-optimizing the schedule based on the detected emotional state and fatigue level, and means for receiving real-time feedback on the delivery status and problems and re-optimizing the schedule. This enables efficient schedule generation that takes into account the driver's emotional state and fatigue level, and smooth schedule re-optimization based on real-time feedback.

[0762] A "delivery vehicle" is a vehicle used to transport orders from customers or shippers to their destination.

[0763] "Location information" refers to data that indicates the current geographical coordinates of the delivery vehicle.

[0764] "Order information" refers to information provided by the shipper that includes specific instructions and requirements regarding delivery.

[0765] "Delivery status information" refers to information regarding the location and time of delivery, the progress of preparation for delivery, and so on.

[0766] "Data integration" is the process of centrally combining data collected from different sources.

[0767] "Preprocessing" refers to the preparatory processes performed to ensure data quality and to prepare the data for analysis and application to algorithms.

[0768] An "AI algorithm" is a mathematical model or calculation method that uses artificial intelligence technology to generate the optimal delivery route and schedule.

[0769] A "delivery route" is the path that a delivery vehicle takes to reach its destination.

[0770] A "schedule" is a plan that outlines the specific time allocation and sequence of delivery operations.

[0771] "Emotional state" refers to the psychological and physiological state of the driver, such as their stress level and fatigue level.

[0772] "Real-time feedback" is a function that immediately reports any problems or situations that arise during delivery operations to the system.

[0773] A "break" refers to a short period of rest taken by a driver during work.

[0774] "Service improvement measures" refer to specific suggestions and strategies aimed at improving user satisfaction.

[0775] This invention is a system for efficiently carrying out delivery operations, and in particular, it generates and manages optimal delivery routes and schedules based on the location information and order information of delivery vehicles, as well as the emotional state of the drivers. This system enables the generation of efficient delivery routes and the re-optimization of schedules that take into account the stress and fatigue of drivers.

[0776] The system includes the following key technological elements:

[0777] 1. Data collection methods

[0778] The server has the functionality to collect real-time location information of delivery vehicles. GPS modules are installed in the vehicles, and the data is transmitted to the server. In addition, order information from shippers is collected via terminals and transmitted to the server. Information on the pickup location is also collected simultaneously, and all data is managed centrally.

[0779] 2. Data integration and preprocessing means

[0780] The server has the function of integrating the collected data and supplementing or correcting any deficiencies or anomalies. This allows subsequent processing to be carried out based on high-quality data.

[0781] 3. Optimal route generation method using AI algorithms

[0782] The server uses AI algorithms to generate the optimal delivery route and schedule based on the current location of the delivery vehicle, order information, and planned route. For example, it calculates the optimal route that allows a truck to efficiently handle multiple orders.

[0783] 4. Schedule distribution method

[0784] The server has the function of distributing the generated schedule to delivery vehicle drivers and shippers. The driver's terminal displays the current schedule and route in real time.

[0785] 5. Means for detecting the driver's emotional state

[0786] The server incorporates an emotion engine that collects driver emotional data and evaluates stress and fatigue levels. Based on this emotional data, it generates a schedule that takes the driver's health into consideration.

[0787] 6. Real-time feedback and re-optimization means

[0788] The server receives delivery status and issues collected in real time by drivers and systems, and then reapplies AI algorithms based on this information to update schedules and routes. For example, it instantly reflects traffic congestion and other obstacle information and recalculates the optimal route.

[0789] Explanation of specific examples

[0790] For example, consider a delivery vehicle making a food delivery from Tokyo to Yokohama. Using this system, the server collects the vehicle's GPS data and determines that its current location is Tokyo. Order information from the client is entered, and the order is to deliver sushi and ramen to Yokohama at 2:00 PM. Based on this data, the server applies an AI algorithm to generate a route that allows the truck to complete the order in the shortest possible time.

[0791] If a driver encounters traffic congestion during their journey, they use a terminal to report the information to the server in real time. The server immediately recalculates a new route and notifies the driver. In addition, an emotion engine built into the system senses the driver's stress level and fatigue level and suggests a break if necessary.

[0792] Example of a prompt

[0793] "For a food delivery from Tokyo to Yokohama, please collect GPS location data and emotional state to generate an efficient schedule and route. The current order is to deliver sushi and ramen to Yokohama at 2:00 PM. The driver's stress level is high, so please also suggest optimal rest times."

[0794] As described above, the present invention can simultaneously improve the efficiency of delivery operations and manage the health of drivers.

[0795] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0796] Step 1:

[0797] Data collection

[0798] Input: GPS information of delivery vehicles, order information from the consignor, and delivery status information.

[0799] Processing: The server collects GPS data from delivery vehicles in real time to obtain location information. It also sends order information entered by the shipper via a terminal to the server and simultaneously collects information on the status of receiving the goods.

[0800] Output: Integrated location information, order information, and delivery status information.

[0801] Step 2:

[0802] Data preprocessing

[0803] Input: All collected data (location information, order information, delivery status information)

[0804] Processing: The server centrally manages the collected data and imputes and corrects missing or outlier values. For example, if location information is missing, it is interpolated based on the previous data and the imputed information.

[0805] Output: Replicated and preprocessed dataset

[0806] Step 3:

[0807] Optimal route generation using AI algorithms

[0808] Input: Preprocessed dataset (location information, order information, delivery status information)

[0809] Processing: The server uses this data to apply AI algorithms to generate the optimal delivery route and schedule. For example, it considers the vehicle's current location, the order pickup location, and the delivery destination to calculate the shortest and most efficient route.

[0810] Output: Optimal route and schedule information

[0811] Step 4:

[0812] Scheduled distribution

[0813] Input: Optimal route and schedule information

[0814] Processing: The server distributes the generated schedule to the driver's terminal and the shipper's system. Detailed route information is displayed on the terminal.

[0815] Output: Schedule information distributed to the driver's terminal and the shipper's system.

[0816] Step 5:

[0817] Driver emotional state detection

[0818] Input: Prompt messages sent by the server and feedback data from the driver.

[0819] Processing: The terminal uses an emotion engine to detect the driver's emotional state and sends that data to the server. For example, it evaluates the stress level from the driver's facial expressions and voice.

[0820] Output: Driver's emotional state data

[0821] Step 6:

[0822] Schedule reoptimization based on the driver's emotional state

[0823] Input: Emotional state data (stress level, fatigue level)

[0824] Processing: The server adjusts the schedule as needed based on the driver's emotional state data. For example, if stress levels are high, it suggests a break and recalculates the schedule.

[0825] Output: Adjusted schedule information

[0826] Step 7:

[0827] Real-time feedback and optimization

[0828] Input: Delivery problem reports (traffic information, other disruption information), new order information

[0829] Processing: The driver reports the problem in real time via a terminal. The server receives this information, reapplies the AI ​​algorithm based on the new data, and recalculates the optimal route and schedule.

[0830] Output: Updated optimal route and schedule information

[0831] Each processing step works in conjunction with the entire system to improve the efficiency of delivery operations and ensure the health of drivers.

[0832] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0833] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0834] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0835] [Third Embodiment]

[0836] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0837] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0838] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0839] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0840] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0841] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0842] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0843] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0844] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0845] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0846] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0847] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0848] This invention is a system aimed at reducing the rate of empty return trips and shortening loading / unloading waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and loading / unloading status information, and generating and distributing the optimal route and schedule based on this information. The following describes in detail embodiments for specifically implementing this invention.

[0849] System Configuration

[0850] 1. Data collection methods

[0851] The server collects real-time location information for delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[0852] The server collects order information from shippers. To do this, shippers input order information (origin, destination, type of package, weight, desired delivery time, etc.) through an interface.

[0853] The server collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[0854] 2. Data integration and preprocessing means

[0855] The server integrates and preprocesses the collected location, order, and delivery information. By performing data interpolation and removing outliers, it generates a highly reliable dataset.

[0856] 3. Means for applying the matching algorithm

[0857] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[0858] Specifically, the system calculates the optimal combination based on data such as the truck's current location, load capacity, and the order's origin, destination, weight, and desired delivery time.

[0859] 4. Schedule distribution method

[0860] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The schedule is notified to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[0861] 5. Real-time feedback and optimization means

[0862] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0863] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0864] Explanation of the program's processing

[0865] The program for this system implements the above-mentioned methods to achieve efficient truck transportation. The following describes the processing details of the program.

[0866] 1. Data Collection

[0867] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[0868] The user (shipper) enters order information using a terminal and sends it to the server.

[0869] The server sets up a means to collect information on the status of receiving shipments and understands the acceptance time and preparation status.

[0870] 2. Data Integration and Preprocessing

[0871] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[0872] 3. Application of the matching algorithm

[0873] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it calculates that truck A can pick up two orders on its way from Tokyo to Yokohama.

[0874] 4. Scheduled distribution

[0875] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The driver's smartphone displays the specific route and loading / unloading instructions.

[0876] 5. Real-time feedback

[0877] Users (drivers) report real-time information such as traffic congestion and changes in delivery destinations from their terminals.

[0878] Based on this information, the server reapplies the AI ​​algorithm to recalculate the optimal route and schedule for delivery.

[0879] Specific example

[0880] As an example, consider the case where truck A travels from Tokyo to Yokohama. GPS data from the delivery vehicle is collected to determine that its current location is Tokyo. Two delivery requests (orders 1 and 2) from Tokyo to Yokohama are entered as order information from the shipper. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A accepts orders 1 and 2 via the optimal route. The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up the two packages at the Tokyo warehouse and deliver them to Yokohama. If traffic congestion occurs along the way, the driver reports it to the server in real time, and the server calculates a new route and delivers it again.

[0881] In this way, this system reduces the rate at which trucks are empty and shortens waiting times for loading and unloading, thereby achieving efficient delivery operation management.

[0882] The following describes the processing flow.

[0883] Step 1: Data Collection

[0884] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[0885] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[0886] The device sends the above data to the server.

[0887] Step 2: Data Integration and Preprocessing

[0888] The server stores the received data in a centrally managed database.

[0889] The server checks data integrity and fills in any missing data. For example, if there is a missing input, it will fill in the estimated value based on the previous data.

[0890] The server filters out abnormal values ​​(for example, delivery times exceeding the possible range) and sends a correction request to the user if an abnormality is found.

[0891] Step 3: Matching using AI algorithms

[0892] The server runs an AI algorithm based on the current location, order information, and planned route of all trucks.

[0893] The server performs optimal matching of each truck with an order. Specifically, it determines the best combination based on factors such as the distance and time from the dispatched vehicle's current location to the order's departure point, load capacity, and environmental impact.

[0894] Step 4: Generate Optimal Route and Schedule

[0895] The server generates the optimal route and schedule calculated by an AI algorithm. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[0896] Step 5: Scheduled distribution

[0897] The server sends the generated schedule to each truck driver's terminal. Specifically, it provides detailed instructions to the driver's terminal on where to pick up the cargo and where to deliver it.

[0898] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[0899] Step 6: Real-time feedback and reoptimization

[0900] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[0901] The server reapplies the AI ​​algorithm based on the received feedback (e.g., traffic information) to calculate a new, optimal route.

[0902] The server resends the updated schedule and route to the driver's terminal.

[0903] (Example 1)

[0904] Next, we will describe Example 1. 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."

[0905] There is a need to solve the problems of empty vehicle return rates and waiting times in truck transportation. Conventional systems have insufficient management of delivery vehicle location information and order information, making it difficult to optimize delivery routes efficiently. In addition, the inability to flexibly change schedules in response to real-time changes in circumstances led to problems with reduced operational efficiency.

[0906] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0907] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and re-optimizing the schedule, means for determining location information using a GPS device, means for inputting order information via a terminal, pre-processing means for data completion and removal of anomalies, and means for distributing schedule information using a notification system. This makes it possible to reduce the rate of empty return trips of trucks and shorten waiting times for loading and unloading.

[0908] "Delivery vehicles" refer to means of transport such as automobiles, trucks, and vans used to transport goods and products.

[0909] "Location information" refers to data that indicates the geographical location of a specific object or person, obtained by location measurement devices such as GPS devices.

[0910] "Order information" refers to data provided by shippers when requesting delivery services, including details such as the origin, destination, type of package, weight, and desired delivery time.

[0911] "Receiving information" refers to information such as the readiness status of the receiving location and the available receiving times for packages.

[0912] "Integration" is the process of bringing together different types of data and managing them comprehensively.

[0913] "Preprocessing" refers to the process of transforming collected raw data into a format that is easy to analyze, and includes data interpolation and removal of outliers.

[0914] An "AI algorithm" is a set of computational procedures that use artificial intelligence technology to analyze data and perform optimization and predictions.

[0915] A "schedule" is a plan of time and location, outlining when and where a delivery vehicle will pick up a package and where it will deliver it.

[0916] "Feedback" is the process of receiving information about the system's operation status and problems from the system and its users, and using that information to improve and adjust the system.

[0917] "Optimization" is the process of adjusting calculations and procedures to obtain the best possible result under given conditions and constraints.

[0918] A "GPS device" is a device that measures and reports a specific location on Earth, and it obtains location information using satellite signals.

[0919] A "terminal" is a device, such as a computer or smartphone, that a user uses to input information or receive information from a system.

[0920] A "notification system" is a communication method used to instantly deliver important information and updates to users and systems, and includes SMS and push notifications.

[0921] This invention is a system aimed at reducing the rate of empty return trips and shortening waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and cargo receiving status information, and generating and distributing the optimal route and schedule based on this information.

[0922] Hardware and software to be used

[0923] The hardware used includes GPS devices, user terminals (smartphones and PCs), and servers. The software includes data collection software, AI algorithms, data integration and preprocessing software, and notification systems.

[0924] Overall flow

[0925] 1. Data Collection

[0926] The server collects location information in real time from GPS devices attached to delivery vehicles. This information includes the vehicle's current location, speed, and direction of travel.

[0927] The user (shipper) enters order information (origin, destination, type of package, weight, desired delivery time, etc.) via a terminal and sends it to the server.

[0928] The server collects information on the status of receiving shipments (such as readiness for acceptance and available acceptance times). This information is either entered by the person in charge at the receiving location or automatically retrieved by the system.

[0929] 2. Data Integration and Preprocessing

[0930] The server integrates collected location information, order information, and delivery information, and manages them centrally in real time.

[0931] The server performs preprocessing to complete the data and remove outliers. This process fills in missing data and corrects outliers, resulting in a reliable dataset.

[0932] 3. Application of the matching algorithm

[0933] The server uses an AI algorithm to generate the optimal delivery route and schedule. This algorithm considers the current location, load capacity, origin, destination, weight, and desired delivery time of each delivery vehicle to calculate the most efficient route and schedule.

[0934] 4. Scheduled distribution

[0935] The server distributes the generated schedule to the delivery vehicle drivers and shippers. This distribution is done through a notification system, and the specific route and loading / unloading instructions are displayed on the drivers' smartphones or tablets.

[0936] 5. Real-time feedback and optimization

[0937] Users (drivers) report operational status and problems (such as traffic congestion or changes in delivery destinations) to the server in real time from their terminals.

[0938] The server reapplies the AI ​​algorithm based on this status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0939] Specific example

[0940] As an example, let's consider the case where truck A is traveling from Tokyo to Yokohama.

[0941] 1. Data Collection: The server obtains the current location of truck A (Tokyo) from a GPS device. The shipper also inputs order information, such as "I would like a 500kg package delivered from a warehouse in Tokyo to a warehouse in Yokohama," and sends it to the server.

[0942] 2. Data Integration and Preprocessing: The server integrates the collected data (location information of truck A, order information, and acceptance time information for the Yokohama warehouse) and supplements any missing data or outliers.

[0943] 3. Application of Matching Algorithm: The server uses an AI algorithm to generate the optimal schedule for truck A to pick up goods from a warehouse in Tokyo via the shortest route and deliver them to a warehouse in Yokohama.

[0944] 4. Schedule Distribution: The server distributes the generated schedule to the driver of truck A's smartphone. The smartphone displays instructions such as, "Pick up the cargo at the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[0945] 5. Real-time feedback and optimization: If traffic congestion occurs along the way, the user (driver) reports "traffic congestion" information from their device. The server then reapplies the AI ​​algorithm based on this information, calculates an alternative route, and redistributes it to the driver.

[0946] Example of a prompt:

[0947] "The system uses the current location data of trucks collected from GPS devices as input to calculate the optimal delivery route."

[0948] "Using multiple order details from shippers as input, an AI algorithm is applied to generate the optimal schedule."

[0949] "We will re-optimize the route and schedule based on real-time feedback from drivers."

[0950] This system will reduce the rate of empty truck return trips and waiting times for loading and unloading, enabling more efficient delivery operation management.

[0951] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0952] Step 1: Data Collection

[0953] The server collects location information in real time from GPS devices installed in delivery vehicles. The input data includes the current location, speed, and direction of movement of each vehicle, and this data is analyzed to output accurate location information.

[0954] The user (shipper) enters order information using a terminal. This information includes the origin, destination, type of package, weight, and desired delivery time. This information is then sent to the server via the terminal.

[0955] The server collects information on the status of receiving shipments (readiness for receiving, available time for receiving). This includes means of obtaining data entered by the person in charge at the receiving location. The server analyzes the input data and outputs the available time slots for receiving shipments.

[0956] Step 2: Data Integration and Preprocessing

[0957] The server centrally integrates the collected location information, order information, and delivery information. The input data consists of the above-mentioned collected items, and it outputs a manageable dataset by integrating these items.

[0958] The server performs preprocessing on the integrated data, including data imputation and outlier removal. The input data includes integrated raw data, and the server outputs a reliable dataset after imputing missing data and detecting and correcting outliers.

[0959] Step 3: Applying the Matching Algorithm

[0960] The server uses AI algorithms to generate the optimal delivery route and schedule. Input data includes the current location of the delivery vehicle, its load capacity, and order information (origin, destination, weight, desired delivery time). This data is analyzed to output an efficient route and schedule.

[0961] Specifically, the server calculates the optimal location and time for truck A to pick up two orders within Tokyo, and generates its route and schedule.

[0962] Step 4: Scheduled delivery

[0963] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The input data is the generated schedule information, which is distributed via the notification system. As a result of the distribution, the specific route and loading instructions are output to the driver's smartphone.

[0964] In terms of specific actions, the server distributes schedules such as "Pick up the package from the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[0965] Step 5: Real-time feedback and optimization

[0966] Users (drivers) report problems and situations during their journey (such as traffic congestion or changes in delivery destinations) in real time from their terminals. The input data includes the driver's reported information.

[0967] The server re-optimizes the schedule and route by applying the AI ​​algorithm again based on real-time feedback. The input data is feedback information from the driver, which is analyzed to output a new route and schedule.

[0968] Specifically, the server generates a new instruction stating, "There is currently traffic congestion, so take an alternative route," and redistributes it to the driver.

[0969] (Application Example 1)

[0970] Next, we will explain Application Example 1. In the following explanation, 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."

[0971] This invention aims to reduce the rate of empty truck return trips and shorten loading / unloading waiting times in truck transportation, but existing systems have not been able to completely solve this problem. Specifically, real-time location information collection, optimal route generation, and rapid response to problems are not adequately performed, and efficient delivery operation management has not been achieved. Furthermore, even when using autonomous vehicles, there are still aspects that are difficult to address.

[0972] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0973] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and optimizing the schedule again, and an autonomous vehicle control system for comfortable delivery operation management. This makes it possible to reduce the rate of empty return trips, shorten waiting times for cargo, and improve the efficiency of autonomous vehicle operation management.

[0974] "Means for collecting location information of delivery vehicles" refers to a device that uses a GPS device to obtain the current location of delivery vehicles in real time.

[0975] "Means for collecting order information from shippers" refers to an interface and system on which shippers input order information such as origin, destination, type of goods, weight, and desired delivery time, and transmit it to a server.

[0976] "Means for collecting information on the status of receiving goods" refers to devices and systems that collect information from the receiving party regarding the status of preparation for receiving goods, the time when they can be received, etc.

[0977] "Means for integrating and preprocessing data" refers to devices and systems that centrally manage multiple collected data sets and perform processes to supplement and correct deficiencies and abnormal values.

[0978] "A method for generating optimal delivery routes and schedules using AI algorithms" refers to a software algorithm that uses artificial intelligence technology to calculate and generate optimal delivery routes and schedules based on collected data.

[0979] "Means for distributing the generated schedule to delivery vehicle drivers and shippers" refers to a system that notifies drivers' terminals and shippers' management systems of the calculated and generated schedule.

[0980] "A means of receiving real-time feedback on delivery status and problems and re-optimizing the schedule" refers to a system that receives real-time information on problems and delays from vehicles in operation, and then applies AI algorithms to calculate and distribute new routes and schedules.

[0981] The "Autonomous Vehicle Control System for Comfortable Delivery Operation Management" is a system that efficiently manages the operation of autonomous vehicles and distributes optimal routes and schedules to enable quick responses in the event of problems.

[0982] A "generative AI model" is an artificial intelligence model that has been trained to efficiently perform a specific task based on training data.

[0983] A "prompt statement" is an instruction given to a generative AI model to obtain a specific output.

[0984] This invention relates to a truck transportation management system that utilizes autonomous vehicles to maximize transportation efficiency. The configuration and operation of the system for specifically implementing this invention, including the hardware and software used, are described below.

[0985] System Configuration

[0986] 1. Data collection methods

[0987] The server collects real-time location information for delivery vehicles. For this purpose, each vehicle is equipped with a GPS device to collect location data.

[0988] The system also collects order information from shippers. This involves providing an interface for inputting data such as origin, destination, type of package, weight, and desired delivery time.

[0989] The server also collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[0990] 2. Data integration and preprocessing means

[0991] The server centrally manages the collected data. This includes a data cleansing process to supplement and correct any missing or outlier values.

[0992] 3. Means for applying the matching algorithm

[0993] The server uses AI algorithms to generate the optimal delivery route and schedule. It utilizes technologies such as TensorFlow and PyTorch to calculate and generate the optimal route and schedule based on all the collected data.

[0994] 4. Schedule distribution method

[0995] The generated schedule is distributed to the delivery vehicle drivers and the shippers. Notifications are sent to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[0996] 5. Real-time feedback and optimization means

[0997] The user (driver) reports the situation and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[0998] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[0999] Specific example

[1000] As an example, consider the case of truck B traveling from Osaka to Nagoya. Real-time location information collected from the delivery vehicle's GPS device determines that its current location is Osaka. The shipper inputs order information: departure point is Osaka, destination is Nagoya, large cargo, weight 500kg, desired delivery time 10:00-12:00. The server integrates and preprocesses this data and generates the optimal route and schedule for truck B using an AI algorithm (e.g., using TensorFlow or PyTorch). The generated schedule is delivered to the driver's smartphone, displaying instructions for departure time 08:00 and arrival time 11:30. If traffic congestion occurs near Kyoto along the way, the driver's terminal automatically detects this and provides feedback to the cloud server. The server recalculates and generates a new route (e.g., Kyoto – Shiga – Nagoya) and delivers that information again. In this way, a reduction in empty return trips and a reduction in waiting time for loading and unloading are achieved.

[1001] Example of a prompt:

[1002] "Departure point: Osaka, Arrival point: Nagoya, Departure time: 08:00, Desired arrival time: 10:00-12:00, Package type: Large, Weight: 500kg. Based on these conditions, please generate the optimal delivery route and schedule."

[1003] This will enable efficient truck transportation using autonomous vehicles.

[1004] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1005] Step 1:

[1006] The server collects location information in real time from the GPS devices of delivery vehicles. The input data is the current location of the delivery vehicle, and the output is the collected location data. This data is formatted into a predetermined format and saved.

[1007] Step 2:

[1008] The user (shipper) enters order information using the interface. The input data includes origin, destination, package type, weight, and desired delivery time. The output is a dataset that centrally manages this order information. This data is sent to and stored on the server.

[1009] Step 3:

[1010] The server collects information on the status of receiving shipments. The input data includes the preparation status and acceptance time for receiving shipments, and the output is integrated receiving information data. This data is also formatted and saved in a predetermined format.

[1011] Step 4:

[1012] The server integrates the collected location information, order information, and receiving information, and performs data preprocessing. The input data consists of location information, order information, and receiving information, and the output is integrated data with outliers removed and imputed. Specifically, it imputes missing data and removes outliers.

[1013] Step 5:

[1014] The server uses AI algorithms to generate optimal delivery routes and schedules. The input data is pre-processed, integrated data, and the output is optimal route and schedule information. Specifically, it applies AI algorithms using TensorFlow or PyTorch to calculate delivery routes and schedules.

[1015] Step 6:

[1016] The server distributes the generated schedule to the delivery vehicle drivers and the shippers. The input data consists of the generated route and schedule information, and the output is a notification to the driver's terminal and the shipper's management system. Specifically, it displays the detailed route and schedule on the driver's smartphone.

[1017] Step 7:

[1018] The user (driver) reports the status and problems encountered during operation to the server in real time from their terminal. The input data is information about problems that occurred during operation, such as traffic congestion or changes in delivery destinations, and the output is feedback data to the server.

[1019] Step 8:

[1020] The server reapplies the AI ​​algorithm based on the received situation data to re-optimize the schedule and route. The input data is real-time feedback of situation data, and the output is the re-optimized route and schedule. Specifically, it calculates the new route and schedule and redistributes them to the driver's terminal.

[1021] In this way, efficient truck transportation management using autonomous vehicles is realized by utilizing the generated AI model and prompt messages.

[1022] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1023] This invention combines a system that matches delivery vehicle location information with order information to generate and distribute efficient delivery routes and schedules, with an emotion engine that recognizes user emotions. This system enables the re-optimization of schedules that take into account the driver's stress and fatigue levels, and schedule updates based on real-time feedback.

[1024] System Configuration

[1025] 1. Data collection methods

[1026] The server collects real-time location information of delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[1027] The server collects order information from shippers, who input the order information through an interface.

[1028] The server provides a means to collect information on the status of receiving shipments, and to understand the readiness for receiving shipments and the available time for receiving them.

[1029] 2. Data integration and preprocessing means

[1030] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[1031] 3. Matching methods using AI algorithms

[1032] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[1033] Specifically, the system calculates the optimal combination based on the truck's current location, load capacity, and detailed order information.

[1034] 4. Schedule distribution method

[1035] The server sends the generated schedule to each truck driver's terminal and also distributes the schedule to the shipper.

[1036] 5. Real-time feedback and optimization means

[1037] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[1038] The server reapplies the AI ​​algorithm based on the received status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[1039] 6. Emotional Engine

[1040] The server uses an emotion engine to collect emotional information from users (drivers and shippers). This information is used to evaluate stress levels and satisfaction levels.

[1041] The emotional engine senses the driver's stress and fatigue levels and re-optimizes the schedule accordingly. For example, if the driver is highly fatigued while driving, it can incorporate break time into the schedule.

[1042] The server reapplies AI algorithms and updates schedules based on sentiment information collected in real time. It also evaluates user satisfaction and suggests ways to improve the service.

[1043] Explanation of the program's processing

[1044] The program for this system implements the above-mentioned methods to achieve efficient truck transportation while also taking user emotions into consideration. The following describes the program's processing details.

[1045] 1. Data Collection

[1046] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[1047] The user (shipper) enters order information using a terminal and sends it to the server.

[1048] The server uses means to collect information on the status of receiving shipments and to understand the readiness for acceptance.

[1049] 2. Data Integration and Preprocessing

[1050] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[1051] 3. Application of AI algorithms

[1052] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[1053] 4. Scheduled distribution

[1054] The server distributes the generated schedule to each truck driver's terminal. The driver's terminal provides detailed instructions on where to pick up the cargo and where to deliver it.

[1055] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[1056] 5. Real-time feedback

[1057] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[1058] Based on this information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and delivers it again.

[1059] 6. Application of the emotion engine

[1060] The server uses an emotion engine to collect emotional information from users (drivers and shippers). For example, it can sense a driver's stress level and suggest a break if stress levels are high.

[1061] The user (driver) reports emotional information through their device, and the server uses this information to re-optimize the schedule.

[1062] The server proposes service improvements based on emotional information, thereby improving overall delivery efficiency.

[1063] Specific example

[1064] For example, consider the case where truck A is traveling from Tokyo to Yokohama. This system collects GPS data from the delivery vehicle to determine its current location is Tokyo. Two delivery requests from the shipper (orders 1 and 2) from Tokyo to Yokohama are entered as order information. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A takes the optimal route to accept orders 1 and 2.

[1065] The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up two packages at the Tokyo warehouse and deliver them to Yokohama. If the driver encounters traffic congestion during the trip, they can report it to the server in real time using their device, and the server will calculate and redistribute a new route.

[1066] Furthermore, the emotion engine integrated into this system senses the driver's stress level and fatigue, and suggests breaks as needed. It also collects feedback from shippers and drivers in real time, and reapplies the AI ​​algorithm to update the schedule. In this way, it is possible to reduce the rate of empty trucks returning to port, shorten waiting times for loading and unloading, and improve user satisfaction.

[1067] The following describes the processing flow.

[1068] Step 1: Data Collection

[1069] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[1070] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[1071] The device sends the above data to the server.

[1072] The server integrates the collected location information, order information, and delivery status information.

[1073] Step 2: Data Integration and Preprocessing

[1074] The server stores the received data in the database.

[1075] The server checks data integrity, completes missing data, and removes outliers. If data is missing, it is completed using estimates or previous data.

[1076] The server filters out abnormal values ​​(for example, extremely long delivery times) and sends correction requests to users for data where abnormalities are detected.

[1077] Step 3: Matching using AI algorithms

[1078] The server runs an AI algorithm based on the current location of all delivery vehicles, order information, and planned routes.

[1079] The server performs optimal matching of each delivery vehicle with each order. Specifically, it calculates the best combination by considering factors such as the distance and time from each truck's current location to the order's departure point, load capacity, and environmental impact.

[1080] Step 4: Gathering emotional information

[1081] The user's (driver's) emotional state (stress level, fatigue level, etc.) is collected through an emotion engine.

[1082] The server integrates the collected sentiment information and performs data preprocessing based on it.

[1083] Step 5: Generate Optimal Route and Schedule

[1084] The server uses AI algorithms and collected data to generate the optimal delivery route and schedule. For example, it calculates a route where truck A can pick up two orders on its way from Tokyo to Yokohama.

[1085] Furthermore, the server generates a schedule that includes breaks and adjustments to the route based on the driver's emotional state (stress and fatigue levels).

[1086] Step 6: Scheduled delivery

[1087] The server sends the generated schedule to each driver's terminal. Specifically, it provides information such as where to pick up packages, where to deliver them, and even rest instructions based on the driver's emotional state.

[1088] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[1089] Step 7: Real-time feedback and re-optimization

[1090] Users (drivers) use a terminal to report traffic conditions and the status of their trucks in real time while they are driving. For example, they might report traffic jams or accidents.

[1091] The server reapplies the AI ​​algorithm based on the received feedback data and recalculates the optimal route and schedule.

[1092] The server redistributes the recalculated schedule and route to the driver's terminal.

[1093] Step 8: Evaluation and improvement using the emotional engine

[1094] The server evaluates emotional information collected in real time to check the driver's stress level and satisfaction level.

[1095] The server uses emotional information to suggest service improvements and incorporates them into the operational plan. For example, if stress levels are high, it may schedule more breaks or change the route to reduce the burden.

[1096] In this way, an efficient delivery operation management system is realized that reduces the rate of empty vehicle return trips and shortens waiting times for loading and unloading, while also taking into consideration the feelings of users (drivers) and shippers.

[1097] (Example 2)

[1098] Next, we will describe Example 2. 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."

[1099] Traditional delivery systems perform simple route optimization based on the location and order information of delivery vehicles, but they lack the ability to respond to user emotions and unexpected problems in real time. This has resulted in challenges such as insufficient improvement in driver and shipper satisfaction, and inadequate reduction of driver workload. Furthermore, traditional systems have difficulty responding flexibly to traffic congestion and delivery disruptions.

[1100] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1101] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving goods, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and re-optimizing the schedule, and means for collecting user sentiment information, analyzing it using a sentiment engine, and re-optimizing the delivery schedule. This makes it possible to improve the satisfaction of delivery vehicle drivers and shippers, reduce the burden on drivers, and enable flexible responses in real time.

[1102] A "delivery vehicle" is a vehicle used to transport goods or packages from one point to another.

[1103] "Location information" refers to information obtained using location measurement technologies such as GPS, which indicates the current location of a specific object or person.

[1104] "Order information" refers to data that includes detailed information such as the type, quantity, and destination of the goods being shipped by the shipper.

[1105] "Receiving status information" refers to information regarding the readiness of the delivery destination to receive the package and the available time slots for receiving it.

[1106] A "server" is a computer system used to collect, integrate, and analyze data, and to distribute the results.

[1107] "Methods for integrating and pre-processing data" refers to technologies that centrally manage collected location information, order information, and delivery status information, and supplement and correct any deficiencies or anomalies.

[1108] An "AI algorithm" is an algorithm that uses machine learning and artificial intelligence technologies to calculate the optimal delivery route and schedule.

[1109] "Methods for generating optimal delivery routes and schedules" refers to technologies that analyze collected data to create efficient delivery routes and schedules that meet user requirements.

[1110] "Means for distributing schedules to delivery vehicle drivers and shippers" refers to a function that transmits the generated delivery routes and schedules to the drivers' terminals and the shippers' terminals.

[1111] "A means of receiving real-time feedback on delivery status and problems, and re-optimizing the schedule" refers to a technology that receives feedback information from drivers and shippers during operations, and then reapplies an AI algorithm based on this information to update the schedule.

[1112] "Users" refer to people such as drivers and shippers who use the delivery system.

[1113] "Emotional information" refers to data about the user's emotional state, such as stress levels and satisfaction levels.

[1114] An "emotion engine" is a system that collects and analyzes user emotional information to provide appropriate responses and suggestions.

[1115] "Methods for re-optimizing delivery schedules" refer to technologies that generate more efficient delivery schedules based on user sentiment information and real-time feedback.

[1116] This invention combines a system that matches delivery vehicle location information with order information to generate and distribute efficient delivery routes and schedules, with an emotion engine that recognizes user emotions. This enables the re-optimization of schedules that take into account driver stress and fatigue levels, and schedule updates based on real-time feedback.

[1117] This system can be implemented as follows:

[1118] 1. Data collection methods

[1119] The server collects real-time location information for delivery vehicles. To achieve this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal. Users (shippers) use the terminal to enter order information and send it to the server. The server also collects delivery status information from the systems of each delivery destination.

[1120] 2. Data integration and preprocessing means

[1121] The server centrally manages all collected data and compensates for and corrects any omissions or anomalies. A database management system (DBMS) is used for this purpose. For example, historical trends and machine learning models are used to compensate for missing location data.

[1122] 3. Methods for applying AI algorithms

[1123] The server analyzes collected real-time and pre-processed data and applies AI algorithms to generate optimal delivery routes and schedules. For example, it uses machine learning algorithms to calculate the shortest route from delivery destination A to delivery destination B, or a route that efficiently handles specific orders.

[1124] 4. Schedule distribution method

[1125] The server distributes the generated schedule to the delivery vehicle drivers and shippers. Specifically, the driver's terminal displays detailed information about the pickup point and delivery destination. Shippers are notified of the schedule and can understand the overall delivery status.

[1126] 5. Real-time feedback and optimization means

[1127] Users (drivers) report their driving status and problems to the server in real time via their terminals. For example, they send information such as traffic congestion or changes in delivery destinations. Based on this feedback information, the server reapplies an AI algorithm to calculate a new, optimal schedule and route, and delivers it to the driver's terminal.

[1128] 6. Means of applying the emotion engine

[1129] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). This information is used, for example, to evaluate the driver's stress level and fatigue level. If the server detects that the driver is highly stressed, it suggests a break. Users (drivers) report their emotional information through a terminal, and the server uses this information to re-optimize the schedule.

[1130] Specific example

[1131] For example, in the case where truck A is traveling from Tokyo to Yokohama, this system operates as follows:

[1132] 1. Data collection methods

[1133] The server confirms that truck A is currently in Tokyo using its GPS device. The user (shipper) enters orders (orders 1 and 2) for delivery from Tokyo to Yokohama.

[1134] 2. Data integration and preprocessing means

[1135] The server integrates location information, order information, and receiving information, and estimates and supplements any missing data.

[1136] 3. Methods for applying AI algorithms

[1137] The server uses an AI algorithm to calculate the optimal route based on the current location and order information of truck A. For example, it might pick up packages A and B from the Tokyo warehouse and head to the delivery destination in Yokohama.

[1138] 4. Schedule distribution method

[1139] The server delivers this schedule to the driver's smartphone. The device displays, "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama."

[1140] 5. Real-time feedback and optimization means

[1141] When a user (driver) encounters traffic congestion, they report it to the server from their device. The server receives this information, calculates a new route, and redistributes it.

[1142] 6. Means of applying the emotion engine

[1143] If the server detects that the driver is stressed, it will suggest a break. For example, a message might appear on the terminal saying, "Take a 15-minute break at the next service area."

[1144] Examples of prompts to input into a generative AI model

[1145] The following are examples of prompts to input into the generative AI model.

[1146] "Based on the current location information of the delivery vehicles, please generate the optimal delivery route and schedule."

[1147] "Please suggest countermeasures for situations where the driver's stress level is high."

[1148] "Please re-optimize the schedule in real time based on the following data: Track A's current location, load capacity, order information, and sentiment information."

[1149] This enables highly accurate scheduling and service improvements using generative AI models.

[1150] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1151] Step 1: Data Collection

[1152] The server collects real-time location information of delivery vehicles from GPS devices installed in the vehicles. Specifically, it receives signals from the GPS devices to determine the vehicle's current location. Users (shippers) use a terminal to input order information (e.g., delivery destination and package details) and send it to the server. The server collects information on the status of package receipt from the delivery destination, receiving data such as the time when the package can be received and the readiness status from the system. This data is aggregated on the server as GPS location information (input), order information (input), and package receipt information (input).

[1153] Step 2: Data Integration and Preprocessing

[1154] The server integrates and centrally manages all collected data. Specifically, it uses a database management system (DBMS) to organize the information and processes data to supplement and correct missing data and outliers. For example, it uses historical trend data and machine learning models to infer and fill in missing location information. As a result, a consistent dataset (output) is created.

[1155] Step 3: Applying the AI ​​algorithm

[1156] The server uses integrated data to apply AI algorithms to generate optimal delivery routes and schedules. Specifically, it analyzes the truck's current location, load capacity, and order details, and uses machine learning algorithms (e.g., route optimization algorithms) to calculate the shortest route and most efficient delivery sequence. This generates the optimal delivery route and schedule (output).

[1157] Step 4: Scheduled delivery

[1158] The server distributes the generated schedule to each driver's terminal and the shipper's terminal. Specifically, it sends detailed pickup and delivery instructions to the driver's terminal and notifies the shipper of the overall delivery status. On the driver's terminal, instructions such as "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama" will be displayed. As a result, the schedule is distributed (output) to each terminal.

[1159] Step 5: Real-time feedback and optimization

[1160] The user (driver) reports the status and problems during their journey (e.g., traffic congestion or changes in delivery destinations) to the server in real time using their terminal. Specifically, they input feedback information using the status reporting menu. Based on the received feedback information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and schedule, and redistributes it. The optimized schedule (output) is then delivered back to the driver's terminal.

[1161] Step 6: Apply the emotion engine

[1162] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). Specifically, it senses the driver's stress level using facial recognition and voice analysis technology. For example, if a high stress level is detected, it suggests taking a break. Users (drivers) report their emotional information from their terminals, and the server re-optimizes the schedule based on this information. The re-optimized schedule (output) based on the emotional information is delivered to the driver's terminal. The server also suggests service improvement measures to enhance user satisfaction.

[1163] The above describes the specific program processing flow of this system.

[1164] (Application Example 2)

[1165] Next, we will explain application example 2. In the following explanation, 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."

[1166] Currently, delivery systems exist that generate efficient delivery routes based on the location and order information of delivery vehicles. However, they lack sufficient functionality to optimize schedules while considering driver stress and fatigue. This can lead to accumulated driver fatigue and decreased efficiency. Furthermore, the lack of smooth real-time feedback and schedule re-optimization can result in a decline in service quality.

[1167] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1168] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving goods, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle driver and shipper, means for detecting the driver's emotional state, means for re-optimizing the schedule based on the detected emotional state and fatigue level, and means for receiving real-time feedback on the delivery status and problems and re-optimizing the schedule. This enables efficient schedule generation that takes into account the driver's emotional state and fatigue level, and smooth schedule re-optimization based on real-time feedback.

[1169] A "delivery vehicle" is a vehicle used to transport orders from customers or shippers to their destination.

[1170] "Location information" refers to data that indicates the current geographical coordinates of the delivery vehicle.

[1171] "Order information" refers to information provided by the shipper that includes specific instructions and requirements regarding delivery.

[1172] "Delivery status information" refers to information regarding the location and time of delivery, the progress of preparation for delivery, and so on.

[1173] "Data integration" is the process of centrally combining data collected from different sources.

[1174] "Preprocessing" refers to the preparatory processes performed to ensure data quality and to prepare the data for analysis and application to algorithms.

[1175] An "AI algorithm" is a mathematical model or calculation method that uses artificial intelligence technology to generate the optimal delivery route and schedule.

[1176] A "delivery route" is the path that a delivery vehicle takes to reach its destination.

[1177] A "schedule" is a plan that outlines the specific time allocation and sequence of delivery operations.

[1178] "Emotional state" refers to the psychological and physiological state of the driver, such as their stress level and fatigue level.

[1179] "Real-time feedback" is a function that immediately reports any problems or situations that arise during delivery operations to the system.

[1180] A "break" refers to a short period of rest taken by a driver during work.

[1181] "Service improvement measures" refer to specific suggestions and strategies aimed at improving user satisfaction.

[1182] This invention is a system for efficiently carrying out delivery operations, and in particular, it generates and manages optimal delivery routes and schedules based on the location information and order information of delivery vehicles, as well as the emotional state of the drivers. This system enables the generation of efficient delivery routes and the re-optimization of schedules that take into account the stress and fatigue of drivers.

[1183] The system includes the following key technological elements:

[1184] 1. Data collection methods

[1185] The server has the functionality to collect real-time location information of delivery vehicles. GPS modules are installed in the vehicles, and the data is transmitted to the server. In addition, order information from shippers is collected via terminals and transmitted to the server. Information on the pickup location is also collected simultaneously, and all data is managed centrally.

[1186] 2. Data integration and preprocessing means

[1187] The server has the function of integrating the collected data and supplementing or correcting any deficiencies or anomalies. This allows subsequent processing to be carried out based on high-quality data.

[1188] 3. Optimal route generation method using AI algorithms

[1189] The server uses AI algorithms to generate the optimal delivery route and schedule based on the current location of the delivery vehicle, order information, and planned route. For example, it calculates the optimal route that allows a truck to efficiently handle multiple orders.

[1190] 4. Schedule distribution method

[1191] The server has the function of distributing the generated schedule to delivery vehicle drivers and shippers. The driver's terminal displays the current schedule and route in real time.

[1192] 5. Means for detecting the driver's emotional state

[1193] The server incorporates an emotion engine that collects driver emotional data and evaluates stress and fatigue levels. Based on this emotional data, it generates a schedule that takes the driver's health into consideration.

[1194] 6. Real-time feedback and re-optimization means

[1195] The server receives delivery status and issues collected in real time by drivers and systems, and then reapplies AI algorithms based on this information to update schedules and routes. For example, it instantly reflects traffic congestion and other obstacle information and recalculates the optimal route.

[1196] Explanation of specific examples

[1197] For example, consider a delivery vehicle making a food delivery from Tokyo to Yokohama. Using this system, the server collects the vehicle's GPS data and determines that its current location is Tokyo. Order information from the client is entered, and the order is to deliver sushi and ramen to Yokohama at 2:00 PM. Based on this data, the server applies an AI algorithm to generate a route that allows the truck to complete the order in the shortest possible time.

[1198] If a driver encounters traffic congestion during their journey, they use a terminal to report the information to the server in real time. The server immediately recalculates a new route and notifies the driver. In addition, an emotion engine built into the system senses the driver's stress level and fatigue level and suggests a break if necessary.

[1199] Example of a prompt

[1200] "For a food delivery from Tokyo to Yokohama, please collect GPS location data and emotional state to generate an efficient schedule and route. The current order is to deliver sushi and ramen to Yokohama at 2:00 PM. The driver's stress level is high, so please also suggest optimal rest times."

[1201] As described above, the present invention can simultaneously improve the efficiency of delivery operations and manage the health of drivers.

[1202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1203] Step 1:

[1204] Data collection

[1205] Input: GPS information of delivery vehicles, order information from the consignor, and delivery status information.

[1206] Processing: The server collects GPS data from delivery vehicles in real time to obtain location information. It also sends order information entered by the shipper via a terminal to the server and simultaneously collects information on the status of receiving the goods.

[1207] Output: Integrated location information, order information, and delivery status information.

[1208] Step 2:

[1209] Data preprocessing

[1210] Input: All collected data (location information, order information, delivery status information)

[1211] Processing: The server centrally manages the collected data and imputes and corrects missing or outlier values. For example, if location information is missing, it is interpolated based on the previous data and the imputed information.

[1212] Output: Replicated and preprocessed dataset

[1213] Step 3:

[1214] Optimal route generation using AI algorithms

[1215] Input: Preprocessed dataset (location information, order information, delivery status information)

[1216] Processing: The server uses this data to apply AI algorithms to generate the optimal delivery route and schedule. For example, it considers the vehicle's current location, the order pickup location, and the delivery destination to calculate the shortest and most efficient route.

[1217] Output: Optimal route and schedule information

[1218] Step 4:

[1219] Scheduled distribution

[1220] Input: Optimal route and schedule information

[1221] Processing: The server distributes the generated schedule to the driver's terminal and the shipper's system. Detailed route information is displayed on the terminal.

[1222] Output: Schedule information distributed to the driver's terminal and the shipper's system.

[1223] Step 5:

[1224] Driver emotional state detection

[1225] Input: Prompt messages sent by the server and feedback data from the driver.

[1226] Processing: The terminal uses an emotion engine to detect the driver's emotional state and sends that data to the server. For example, it evaluates the stress level from the driver's facial expressions and voice.

[1227] Output: Driver's emotional state data

[1228] Step 6:

[1229] Schedule reoptimization based on the driver's emotional state

[1230] Input: Emotional state data (stress level, fatigue level)

[1231] Processing: The server adjusts the schedule as needed based on the driver's emotional state data. For example, if stress levels are high, it suggests a break and recalculates the schedule.

[1232] Output: Adjusted schedule information

[1233] Step 7:

[1234] Real-time feedback and optimization

[1235] Input: Delivery problem reports (traffic information, other disruption information), new order information

[1236] Processing: The driver reports the problem in real time via a terminal. The server receives this information, reapplies the AI ​​algorithm based on the new data, and recalculates the optimal route and schedule.

[1237] Output: Updated optimal route and schedule information

[1238] Each processing step works in conjunction with the entire system to improve the efficiency of delivery operations and ensure the health of drivers.

[1239] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1240] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio 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 specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1242] [Fourth Embodiment]

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

[1244] As shown in Figure 7, the 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is 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 interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1247] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the 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 image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1249] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1250] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1251] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1252] The specific processing program 56 is an example of a "program" relating to the technology of this 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 the data generation model 58 and the 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 robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1255] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1256] This invention is a system aimed at reducing the rate of empty return trips and shortening loading / unloading waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and loading / unloading status information, and generating and distributing the optimal route and schedule based on this information. The following describes in detail embodiments for specifically implementing this invention.

[1257] System Configuration

[1258] 1. Data collection methods

[1259] The server collects real-time location information for delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[1260] The server collects order information from shippers. To do this, shippers input order information (origin, destination, type of package, weight, desired delivery time, etc.) through an interface.

[1261] The server collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[1262] 2. Data integration and preprocessing means

[1263] The server integrates and preprocesses the collected location, order, and delivery information. By performing data interpolation and removing outliers, it generates a highly reliable dataset.

[1264] 3. Means for applying the matching algorithm

[1265] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[1266] Specifically, the system calculates the optimal combination based on data such as the truck's current location, load capacity, and the order's origin, destination, weight, and desired delivery time.

[1267] 4. Schedule distribution method

[1268] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The schedule is notified to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[1269] 5. Real-time feedback and optimization means

[1270] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[1271] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[1272] Explanation of the program's processing

[1273] The program for this system implements the above-mentioned methods to achieve efficient truck transportation. The following describes the processing details of the program.

[1274] 1. Data Collection

[1275] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[1276] The user (shipper) enters order information using a terminal and sends it to the server.

[1277] The server sets up a means to collect information on the status of receiving shipments and understands the acceptance time and preparation status.

[1278] 2. Data Integration and Preprocessing

[1279] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[1280] 3. Application of the matching algorithm

[1281] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it calculates that truck A can pick up two orders on its way from Tokyo to Yokohama.

[1282] 4. Scheduled distribution

[1283] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The driver's smartphone displays the specific route and loading / unloading instructions.

[1284] 5. Real-time feedback

[1285] Users (drivers) report real-time information such as traffic congestion and changes in delivery destinations from their terminals.

[1286] Based on this information, the server reapplies the AI ​​algorithm to recalculate the optimal route and schedule for delivery.

[1287] Specific example

[1288] As an example, consider the case where truck A travels from Tokyo to Yokohama. GPS data from the delivery vehicle is collected to determine that its current location is Tokyo. Two delivery requests (orders 1 and 2) from Tokyo to Yokohama are entered as order information from the shipper. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A accepts orders 1 and 2 via the optimal route. The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up the two packages at the Tokyo warehouse and deliver them to Yokohama. If traffic congestion occurs along the way, the driver reports it to the server in real time, and the server calculates a new route and delivers it again.

[1289] In this way, this system reduces the rate at which trucks are empty and shortens waiting times for loading and unloading, thereby achieving efficient delivery operation management.

[1290] The following describes the processing flow.

[1291] Step 1: Data Collection

[1292] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[1293] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[1294] The device sends the above data to the server.

[1295] Step 2: Data Integration and Preprocessing

[1296] The server stores the received data in a centrally managed database.

[1297] The server checks data integrity and fills in any missing data. For example, if there is a missing input, it will fill in the estimated value based on the previous data.

[1298] The server filters out abnormal values ​​(for example, delivery times exceeding the possible range) and sends a correction request to the user if an abnormality is found.

[1299] Step 3: Matching using AI algorithms

[1300] The server runs an AI algorithm based on the current location, order information, and planned route of all trucks.

[1301] The server performs optimal matching of each truck with an order. Specifically, it determines the best combination based on factors such as the distance and time from the dispatched vehicle's current location to the order's departure point, load capacity, and environmental impact.

[1302] Step 4: Generate Optimal Route and Schedule

[1303] The server generates the optimal route and schedule calculated by an AI algorithm. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[1304] Step 5: Scheduled distribution

[1305] The server sends the generated schedule to each truck driver's terminal. Specifically, it provides detailed instructions to the driver's terminal on where to pick up the cargo and where to deliver it.

[1306] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[1307] Step 6: Real-time feedback and reoptimization

[1308] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[1309] The server reapplies the AI ​​algorithm based on the received feedback (e.g., traffic information) to calculate a new, optimal route.

[1310] The server resends the updated schedule and route to the driver's terminal.

[1311] (Example 1)

[1312] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1313] There is a need to solve the problems of empty vehicle return rates and waiting times in truck transportation. Conventional systems have insufficient management of delivery vehicle location information and order information, making it difficult to optimize delivery routes efficiently. In addition, the inability to flexibly change schedules in response to real-time changes in circumstances led to problems with reduced operational efficiency.

[1314] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1315] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and re-optimizing the schedule, means for determining location information using a GPS device, means for inputting order information via a terminal, pre-processing means for data completion and removal of anomalies, and means for distributing schedule information using a notification system. This makes it possible to reduce the rate of empty return trips of trucks and shorten waiting times for loading and unloading.

[1316] "Delivery vehicles" refer to means of transport such as automobiles, trucks, and vans used to transport goods and products.

[1317] "Location information" refers to data that indicates the geographical location of a specific object or person, obtained by location measurement devices such as GPS devices.

[1318] "Order information" refers to data provided by shippers when requesting delivery services, including details such as the origin, destination, type of package, weight, and desired delivery time.

[1319] "Receiving information" refers to information such as the readiness status of the receiving location and the available receiving times for packages.

[1320] "Integration" is the process of bringing together different types of data and managing them comprehensively.

[1321] "Preprocessing" refers to the process of transforming collected raw data into a format that is easy to analyze, and includes data interpolation and removal of outliers.

[1322] An "AI algorithm" is a set of computational procedures that use artificial intelligence technology to analyze data and perform optimization and predictions.

[1323] A "schedule" is a plan of time and location, outlining when and where a delivery vehicle will pick up a package and where it will deliver it.

[1324] "Feedback" is the process of receiving information about the system's operation status and problems from the system and its users, and using that information to improve and adjust the system.

[1325] "Optimization" is the process of adjusting calculations and procedures to obtain the best possible result under given conditions and constraints.

[1326] A "GPS device" is a device that measures and reports a specific location on Earth, and it obtains location information using satellite signals.

[1327] A "terminal" is a device, such as a computer or smartphone, that a user uses to input information or receive information from a system.

[1328] A "notification system" is a communication method used to instantly deliver important information and updates to users and systems, and includes SMS and push notifications.

[1329] This invention is a system aimed at reducing the rate of empty return trips and shortening waiting times in truck transportation. This system is characterized by collecting location information of delivery vehicles, order information from shippers, and cargo receiving status information, and generating and distributing the optimal route and schedule based on this information.

[1330] Hardware and software to be used

[1331] The hardware used includes GPS devices, user terminals (smartphones and PCs), and servers. The software includes data collection software, AI algorithms, data integration and preprocessing software, and notification systems.

[1332] Overall flow

[1333] 1. Data Collection

[1334] The server collects location information in real time from GPS devices attached to delivery vehicles. This information includes the vehicle's current location, speed, and direction of travel.

[1335] The user (shipper) enters order information (origin, destination, type of package, weight, desired delivery time, etc.) via a terminal and sends it to the server.

[1336] The server collects information on the status of receiving shipments (such as readiness for acceptance and available acceptance times). This information is either entered by the person in charge at the receiving location or automatically retrieved by the system.

[1337] 2. Data Integration and Preprocessing

[1338] The server integrates collected location information, order information, and delivery information, and manages them centrally in real time.

[1339] The server performs preprocessing to complete the data and remove outliers. This process fills in missing data and corrects outliers, resulting in a reliable dataset.

[1340] 3. Application of the matching algorithm

[1341] The server uses an AI algorithm to generate the optimal delivery route and schedule. This algorithm considers the current location, load capacity, origin, destination, weight, and desired delivery time of each delivery vehicle to calculate the most efficient route and schedule.

[1342] 4. Scheduled distribution

[1343] The server distributes the generated schedule to the delivery vehicle drivers and shippers. This distribution is done through a notification system, and the specific route and loading / unloading instructions are displayed on the drivers' smartphones or tablets.

[1344] 5. Real-time feedback and optimization

[1345] Users (drivers) report operational status and problems (such as traffic congestion or changes in delivery destinations) to the server in real time from their terminals.

[1346] The server reapplies the AI ​​algorithm based on this status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[1347] Specific example

[1348] As an example, let's consider the case where truck A is traveling from Tokyo to Yokohama.

[1349] 1. Data Collection: The server obtains the current location of truck A (Tokyo) from a GPS device. The shipper also inputs order information, such as "I would like a 500kg package delivered from a warehouse in Tokyo to a warehouse in Yokohama," and sends it to the server.

[1350] 2. Data Integration and Preprocessing: The server integrates the collected data (location information of truck A, order information, and acceptance time information for the Yokohama warehouse) and supplements any missing data or outliers.

[1351] 3. Application of Matching Algorithm: The server uses an AI algorithm to generate the optimal schedule for truck A to pick up goods from a warehouse in Tokyo via the shortest route and deliver them to a warehouse in Yokohama.

[1352] 4. Schedule Distribution: The server distributes the generated schedule to the driver of truck A's smartphone. The smartphone displays instructions such as, "Pick up the cargo at the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[1353] 5. Real-time feedback and optimization: If traffic congestion occurs along the way, the user (driver) reports "traffic congestion" information from their device. The server then reapplies the AI ​​algorithm based on this information, calculates an alternative route, and redistributes it to the driver.

[1354] Example of a prompt:

[1355] "The system uses the current location data of trucks collected from GPS devices as input to calculate the optimal delivery route."

[1356] "Using multiple order details from shippers as input, an AI algorithm is applied to generate the optimal schedule."

[1357] "We will re-optimize the route and schedule based on real-time feedback from drivers."

[1358] This system will reduce the rate of empty truck return trips and waiting times for loading and unloading, enabling more efficient delivery operation management.

[1359] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1360] Step 1: Data Collection

[1361] The server collects location information in real time from GPS devices installed in delivery vehicles. The input data includes the current location, speed, and direction of movement of each vehicle, and this data is analyzed to output accurate location information.

[1362] The user (shipper) enters order information using a terminal. This information includes the origin, destination, type of package, weight, and desired delivery time. This information is then sent to the server via the terminal.

[1363] The server collects information on the status of receiving shipments (readiness for receiving, available time for receiving). This includes means of obtaining data entered by the person in charge at the receiving location. The server analyzes the input data and outputs the available time slots for receiving shipments.

[1364] Step 2: Data Integration and Preprocessing

[1365] The server centrally integrates the collected location information, order information, and delivery information. The input data consists of the above-mentioned collected items, and it outputs a manageable dataset by integrating these items.

[1366] The server performs preprocessing on the integrated data, including data imputation and outlier removal. The input data includes integrated raw data, and the server outputs a reliable dataset after imputing missing data and detecting and correcting outliers.

[1367] Step 3: Applying the Matching Algorithm

[1368] The server uses AI algorithms to generate the optimal delivery route and schedule. Input data includes the current location of the delivery vehicle, its load capacity, and order information (origin, destination, weight, desired delivery time). This data is analyzed to output an efficient route and schedule.

[1369] Specifically, the server calculates the optimal location and time for truck A to pick up two orders within Tokyo, and generates its route and schedule.

[1370] Step 4: Scheduled delivery

[1371] The server distributes the generated schedule to the delivery vehicle drivers and shippers. The input data is the generated schedule information, which is distributed via the notification system. As a result of the distribution, the specific route and loading instructions are output to the driver's smartphone.

[1372] In terms of specific actions, the server distributes schedules such as "Pick up the package from the Tokyo warehouse at 10:00 AM, then deliver it to the Yokohama warehouse."

[1373] Step 5: Real-time feedback and optimization

[1374] Users (drivers) report problems and situations during their journey (such as traffic congestion or changes in delivery destinations) in real time from their terminals. The input data includes the driver's reported information.

[1375] The server re-optimizes the schedule and route by applying the AI ​​algorithm again based on real-time feedback. The input data is feedback information from the driver, which is analyzed to output a new route and schedule.

[1376] Specifically, the server generates a new instruction stating, "There is currently traffic congestion, so take an alternative route," and redistributes it to the driver.

[1377] (Application Example 1)

[1378] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1379] This invention aims to reduce the rate of empty truck return trips and shorten loading / unloading waiting times in truck transportation, but existing systems have not been able to completely solve this problem. Specifically, real-time location information collection, optimal route generation, and rapid response to problems are not adequately performed, and efficient delivery operation management has not been achieved. Furthermore, even when using autonomous vehicles, there are still aspects that are difficult to address.

[1380] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1381] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving cargo, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and optimizing the schedule again, and an autonomous vehicle control system for comfortable delivery operation management. This makes it possible to reduce the rate of empty return trips, shorten waiting times for cargo, and improve the efficiency of autonomous vehicle operation management.

[1382] "Means for collecting location information of delivery vehicles" refers to a device that uses a GPS device to obtain the current location of delivery vehicles in real time.

[1383] "Means for collecting order information from shippers" refers to an interface and system on which shippers input order information such as origin, destination, type of goods, weight, and desired delivery time, and transmit it to a server.

[1384] "Means for collecting information on the status of receiving goods" refers to devices and systems that collect information from the receiving party regarding the status of preparation for receiving goods, the time when they can be received, etc.

[1385] "Means for integrating and preprocessing data" refers to devices and systems that centrally manage multiple collected data sets and perform processes to supplement and correct deficiencies and abnormal values.

[1386] "A method for generating optimal delivery routes and schedules using AI algorithms" refers to a software algorithm that uses artificial intelligence technology to calculate and generate optimal delivery routes and schedules based on collected data.

[1387] "Means for distributing the generated schedule to delivery vehicle drivers and shippers" refers to a system that notifies drivers' terminals and shippers' management systems of the calculated and generated schedule.

[1388] "A means of receiving real-time feedback on delivery status and problems and re-optimizing the schedule" refers to a system that receives real-time information on problems and delays from vehicles in operation, and then applies AI algorithms to calculate and distribute new routes and schedules.

[1389] The "Autonomous Vehicle Control System for Comfortable Delivery Operation Management" is a system that efficiently manages the operation of autonomous vehicles and distributes optimal routes and schedules to enable quick responses in the event of problems.

[1390] A "generative AI model" is an artificial intelligence model that has been trained to efficiently perform a specific task based on training data.

[1391] A "prompt statement" is an instruction given to a generative AI model to obtain a specific output.

[1392] This invention relates to a truck transportation management system that utilizes autonomous vehicles to maximize transportation efficiency. The configuration and operation of the system for specifically implementing this invention, including the hardware and software used, are described below.

[1393] System Configuration

[1394] 1. Data collection methods

[1395] The server collects real-time location information for delivery vehicles. For this purpose, each vehicle is equipped with a GPS device to collect location data.

[1396] The system also collects order information from shippers. This involves providing an interface for inputting data such as origin, destination, type of package, weight, and desired delivery time.

[1397] The server also collects information on the status of package acceptance (such as the preparation status for receiving deliveries and the available acceptance time).

[1398] 2. Data integration and preprocessing means

[1399] The server centrally manages the collected data. This includes a data cleansing process to supplement and correct any missing or outlier values.

[1400] 3. Means for applying the matching algorithm

[1401] The server uses AI algorithms to generate the optimal delivery route and schedule. It utilizes technologies such as TensorFlow and PyTorch to calculate and generate the optimal route and schedule based on all the collected data.

[1402] 4. Schedule distribution method

[1403] The generated schedule is distributed to the delivery vehicle drivers and the shippers. Notifications are sent to the drivers' devices (smartphones or tablets) and the shippers' management systems.

[1404] 5. Real-time feedback and optimization means

[1405] The user (driver) reports the situation and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[1406] The server reapplies the AI ​​algorithm based on the received status data, re-optimizing the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[1407] Specific example

[1408] As an example, consider the case of truck B traveling from Osaka to Nagoya. Real-time location information collected from the delivery vehicle's GPS device determines that its current location is Osaka. The shipper inputs order information: departure point is Osaka, destination is Nagoya, large cargo, weight 500kg, desired delivery time 10:00-12:00. The server integrates and preprocesses this data and generates the optimal route and schedule for truck B using an AI algorithm (e.g., using TensorFlow or PyTorch). The generated schedule is delivered to the driver's smartphone, displaying instructions for departure time 08:00 and arrival time 11:30. If traffic congestion occurs near Kyoto along the way, the driver's terminal automatically detects this and provides feedback to the cloud server. The server recalculates and generates a new route (e.g., Kyoto – Shiga – Nagoya) and delivers that information again. In this way, a reduction in empty return trips and a reduction in waiting time for loading and unloading are achieved.

[1409] Example of a prompt:

[1410] "Departure point: Osaka, Arrival point: Nagoya, Departure time: 08:00, Desired arrival time: 10:00-12:00, Package type: Large, Weight: 500kg. Based on these conditions, please generate the optimal delivery route and schedule."

[1411] This will enable efficient truck transportation using autonomous vehicles.

[1412] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1413] Step 1:

[1414] The server collects location information in real time from the GPS devices of delivery vehicles. The input data is the current location of the delivery vehicle, and the output is the collected location data. This data is formatted into a predetermined format and saved.

[1415] Step 2:

[1416] The user (shipper) enters order information using the interface. The input data includes origin, destination, package type, weight, and desired delivery time. The output is a dataset that centrally manages this order information. This data is sent to and stored on the server.

[1417] Step 3:

[1418] The server collects information on the status of receiving shipments. The input data includes the preparation status and acceptance time for receiving shipments, and the output is integrated receiving information data. This data is also formatted and saved in a predetermined format.

[1419] Step 4:

[1420] The server integrates the collected location information, order information, and receiving information, and performs data preprocessing. The input data consists of location information, order information, and receiving information, and the output is integrated data with outliers removed and imputed. Specifically, it imputes missing data and removes outliers.

[1421] Step 5:

[1422] The server uses AI algorithms to generate optimal delivery routes and schedules. The input data is pre-processed, integrated data, and the output is optimal route and schedule information. Specifically, it applies AI algorithms using TensorFlow or PyTorch to calculate delivery routes and schedules.

[1423] Step 6:

[1424] The server distributes the generated schedule to the delivery vehicle drivers and the shippers. The input data consists of the generated route and schedule information, and the output is a notification to the driver's terminal and the shipper's management system. Specifically, it displays the detailed route and schedule on the driver's smartphone.

[1425] Step 7:

[1426] The user (driver) reports the status and problems encountered during operation to the server in real time from their terminal. The input data is information about problems that occurred during operation, such as traffic congestion or changes in delivery destinations, and the output is feedback data to the server.

[1427] Step 8:

[1428] The server reapplies the AI ​​algorithm based on the received situation data to re-optimize the schedule and route. The input data is real-time feedback of situation data, and the output is the re-optimized route and schedule. Specifically, it calculates the new route and schedule and redistributes them to the driver's terminal.

[1429] In this way, efficient truck transportation management using autonomous vehicles is realized by utilizing the generated AI model and prompt messages.

[1430] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1431] This invention combines a system that matches delivery vehicle location information with order information to generate and distribute efficient delivery routes and schedules, with an emotion engine that recognizes user emotions. This system enables the re-optimization of schedules that take into account the driver's stress and fatigue levels, and schedule updates based on real-time feedback.

[1432] System Configuration

[1433] 1. Data collection methods

[1434] The server collects real-time location information of delivery vehicles. To do this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal.

[1435] The server collects order information from shippers, who input the order information through an interface.

[1436] The server provides a means to collect information on the status of receiving shipments, and to understand the readiness for receiving shipments and the available time for receiving them.

[1437] 2. Data integration and preprocessing means

[1438] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[1439] 3. Matching methods using AI algorithms

[1440] The server uses AI algorithms to analyze data from each delivery vehicle and order, and generates the optimal delivery route and schedule.

[1441] Specifically, the system calculates the optimal combination based on the truck's current location, load capacity, and detailed order information.

[1442] 4. Schedule distribution method

[1443] The server sends the generated schedule to each truck driver's terminal and also distributes the schedule to the shipper.

[1444] 5. Real-time feedback and optimization means

[1445] The user (driver) reports the status and problems during operation (e.g., traffic congestion or changes in delivery destination) to the server in real time from their terminal.

[1446] The server reapplies the AI ​​algorithm based on the received status data to re-optimize the schedule and route. The updated schedule is then delivered to the driver's terminal again.

[1447] 6. Emotional Engine

[1448] The server uses an emotion engine to collect emotional information from users (drivers and shippers). This information is used to evaluate stress levels and satisfaction levels.

[1449] The emotional engine senses the driver's stress and fatigue levels and re-optimizes the schedule accordingly. For example, if the driver is highly fatigued while driving, it can incorporate break time into the schedule.

[1450] The server reapplies AI algorithms and updates schedules based on sentiment information collected in real time. It also evaluates user satisfaction and suggests ways to improve the service.

[1451] Explanation of the program's processing

[1452] The program for this system implements the above-mentioned methods to achieve efficient truck transportation while also taking user emotions into consideration. The following describes the program's processing details.

[1453] 1. Data Collection

[1454] The server collects GPS data from each delivery vehicle and tracks their location in real time.

[1455] The user (shipper) enters order information using a terminal and sends it to the server.

[1456] The server uses means to collect information on the status of receiving shipments and to understand the readiness for acceptance.

[1457] 2. Data Integration and Preprocessing

[1458] The server centrally manages all collected data and supplements or corrects any missing or abnormal values.

[1459] 3. Application of AI algorithms

[1460] The server uses AI algorithms to generate the optimal delivery route and schedule. For example, it creates the optimal route for truck A to pick up two orders on its way from Tokyo to Yokohama.

[1461] 4. Scheduled distribution

[1462] The server distributes the generated schedule to each truck driver's terminal. The driver's terminal provides detailed instructions on where to pick up the cargo and where to deliver it.

[1463] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[1464] 5. Real-time feedback

[1465] The user (driver) reports traffic conditions and truck status in real time using a terminal while driving.

[1466] Based on this information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and delivers it again.

[1467] 6. Application of the emotion engine

[1468] The server uses an emotion engine to collect emotional information from users (drivers and shippers). For example, it can sense a driver's stress level and suggest a break if stress levels are high.

[1469] The user (driver) reports emotional information through their device, and the server uses this information to re-optimize the schedule.

[1470] The server proposes service improvements based on emotional information, thereby improving overall delivery efficiency.

[1471] Specific example

[1472] For example, consider the case where truck A is traveling from Tokyo to Yokohama. This system collects GPS data from the delivery vehicle to determine its current location is Tokyo. Two delivery requests from the shipper (orders 1 and 2) from Tokyo to Yokohama are entered as order information. The server integrates and preprocesses this data and uses an AI algorithm to generate a schedule in which truck A takes the optimal route to accept orders 1 and 2.

[1473] The generated schedule is delivered to the driver's smartphone, displaying instructions to pick up two packages at the Tokyo warehouse and deliver them to Yokohama. If the driver encounters traffic congestion during the trip, they can report it to the server in real time using their device, and the server will calculate and redistribute a new route.

[1474] Furthermore, the emotion engine integrated into this system senses the driver's stress level and fatigue, and suggests breaks as needed. It also collects feedback from shippers and drivers in real time, and reapplies the AI ​​algorithm to update the schedule. In this way, it is possible to reduce the rate of empty trucks returning to port, shorten waiting times for loading and unloading, and improve user satisfaction.

[1475] The following describes the processing flow.

[1476] Step 1: Data Collection

[1477] The user (driver) inputs the truck's current location and operational status (empty, loading, delivery, etc.) via a terminal.

[1478] The user (shipper) enters new delivery order information (origin, destination, type of package, weight, desired delivery time, etc.) into the server from their terminal.

[1479] The device sends the above data to the server.

[1480] The server integrates the collected location information, order information, and delivery status information.

[1481] Step 2: Data Integration and Preprocessing

[1482] The server stores the received data in the database.

[1483] The server checks data integrity, completes missing data, and removes outliers. If data is missing, it is completed using estimates or previous data.

[1484] The server filters out abnormal values ​​(for example, extremely long delivery times) and sends correction requests to users for data where abnormalities are detected.

[1485] Step 3: Matching using AI algorithms

[1486] The server runs an AI algorithm based on the current location of all delivery vehicles, order information, and planned routes.

[1487] The server performs optimal matching of each delivery vehicle with each order. Specifically, it calculates the best combination by considering factors such as the distance and time from each truck's current location to the order's departure point, load capacity, and environmental impact.

[1488] Step 4: Gathering emotional information

[1489] The user's (driver's) emotional state (stress level, fatigue level, etc.) is collected through an emotion engine.

[1490] The server integrates the collected sentiment information and performs data preprocessing based on it.

[1491] Step 5: Generate Optimal Route and Schedule

[1492] The server uses AI algorithms and collected data to generate the optimal delivery route and schedule. For example, it calculates a route where truck A can pick up two orders on its way from Tokyo to Yokohama.

[1493] Furthermore, the server generates a schedule that includes breaks and adjustments to the route based on the driver's emotional state (stress and fatigue levels).

[1494] Step 6: Scheduled delivery

[1495] The server sends the generated schedule to each driver's terminal. Specifically, it provides information such as where to pick up packages, where to deliver them, and even rest instructions based on the driver's emotional state.

[1496] The server also distributes the schedule to the shipper, allowing them to monitor the overall delivery status.

[1497] Step 7: Real-time feedback and re-optimization

[1498] Users (drivers) use a terminal to report traffic conditions and the status of their trucks in real time while they are driving. For example, they might report traffic jams or accidents.

[1499] The server reapplies the AI ​​algorithm based on the received feedback data and recalculates the optimal route and schedule.

[1500] The server redistributes the recalculated schedule and route to the driver's terminal.

[1501] Step 8: Evaluation and improvement using the emotional engine

[1502] The server evaluates emotional information collected in real time to check the driver's stress level and satisfaction level.

[1503] The server uses emotional information to suggest service improvements and incorporates them into the operational plan. For example, if stress levels are high, it may schedule more breaks or change the route to reduce the burden.

[1504] In this way, an efficient delivery operation management system is realized that reduces the rate of empty vehicle return trips and shortens waiting times for loading and unloading, while also taking into consideration the feelings of users (drivers) and shippers.

[1505] (Example 2)

[1506] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1507] Traditional delivery systems perform simple route optimization based on the location and order information of delivery vehicles, but they lack the ability to respond to user emotions and unexpected problems in real time. This has resulted in challenges such as insufficient improvement in driver and shipper satisfaction, and inadequate reduction of driver workload. Furthermore, traditional systems have difficulty responding flexibly to traffic congestion and delivery disruptions.

[1508] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1509] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving goods, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to delivery vehicle drivers and shippers, means for receiving real-time feedback on delivery status and problems and re-optimizing the schedule, and means for collecting user sentiment information, analyzing it using a sentiment engine, and re-optimizing the delivery schedule. This makes it possible to improve the satisfaction of delivery vehicle drivers and shippers, reduce the burden on drivers, and enable flexible responses in real time.

[1510] A "delivery vehicle" is a vehicle used to transport goods or packages from one point to another.

[1511] "Location information" refers to information obtained using location measurement technologies such as GPS, which indicates the current location of a specific object or person.

[1512] "Order information" refers to data that includes detailed information such as the type, quantity, and destination of the goods being shipped by the shipper.

[1513] "Receiving status information" refers to information regarding the readiness of the delivery destination to receive the package and the available time slots for receiving it.

[1514] A "server" is a computer system used to collect, integrate, and analyze data, and to distribute the results.

[1515] "Methods for integrating and pre-processing data" refers to technologies that centrally manage collected location information, order information, and delivery status information, and supplement and correct any deficiencies or anomalies.

[1516] An "AI algorithm" is an algorithm that uses machine learning and artificial intelligence technologies to calculate the optimal delivery route and schedule.

[1517] "Methods for generating optimal delivery routes and schedules" refers to technologies that analyze collected data to create efficient delivery routes and schedules that meet user requirements.

[1518] "Means for distributing schedules to delivery vehicle drivers and shippers" refers to a function that transmits the generated delivery routes and schedules to the drivers' terminals and the shippers' terminals.

[1519] "A means of receiving real-time feedback on delivery status and problems, and re-optimizing the schedule" refers to a technology that receives feedback information from drivers and shippers during operations, and then reapplies an AI algorithm based on this information to update the schedule.

[1520] "Users" refer to people such as drivers and shippers who use the delivery system.

[1521] "Emotional information" refers to data about the user's emotional state, such as stress levels and satisfaction levels.

[1522] An "emotion engine" is a system that collects and analyzes user emotional information to provide appropriate responses and suggestions.

[1523] "Methods for re-optimizing delivery schedules" refer to technologies that generate more efficient delivery schedules based on user sentiment information and real-time feedback.

[1524] This invention combines a system that matches delivery vehicle location information with order information to generate and distribute efficient delivery routes and schedules, with an emotion engine that recognizes user emotions. This enables the re-optimization of schedules that take into account driver stress and fatigue levels, and schedule updates based on real-time feedback.

[1525] This system can be implemented as follows:

[1526] 1. Data collection methods

[1527] The server collects real-time location information for delivery vehicles. To achieve this, GPS devices are installed in each vehicle, and data is collected through the driver's terminal. Users (shippers) use the terminal to enter order information and send it to the server. The server also collects delivery status information from the systems of each delivery destination.

[1528] 2. Data integration and preprocessing means

[1529] The server centrally manages all collected data and compensates for and corrects any omissions or anomalies. A database management system (DBMS) is used for this purpose. For example, historical trends and machine learning models are used to compensate for missing location data.

[1530] 3. Methods for applying AI algorithms

[1531] The server analyzes collected real-time and pre-processed data and applies AI algorithms to generate optimal delivery routes and schedules. For example, it uses machine learning algorithms to calculate the shortest route from delivery destination A to delivery destination B, or a route that efficiently handles specific orders.

[1532] 4. Schedule distribution method

[1533] The server distributes the generated schedule to the delivery vehicle drivers and shippers. Specifically, the driver's terminal displays detailed information about the pickup point and delivery destination. Shippers are notified of the schedule and can understand the overall delivery status.

[1534] 5. Real-time feedback and optimization means

[1535] Users (drivers) report their driving status and problems to the server in real time via their terminals. For example, they send information such as traffic congestion or changes in delivery destinations. Based on this feedback information, the server reapplies an AI algorithm to calculate a new, optimal schedule and route, and delivers it to the driver's terminal.

[1536] 6. Means of applying the emotion engine

[1537] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). This information is used, for example, to evaluate the driver's stress level and fatigue level. If the server detects that the driver is highly stressed, it suggests a break. Users (drivers) report their emotional information through a terminal, and the server uses this information to re-optimize the schedule.

[1538] Specific example

[1539] For example, in the case where truck A is traveling from Tokyo to Yokohama, this system operates as follows:

[1540] 1. Data collection methods

[1541] The server confirms that truck A is currently in Tokyo using its GPS device. The user (shipper) enters orders (orders 1 and 2) for delivery from Tokyo to Yokohama.

[1542] 2. Data integration and preprocessing means

[1543] The server integrates location information, order information, and receiving information, and estimates and supplements any missing data.

[1544] 3. Methods for applying AI algorithms

[1545] The server uses an AI algorithm to calculate the optimal route based on the current location and order information of truck A. For example, it might pick up packages A and B from the Tokyo warehouse and head to the delivery destination in Yokohama.

[1546] 4. Schedule distribution method

[1547] The server delivers this schedule to the driver's smartphone. The device displays, "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama."

[1548] 5. Real-time feedback and optimization means

[1549] When a user (driver) encounters traffic congestion, they report it to the server from their device. The server receives this information, calculates a new route, and redistributes it.

[1550] 6. Means of applying the emotion engine

[1551] If the server detects that the driver is stressed, it will suggest a break. For example, a message might appear on the terminal saying, "Take a 15-minute break at the next service area."

[1552] Examples of prompts to input into a generative AI model

[1553] The following are examples of prompts to input into the generative AI model.

[1554] "Based on the current location information of the delivery vehicles, please generate the optimal delivery route and schedule."

[1555] "Please suggest countermeasures for situations where the driver's stress level is high."

[1556] "Please re-optimize the schedule in real time based on the following data: Track A's current location, load capacity, order information, and sentiment information."

[1557] This enables highly accurate scheduling and service improvements using generative AI models.

[1558] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1559] Step 1: Data Collection

[1560] The server collects real-time location information of delivery vehicles from GPS devices installed in the vehicles. Specifically, it receives signals from the GPS devices to determine the vehicle's current location. Users (shippers) use a terminal to input order information (e.g., delivery destination and package details) and send it to the server. The server collects information on the status of package receipt from the delivery destination, receiving data such as the time when the package can be received and the readiness status from the system. This data is aggregated on the server as GPS location information (input), order information (input), and package receipt information (input).

[1561] Step 2: Data Integration and Preprocessing

[1562] The server integrates and centrally manages all collected data. Specifically, it uses a database management system (DBMS) to organize the information and processes data to supplement and correct missing data and outliers. For example, it uses historical trend data and machine learning models to infer and fill in missing location information. As a result, a consistent dataset (output) is created.

[1563] Step 3: Applying the AI ​​algorithm

[1564] The server uses integrated data to apply AI algorithms to generate optimal delivery routes and schedules. Specifically, it analyzes the truck's current location, load capacity, and order details, and uses machine learning algorithms (e.g., route optimization algorithms) to calculate the shortest route and most efficient delivery sequence. This generates the optimal delivery route and schedule (output).

[1565] Step 4: Scheduled delivery

[1566] The server distributes the generated schedule to each driver's terminal and the shipper's terminal. Specifically, it sends detailed pickup and delivery instructions to the driver's terminal and notifies the shipper of the overall delivery status. On the driver's terminal, instructions such as "Pick up packages A and B at the Tokyo warehouse and deliver them to Yokohama" will be displayed. As a result, the schedule is distributed (output) to each terminal.

[1567] Step 5: Real-time feedback and optimization

[1568] The user (driver) reports the status and problems during their journey (e.g., traffic congestion or changes in delivery destinations) to the server in real time using their terminal. Specifically, they input feedback information using the status reporting menu. Based on the received feedback information, the server reapplies the AI ​​algorithm to calculate a new, optimal route and schedule, and redistributes it. The optimized schedule (output) is then delivered back to the driver's terminal.

[1569] Step 6: Apply the emotion engine

[1570] The server uses an emotion engine to collect and analyze emotional information from users (drivers and shippers). Specifically, it senses the driver's stress level using facial recognition and voice analysis technology. For example, if a high stress level is detected, it suggests taking a break. Users (drivers) report their emotional information from their terminals, and the server re-optimizes the schedule based on this information. The re-optimized schedule (output) based on the emotional information is delivered to the driver's terminal. The server also suggests service improvement measures to enhance user satisfaction.

[1571] The above describes the specific program processing flow of this system.

[1572] (Application Example 2)

[1573] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1574] Currently, delivery systems exist that generate efficient delivery routes based on the location and order information of delivery vehicles. However, they lack sufficient functionality to optimize schedules while considering driver stress and fatigue. This can lead to accumulated driver fatigue and decreased efficiency. Furthermore, the lack of smooth real-time feedback and schedule re-optimization can result in a decline in service quality.

[1575] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1576] In this invention, the server includes means for collecting location information of delivery vehicles, means for collecting order information from shippers, means for collecting information on the status of receiving goods, means for integrating and pre-processing this data, means for generating an optimal delivery route and schedule using an AI algorithm, means for distributing the generated schedule to the delivery vehicle driver and shipper, means for detecting the driver's emotional state, means for re-optimizing the schedule based on the detected emotional state and fatigue level, and means for receiving real-time feedback on the delivery status and problems and re-optimizing the schedule. This enables efficient schedule generation that takes into account the driver's emotional state and fatigue level, and smooth schedule re-optimization based on real-time feedback.

[1577] A "delivery vehicle" is a vehicle used to transport orders from customers or shippers to their destination.

[1578] "Location information" refers to data that indicates the current geographical coordinates of the delivery vehicle.

[1579] "Order information" refers to information provided by the shipper that includes specific instructions and requirements regarding delivery.

[1580] "Delivery status information" refers to information regarding the location and time of delivery, the progress of preparation for delivery, and so on.

[1581] "Data integration" is the process of centrally combining data collected from different sources.

[1582] "Preprocessing" refers to the preparatory processes performed to ensure data quality and to prepare the data for analysis and application to algorithms.

[1583] An "AI algorithm" is a mathematical model or calculation method that uses artificial intelligence technology to generate the optimal delivery route and schedule.

[1584] A "delivery route" is the path that a delivery vehicle takes to reach its destination.

[1585] A "schedule" is a plan that outlines the specific time allocation and sequence of delivery operations.

[1586] "Emotional state" refers to the psychological and physiological state of the driver, such as their stress level and fatigue level.

[1587] "Real-time feedback" is a function that immediately reports any problems or situations that arise during delivery operations to the system.

[1588] A "break" refers to a short period of rest taken by a driver during work.

[1589] "Service improvement measures" refer to specific suggestions and strategies aimed at improving user satisfaction.

[1590] This invention is a system for efficiently carrying out delivery operations, and in particular, it generates and manages optimal delivery routes and schedules based on the location information and order information of delivery vehicles, as well as the emotional state of the drivers. This system enables the generation of efficient delivery routes and the re-optimization of schedules that take into account the stress and fatigue of drivers.

[1591] The system includes the following key technological elements:

[1592] 1. Data collection methods

[1593] The server has the functionality to collect real-time location information of delivery vehicles. GPS modules are installed in the vehicles, and the data is transmitted to the server. In addition, order information from shippers is collected via terminals and transmitted to the server. Information on the pickup location is also collected simultaneously, and all data is managed centrally.

[1594] 2. Data integration and preprocessing means

[1595] The server has the function of integrating the collected data and supplementing or correcting any deficiencies or anomalies. This allows subsequent processing to be carried out based on high-quality data.

[1596] 3. Optimal route generation method using AI algorithms

[1597] The server uses AI algorithms to generate the optimal delivery route and schedule based on the current location of the delivery vehicle, order information, and planned route. For example, it calculates the optimal route that allows a truck to efficiently handle multiple orders.

[1598] 4. Schedule distribution method

[1599] The server has the function of distributing the generated schedule to delivery vehicle drivers and shippers. The driver's terminal displays the current schedule and route in real time.

[1600] 5. Means for detecting the driver's emotional state

[1601] The server incorporates an emotion engine that collects driver emotional data and evaluates stress and fatigue levels. Based on this emotional data, it generates a schedule that takes the driver's health into consideration.

[1602] 6. Real-time feedback and re-optimization means

[1603] The server receives delivery status and issues collected in real time by drivers and systems, and then reapplies AI algorithms based on this information to update schedules and routes. For example, it instantly reflects traffic congestion and other obstacle information and recalculates the optimal route.

[1604] Explanation of specific examples

[1605] For example, consider a delivery vehicle making a food delivery from Tokyo to Yokohama. Using this system, the server collects the vehicle's GPS data and determines that its current location is Tokyo. Order information from the client is entered, and the order is to deliver sushi and ramen to Yokohama at 2:00 PM. Based on this data, the server applies an AI algorithm to generate a route that allows the truck to complete the order in the shortest possible time.

[1606] If a driver encounters traffic congestion during their journey, they use a terminal to report the information to the server in real time. The server immediately recalculates a new route and notifies the driver. In addition, an emotion engine built into the system senses the driver's stress level and fatigue level and suggests a break if necessary.

[1607] Example of a prompt

[1608] "For a food delivery from Tokyo to Yokohama, please collect GPS location data and emotional state to generate an efficient schedule and route. The current order is to deliver sushi and ramen to Yokohama at 2:00 PM. The driver's stress level is high, so please also suggest optimal rest times."

[1609] As described above, the present invention can simultaneously improve the efficiency of delivery operations and manage the health of drivers.

[1610] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1611] Step 1:

[1612] Data collection

[1613] Input: GPS information of delivery vehicles, order information from the consignor, and delivery status information.

[1614] Processing: The server collects GPS data from delivery vehicles in real time to obtain location information. It also sends order information entered by the shipper via a terminal to the server and simultaneously collects information on the status of receiving the goods.

[1615] Output: Integrated location information, order information, and delivery status information.

[1616] Step 2:

[1617] Data preprocessing

[1618] Input: All collected data (location information, order information, delivery status information)

[1619] Processing: The server centrally manages the collected data and imputes and corrects missing or outlier values. For example, if location information is missing, it is interpolated based on the previous data and the imputed information.

[1620] Output: Replicated and preprocessed dataset

[1621] Step 3:

[1622] Optimal route generation using AI algorithms

[1623] Input: Preprocessed dataset (location information, order information, delivery status information)

[1624] Processing: The server uses this data to apply AI algorithms to generate the optimal delivery route and schedule. For example, it considers the vehicle's current location, the order pickup location, and the delivery destination to calculate the shortest and most efficient route.

[1625] Output: Optimal route and schedule information

[1626] Step 4:

[1627] Scheduled distribution

[1628] Input: Optimal route and schedule information

[1629] Processing: The server distributes the generated schedule to the driver's terminal and the shipper's system. Detailed route information is displayed on the terminal.

[1630] Output: Schedule information distributed to the driver's terminal and the shipper's system.

[1631] Step 5:

[1632] Driver emotional state detection

[1633] Input: Prompt messages sent by the server and feedback data from the driver.

[1634] Processing: The terminal uses an emotion engine to detect the driver's emotional state and sends that data to the server. For example, it evaluates the stress level from the driver's facial expressions and voice.

[1635] Output: Driver's emotional state data

[1636] Step 6:

[1637] Schedule reoptimization based on the driver's emotional state

[1638] Input: Emotional state data (stress level, fatigue level)

[1639] Processing: The server adjusts the schedule as needed based on the driver's emotional state data. For example, if stress levels are high, it suggests a break and recalculates the schedule.

[1640] Output: Adjusted schedule information

[1641] Step 7:

[1642] Real-time feedback and optimization

[1643] Input: Delivery problem reports (traffic information, other disruption information), new order information

[1644] Processing: The driver reports the problem in real time via a terminal. The server receives this information, reapplies the AI ​​algorithm based on the new data, and recalculates the optimal route and schedule.

[1645] Output: Updated optimal route and schedule information

[1646] Each processing step works in conjunction with the entire system to improve the efficiency of delivery operations and ensure the health of drivers.

[1647] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1648] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1649] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1650] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1651] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1652] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1653] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1654] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belongi...

Claims

1. A means of collecting location information of delivery vehicles, Means of collecting order information from shippers, A means of collecting information on the status of receiving goods, A means for integrating and preprocessing this data, A means of generating the optimal delivery route and schedule using an AI algorithm, A means of distributing the generated schedule to the delivery vehicle drivers and shippers, A means to receive real-time feedback on delivery status and problems, and to optimize the schedule again, A system that includes this.

2. The system according to claim 1, which applies an AI algorithm based on the current location of the delivery vehicle, order information, and planned route to perform the optimal matching of each vehicle with the order.

3. The system according to claim 1, which receives real-time traffic congestion information and delivery disruption information as feedback, and updates the schedule and route by reapplying an AI algorithm.

Images