system

Abstract

To provide a system for realizing efficient distribution of vehicles and personnel in taxi and logistics fields.SOLUTION: A system comprising: means for collecting real-time GPS location data, demand forecast data, and traffic condition data; means for analyzing the collected data to forecast demand in the next time period; means for assigning available vehicles and drivers based on the forecasted demand; means for assigning optimal routes and tasks to the identified vehicles and drivers; means for sending notifications and instructions to the vehicles and drivers; and means for monitoring the progress of the vehicles and drivers in real-time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, the taxi and logistics industries have each been facing different labor-related issues. In the taxi industry, fluctuations in demand during certain hours have resulted in busy and slow times. Meanwhile, the logistics industry is facing a chronic driver shortage, which is a serious issue. The 2024 problem, which will see truck drivers' working hours reduced, is particularly threatening, raising concerns about further labor shortages and increased costs. Given this background, both the taxi and logistics industries require a system that can efficiently allocate labor and resolve driver shortages and excess driver issues. [Means for solving the problem]

[0005] The present invention provides a system for realizing efficient allocation of vehicles and personnel in the taxi and logistics fields. Specifically, the system includes the following means:

[0006] a means for collecting real-time GPS location data, demand forecast data, and traffic condition data;

[0007] A means for analyzing the collected data to predict demand for the next time period;

[0008] a means for identifying available vehicles and drivers based on predicted demand;

[0009] a means for assigning optimal routes and tasks to the identified vehicles and drivers;

[0010] means for sending notifications and instructions to the vehicle and driver;

[0011] a means of monitoring the progress of the vehicle and driver in real time;

[0012] It has the means to get taxi drivers to transport goods and truck drivers to transport people,

[0013] It also provides a means for efficiently reallocating vehicles and drivers that are on standby or have gaps in service based on predicted demand.

[0014] This will enable efficient allocation of labor in the taxi and logistics industries, solving problems such as driver shortages and surpluses.

[0015] "Real-time GPS location data" refers to data that acquires and records the current location of a vehicle in real time.

[0016] "Demand forecast data" is data that predicts future demand based on past data and statistical information.

[0017] "Traffic condition data" refers to data including real-time traffic information obtained from traffic control systems and map services.

[0018] "Vehicle" refers to any vehicle used for transportation, such as a taxi or truck.

[0019] "Driver" means a person whose job is to drive a vehicle and transport people or goods.

[0020] "Means of collection" refers to devices or systems for collecting data using GPS devices, sensors, communication modules, etc.

[0021] "Means of analysis and prediction" refers to a system that analyzes collected data using algorithms and machine learning models to predict future demand.

[0022] A "means for identifying" is a system for selecting available vehicles and drivers based on predicted demand.

[0023] The "allocation means" is a system for instructing the identified vehicles and drivers on optimal routes and tasks.

[0024] The "means for sending notifications" refers to a communication device or application that sends information to the driver's terminal and instructs the driver on tasks and routes.

[0025] "Monitoring means" means a system for monitoring the progress of the vehicle and driver in real time.

[0026] A "relocation means" is a system for efficiently relocating waiting or idle vehicles and drivers in response to predicted demand. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0028] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0029] First, the terms used in the following description will be explained.

[0030] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0031] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0032] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0033] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0034] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0035] [First embodiment]

[0036] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0037] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0038] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0039] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0040] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0041] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0042] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0043] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0044] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0045] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0046] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0047] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0048] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[0049] System Overview

[0050] 1. Data Collection

[0051] The server collects real-time information on the current location of taxis and trucks from GPS devices, as well as past ride data, package delivery data, and event information, and statistically processes it. It also obtains real-time traffic information from traffic control systems and map services.

[0052] 2. Demand forecast

[0053] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[0054] 3. Resource Matching

[0055] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[0056] 4. Optimal Route and Task Allocation

[0057] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, and also decides whether the vehicle is delivering goods or transporting people, and assigns each vehicle a specific task.

[0058] 5. Notices and Instructions

[0059] The terminal (driver) receives notification messages sent from the server and receives task and route instructions.

[0060] 6. Execution and Monitoring

[0061] The server monitors in real time whether the driver is following instructions and performing the task, and generates alerts as needed, providing instructions on appropriate countermeasures based on progress reports from the driver's device.

[0062] Specific examples

[0063] Example: Transporting goods by taxi

[0064] 1. Data Collection

[0065] The server collects real-time demand data for a region and the location of waiting taxis.

[0066] 2. Demand forecast

[0067] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[0068] 3. Resource Matching

[0069] The server checks the waiting taxis in area A and identifies a vehicle suitable for delivering the goods.

[0070] 4. Optimal Route and Task Allocation

[0071] The server assigns the optimal route from area A to area B and a delivery task to the taxi.

[0072] 5. Notices and Instructions

[0073] The terminal (driver) receives notification messages sent from the server and receives delivery tasks and route instructions.

[0074] 6. Execution and Monitoring

[0075] The server monitors the process in real time as the taxi driver picks up the item and delivers it to the specified area B.

[0076] As described above, the present invention can realize efficient allocation of labor in the taxi and logistics industries, and solve problems such as driver shortages and surpluses.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The server collects the current location of taxis and trucks in real time from GPS devices.

[0080] Step 2:

[0081] The server collects historical ride data, package delivery data, and event information from a database.

[0082] Step 3:

[0083] The server obtains real-time traffic data from traffic control systems and map services.

[0084] Step 4:

[0085] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[0086] Step 5:

[0087] The server identifies available vehicles and drivers based on the demand forecast.

[0088] Step 6:

[0089] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[0090] Step 7:

[0091] The server generates notification messages about the assigned tasks and routes and sends them to the driver's terminal.

[0092] Step 8:

[0093] The device (driver) receives the notification message and confirms the task and route instructions.

[0094] Step 9:

[0095] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[0096] Step 10:

[0097] The server monitors the driver's progress in real time, generating alerts and sending response instructions as needed.

[0098] As described above, the system of the present invention can realize efficient allocation of labor in the taxi and logistics fields, and solve the problems of driver shortages and labor surpluses.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] Efficient allocation of vehicles and personnel is a challenge in the taxi and logistics sectors. Currently, it is difficult to quickly and appropriately reallocate waiting vehicles and driver resources, resulting in frequent mismatches between supply and demand. This reduces driver work efficiency and reduces user satisfaction. Furthermore, a lack of real-time monitoring and optimal route instructions makes traffic congestion and operational delays more likely to occur. Therefore, a system that can solve these issues is needed.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes means for collecting real-time location information, means for collecting past behavior data and current traffic condition data, means for analyzing the collected data and predicting demand for the next time slot, means for identifying available vehicles and drivers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for sending notifications and instructions to the vehicles and drivers, and means for monitoring the progress of the drivers in real time. This allows for appropriate and efficient allocation of vehicle and driver resources, eliminating mismatches between supply and demand, and enabling improved business efficiency and customer satisfaction.

[0104] "Real-time location information" is data that indicates the specific location of a vehicle or driver at the current time.

[0105] "Past behavior data" is information that records the past behavior history of a vehicle and a driver.

[0106] "Current traffic condition data" refers to data that includes current traffic flow and congestion information in a specific area.

[0107] "Demand forecasting" is the process of calculating traffic demand for a specific time period in the future based on past data and current conditions.

[0108] "Available vehicles and drivers" refers to vehicles and drivers that are currently in operation or on standby and immediately available for work.

[0109] An "optimal route" is a route that takes into account time, distance, traffic conditions, and other factors to reach a destination in the most efficient manner.

[0110] "Task" means a specific task or instruction given to a vehicle and driver.

[0111] A "notification" is a message conveying instructions or information that is sent by the server to a vehicle or driver.

[0112] "Progress" is information indicating how far the vehicle and driver have progressed in completing the specified task.

[0113] "Real-time monitoring" is the process of constantly knowing the current status of the vehicle and driver.

[0114] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[0115] System Overview

[0116] Data collection

[0117] The server obtains real-time location information from the GPS devices installed in each vehicle. The hardware used for this is a GPS module such as the u-blox NEO-M8N. It also obtains past ride and delivery data from a database such as MySQL (registered trademark). Traffic condition data is obtained in real time from, for example, the Google (registered trademark) Traffic API.

[0118] Example: The server collects the current location information of taxis in the Tokyo area, ride data around Shinjuku Station for the past month, and current traffic situation data around Shinjuku Station.

[0119] Demand forecasting

[0120] The server analyzes the collected data and runs a demand forecasting algorithm using a machine learning model such as "TENSORFLOW (registered trademark)." The analysis results are stored in a database such as "PostgreSQL."

[0121] Example: Based on data from the past month, the server predicts that there will be an increase in demand for taxis from Shinjuku Station to Roppongi in the next hour.

[0122] Resource Matching

[0123] The server compares the predicted demand with current vehicle location data to identify areas where demand is lacking, then checks available vehicles and drivers and selects the most suitable vehicle and driver.

[0124] Example: The server checks for taxis waiting around Shinjuku Station and identifies the vehicle that is suitable for delivering an item.

[0125] Optimal Routes and Task Allocation

[0126] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle, using the Google Directions API, and assigns specific tasks to each vehicle.

[0127] Example: The server calculates the optimal route for a taxi from Shinjuku Station to Roppongi and assigns a delivery task.

[0128] Notices and Instructions

[0129] The device (driver) receives notification messages sent from the server and receives task and route instructions. The driver checks the notifications on a smartphone or tablet (e.g., Samsung Galaxy Tab).

[0130] Example: A driver receives a notification for a delivery task from Shinjuku Station to Roppongi.

[0131] Execution and Monitoring

[0132] The server monitors the driver's real-time progress as he or she performs the task according to the instructions, and generates alerts and additional instructions based on progress reports from the driver's device.

[0133] Example: The server monitors in real time that the driver has picked up his luggage at Shinjuku Station and is heading to Roppongi.

[0134] In this way, this system can realize efficient labor allocation in the taxi and logistics industries, and solve the problems of driver shortages and surpluses. This system uses TensorFlow as a generative AI model, and examples of its prompts include the following:

[0135] "Predict the demand for taxis from Shinjuku Station to Roppongi for the next hour and allocate appropriate vehicles."

[0136] By inputting such prompt statements into the model, highly accurate demand forecasting and resource matching become possible.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1: Data collection

[0139] The server receives real-time vehicle location information from GPS devices. The input is location data provided by the GPS device (e.g., u-blox NEO-M8N). This data is collected at regular intervals and stored in a database. The output is a database entry for each vehicle's latest location.

[0140] Specific operation: Obtain the current location (latitude, longitude) of each vehicle every minute and update it in the "Vehicle Location Data" table.

[0141] The server retrieves historical trip data, delivery data, and event information from a database (e.g., MySQL). The input is historical database queries. This data is aggregated and formatted for demand forecasting. The output is a historical dataset that can be analyzed.

[0142] Specific operation: Extract taxi usage history data for the past month using an SQL query, aggregate it, and store it in the "Past Data" table.

[0143] The server retrieves current traffic situation data from traffic control systems and mapping services (e.g., Google Traffic API). The input is the API request. This data is retrieved in real time and stored for analysis. The output is a dataset of current traffic conditions.

[0144] Specific operation: Obtain the latest traffic congestion information from the traffic API every 5 minutes and store it in the "traffic condition data" table.

[0145] Step 2: Demand forecast

[0146] The server analyzes the collected historical and real-time data and executes a demand forecasting algorithm. The inputs are historical behavior data, current location information, and traffic condition data. A machine learning model (e.g., TensorFlow) is used to predict demand for the next time slot. The output is the demand forecast for the next time slot.

[0147] Specific operation: Using the TensorFlow model, predict taxi demand for the next hour based on data from the past month and current traffic data, and save it in the "Demand forecast data" table.

[0148] Step 3: Resource Matching

[0149] The server compares the predicted demand with the current vehicle location data to identify areas where there is a shortage of demand. The inputs are demand forecast data and current location information data. Based on this data, areas with a supply shortage are identified. The output is a list of areas with a supply shortage.

[0150] Specific operation: Compare the demand forecast results with current vehicle location information and list areas where supply is insufficient.

[0151] The server allocates available vehicles and drivers to the identified areas. The inputs are a list of areas with shortages and vehicle location data. Based on this data, the server selects the most suitable vehicles and drivers. The output is a list of allocated vehicles and drivers.

[0152] Specific operation: Select the vehicle closest to the shortage area and add that vehicle and driver to the "assignment data" table.

[0153] Step 4: Optimal Route and Task Allocation

[0154] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle. The inputs are the driver's current location, destination, and the latest traffic data. The optimal route is calculated using the Google Directions API. The output is the optimal route information.

[0155] Specific operation: Using the Google Directions API, calculate the optimal route from Shinjuku Station to Roppongi and save it in the "Route Information" table.

[0156] The server assigns specific tasks to each vehicle. The inputs are optimal route information and resource matching results. Based on these, tasks are generated and assigned to vehicles. The output is a task assignment list.

[0157] Specific behavior: Create a delivery task from Shinjuku Station to Roppongi and assign it to the appropriate taxi.

[0158] Step 5: Notification and Instructions

[0159] The terminal (driver) receives notification messages sent from the server and receives task and route instructions. The input is a notification message from the server. This notification is displayed on the terminal and conveyed to the driver reliably. The output is a notification confirmation to the driver.

[0160] Specific operation: A notification message is sent to the driver's device (e.g., smartphone), displaying the delivery task from Shinjuku Station to Roppongi and information about the optimal route.

[0161] Step 6: Running and monitoring

[0162] The server monitors in real time the process of the driver following instructions to carry out the task. The inputs include progress reports and location information from the driver. Based on this, the server monitors and manages the process, issuing alerts or additional instructions as necessary. The output is the progress monitoring results.

[0163] Specific operation: The system monitors the driver's journey from picking up the luggage to heading to Roppongi in real time, and provides instructions on an alternative route if traffic congestion occurs.

[0164] The above is the specific processing flow and operation at each step of this system. This series of steps achieves efficient and optimized resource allocation.

[0165] (Application example 1)

[0166] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0167] Conventional systems in the taxi and logistics fields have faced challenges such as inefficient vehicle and personnel allocation, low demand forecast accuracy, and difficulty in real-time management. These challenges are particularly evident in inventory management, inbound and outbound operations, and delivery preparation within logistics centers. This has led to problems such as reduced operational efficiency and delivery delays. The present invention aims to solve these challenges and achieve more efficient resource allocation and management.

[0168] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0169] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and workers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and workers, means for sending notifications and instructions to vehicles and workers, means for monitoring the progress of vehicles and workers in real time, means for managing inventory status, incoming and outgoing work, and delivery preparation within the logistics center, and means for sending notifications and instructions to staff and robots using smartphones, smart glasses, or robots, thereby enabling efficient allocation and real-time management of vehicles and personnel.

[0170] "Real-time location data" refers to data that is acquired and reflects the current location of vehicles and workers in real time.

[0171] "Demand forecast data" is data for predicting future demand based on past data and current conditions.

[0172] "Traffic condition data" is data that contains information about the current traffic conditions on the roads.

[0173] "Collecting means" refers to devices and methods for acquiring location data, demand forecast data, and traffic condition data.

[0174] The "means for analyzing and predicting demand in the next time period" refers to a method or system for calculating and predicting demand in the next time period using collected data.

[0175] "Means for identifying available vehicles and personnel" refers to a method or system for identifying and selecting currently available vehicles and personnel.

[0176] The "means for assigning optimal routes and tasks" refers to a method or system for instructing the specified vehicles and workers on efficient routes and tasks.

[0177] "Means for sending notifications and issuing instructions" refers to a method or system for transmitting necessary notifications and instructions to vehicles and workers.

[0178] "Means for monitoring progress in real time" refers to a method or system for monitoring task progress of vehicles and workers in real time.

[0179] "Means for managing inventory status, incoming and outgoing work, and delivery preparation within a logistics center" refers to methods and systems for supervising and adjusting inventory status, incoming and outgoing work, and delivery preparation work within a logistics center.

[0180] "Means for sending notifications and instructions using a smartphone, smart glasses, or robot" refers to a method or system for transmitting notifications and instructions to staff or robots via a smart device.

[0181] The present invention is a system for realizing efficient allocation of vehicles and personnel, and in particular, maximizes the work efficiency within a logistics center through real-time demand forecasting and resource management.

[0182] Overall system overview

[0183] This system mainly consists of the following six means:

[0184] 1. Data Collection Methods

[0185] 2. Demand forecasting methods

[0186] 3. Resource Identification Methods

[0187] 4. Task Allocation Method

[0188] 5. Notice and Instructions

[0189] 6. Monitoring Methods

[0190] Server-based data collection method

[0191] The server collects real-time location data, demand forecast data, and traffic data from hardware such as GPS devices, various sensors, and surveillance cameras in the distribution center. This data is then stored in a database.

[0192] Server-based demand forecasting method

[0193] The server analyzes the collected data and uses machine learning models to predict demand for the next time slot. The software used is a machine learning framework such as TensorFlow, which enables highly accurate demand forecasts.

[0194] Resource Identification Method

[0195] The server identifies available vehicles and crews based on predicted demand, matching real-time location data with each crew's schedule and status information.

[0196] Task Allocation Method

[0197] The server then assigns the optimal route and tasks to the identified vehicles and workers using the task allocation means. This process uses the Google Maps API to calculate the optimal route. Specifically, instructions are given taking into account the inventory status within the logistics center, incoming and outgoing work, and delivery preparations.

[0198] Notification and Instructions

[0199] Identified vehicles and workers are then notified and instructed via smartphone, smart glasses, or robot, allowing for quick and clear communication.

[0200] Monitoring Methods

[0201] Finally, the server monitors the progress of vehicles and workers in real time, reporting progress and instantly generating alerts and directing remedial action in the event of any deficiencies or problems.

[0202] Specific examples

[0203] Prompt Sentence Examples

[0204] "Please predict the inbound and outbound demand for Distribution Center A for the next two hours based on historical data, current inventory, weather, and traffic information."

[0205] Example

[0206] At a large logistics center, many delivery tasks are predicted between 3:00 PM and 5:00 PM. The system monitors the inventory status and staff locations in the warehouse in real time and predicts peak demand during this time period. Staff wearing smart glasses receive optimal routes and task instructions in real time, allowing them to work efficiently.

[0207] In this way, the present invention enables efficient allocation of vehicles and workers, greatly improving the operational efficiency of logistics centers.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] Data collection

[0211] The server collects real-time location data, demand forecast data, and traffic condition data. This data is obtained from GPS devices, various sensors in the distribution center, and surveillance cameras. Input data includes vehicle location information, inventory status, weather information, traffic information, etc. The server centrally manages this data and stores it in a database.

[0212] Step 2:

[0213] Demand forecasting

[0214] The server analyzes the collected historical and real-time data to predict demand for the next time slot. This process uses machine learning frameworks such as TensorFlow to train a generative AI model and execute a demand forecasting algorithm. Input data includes past ride data, shipping data, weather information, and traffic conditions, and outputs demand forecast data based on this.

[0215] Step 3:

[0216] Resource Identification

[0217] The server identifies available vehicles and workers based on predicted demand. It compares current location information with each worker's schedule and status information to determine which resources are available. It takes real-time location information and worker status information as input data and outputs available resources based on that information.

[0218] Step 4:

[0219] Task assignment

[0220] The server then assigns optimal routes and tasks to the identified vehicles and workers. In this step, it uses the Google Maps API to calculate optimal routes and generates instructions taking into account inventory status within the logistics center, inbound and outbound operations, and delivery preparations. Input data includes information on available vehicles and workers, and the results of optimal route calculations, and it outputs task assignment information based on this.

[0221] Step 5:

[0222] Notices and Instructions

[0223] The server then sends notifications and instructions to the identified vehicles and workers via smartphones, smart glasses, or robots. The server takes input data, such as assigned tasks and route information, and generates and sends notification messages based on them.

[0224] Step 6:

[0225] Progress monitoring

[0226] The server monitors the progress of vehicles and workers in real time. Work progress is reported in real time, and if any deficiencies or problems occur, an alert is immediately generated and countermeasures are instructed. The input data is real-time progress data, and based on that, progress reports and alert information are output.

[0227] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0228] This invention is a system that includes an emotion engine to efficiently allocate vehicles and personnel in the taxi and logistics industries. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them, and predicts demand for the next time slot. Furthermore, by recognizing the emotions of users (drivers and customers), the system monitors driver fatigue and stress, provides appropriate rest instructions, and optimizes taxi routes and services to improve customer satisfaction. It also evaluates the emotional state of logistics drivers and provides warnings and assistance to promote safe driving.

[0229] System Overview

[0230] 1. Data Collection

[0231] The server collects real-time information about the current location of taxis and trucks from GPS devices, past ride data, package delivery data, and event information from a database, real-time traffic conditions from traffic control systems and map services, and user emotion data using an emotion engine.

[0232] 2. Demand forecast

[0233] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[0234] 3. Resource Matching

[0235] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[0236] 4. Optimal Route and Task Allocation

[0237] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, determine whether the vehicle is delivering goods or transporting people, and assign specific tasks to each vehicle. It also optimizes routes and services by taking into account user sentiment data.

[0238] 5. Notices and Instructions

[0239] The terminal (driver) receives notification messages sent from the server and confirms task and route instructions.

[0240] 6. Execution and Monitoring

[0241] The server monitors in real time whether the driver is performing the task according to the instructions. The driver's device reports the progress, and if necessary, generates an alert and sends response instructions. Utilizing an emotion engine, the server monitors the driver's fatigue and stress state and instructs them to take appropriate breaks. Furthermore, it provides feedback to improve the quality of service based on the customer's emotional state.

[0242] Specific examples

[0243] Example: Transporting goods by taxi and using emotion engines

[0244] 1. Data Collection

[0245] The server collects real-time demand data for a given area and the location of waiting taxis, as well as driver sentiment data.

[0246] 2. Demand forecast

[0247] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[0248] 3. Resource Matching

[0249] The server checks the taxis waiting in area A and identifies vehicles suitable for delivering goods. It also evaluates the emotional state of the drivers and prioritizes drivers who are less tired.

[0250] 4. Optimal Route and Task Allocation

[0251] The server assigns the optimal route and delivery task to the taxi from area A to area B. At this time, it takes into account the driver's emotional data to select a safe and efficient route.

[0252] 5. Notices and Instructions

[0253] The terminal (driver) receives the notification message sent from the server and confirms the delivery task and route instructions.

[0254] 6. Execution and Monitoring

[0255] The server monitors in real time the process of the taxi driver receiving the item and delivering it to the designated area B. If the driver's emotional state deteriorates, it will give appropriate rest instructions.

[0256] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[0257] The processing flow will be explained below.

[0258] Step 1:

[0259] The server collects the current location of taxis and trucks in real time from GPS devices.

[0260] Step 2:

[0261] The server collects historical ride data, package delivery data, and event information from a database.

[0262] Step 3:

[0263] The server obtains real-time traffic data from traffic control systems and map services.

[0264] Step 4:

[0265] The server uses an emotion engine to collect emotion data of drivers and customers in real time.

[0266] Step 5:

[0267] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[0268] Step 6:

[0269] The server identifies available vehicles and drivers based on predicted demand.

[0270] Step 7:

[0271] The server evaluates the driver's fatigue and stress state and selects an appropriate driver.

[0272] Step 8:

[0273] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[0274] Step 9:

[0275] The server generates a notification message about the specified task and route and sends it to the driver's device.

[0276] Step 10:

[0277] The device (driver) receives the notification message and confirms the task and route instructions.

[0278] Step 11:

[0279] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[0280] Step 12:

[0281] The server monitors the driver and vehicle's progress in real time, generating alerts and sending response instructions as needed.

[0282] Step 13:

[0283] If the driver's emotional state deteriorates, the server will give appropriate rest instructions.

[0284] Step 14:

[0285] The server provides feedback to improve the quality of service based on the emotional state of the customer.

[0286] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[0287] Example 2

[0288] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0289] The taxi and logistics industries require efficient allocation of vehicles and personnel. Conventional technologies have difficulty in responding to real-time demand forecasts and fluctuations in traffic conditions, and driver fatigue and stress management are insufficient. As a result, service quality has declined, and improving customer satisfaction has become an issue. Furthermore, optimal resource matching is often not possible when transporting goods or people, resulting in a decline in overall efficiency.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0291] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and drivers based on the prediction, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for transmitting communication and issuing task instructions to the vehicles and drivers, means for monitoring the progress of the vehicles and drivers in real time, means for collecting and analyzing user emotions, and means for optimizing task instructions based on the emotion data to manage fatigue and improve service quality. This enables efficient allocation of vehicles and personnel and improves driver fatigue and stress management. Furthermore, it can increase customer satisfaction and improve the efficiency of transporting goods and people.

[0292] "Real-time location data" means data that uses a GPS device to instantly obtain and update the vehicle's precise current location.

[0293] "Demand forecast data" is data that predicts the demand for goods and people movement in the next time period based on past data and real-time data.

[0294] "Traffic condition data" refers to data that includes information related to traffic, such as road congestion, accident information, and travel speed.

[0295] "Means of collection" refers to a combination of hardware and software for acquiring various data.

[0296] "Analytical means" are algorithms and software for processing collected data and generating useful information or predictions.

[0297] "Means for identifying available vehicles and drivers" refers to a system for identifying currently available vehicles and drivers and assigning them to optimal positions and tasks.

[0298] The "means for allocating optimal routes and tasks" is a system that determines efficient and timely routes and instructs vehicles and drivers on appropriate tasks.

[0299] "Means for sending communications and providing operational instructions" means a messaging system for communicating operational and route instructions to vehicles and operators.

[0300] "Means for monitoring progress in real time" refers to a system that constantly checks the current location and status of the vehicle and driver and takes any necessary action.

[0301] The "means for collecting and analyzing user emotions" refers to hardware and software for acquiring and analyzing emotional information from the user's facial expressions, voice, etc.

[0302] "Means for optimizing work instructions based on emotional data and improving fatigue management and service quality" is a system that uses emotional information to provide appropriate work instructions and breaks, improving service quality.

[0303] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields. The system collects and analyzes real-time location data, demand forecast data, and traffic condition data to predict demand for the next time slot. It also collects and analyzes user emotion data to manage driver fatigue and improve service quality.

[0304] Data collection

[0305] The server collects real-time vehicle location information from GPS devices, such as Garmin and TomTom. It also collects past ride and package delivery data by querying a MySQL database. Traffic condition data is obtained using the Google Maps API. Furthermore, it uses Affectiva's SDK as an emotion engine to collect driver and customer sentiment data.

[0306] Demand forecasting

[0307] The server uses collected historical data and real-time data to analyze it using TensorFlow machine learning models (e.g., regression models), which predicts the demand for goods and people for the next time period, and stores the results in a MySQL database.

[0308] Resource Matching

[0309] The server compares predicted demand with real-time location data to identify areas where supply is insufficient. It then checks available vehicles and drivers and identifies the most suitable vehicle and driver. It also references emotional data to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[0310] Optimal Routes and Task Allocation

[0311] The server generates optimal routes using the Here Maps API, assigning efficient routes and tasks to each vehicle, whether delivering goods or transporting people, and selecting safe and efficient routes taking into account Affectiva's emotional data.

[0312] Notices and Instructions

[0313] The device (driver) receives notification messages from the server and checks the assigned tasks and routes. The driver's device has an ANDROID application installed, allowing them to receive real-time instructions and alerts.

[0314] Execution and Monitoring

[0315] The server monitors the driver's progress in real time as he or she follows instructions and performs the task. HTTP requests are used to report progress, and Twilio is used to generate SMS alerts and send response instructions as needed. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue and stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[0316] Specific examples

[0317] Transporting goods by taxi and using emotion engines

[0318] The server collects real-time demand data for a certain area and the location information of waiting taxis. It also collects driver emotional data. It predicts that demand for delivery of goods from area A to area B will increase over the next hour. It checks waiting taxis in area A and identifies vehicles suitable for delivering goods. It evaluates the emotional state of the drivers and prioritizes allocation to drivers who are less tired. It generates an optimal route from area A to area B using the Here Maps API and assigns delivery tasks. Drivers receive notifications from the server through an Android application and check the delivery task and route instructions. It monitors in real time the taxi drivers' ability to pick up goods and deliver them to the specified area B. Meanwhile, if the driver's emotional state deteriorates, appropriate rest instructions are sent via SMS using Twilio.

[0319] Prompt Sentence Examples

[0320] "We want to obtain location and sentiment data of taxi drivers and predict demand for the next hour. What algorithms and devices should we use?"

[0321] The system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality. It also utilizes emotional data to increase user satisfaction.

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

[0323] Step 1: Data collection

[0324] The server collects real-time vehicle location data (output) from GPS devices (input). Specifically, it communicates with Garmin and TomTom GPS devices to obtain location information. It also queries and collects past ride and package delivery data (output) from a MySQL database (input). It also uses Google Maps API to obtain traffic condition data (input) and stores this on the server (output). Additionally, it uses Affectiva's SDK as an emotion engine to collect driver and customer emotion data (input) (output).

[0325] Step 2: Demand forecast

[0326] The server uses TensorFlow to analyze the collected historical data and real-time data (input). This analysis is used to predict demand for the next time slot (output). Specifically, the data is analyzed using a machine learning model (regression model), and the results are stored in a MySQL database. This makes it possible to quantify the demand for goods and people movement in the next time slot.

[0327] Step 3: Resource Matching

[0328] The server compares predicted demand data (input) with real-time location data (input) to identify areas where supply is insufficient (output). It checks available vehicles and drivers and identifies the most suitable vehicle and driver (output). In this process, it references emotional data (input) to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[0329] Step 4: Optimal Route and Task Allocation

[0330] The server generates optimal routes (output) using the Here Maps API. Whether delivering goods or transporting people, it assigns efficient routes and tasks to each vehicle. It also considers Affectiva's emotion data (input) to select safe and efficient routes (output).

[0331] Step 5: Notification and Instructions

[0332] The device (driver) receives notification messages (input) sent from the server and checks the assigned tasks and routes (output). An Android application is installed on the driver's device, allowing it to receive real-time instructions and alerts. Specifically, an app with the function to receive and display notification messages is required.

[0333] Step 6: Running and monitoring

[0334] The server monitors in real time (input) the driver's process of completing tasks according to instructions (output). The driver reports their progress to the server through an Android application, which then sends an HTTP request to the server, which collects the progress data. If necessary, Twilio is used to generate an SMS alert and send instructions on how to respond. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue or stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[0335] Through these steps, the system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality.

[0336] (Application example 2)

[0337] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0338] In the modern taxi and logistics industry, efficient allocation of vehicles and personnel is required, but there is a lack of systems that take into account traffic conditions, fluctuations in demand, and staff fatigue and stress levels in real time. This can lead to a decline in service quality and safety issues. In addition, the inability to properly manage staff emotional states leads to a decline in work efficiency and customer satisfaction. A system to solve these issues is needed.

[0339] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0340] In this invention, the server includes means for collecting real-time GPS position data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time period, means for identifying available vehicles and staff based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and staff, means for sending notifications and giving instructions to the vehicles and staff, means for monitoring the progress of the vehicles and staff in real time, means for monitoring the emotional state of the staff and giving appropriate rest instructions, and means for providing feedback to improve service quality based on the emotional state. This enables efficient allocation of vehicles and staff, improving safety and service quality, and further improving staff work efficiency.

[0341] "Real-time GPS location data" is data used to obtain the current location of vehicles and staff in real time.

[0342] "Demand forecast data" is data used to predict future demand by analyzing collected past data and current conditions.

[0343] "Traffic condition data" refers to data including current traffic congestion and flow, accident information, and the like.

[0344] "Means of collection" refers to devices and systems for collecting various types of data.

[0345] "Means of analyzing and forecasting demand for the next time period" refers to algorithms and software that analyze collected data and forecast future demand.

[0346] "Means for identifying available vehicles and staff" refers to devices or systems for identifying available vehicles and staff from those currently in operation.

[0347] "Means for assigning optimal routes and tasks" refers to devices and systems for instructing identified vehicles and staff on the most efficient routes and tasks.

[0348] "Means for sending notifications and giving instructions" refers to devices and systems for sending notifications and giving instructions to vehicles and staff.

[0349] "Means for monitoring progress in real time" refers to devices and systems for monitoring the work progress of vehicles and staff in real time.

[0350] "Means for monitoring emotional state and issuing appropriate break instructions" refers to devices or systems for monitoring staff's emotional state and issuing break instructions as necessary.

[0351] "Means for providing feedback to improve service quality" refers to a device or system for providing feedback to staff to improve service quality based on data such as emotional state.

[0352] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields, and a specific implementation method thereof will be described below.

[0353] System configuration and data processing

[0354] This system uses the following hardware and software:

[0355] 1. Hardware:

[0356] Server: Cloud server, database server

[0357] Device: Smartphone (Android / iOS)

[0358] GPS device: Equipment installed in logistics vehicles

[0359] Sensors: devices to measure the emotional state of staff

[0360] 2. Software:

[0361] Emotion Recognition Engine: API

[0362] Machine learning model: Demand forecasting algorithm

[0363] Data collection and analysis

[0364] The server has a means for collecting real-time GPS location data, demand forecast data, and traffic condition data, and then predicts demand for the next time period based on the collected data.

[0365] The terminal (smartphone) receives GPS signals from logistics vehicles to collect current location data and uses sensors to acquire staff emotion data. The server analyzes this data and runs an algorithm to predict future demand.

[0366] Optimal allocation of resources

[0367] The server identifies available vehicles and staff based on predicted demand, assigns optimal routes and tasks, and then sends notifications and instructions to vehicles and staff.

[0368] For example, if a logistics center predicts an increase in shipping demand over the next hour, the server will identify waiting vehicles and less fatigued staff and assign appropriate delivery routes and tasks to each.

[0369] Execution and Monitoring

[0370] The server monitors the progress of vehicles and staff in real time, and also uses an emotion recognition engine to monitor the emotional state of staff and give appropriate break instructions when necessary.

[0371] For example, if Driver A's emotional state is deteriorating and fatigue is building up, the server can instruct him / her to:

[0372] "Judging from your current emotional state, fatigue is building up. If you continue driving, the risk of an accident increases. Please take a 20-minute break at the nearest rest stop."

[0373] Furthermore, based on the emotional state, feedback is provided to improve the quality of service, which allows for more efficient allocation of vehicles and personnel, improving safety, service quality, and staff efficiency.

[0374] Examples of prompt statements

[0375] For example, a prompt for a generative AI model might be entered in the following format:

[0376] "Enter a few lines of Japanese text. Generate a message instructing Driver A to take an appropriate break if he is experiencing a worsening emotional state and fatigue."

[0377] (Example input)

[0378] After monitoring Driver A's emotional state, it was determined that he was highly fatigued. The vehicle's current location was obtained from the location information system, and the next rest stop was approximately 5 km away.

[0379] (Example output)

[0380] Driver A, you are currently very tired, so we recommend that you take a 20-minute break at the rest area 5 km ahead. Refreshing yourself is important for safe driving.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1: Data collection

[0383] The server collects GPS location data of logistics vehicles, historical logistics data, real-time traffic condition data, and staff sentiment data.

[0384] Input: Location data from GPS devices, historical database information, traffic API data, emotion recognition engine data

[0385] Output: All collected data

[0386] Specific operation: The server acquires data from each data source and stores it in the integrated database.

[0387] Step 2: Demand forecast

[0388] The server analyzes the collected data and predicts demand for the next time period, using machine learning models to forecast future demand patterns.

[0389] Input: Collected data

[0390] Output: Demand forecast model and forecast results for the next time period

[0391] Specific operation: The server inputs the collected data into a machine learning model and executes a demand forecasting algorithm.

[0392] Step 3: Identify available resources

[0393] The server checks the location and status of vehicles and staff currently in operation and identifies available resources.

[0394] Inputs: Demand forecast results, real-time GPS location data, staff sentiment data

[0395] Output: List of available vehicles and staff

[0396] What it does: The server compares predicted demand with real-time data to identify the best vehicles and staff.

[0397] Step 4: Route and task assignment

[0398] The server assigns optimal routes and tasks, sends notifications to vehicles and staff, and takes emotional data into account to provide safe and efficient instructions.

[0399] Input: list of available vehicles and staff, traffic data

[0400] Output: Optimal route and task instructions for each vehicle and crew member

[0401] Specific operation: The server executes a route calculation algorithm based on the collected data and notifies the user (staff member) of specific instructions.

[0402] Step 5: Running and monitoring

[0403] The server monitors the task execution status of vehicles and staff in real time, checking their emotional state as needed and issuing break instructions as necessary.

[0404] Input: Real-time GPS location data, emotion data

[0405] Output: Task execution status monitoring results, break instructions

[0406] Specific operation: The server tracks the progress of vehicles and staff in real time, notifies and instructs in case of abnormalities, and instructs staff to take breaks based on data provided by the emotion recognition engine.

[0407] Step 6: Provide feedback

[0408] The server evaluates the emotional state and work performance of the staff and provides feedback to improve the quality of service.

[0409] Input: Task execution status monitoring results, emotion data

[0410] Output: Feedback report

[0411] Specific Actions: The server analyzes the collected data and provides specific improvements and recommendations to staff.

[0412] The above are the specific processing steps of this system.

[0413] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0414] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0415] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0416] [Second embodiment]

[0417] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0418] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0419] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0420] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0421] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0422] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0423] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0424] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0425] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0426] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0427] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0428] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0429] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[0430] System Overview

[0431] 1. Data Collection

[0432] The server collects real-time information on the current location of taxis and trucks from GPS devices, as well as past ride data, package delivery data, and event information, and statistically processes it. It also obtains real-time traffic information from traffic control systems and map services.

[0433] 2. Demand forecast

[0434] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[0435] 3. Resource Matching

[0436] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[0437] 4. Optimal Route and Task Allocation

[0438] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, and also decides whether the vehicle is delivering goods or transporting people, and assigns each vehicle a specific task.

[0439] 5. Notices and Instructions

[0440] The terminal (driver) receives notification messages sent from the server and receives task and route instructions.

[0441] 6. Execution and Monitoring

[0442] The server monitors in real time whether the driver is following instructions and performing the task, and generates alerts as needed, providing instructions on appropriate countermeasures based on progress reports from the driver's device.

[0443] Specific examples

[0444] Example: Transporting goods by taxi

[0445] 1. Data Collection

[0446] The server collects real-time demand data for a region and the location of waiting taxis.

[0447] 2. Demand forecast

[0448] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[0449] 3. Resource Matching

[0450] The server checks the waiting taxis in area A and identifies a vehicle suitable for delivering the goods.

[0451] 4. Optimal Route and Task Allocation

[0452] The server assigns the optimal route from area A to area B and a delivery task to the taxi.

[0453] 5. Notices and Instructions

[0454] The terminal (driver) receives notification messages sent from the server and receives delivery tasks and route instructions.

[0455] 6. Execution and Monitoring

[0456] The server monitors the process in real time as the taxi driver picks up the item and delivers it to the specified area B.

[0457] As described above, the present invention can realize efficient allocation of labor in the taxi and logistics industries, and solve problems such as driver shortages and surpluses.

[0458] The processing flow will be explained below.

[0459] Step 1:

[0460] The server collects the current location of taxis and trucks in real time from GPS devices.

[0461] Step 2:

[0462] The server collects historical ride data, package delivery data, and event information from a database.

[0463] Step 3:

[0464] The server obtains real-time traffic data from traffic control systems and map services.

[0465] Step 4:

[0466] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[0467] Step 5:

[0468] The server identifies available vehicles and drivers based on the demand forecast.

[0469] Step 6:

[0470] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[0471] Step 7:

[0472] The server generates notification messages about the assigned tasks and routes and sends them to the driver's terminal.

[0473] Step 8:

[0474] The device (driver) receives the notification message and confirms the task and route instructions.

[0475] Step 9:

[0476] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[0477] Step 10:

[0478] The server monitors the driver's progress in real time, generating alerts and sending response instructions as needed.

[0479] As described above, the system of the present invention can realize efficient allocation of labor in the taxi and logistics fields, and solve the problems of driver shortages and labor surpluses.

[0480] Example 1

[0481] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0482] Efficient allocation of vehicles and personnel is a challenge in the taxi and logistics sectors. Currently, it is difficult to quickly and appropriately reallocate waiting vehicles and driver resources, resulting in frequent mismatches between supply and demand. This reduces driver work efficiency and reduces user satisfaction. Furthermore, a lack of real-time monitoring and optimal route instructions makes traffic congestion and operational delays more likely to occur. Therefore, a system that can solve these issues is needed.

[0483] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0484] In this invention, the server includes means for collecting real-time location information, means for collecting past behavior data and current traffic condition data, means for analyzing the collected data and predicting demand for the next time slot, means for identifying available vehicles and drivers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for sending notifications and instructions to the vehicles and drivers, and means for monitoring the progress of the drivers in real time. This allows for appropriate and efficient allocation of vehicle and driver resources, eliminating mismatches between supply and demand, and enabling improved business efficiency and customer satisfaction.

[0485] "Real-time location information" is data that indicates the specific location of a vehicle or driver at the current time.

[0486] "Past behavior data" is information that records the past behavior history of a vehicle and a driver.

[0487] "Current traffic condition data" refers to data that includes current traffic flow and congestion information in a specific area.

[0488] "Demand forecasting" is the process of calculating traffic demand for a specific time period in the future based on past data and current conditions.

[0489] "Available vehicles and drivers" refers to vehicles and drivers that are currently in operation or on standby and immediately available for work.

[0490] An "optimal route" is a route that takes into account time, distance, traffic conditions, and other factors to reach a destination in the most efficient manner.

[0491] "Task" means a specific task or instruction given to a vehicle and driver.

[0492] A "notification" is a message conveying instructions or information that is sent by the server to a vehicle or driver.

[0493] "Progress" is information indicating how far the vehicle and driver have progressed in completing the specified task.

[0494] "Real-time monitoring" is the process of constantly knowing the current status of the vehicle and driver.

[0495] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[0496] System Overview

[0497] Data collection

[0498] The server obtains real-time location information from the GPS devices installed in each vehicle. The hardware used for this is a GPS module such as the u-blox NEO-M8N. It also obtains past ride and delivery data from a database such as MySQL. Traffic condition data is obtained in real time from the Google Traffic API, for example.

[0499] Example: The server collects the current location information of taxis in the Tokyo area, ride data around Shinjuku Station for the past month, and current traffic situation data around Shinjuku Station.

[0500] Demand forecasting

[0501] The server analyzes the collected data and runs a demand forecasting algorithm using machine learning models such as TensorFlow. The analysis results are stored in a database such as PostgreSQL.

[0502] Example: Based on data from the past month, the server predicts that there will be an increase in demand for taxis from Shinjuku Station to Roppongi in the next hour.

[0503] Resource Matching

[0504] The server compares the predicted demand with current vehicle location data to identify areas where demand is lacking, then checks available vehicles and drivers and selects the most suitable vehicle and driver.

[0505] Example: The server checks for taxis waiting around Shinjuku Station and identifies the vehicle that is suitable for delivering an item.

[0506] Optimal Routes and Task Allocation

[0507] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle, using the Google Directions API, and assigns specific tasks to each vehicle.

[0508] Example: The server calculates the optimal route for a taxi from Shinjuku Station to Roppongi and assigns a delivery task.

[0509] Notices and Instructions

[0510] The device (driver) receives notification messages sent from the server and receives task and route instructions. The driver checks the notifications on a smartphone or tablet (e.g., Samsung Galaxy Tab).

[0511] Example: A driver receives a notification for a delivery task from Shinjuku Station to Roppongi.

[0512] Execution and Monitoring

[0513] The server monitors the driver's real-time progress as he or she performs the task according to the instructions, and generates alerts and additional instructions based on progress reports from the driver's device.

[0514] Example: The server monitors in real time that the driver has picked up his luggage at Shinjuku Station and is heading to Roppongi.

[0515] In this way, this system can realize efficient labor allocation in the taxi and logistics industries, and solve the problems of driver shortages and surpluses. This system uses TensorFlow as a generative AI model, and examples of its prompts include the following:

[0516] "Predict the demand for taxis from Shinjuku Station to Roppongi for the next hour and allocate appropriate vehicles."

[0517] By inputting such prompt statements into the model, highly accurate demand forecasting and resource matching become possible.

[0518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0519] Step 1: Data collection

[0520] The server receives real-time vehicle location information from GPS devices. The input is location data provided by the GPS device (e.g., u-blox NEO-M8N). This data is collected at regular intervals and stored in a database. The output is a database entry for each vehicle's latest location.

[0521] Specific operation: Obtain the current location (latitude, longitude) of each vehicle every minute and update it in the "Vehicle Location Data" table.

[0522] The server retrieves historical trip data, delivery data, and event information from a database (e.g., MySQL). The input is historical database queries. This data is aggregated and formatted for demand forecasting. The output is a historical dataset that can be analyzed.

[0523] Specific operation: Extract taxi usage history data for the past month using an SQL query, aggregate it, and store it in the "Past Data" table.

[0524] The server retrieves current traffic situation data from traffic control systems and mapping services (e.g., Google Traffic API). The input is the API request. This data is retrieved in real time and stored for analysis. The output is a dataset of current traffic conditions.

[0525] Specific operation: Obtain the latest traffic congestion information from the traffic API every 5 minutes and store it in the "traffic condition data" table.

[0526] Step 2: Demand forecast

[0527] The server analyzes the collected historical and real-time data and executes a demand forecasting algorithm. The inputs are historical behavior data, current location information, and traffic condition data. A machine learning model (e.g., TensorFlow) is used to predict demand for the next time slot. The output is the demand forecast for the next time slot.

[0528] Specific operation: Using the TensorFlow model, predict taxi demand for the next hour based on data from the past month and current traffic data, and save it in the "Demand forecast data" table.

[0529] Step 3: Resource Matching

[0530] The server compares the predicted demand with the current vehicle location data to identify areas where there is a shortage of demand. The inputs are demand forecast data and current location information data. Based on this data, areas with a supply shortage are identified. The output is a list of areas with a supply shortage.

[0531] Specific operation: Compare the demand forecast results with current vehicle location information and list areas where supply is insufficient.

[0532] The server allocates available vehicles and drivers to the identified areas. The inputs are a list of areas with shortages and vehicle location data. Based on this data, the server selects the most suitable vehicles and drivers. The output is a list of allocated vehicles and drivers.

[0533] Specific operation: Select the vehicle closest to the shortage area and add that vehicle and driver to the "assignment data" table.

[0534] Step 4: Optimal Route and Task Allocation

[0535] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle. The inputs are the driver's current location, destination, and the latest traffic data. The optimal route is calculated using the Google Directions API. The output is the optimal route information.

[0536] Specific operation: Using the Google Directions API, calculate the optimal route from Shinjuku Station to Roppongi and save it in the "Route Information" table.

[0537] The server assigns specific tasks to each vehicle. The inputs are optimal route information and resource matching results. Based on these, tasks are generated and assigned to vehicles. The output is a task assignment list.

[0538] Specific behavior: Create a delivery task from Shinjuku Station to Roppongi and assign it to the appropriate taxi.

[0539] Step 5: Notification and Instructions

[0540] The terminal (driver) receives notification messages sent from the server and receives task and route instructions. The input is a notification message from the server. This notification is displayed on the terminal and conveyed to the driver reliably. The output is a notification confirmation to the driver.

[0541] Specific operation: A notification message is sent to the driver's device (e.g., smartphone), displaying the delivery task from Shinjuku Station to Roppongi and information about the optimal route.

[0542] Step 6: Running and monitoring

[0543] The server monitors in real time the process of the driver following instructions to carry out the task. The inputs include progress reports and location information from the driver. Based on this, the server monitors and manages the process, issuing alerts or additional instructions as necessary. The output is the progress monitoring results.

[0544] Specific operation: The system monitors the driver's journey from picking up the luggage to heading to Roppongi in real time, and provides instructions on an alternative route if traffic congestion occurs.

[0545] The above is the specific processing flow and operation at each step of this system. This series of steps achieves efficient and optimized resource allocation.

[0546] (Application example 1)

[0547] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0548] Conventional systems in the taxi and logistics fields have faced challenges such as inefficient vehicle and personnel allocation, low demand forecast accuracy, and difficulty in real-time management. These challenges are particularly evident in inventory management, inbound and outbound operations, and delivery preparation within logistics centers. This has led to problems such as reduced operational efficiency and delivery delays. The present invention aims to solve these challenges and achieve more efficient resource allocation and management.

[0549] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0550] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and workers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and workers, means for sending notifications and instructions to vehicles and workers, means for monitoring the progress of vehicles and workers in real time, means for managing inventory status, incoming and outgoing work, and delivery preparation within the logistics center, and means for sending notifications and instructions to staff and robots using smartphones, smart glasses, or robots, thereby enabling efficient allocation and real-time management of vehicles and personnel.

[0551] "Real-time location data" refers to data that is acquired and reflects the current location of vehicles and workers in real time.

[0552] "Demand forecast data" is data for predicting future demand based on past data and current conditions.

[0553] "Traffic condition data" is data that contains information about the current traffic conditions on the roads.

[0554] "Collecting means" refers to devices and methods for acquiring location data, demand forecast data, and traffic condition data.

[0555] The "means for analyzing and predicting demand in the next time period" refers to a method or system for calculating and predicting demand in the next time period using collected data.

[0556] "Means for identifying available vehicles and personnel" refers to a method or system for identifying and selecting currently available vehicles and personnel.

[0557] The "means for assigning optimal routes and tasks" refers to a method or system for instructing the specified vehicles and workers on efficient routes and tasks.

[0558] "Means for sending notifications and issuing instructions" refers to a method or system for transmitting necessary notifications and instructions to vehicles and workers.

[0559] "Means for monitoring progress in real time" refers to a method or system for monitoring task progress of vehicles and workers in real time.

[0560] "Means for managing inventory status, incoming and outgoing work, and delivery preparation within a logistics center" refers to methods and systems for supervising and adjusting inventory status, incoming and outgoing work, and delivery preparation work within a logistics center.

[0561] "Means for sending notifications and instructions using a smartphone, smart glasses, or robot" refers to a method or system for transmitting notifications and instructions to staff or robots via a smart device.

[0562] The present invention is a system for realizing efficient allocation of vehicles and personnel, and in particular, maximizes the work efficiency within a logistics center through real-time demand forecasting and resource management.

[0563] Overall system overview

[0564] This system mainly consists of the following six means:

[0565] 1. Data Collection Methods

[0566] 2. Demand forecasting methods

[0567] 3. Resource Identification Methods

[0568] 4. Task Allocation Method

[0569] 5. Notice and Instructions

[0570] 6. Monitoring Methods

[0571] Server-based data collection method

[0572] The server collects real-time location data, demand forecast data, and traffic data from hardware such as GPS devices, various sensors, and surveillance cameras in the distribution center. This data is then stored in a database.

[0573] Server-based demand forecasting method

[0574] The server analyzes the collected data and uses machine learning models to predict demand for the next time slot. The software used is a machine learning framework such as TensorFlow, which enables highly accurate demand forecasts.

[0575] Resource Identification Method

[0576] The server identifies available vehicles and crews based on predicted demand, matching real-time location data with each crew's schedule and status information.

[0577] Task Allocation Method

[0578] The server then assigns the optimal route and tasks to the identified vehicles and workers using the task allocation means. This process uses the Google Maps API to calculate the optimal route. Specifically, instructions are given taking into account the inventory status within the logistics center, incoming and outgoing work, and delivery preparations.

[0579] Notification and Instructions

[0580] Identified vehicles and workers are then notified and instructed via smartphone, smart glasses, or robot, allowing for quick and clear communication.

[0581] Monitoring Methods

[0582] Finally, the server monitors the progress of vehicles and workers in real time, reporting progress and instantly generating alerts and directing remedial action in the event of any deficiencies or problems.

[0583] Specific examples

[0584] Prompt Sentence Examples

[0585] "Please predict the inbound and outbound demand for Distribution Center A for the next two hours based on historical data, current inventory, weather, and traffic information."

[0586] Example

[0587] At a large logistics center, many delivery tasks are predicted between 3:00 PM and 5:00 PM. The system monitors the inventory status and staff locations in the warehouse in real time and predicts peak demand during this time period. Staff wearing smart glasses receive optimal routes and task instructions in real time, allowing them to work efficiently.

[0588] In this way, the present invention enables efficient allocation of vehicles and workers, greatly improving the operational efficiency of logistics centers.

[0589] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0590] Step 1:

[0591] Data collection

[0592] The server collects real-time location data, demand forecast data, and traffic condition data. This data is obtained from GPS devices, various sensors in the distribution center, and surveillance cameras. Input data includes vehicle location information, inventory status, weather information, traffic information, etc. The server centrally manages this data and stores it in a database.

[0593] Step 2:

[0594] Demand forecasting

[0595] The server analyzes the collected historical and real-time data to predict demand for the next time slot. This process uses machine learning frameworks such as TensorFlow to train a generative AI model and execute a demand forecasting algorithm. Input data includes past ride data, shipping data, weather information, and traffic conditions, and outputs demand forecast data based on this.

[0596] Step 3:

[0597] Resource Identification

[0598] The server identifies available vehicles and workers based on predicted demand. It compares current location information with each worker's schedule and status information to determine which resources are available. It takes real-time location information and worker status information as input data and outputs available resources based on that information.

[0599] Step 4:

[0600] Task assignment

[0601] The server then assigns optimal routes and tasks to the identified vehicles and workers. In this step, it uses the Google Maps API to calculate optimal routes and generates instructions taking into account inventory status within the logistics center, inbound and outbound operations, and delivery preparations. Input data includes information on available vehicles and workers, and the results of optimal route calculations, and it outputs task assignment information based on this.

[0602] Step 5:

[0603] Notices and Instructions

[0604] The server then sends notifications and instructions to the identified vehicles and workers via smartphones, smart glasses, or robots. The server takes input data, such as assigned tasks and route information, and generates and sends notification messages based on them.

[0605] Step 6:

[0606] Progress monitoring

[0607] The server monitors the progress of vehicles and workers in real time. Work progress is reported in real time, and if any deficiencies or problems occur, an alert is immediately generated and countermeasures are instructed. The input data is real-time progress data, and based on that, progress reports and alert information are output.

[0608] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0609] This invention is a system that includes an emotion engine to efficiently allocate vehicles and personnel in the taxi and logistics industries. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them, and predicts demand for the next time slot. Furthermore, by recognizing the emotions of users (drivers and customers), the system monitors driver fatigue and stress, provides appropriate rest instructions, and optimizes taxi routes and services to improve customer satisfaction. It also evaluates the emotional state of logistics drivers and provides warnings and assistance to promote safe driving.

[0610] System Overview

[0611] 1. Data Collection

[0612] The server collects real-time information about the current location of taxis and trucks from GPS devices, past ride data, package delivery data, and event information from a database, real-time traffic conditions from traffic control systems and map services, and user emotion data using an emotion engine.

[0613] 2. Demand forecast

[0614] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[0615] 3. Resource Matching

[0616] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[0617] 4. Optimal Route and Task Allocation

[0618] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, determine whether the vehicle is delivering goods or transporting people, and assign specific tasks to each vehicle. It also optimizes routes and services by taking into account user sentiment data.

[0619] 5. Notices and Instructions

[0620] The terminal (driver) receives notification messages sent from the server and confirms task and route instructions.

[0621] 6. Execution and Monitoring

[0622] The server monitors in real time whether the driver is performing the task according to the instructions. The driver's device reports the progress, and if necessary, generates an alert and sends response instructions. Utilizing an emotion engine, the server monitors the driver's fatigue and stress state and instructs them to take appropriate breaks. Furthermore, it provides feedback to improve the quality of service based on the customer's emotional state.

[0623] Specific examples

[0624] Example: Transporting goods by taxi and using emotion engines

[0625] 1. Data Collection

[0626] The server collects real-time demand data for a given area and the location of waiting taxis, as well as driver sentiment data.

[0627] 2. Demand forecast

[0628] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[0629] 3. Resource Matching

[0630] The server checks the taxis waiting in area A and identifies vehicles suitable for delivering goods. It also evaluates the emotional state of the drivers and prioritizes drivers who are less tired.

[0631] 4. Optimal Route and Task Allocation

[0632] The server assigns the optimal route and delivery task to the taxi from area A to area B. At this time, it takes into account the driver's emotional data to select a safe and efficient route.

[0633] 5. Notices and Instructions

[0634] The terminal (driver) receives the notification message sent from the server and confirms the delivery task and route instructions.

[0635] 6. Execution and Monitoring

[0636] The server monitors in real time the process of the taxi driver receiving the item and delivering it to the designated area B. If the driver's emotional state deteriorates, it will give appropriate rest instructions.

[0637] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[0638] The processing flow will be explained below.

[0639] Step 1:

[0640] The server collects the current location of taxis and trucks in real time from GPS devices.

[0641] Step 2:

[0642] The server collects historical ride data, package delivery data, and event information from a database.

[0643] Step 3:

[0644] The server obtains real-time traffic data from traffic control systems and map services.

[0645] Step 4:

[0646] The server uses an emotion engine to collect emotion data of drivers and customers in real time.

[0647] Step 5:

[0648] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[0649] Step 6:

[0650] The server identifies available vehicles and drivers based on predicted demand.

[0651] Step 7:

[0652] The server evaluates the driver's fatigue and stress state and selects an appropriate driver.

[0653] Step 8:

[0654] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[0655] Step 9:

[0656] The server generates a notification message about the specified task and route and sends it to the driver's device.

[0657] Step 10:

[0658] The device (driver) receives the notification message and confirms the task and route instructions.

[0659] Step 11:

[0660] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[0661] Step 12:

[0662] The server monitors the driver and vehicle's progress in real time, generating alerts and sending response instructions as needed.

[0663] Step 13:

[0664] If the driver's emotional state deteriorates, the server will give appropriate rest instructions.

[0665] Step 14:

[0666] The server provides feedback to improve the quality of service based on the emotional state of the customer.

[0667] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[0668] Example 2

[0669] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0670] The taxi and logistics industries require efficient allocation of vehicles and personnel. Conventional technologies have difficulty in responding to real-time demand forecasts and fluctuations in traffic conditions, and driver fatigue and stress management are insufficient. As a result, service quality has declined, and improving customer satisfaction has become an issue. Furthermore, optimal resource matching is often not possible when transporting goods or people, resulting in a decline in overall efficiency.

[0671] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0672] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and drivers based on the prediction, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for transmitting communication and issuing task instructions to the vehicles and drivers, means for monitoring the progress of the vehicles and drivers in real time, means for collecting and analyzing user emotions, and means for optimizing task instructions based on the emotion data to manage fatigue and improve service quality. This enables efficient allocation of vehicles and personnel and improves driver fatigue and stress management. Furthermore, it can increase customer satisfaction and improve the efficiency of transporting goods and people.

[0673] "Real-time location data" means data that uses a GPS device to instantly obtain and update the vehicle's precise current location.

[0674] "Demand forecast data" is data that predicts the demand for goods and people movement in the next time period based on past data and real-time data.

[0675] "Traffic condition data" refers to data that includes information related to traffic, such as road congestion, accident information, and travel speed.

[0676] "Means of collection" refers to a combination of hardware and software for acquiring various data.

[0677] "Analytical means" are algorithms and software for processing collected data and generating useful information or predictions.

[0678] "Means for identifying available vehicles and drivers" refers to a system for identifying currently available vehicles and drivers and assigning them to optimal positions and tasks.

[0679] The "means for allocating optimal routes and tasks" is a system that determines efficient and timely routes and instructs vehicles and drivers on appropriate tasks.

[0680] "Means for sending communications and providing operational instructions" means a messaging system for communicating operational and route instructions to vehicles and operators.

[0681] "Means for monitoring progress in real time" refers to a system that constantly checks the current location and status of the vehicle and driver and takes any necessary action.

[0682] The "means for collecting and analyzing user emotions" refers to hardware and software for acquiring and analyzing emotional information from the user's facial expressions, voice, etc.

[0683] "Means for optimizing work instructions based on emotional data and improving fatigue management and service quality" is a system that uses emotional information to provide appropriate work instructions and breaks, improving service quality.

[0684] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields. The system collects and analyzes real-time location data, demand forecast data, and traffic condition data to predict demand for the next time slot. It also collects and analyzes user emotion data to manage driver fatigue and improve service quality.

[0685] Data collection

[0686] The server collects real-time vehicle location information from GPS devices, such as Garmin and TomTom. It also collects past ride and package delivery data by querying a MySQL database. Traffic condition data is obtained using the Google Maps API. Furthermore, it uses Affectiva's SDK as an emotion engine to collect driver and customer sentiment data.

[0687] Demand forecasting

[0688] The server uses collected historical data and real-time data to analyze it using TensorFlow machine learning models (e.g., regression models), which predicts the demand for goods and people for the next time period, and stores the results in a MySQL database.

[0689] Resource Matching

[0690] The server compares predicted demand with real-time location data to identify areas where supply is insufficient. It then checks available vehicles and drivers and identifies the most suitable vehicle and driver. It also references emotional data to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[0691] Optimal Routes and Task Allocation

[0692] The server generates optimal routes using the Here Maps API, assigning efficient routes and tasks to each vehicle, whether delivering goods or transporting people, and selecting safe and efficient routes taking into account Affectiva's emotional data.

[0693] Notices and Instructions

[0694] The device (driver) receives notification messages from the server and confirms the assigned tasks and routes. The driver's device has an Android application installed, allowing them to receive real-time instructions and alerts.

[0695] Execution and Monitoring

[0696] The server monitors the driver's progress in real time as he or she follows instructions and performs the task. HTTP requests are used to report progress, and Twilio is used to generate SMS alerts and send response instructions as needed. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue and stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[0697] Specific examples

[0698] Transporting goods by taxi and using emotion engines

[0699] The server collects real-time demand data for a certain area and the location information of waiting taxis. It also collects driver emotional data. It predicts that demand for delivery of goods from area A to area B will increase over the next hour. It checks waiting taxis in area A and identifies vehicles suitable for delivering goods. It evaluates the emotional state of the drivers and prioritizes allocation to drivers who are less tired. It generates an optimal route from area A to area B using the Here Maps API and assigns delivery tasks. Drivers receive notifications from the server through an Android application and check the delivery task and route instructions. It monitors in real time the taxi drivers' ability to pick up goods and deliver them to the specified area B. Meanwhile, if the driver's emotional state deteriorates, appropriate rest instructions are sent via SMS using Twilio.

[0700] Prompt Sentence Examples

[0701] "We want to obtain location and sentiment data of taxi drivers and predict demand for the next hour. What algorithms and devices should we use?"

[0702] The system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality. It also utilizes emotional data to increase user satisfaction.

[0703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0704] Step 1: Data collection

[0705] The server collects real-time vehicle location data (output) from GPS devices (input). Specifically, it communicates with Garmin and TomTom GPS devices to obtain location information. It also queries and collects past ride and package delivery data (output) from a MySQL database (input). It also uses Google Maps API to obtain traffic condition data (input) and stores this on the server (output). Additionally, it uses Affectiva's SDK as an emotion engine to collect driver and customer emotion data (input) (output).

[0706] Step 2: Demand forecast

[0707] The server uses TensorFlow to analyze the collected historical data and real-time data (input). This analysis is used to predict demand for the next time slot (output). Specifically, the data is analyzed using a machine learning model (regression model), and the results are stored in a MySQL database. This makes it possible to quantify the demand for goods and people movement in the next time slot.

[0708] Step 3: Resource Matching

[0709] The server compares predicted demand data (input) with real-time location data (input) to identify areas where supply is insufficient (output). It checks available vehicles and drivers and identifies the most suitable vehicle and driver (output). In this process, it references emotional data (input) to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[0710] Step 4: Optimal Route and Task Allocation

[0711] The server generates optimal routes (output) using the Here Maps API. Whether delivering goods or transporting people, it assigns efficient routes and tasks to each vehicle. It also considers Affectiva's emotion data (input) to select safe and efficient routes (output).

[0712] Step 5: Notification and Instructions

[0713] The device (driver) receives notification messages (input) sent from the server and checks the assigned tasks and routes (output). An Android application is installed on the driver's device, allowing it to receive real-time instructions and alerts. Specifically, an app with the function to receive and display notification messages is required.

[0714] Step 6: Running and monitoring

[0715] The server monitors in real time (input) the driver's process of completing tasks according to instructions (output). The driver reports their progress to the server through an Android application, which then sends an HTTP request to the server, which collects the progress data. If necessary, Twilio is used to generate an SMS alert and send instructions on how to respond. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue or stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[0716] Through these steps, the system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality.

[0717] (Application example 2)

[0718] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0719] In the modern taxi and logistics industry, efficient allocation of vehicles and personnel is required, but there is a lack of systems that take into account traffic conditions, fluctuations in demand, and staff fatigue and stress levels in real time. This can lead to a decline in service quality and safety issues. In addition, the inability to properly manage staff emotional states leads to a decline in work efficiency and customer satisfaction. A system to solve these issues is needed.

[0720] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0721] In this invention, the server includes means for collecting real-time GPS position data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time period, means for identifying available vehicles and staff based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and staff, means for sending notifications and giving instructions to the vehicles and staff, means for monitoring the progress of the vehicles and staff in real time, means for monitoring the emotional state of the staff and giving appropriate rest instructions, and means for providing feedback to improve service quality based on the emotional state. This enables efficient allocation of vehicles and staff, improving safety and service quality, and further improving staff work efficiency.

[0722] "Real-time GPS location data" is data used to obtain the current location of vehicles and staff in real time.

[0723] "Demand forecast data" is data used to predict future demand by analyzing collected past data and current conditions.

[0724] "Traffic condition data" refers to data including current traffic congestion and flow, accident information, and the like.

[0725] "Means of collection" refers to devices and systems for collecting various types of data.

[0726] "Means of analyzing and forecasting demand for the next time period" refers to algorithms and software that analyze collected data and forecast future demand.

[0727] "Means for identifying available vehicles and staff" refers to devices or systems for identifying available vehicles and staff from those currently in operation.

[0728] "Means for assigning optimal routes and tasks" refers to devices and systems for instructing identified vehicles and staff on the most efficient routes and tasks.

[0729] "Means for sending notifications and giving instructions" refers to devices and systems for sending notifications and giving instructions to vehicles and staff.

[0730] "Means for monitoring progress in real time" refers to devices and systems for monitoring the work progress of vehicles and staff in real time.

[0731] "Means for monitoring emotional state and issuing appropriate break instructions" refers to devices or systems for monitoring staff's emotional state and issuing break instructions as necessary.

[0732] "Means for providing feedback to improve service quality" refers to a device or system for providing feedback to staff to improve service quality based on data such as emotional state.

[0733] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields, and a specific implementation method thereof will be described below.

[0734] System configuration and data processing

[0735] This system uses the following hardware and software:

[0736] 1. Hardware:

[0737] Server: Cloud server, database server

[0738] Device: Smartphone (Android / iOS)

[0739] GPS device: Equipment installed in logistics vehicles

[0740] Sensors: devices to measure the emotional state of staff

[0741] 2. Software:

[0742] Emotion Recognition Engine: API

[0743] Machine learning model: Demand forecasting algorithm

[0744] Data collection and analysis

[0745] The server has a means for collecting real-time GPS location data, demand forecast data, and traffic condition data, and then predicts demand for the next time period based on the collected data.

[0746] The terminal (smartphone) receives GPS signals from logistics vehicles to collect current location data and uses sensors to acquire staff emotion data. The server analyzes this data and runs an algorithm to predict future demand.

[0747] Optimal allocation of resources

[0748] The server identifies available vehicles and staff based on predicted demand, assigns optimal routes and tasks, and then sends notifications and instructions to vehicles and staff.

[0749] For example, if a logistics center predicts an increase in shipping demand over the next hour, the server will identify waiting vehicles and less fatigued staff and assign appropriate delivery routes and tasks to each.

[0750] Execution and Monitoring

[0751] The server monitors the progress of vehicles and staff in real time, and also uses an emotion recognition engine to monitor the emotional state of staff and give appropriate break instructions when necessary.

[0752] For example, if Driver A's emotional state is deteriorating and fatigue is building up, the server can instruct him / her to:

[0753] "Judging from your current emotional state, fatigue is building up. If you continue driving, the risk of an accident increases. Please take a 20-minute break at the nearest rest stop."

[0754] Furthermore, based on the emotional state, feedback is provided to improve the quality of service, which allows for more efficient allocation of vehicles and personnel, improving safety, service quality, and staff efficiency.

[0755] Examples of prompt statements

[0756] For example, a prompt for a generative AI model might be entered in the following format:

[0757] "Enter a few lines of Japanese text. Generate a message instructing Driver A to take an appropriate break if he is experiencing a worsening emotional state and fatigue."

[0758] (Example input)

[0759] After monitoring Driver A's emotional state, it was determined that he was highly fatigued. The vehicle's current location was obtained from the location information system, and the next rest stop was approximately 5 km away.

[0760] (Example output)

[0761] Driver A, you are currently very tired, so we recommend that you take a 20-minute break at the rest area 5 km ahead. Refreshing yourself is important for safe driving.

[0762] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0763] Step 1: Data collection

[0764] The server collects GPS location data of logistics vehicles, historical logistics data, real-time traffic condition data, and staff sentiment data.

[0765] Input: Location data from GPS devices, historical database information, traffic API data, emotion recognition engine data

[0766] Output: All collected data

[0767] Specific operation: The server acquires data from each data source and stores it in the integrated database.

[0768] Step 2: Demand forecast

[0769] The server analyzes the collected data and predicts demand for the next time period, using machine learning models to forecast future demand patterns.

[0770] Input: Collected data

[0771] Output: Demand forecast model and forecast results for the next time period

[0772] Specific operation: The server inputs the collected data into a machine learning model and executes a demand forecasting algorithm.

[0773] Step 3: Identify available resources

[0774] The server checks the location and status of vehicles and staff currently in operation and identifies available resources.

[0775] Inputs: Demand forecast results, real-time GPS location data, staff sentiment data

[0776] Output: List of available vehicles and staff

[0777] What it does: The server compares predicted demand with real-time data to identify the best vehicles and staff.

[0778] Step 4: Route and task assignment

[0779] The server assigns optimal routes and tasks, sends notifications to vehicles and staff, and takes emotional data into account to provide safe and efficient instructions.

[0780] Input: list of available vehicles and staff, traffic data

[0781] Output: Optimal route and task instructions for each vehicle and crew member

[0782] Specific operation: The server executes a route calculation algorithm based on the collected data and notifies the user (staff member) of specific instructions.

[0783] Step 5: Running and monitoring

[0784] The server monitors the task execution status of vehicles and staff in real time, checking their emotional state as needed and issuing break instructions as necessary.

[0785] Input: Real-time GPS location data, emotion data

[0786] Output: Task execution status monitoring results, break instructions

[0787] Specific operation: The server tracks the progress of vehicles and staff in real time, notifies and instructs in case of abnormalities, and instructs staff to take breaks based on data provided by the emotion recognition engine.

[0788] Step 6: Provide feedback

[0789] The server evaluates the emotional state and work performance of the staff and provides feedback to improve the quality of service.

[0790] Input: Task execution status monitoring results, emotion data

[0791] Output: Feedback report

[0792] Specific Actions: The server analyzes the collected data and provides specific improvements and recommendations to staff.

[0793] The above are the specific processing steps of this system.

[0794] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0795] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0796] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0797] [Third embodiment]

[0798] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0799] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0800] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0801] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0802] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0803] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0804] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0805] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0806] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0807] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0808] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0809] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0810] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[0811] System Overview

[0812] 1. Data Collection

[0813] The server collects real-time information on the current location of taxis and trucks from GPS devices, as well as past ride data, package delivery data, and event information, and statistically processes it. It also obtains real-time traffic information from traffic control systems and map services.

[0814] 2. Demand forecast

[0815] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[0816] 3. Resource Matching

[0817] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[0818] 4. Optimal Route and Task Allocation

[0819] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, and also decides whether the vehicle is delivering goods or transporting people, and assigns each vehicle a specific task.

[0820] 5. Notices and Instructions

[0821] The terminal (driver) receives notification messages sent from the server and receives task and route instructions.

[0822] 6. Execution and Monitoring

[0823] The server monitors in real time whether the driver is following instructions and performing the task, and generates alerts as needed, providing instructions on appropriate countermeasures based on progress reports from the driver's device.

[0824] Specific examples

[0825] Example: Transporting goods by taxi

[0826] 1. Data Collection

[0827] The server collects real-time demand data for a region and the location of waiting taxis.

[0828] 2. Demand forecast

[0829] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[0830] 3. Resource Matching

[0831] The server checks the waiting taxis in area A and identifies a vehicle suitable for delivering the goods.

[0832] 4. Optimal Route and Task Allocation

[0833] The server assigns the optimal route from area A to area B and a delivery task to the taxi.

[0834] 5. Notices and Instructions

[0835] The terminal (driver) receives notification messages sent from the server and receives delivery tasks and route instructions.

[0836] 6. Execution and Monitoring

[0837] The server monitors the process in real time as the taxi driver picks up the item and delivers it to the specified area B.

[0838] As described above, the present invention can realize efficient allocation of labor in the taxi and logistics industries, and solve problems such as driver shortages and surpluses.

[0839] The processing flow will be explained below.

[0840] Step 1:

[0841] The server collects the current location of taxis and trucks in real time from GPS devices.

[0842] Step 2:

[0843] The server collects historical ride data, package delivery data, and event information from a database.

[0844] Step 3:

[0845] The server obtains real-time traffic data from traffic control systems and map services.

[0846] Step 4:

[0847] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[0848] Step 5:

[0849] The server identifies available vehicles and drivers based on the demand forecast.

[0850] Step 6:

[0851] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[0852] Step 7:

[0853] The server generates notification messages about the assigned tasks and routes and sends them to the driver's terminal.

[0854] Step 8:

[0855] The device (driver) receives the notification message and confirms the task and route instructions.

[0856] Step 9:

[0857] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[0858] Step 10:

[0859] The server monitors the driver's progress in real time, generating alerts and sending response instructions as needed.

[0860] As described above, the system of the present invention can realize efficient allocation of labor in the taxi and logistics fields, and solve the problems of driver shortages and labor surpluses.

[0861] Example 1

[0862] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0863] Efficient allocation of vehicles and personnel is a challenge in the taxi and logistics sectors. Currently, it is difficult to quickly and appropriately reallocate waiting vehicles and driver resources, resulting in frequent mismatches between supply and demand. This reduces driver work efficiency and reduces user satisfaction. Furthermore, a lack of real-time monitoring and optimal route instructions makes traffic congestion and operational delays more likely to occur. Therefore, a system that can solve these issues is needed.

[0864] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0865] In this invention, the server includes means for collecting real-time location information, means for collecting past behavior data and current traffic condition data, means for analyzing the collected data and predicting demand for the next time slot, means for identifying available vehicles and drivers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for sending notifications and instructions to the vehicles and drivers, and means for monitoring the progress of the drivers in real time. This allows for appropriate and efficient allocation of vehicle and driver resources, eliminating mismatches between supply and demand, and enabling improved business efficiency and customer satisfaction.

[0866] "Real-time location information" is data that indicates the specific location of a vehicle or driver at the current time.

[0867] "Past behavior data" is information that records the past behavior history of a vehicle and a driver.

[0868] "Current traffic condition data" refers to data that includes current traffic flow and congestion information in a specific area.

[0869] "Demand forecasting" is the process of calculating traffic demand for a specific time period in the future based on past data and current conditions.

[0870] "Available vehicles and drivers" refers to vehicles and drivers that are currently in operation or on standby and immediately available for work.

[0871] An "optimal route" is a route that takes into account time, distance, traffic conditions, and other factors to reach a destination in the most efficient manner.

[0872] "Task" means a specific task or instruction given to a vehicle and driver.

[0873] A "notification" is a message conveying instructions or information that is sent by the server to a vehicle or driver.

[0874] "Progress" is information indicating how far the vehicle and driver have progressed in completing the specified task.

[0875] "Real-time monitoring" is the process of constantly knowing the current status of the vehicle and driver.

[0876] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[0877] System Overview

[0878] Data collection

[0879] The server obtains real-time location information from the GPS devices installed in each vehicle. The hardware used for this is a GPS module such as the u-blox NEO-M8N. It also obtains past ride and delivery data from a database such as MySQL. Traffic condition data is obtained in real time from the Google Traffic API, for example.

[0880] Example: The server collects the current location information of taxis in the Tokyo area, ride data around Shinjuku Station for the past month, and current traffic situation data around Shinjuku Station.

[0881] Demand forecasting

[0882] The server analyzes the collected data and runs a demand forecasting algorithm using machine learning models such as TensorFlow. The analysis results are stored in a database such as PostgreSQL.

[0883] Example: Based on data from the past month, the server predicts that there will be an increase in demand for taxis from Shinjuku Station to Roppongi in the next hour.

[0884] Resource Matching

[0885] The server compares the predicted demand with current vehicle location data to identify areas where demand is lacking, then checks available vehicles and drivers and selects the most suitable vehicle and driver.

[0886] Example: The server checks for taxis waiting around Shinjuku Station and identifies the vehicle that is suitable for delivering an item.

[0887] Optimal Routes and Task Allocation

[0888] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle, using the Google Directions API, and assigns specific tasks to each vehicle.

[0889] Example: The server calculates the optimal route for a taxi from Shinjuku Station to Roppongi and assigns a delivery task.

[0890] Notices and Instructions

[0891] The device (driver) receives notification messages sent from the server and receives task and route instructions. The driver checks the notifications on a smartphone or tablet (e.g., Samsung Galaxy Tab).

[0892] Example: A driver receives a notification for a delivery task from Shinjuku Station to Roppongi.

[0893] Execution and Monitoring

[0894] The server monitors the driver's real-time progress as he or she performs the task according to the instructions, and generates alerts and additional instructions based on progress reports from the driver's device.

[0895] Example: The server monitors in real time that the driver has picked up his luggage at Shinjuku Station and is heading to Roppongi.

[0896] In this way, this system can realize efficient labor allocation in the taxi and logistics industries, and solve the problems of driver shortages and surpluses. This system uses TensorFlow as a generative AI model, and examples of its prompts include the following:

[0897] "Predict the demand for taxis from Shinjuku Station to Roppongi for the next hour and allocate appropriate vehicles."

[0898] By inputting such prompt statements into the model, highly accurate demand forecasting and resource matching become possible.

[0899] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0900] Step 1: Data collection

[0901] The server receives real-time vehicle location information from GPS devices. The input is location data provided by the GPS device (e.g., u-blox NEO-M8N). This data is collected at regular intervals and stored in a database. The output is a database entry for each vehicle's latest location.

[0902] Specific operation: Obtain the current location (latitude, longitude) of each vehicle every minute and update it in the "Vehicle Location Data" table.

[0903] The server retrieves historical trip data, delivery data, and event information from a database (e.g., MySQL). The input is historical database queries. This data is aggregated and formatted for demand forecasting. The output is a historical dataset that can be analyzed.

[0904] Specific operation: Extract taxi usage history data for the past month using an SQL query, aggregate it, and store it in the "Past Data" table.

[0905] The server retrieves current traffic situation data from traffic control systems and mapping services (e.g., Google Traffic API). The input is the API request. This data is retrieved in real time and stored for analysis. The output is a dataset of current traffic conditions.

[0906] Specific operation: Obtain the latest traffic congestion information from the traffic API every 5 minutes and store it in the "traffic condition data" table.

[0907] Step 2: Demand forecast

[0908] The server analyzes the collected historical and real-time data and executes a demand forecasting algorithm. The inputs are historical behavior data, current location information, and traffic condition data. A machine learning model (e.g., TensorFlow) is used to predict demand for the next time slot. The output is the demand forecast for the next time slot.

[0909] Specific operation: Using the TensorFlow model, predict taxi demand for the next hour based on data from the past month and current traffic data, and save it in the "Demand forecast data" table.

[0910] Step 3: Resource Matching

[0911] The server compares the predicted demand with the current vehicle location data to identify areas where there is a shortage of demand. The inputs are demand forecast data and current location information data. Based on this data, areas with a supply shortage are identified. The output is a list of areas with a supply shortage.

[0912] Specific operation: Compare the demand forecast results with current vehicle location information and list areas where supply is insufficient.

[0913] The server allocates available vehicles and drivers to the identified areas. The inputs are a list of areas with shortages and vehicle location data. Based on this data, the server selects the most suitable vehicles and drivers. The output is a list of allocated vehicles and drivers.

[0914] Specific operation: Select the vehicle closest to the shortage area and add that vehicle and driver to the "assignment data" table.

[0915] Step 4: Optimal Route and Task Allocation

[0916] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle. The inputs are the driver's current location, destination, and the latest traffic data. The optimal route is calculated using the Google Directions API. The output is the optimal route information.

[0917] Specific operation: Using the Google Directions API, calculate the optimal route from Shinjuku Station to Roppongi and save it in the "Route Information" table.

[0918] The server assigns specific tasks to each vehicle. The inputs are optimal route information and resource matching results. Based on these, tasks are generated and assigned to vehicles. The output is a task assignment list.

[0919] Specific behavior: Create a delivery task from Shinjuku Station to Roppongi and assign it to the appropriate taxi.

[0920] Step 5: Notification and Instructions

[0921] The terminal (driver) receives notification messages sent from the server and receives task and route instructions. The input is a notification message from the server. This notification is displayed on the terminal and conveyed to the driver reliably. The output is a notification confirmation to the driver.

[0922] Specific operation: A notification message is sent to the driver's device (e.g., smartphone), displaying the delivery task from Shinjuku Station to Roppongi and information about the optimal route.

[0923] Step 6: Running and monitoring

[0924] The server monitors in real time the process of the driver following instructions to carry out the task. The inputs include progress reports and location information from the driver. Based on this, the server monitors and manages the process, issuing alerts or additional instructions as necessary. The output is the progress monitoring results.

[0925] Specific operation: The system monitors the driver's journey from picking up the luggage to heading to Roppongi in real time, and provides instructions on an alternative route if traffic congestion occurs.

[0926] The above is the specific processing flow and operation at each step of this system. This series of steps achieves efficient and optimized resource allocation.

[0927] (Application example 1)

[0928] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0929] Conventional systems in the taxi and logistics fields have faced challenges such as inefficient vehicle and personnel allocation, low demand forecast accuracy, and difficulty in real-time management. These challenges are particularly evident in inventory management, inbound and outbound operations, and delivery preparation within logistics centers. This has led to problems such as reduced operational efficiency and delivery delays. The present invention aims to solve these challenges and achieve more efficient resource allocation and management.

[0930] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0931] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and workers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and workers, means for sending notifications and instructions to vehicles and workers, means for monitoring the progress of vehicles and workers in real time, means for managing inventory status, incoming and outgoing work, and delivery preparation within the logistics center, and means for sending notifications and instructions to staff and robots using smartphones, smart glasses, or robots, thereby enabling efficient allocation and real-time management of vehicles and personnel.

[0932] "Real-time location data" refers to data that is acquired and reflects the current location of vehicles and workers in real time.

[0933] "Demand forecast data" is data for predicting future demand based on past data and current conditions.

[0934] "Traffic condition data" is data that contains information about the current traffic conditions on the roads.

[0935] "Collecting means" refers to devices and methods for acquiring location data, demand forecast data, and traffic condition data.

[0936] The "means for analyzing and predicting demand in the next time period" refers to a method or system for calculating and predicting demand in the next time period using collected data.

[0937] "Means for identifying available vehicles and personnel" refers to a method or system for identifying and selecting currently available vehicles and personnel.

[0938] The "means for assigning optimal routes and tasks" refers to a method or system for instructing the specified vehicles and workers on efficient routes and tasks.

[0939] "Means for sending notifications and issuing instructions" refers to a method or system for transmitting necessary notifications and instructions to vehicles and workers.

[0940] "Means for monitoring progress in real time" refers to a method or system for monitoring task progress of vehicles and workers in real time.

[0941] "Means for managing inventory status, incoming and outgoing work, and delivery preparation within a logistics center" refers to methods and systems for supervising and adjusting inventory status, incoming and outgoing work, and delivery preparation work within a logistics center.

[0942] "Means for sending notifications and instructions using a smartphone, smart glasses, or robot" refers to a method or system for transmitting notifications and instructions to staff or robots via a smart device.

[0943] The present invention is a system for realizing efficient allocation of vehicles and personnel, and in particular, maximizes the work efficiency within a logistics center through real-time demand forecasting and resource management.

[0944] Overall system overview

[0945] This system mainly consists of the following six means:

[0946] 1. Data Collection Methods

[0947] 2. Demand forecasting methods

[0948] 3. Resource Identification Methods

[0949] 4. Task Allocation Method

[0950] 5. Notice and Instructions

[0951] 6. Monitoring Methods

[0952] Server-based data collection method

[0953] The server collects real-time location data, demand forecast data, and traffic data from hardware such as GPS devices, various sensors, and surveillance cameras in the distribution center. This data is then stored in a database.

[0954] Server-based demand forecasting method

[0955] The server analyzes the collected data and uses machine learning models to predict demand for the next time slot. The software used is a machine learning framework such as TensorFlow, which enables highly accurate demand forecasts.

[0956] Resource Identification Method

[0957] The server identifies available vehicles and crews based on predicted demand, matching real-time location data with each crew's schedule and status information.

[0958] Task Allocation Method

[0959] The server then assigns the optimal route and tasks to the identified vehicles and workers using the task allocation means. This process uses the Google Maps API to calculate the optimal route. Specifically, instructions are given taking into account the inventory status within the logistics center, incoming and outgoing work, and delivery preparations.

[0960] Notification and Instructions

[0961] Identified vehicles and workers are then notified and instructed via smartphone, smart glasses, or robot, allowing for quick and clear communication.

[0962] Monitoring Methods

[0963] Finally, the server monitors the progress of vehicles and workers in real time, reporting progress and instantly generating alerts and directing remedial action in the event of any deficiencies or problems.

[0964] Specific examples

[0965] Prompt Sentence Examples

[0966] "Please predict the inbound and outbound demand for Distribution Center A for the next two hours based on historical data, current inventory, weather, and traffic information."

[0967] Example

[0968] At a large logistics center, many delivery tasks are predicted between 3:00 PM and 5:00 PM. The system monitors the inventory status and staff locations in the warehouse in real time and predicts peak demand during this time period. Staff wearing smart glasses receive optimal routes and task instructions in real time, allowing them to work efficiently.

[0969] In this way, the present invention enables efficient allocation of vehicles and workers, greatly improving the operational efficiency of logistics centers.

[0970] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0971] Step 1:

[0972] Data collection

[0973] The server collects real-time location data, demand forecast data, and traffic condition data. This data is obtained from GPS devices, various sensors in the distribution center, and surveillance cameras. Input data includes vehicle location information, inventory status, weather information, traffic information, etc. The server centrally manages this data and stores it in a database.

[0974] Step 2:

[0975] Demand forecasting

[0976] The server analyzes the collected historical and real-time data to predict demand for the next time slot. This process uses machine learning frameworks such as TensorFlow to train a generative AI model and execute a demand forecasting algorithm. Input data includes past ride data, shipping data, weather information, and traffic conditions, and outputs demand forecast data based on this.

[0977] Step 3:

[0978] Resource Identification

[0979] The server identifies available vehicles and workers based on predicted demand. It compares current location information with each worker's schedule and status information to determine which resources are available. It takes real-time location information and worker status information as input data and outputs available resources based on that information.

[0980] Step 4:

[0981] Task assignment

[0982] The server then assigns optimal routes and tasks to the identified vehicles and workers. In this step, it uses the Google Maps API to calculate optimal routes and generates instructions taking into account inventory status within the logistics center, inbound and outbound operations, and delivery preparations. Input data includes information on available vehicles and workers, and the results of optimal route calculations, and it outputs task assignment information based on this.

[0983] Step 5:

[0984] Notices and Instructions

[0985] The server then sends notifications and instructions to the identified vehicles and workers via smartphones, smart glasses, or robots. The server takes input data, such as assigned tasks and route information, and generates and sends notification messages based on them.

[0986] Step 6:

[0987] Progress monitoring

[0988] The server monitors the progress of vehicles and workers in real time. Work progress is reported in real time, and if any deficiencies or problems occur, an alert is immediately generated and countermeasures are instructed. The input data is real-time progress data, and based on that, progress reports and alert information are output.

[0989] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0990] This invention is a system that includes an emotion engine to efficiently allocate vehicles and personnel in the taxi and logistics industries. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them, and predicts demand for the next time slot. Furthermore, by recognizing the emotions of users (drivers and customers), the system monitors driver fatigue and stress, provides appropriate rest instructions, and optimizes taxi routes and services to improve customer satisfaction. It also evaluates the emotional state of logistics drivers and provides warnings and assistance to promote safe driving.

[0991] System Overview

[0992] 1. Data Collection

[0993] The server collects real-time information about the current location of taxis and trucks from GPS devices, past ride data, package delivery data, and event information from a database, real-time traffic conditions from traffic control systems and map services, and user emotion data using an emotion engine.

[0994] 2. Demand forecast

[0995] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[0996] 3. Resource Matching

[0997] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[0998] 4. Optimal Route and Task Allocation

[0999] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, determine whether the vehicle is delivering goods or transporting people, and assign specific tasks to each vehicle. It also optimizes routes and services by taking into account user sentiment data.

[1000] 5. Notices and Instructions

[1001] The terminal (driver) receives notification messages sent from the server and confirms task and route instructions.

[1002] 6. Execution and Monitoring

[1003] The server monitors in real time whether the driver is performing the task according to the instructions. The driver's device reports the progress, and if necessary, generates an alert and sends response instructions. Utilizing an emotion engine, the server monitors the driver's fatigue and stress state and instructs them to take appropriate breaks. Furthermore, it provides feedback to improve the quality of service based on the customer's emotional state.

[1004] Specific examples

[1005] Example: Transporting goods by taxi and using emotion engines

[1006] 1. Data Collection

[1007] The server collects real-time demand data for a given area and the location of waiting taxis, as well as driver sentiment data.

[1008] 2. Demand forecast

[1009] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[1010] 3. Resource Matching

[1011] The server checks the taxis waiting in area A and identifies vehicles suitable for delivering goods. It also evaluates the emotional state of the drivers and prioritizes drivers who are less tired.

[1012] 4. Optimal Route and Task Allocation

[1013] The server assigns the optimal route and delivery task to the taxi from area A to area B. At this time, it takes into account the driver's emotional data to select a safe and efficient route.

[1014] 5. Notices and Instructions

[1015] The terminal (driver) receives the notification message sent from the server and confirms the delivery task and route instructions.

[1016] 6. Execution and Monitoring

[1017] The server monitors in real time the process of the taxi driver receiving the item and delivering it to the designated area B. If the driver's emotional state deteriorates, it will give appropriate rest instructions.

[1018] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[1019] The processing flow will be explained below.

[1020] Step 1:

[1021] The server collects the current location of taxis and trucks in real time from GPS devices.

[1022] Step 2:

[1023] The server collects historical ride data, package delivery data, and event information from a database.

[1024] Step 3:

[1025] The server obtains real-time traffic data from traffic control systems and map services.

[1026] Step 4:

[1027] The server uses an emotion engine to collect emotion data of drivers and customers in real time.

[1028] Step 5:

[1029] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[1030] Step 6:

[1031] The server identifies available vehicles and drivers based on predicted demand.

[1032] Step 7:

[1033] The server evaluates the driver's fatigue and stress state and selects an appropriate driver.

[1034] Step 8:

[1035] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[1036] Step 9:

[1037] The server generates a notification message about the specified task and route and sends it to the driver's device.

[1038] Step 10:

[1039] The device (driver) receives the notification message and confirms the task and route instructions.

[1040] Step 11:

[1041] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[1042] Step 12:

[1043] The server monitors the driver and vehicle's progress in real time, generating alerts and sending response instructions as needed.

[1044] Step 13:

[1045] If the driver's emotional state deteriorates, the server will give appropriate rest instructions.

[1046] Step 14:

[1047] The server provides feedback to improve the quality of service based on the emotional state of the customer.

[1048] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[1049] Example 2

[1050] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1051] The taxi and logistics industries require efficient allocation of vehicles and personnel. Conventional technologies have difficulty in responding to real-time demand forecasts and fluctuations in traffic conditions, and driver fatigue and stress management are insufficient. As a result, service quality has declined, and improving customer satisfaction has become an issue. Furthermore, optimal resource matching is often not possible when transporting goods or people, resulting in a decline in overall efficiency.

[1052] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1053] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and drivers based on the prediction, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for transmitting communication and issuing task instructions to the vehicles and drivers, means for monitoring the progress of the vehicles and drivers in real time, means for collecting and analyzing user emotions, and means for optimizing task instructions based on the emotion data to manage fatigue and improve service quality. This enables efficient allocation of vehicles and personnel and improves driver fatigue and stress management. Furthermore, it can increase customer satisfaction and improve the efficiency of transporting goods and people.

[1054] "Real-time location data" means data that uses a GPS device to instantly obtain and update the vehicle's precise current location.

[1055] "Demand forecast data" is data that predicts the demand for goods and people movement in the next time period based on past data and real-time data.

[1056] "Traffic condition data" refers to data that includes information related to traffic, such as road congestion, accident information, and travel speed.

[1057] "Means of collection" refers to a combination of hardware and software for acquiring various data.

[1058] "Analytical means" are algorithms and software for processing collected data and generating useful information or predictions.

[1059] "Means for identifying available vehicles and drivers" refers to a system for identifying currently available vehicles and drivers and assigning them to optimal positions and tasks.

[1060] The "means for allocating optimal routes and tasks" is a system that determines efficient and timely routes and instructs vehicles and drivers on appropriate tasks.

[1061] "Means for sending communications and providing operational instructions" means a messaging system for communicating operational and route instructions to vehicles and operators.

[1062] "Means for monitoring progress in real time" refers to a system that constantly checks the current location and status of the vehicle and driver and takes any necessary action.

[1063] The "means for collecting and analyzing user emotions" refers to hardware and software for acquiring and analyzing emotional information from the user's facial expressions, voice, etc.

[1064] "Means for optimizing work instructions based on emotional data and improving fatigue management and service quality" is a system that uses emotional information to provide appropriate work instructions and breaks, improving service quality.

[1065] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields. The system collects and analyzes real-time location data, demand forecast data, and traffic condition data to predict demand for the next time slot. It also collects and analyzes user emotion data to manage driver fatigue and improve service quality.

[1066] Data collection

[1067] The server collects real-time vehicle location information from GPS devices, such as Garmin and TomTom. It also collects past ride and package delivery data by querying a MySQL database. Traffic condition data is obtained using the Google Maps API. Furthermore, it uses Affectiva's SDK as an emotion engine to collect driver and customer sentiment data.

[1068] Demand forecasting

[1069] The server uses collected historical data and real-time data to analyze it using TensorFlow machine learning models (e.g., regression models), which predicts the demand for goods and people for the next time period, and stores the results in a MySQL database.

[1070] Resource Matching

[1071] The server compares predicted demand with real-time location data to identify areas where supply is insufficient. It then checks available vehicles and drivers and identifies the most suitable vehicle and driver. It also references emotional data to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[1072] Optimal Routes and Task Allocation

[1073] The server generates optimal routes using the Here Maps API, assigning efficient routes and tasks to each vehicle, whether delivering goods or transporting people, and selecting safe and efficient routes taking into account Affectiva's emotional data.

[1074] Notices and Instructions

[1075] The device (driver) receives notification messages from the server and confirms the assigned tasks and routes. The driver's device has an Android application installed, allowing them to receive real-time instructions and alerts.

[1076] Execution and Monitoring

[1077] The server monitors the driver's progress in real time as he or she follows instructions and performs the task. HTTP requests are used to report progress, and Twilio is used to generate SMS alerts and send response instructions as needed. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue and stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[1078] Specific examples

[1079] Transporting goods by taxi and using emotion engines

[1080] The server collects real-time demand data for a certain area and the location information of waiting taxis. It also collects driver emotional data. It predicts that demand for delivery of goods from area A to area B will increase over the next hour. It checks waiting taxis in area A and identifies vehicles suitable for delivering goods. It evaluates the emotional state of the drivers and prioritizes allocation to drivers who are less tired. It generates an optimal route from area A to area B using the Here Maps API and assigns delivery tasks. Drivers receive notifications from the server through an Android application and check the delivery task and route instructions. It monitors in real time the taxi drivers' ability to pick up goods and deliver them to the specified area B. Meanwhile, if the driver's emotional state deteriorates, appropriate rest instructions are sent via SMS using Twilio.

[1081] Prompt Sentence Examples

[1082] "We want to obtain location and sentiment data of taxi drivers and predict demand for the next hour. What algorithms and devices should we use?"

[1083] The system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality. It also utilizes emotional data to increase user satisfaction.

[1084] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1085] Step 1: Data collection

[1086] The server collects real-time vehicle location data (output) from GPS devices (input). Specifically, it communicates with Garmin and TomTom GPS devices to obtain location information. It also queries and collects past ride and package delivery data (output) from a MySQL database (input). It also uses Google Maps API to obtain traffic condition data (input) and stores this on the server (output). Additionally, it uses Affectiva's SDK as an emotion engine to collect driver and customer emotion data (input) (output).

[1087] Step 2: Demand forecast

[1088] The server uses TensorFlow to analyze the collected historical data and real-time data (input). This analysis is used to predict demand for the next time slot (output). Specifically, the data is analyzed using a machine learning model (regression model), and the results are stored in a MySQL database. This makes it possible to quantify the demand for goods and people movement in the next time slot.

[1089] Step 3: Resource Matching

[1090] The server compares predicted demand data (input) with real-time location data (input) to identify areas where supply is insufficient (output). It checks available vehicles and drivers and identifies the most suitable vehicle and driver (output). In this process, it references emotional data (input) to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[1091] Step 4: Optimal Route and Task Allocation

[1092] The server generates optimal routes (output) using the Here Maps API. Whether delivering goods or transporting people, it assigns efficient routes and tasks to each vehicle. It also considers Affectiva's emotion data (input) to select safe and efficient routes (output).

[1093] Step 5: Notification and Instructions

[1094] The device (driver) receives notification messages (input) sent from the server and checks the assigned tasks and routes (output). An Android application is installed on the driver's device, allowing it to receive real-time instructions and alerts. Specifically, an app with the function to receive and display notification messages is required.

[1095] Step 6: Running and monitoring

[1096] The server monitors in real time (input) the driver's process of completing tasks according to instructions (output). The driver reports their progress to the server through an Android application, which then sends an HTTP request to the server, which collects the progress data. If necessary, Twilio is used to generate an SMS alert and send instructions on how to respond. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue or stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[1097] Through these steps, the system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality.

[1098] (Application example 2)

[1099] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1100] In the modern taxi and logistics industry, efficient allocation of vehicles and personnel is required, but there is a lack of systems that take into account traffic conditions, fluctuations in demand, and staff fatigue and stress levels in real time. This can lead to a decline in service quality and safety issues. In addition, the inability to properly manage staff emotional states leads to a decline in work efficiency and customer satisfaction. A system to solve these issues is needed.

[1101] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1102] In this invention, the server includes means for collecting real-time GPS position data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time period, means for identifying available vehicles and staff based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and staff, means for sending notifications and giving instructions to the vehicles and staff, means for monitoring the progress of the vehicles and staff in real time, means for monitoring the emotional state of the staff and giving appropriate rest instructions, and means for providing feedback to improve service quality based on the emotional state. This enables efficient allocation of vehicles and staff, improving safety and service quality, and further improving staff work efficiency.

[1103] "Real-time GPS location data" is data used to obtain the current location of vehicles and staff in real time.

[1104] "Demand forecast data" is data used to predict future demand by analyzing collected past data and current conditions.

[1105] "Traffic condition data" refers to data including current traffic congestion and flow, accident information, and the like.

[1106] "Means of collection" refers to devices and systems for collecting various types of data.

[1107] "Means of analyzing and forecasting demand for the next time period" refers to algorithms and software that analyze collected data and forecast future demand.

[1108] "Means for identifying available vehicles and staff" refers to devices or systems for identifying available vehicles and staff from those currently in operation.

[1109] "Means for assigning optimal routes and tasks" refers to devices and systems for instructing identified vehicles and staff on the most efficient routes and tasks.

[1110] "Means for sending notifications and giving instructions" refers to devices and systems for sending notifications and giving instructions to vehicles and staff.

[1111] "Means for monitoring progress in real time" refers to devices and systems for monitoring the work progress of vehicles and staff in real time.

[1112] "Means for monitoring emotional state and issuing appropriate break instructions" refers to devices or systems for monitoring staff's emotional state and issuing break instructions as necessary.

[1113] "Means for providing feedback to improve service quality" refers to a device or system for providing feedback to staff to improve service quality based on data such as emotional state.

[1114] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields, and a specific implementation method thereof will be described below.

[1115] System configuration and data processing

[1116] This system uses the following hardware and software:

[1117] 1. Hardware:

[1118] Server: Cloud server, database server

[1119] Device: Smartphone (Android / iOS)

[1120] GPS device: Equipment installed in logistics vehicles

[1121] Sensors: devices to measure the emotional state of staff

[1122] 2. Software:

[1123] Emotion Recognition Engine: API

[1124] Machine learning model: Demand forecasting algorithm

[1125] Data collection and analysis

[1126] The server has a means for collecting real-time GPS location data, demand forecast data, and traffic condition data, and then predicts demand for the next time period based on the collected data.

[1127] The terminal (smartphone) receives GPS signals from logistics vehicles to collect current location data and uses sensors to acquire staff emotion data. The server analyzes this data and runs an algorithm to predict future demand.

[1128] Optimal allocation of resources

[1129] The server identifies available vehicles and staff based on predicted demand, assigns optimal routes and tasks, and then sends notifications and instructions to vehicles and staff.

[1130] For example, if a logistics center predicts an increase in shipping demand over the next hour, the server will identify waiting vehicles and less fatigued staff and assign appropriate delivery routes and tasks to each.

[1131] Execution and Monitoring

[1132] The server monitors the progress of vehicles and staff in real time, and also uses an emotion recognition engine to monitor the emotional state of staff and give appropriate break instructions when necessary.

[1133] For example, if Driver A's emotional state is deteriorating and fatigue is building up, the server can instruct him / her to:

[1134] "Judging from your current emotional state, fatigue is building up. If you continue driving, the risk of an accident increases. Please take a 20-minute break at the nearest rest stop."

[1135] Furthermore, based on the emotional state, feedback is provided to improve the quality of service, which allows for more efficient allocation of vehicles and personnel, improving safety, service quality, and staff efficiency.

[1136] Examples of prompt statements

[1137] For example, a prompt for a generative AI model might be entered in the following format:

[1138] "Enter a few lines of Japanese text. Generate a message instructing Driver A to take an appropriate break if he is experiencing a worsening emotional state and fatigue."

[1139] (Example input)

[1140] After monitoring Driver A's emotional state, it was determined that he was highly fatigued. The vehicle's current location was obtained from the location information system, and the next rest stop was approximately 5 km away.

[1141] (Example output)

[1142] Driver A, you are currently very tired, so we recommend that you take a 20-minute break at the rest area 5 km ahead. Refreshing yourself is important for safe driving.

[1143] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1144] Step 1: Data collection

[1145] The server collects GPS location data of logistics vehicles, historical logistics data, real-time traffic condition data, and staff sentiment data.

[1146] Input: Location data from GPS devices, historical database information, traffic API data, emotion recognition engine data

[1147] Output: All collected data

[1148] Specific operation: The server acquires data from each data source and stores it in the integrated database.

[1149] Step 2: Demand forecast

[1150] The server analyzes the collected data and predicts demand for the next time period, using machine learning models to forecast future demand patterns.

[1151] Input: Collected data

[1152] Output: Demand forecast model and forecast results for the next time period

[1153] Specific operation: The server inputs the collected data into a machine learning model and executes a demand forecasting algorithm.

[1154] Step 3: Identify available resources

[1155] The server checks the location and status of vehicles and staff currently in operation and identifies available resources.

[1156] Inputs: Demand forecast results, real-time GPS location data, staff sentiment data

[1157] Output: List of available vehicles and staff

[1158] What it does: The server compares predicted demand with real-time data to identify the best vehicles and staff.

[1159] Step 4: Route and task assignment

[1160] The server assigns optimal routes and tasks, sends notifications to vehicles and staff, and takes emotional data into account to provide safe and efficient instructions.

[1161] Input: list of available vehicles and staff, traffic data

[1162] Output: Optimal route and task instructions for each vehicle and crew member

[1163] Specific operation: The server executes a route calculation algorithm based on the collected data and notifies the user (staff member) of specific instructions.

[1164] Step 5: Running and monitoring

[1165] The server monitors the task execution status of vehicles and staff in real time, checking their emotional state as needed and issuing break instructions as necessary.

[1166] Input: Real-time GPS location data, emotion data

[1167] Output: Task execution status monitoring results, break instructions

[1168] Specific operation: The server tracks the progress of vehicles and staff in real time, notifies and instructs in case of abnormalities, and instructs staff to take breaks based on data provided by the emotion recognition engine.

[1169] Step 6: Provide feedback

[1170] The server evaluates the emotional state and work performance of the staff and provides feedback to improve the quality of service.

[1171] Input: Task execution status monitoring results, emotion data

[1172] Output: Feedback report

[1173] Specific Actions: The server analyzes the collected data and provides specific improvements and recommendations to staff.

[1174] The above are the specific processing steps of this system.

[1175] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1176] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1177] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1178] [Fourth embodiment]

[1179] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1180] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1181] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1182] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1183] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1184] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1185] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1186] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1187] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1188] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1189] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1190] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1191] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1192] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[1193] System Overview

[1194] 1. Data Collection

[1195] The server collects real-time information on the current location of taxis and trucks from GPS devices, as well as past ride data, package delivery data, and event information, and statistically processes it. It also obtains real-time traffic information from traffic control systems and map services.

[1196] 2. Demand forecast

[1197] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[1198] 3. Resource Matching

[1199] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[1200] 4. Optimal Route and Task Allocation

[1201] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, and also decides whether the vehicle is delivering goods or transporting people, and assigns each vehicle a specific task.

[1202] 5. Notices and Instructions

[1203] The terminal (driver) receives notification messages sent from the server and receives task and route instructions.

[1204] 6. Execution and Monitoring

[1205] The server monitors in real time whether the driver is following instructions and performing the task, and generates alerts as needed, providing instructions on appropriate countermeasures based on progress reports from the driver's device.

[1206] Specific examples

[1207] Example: Transporting goods by taxi

[1208] 1. Data Collection

[1209] The server collects real-time demand data for a region and the location of waiting taxis.

[1210] 2. Demand forecast

[1211] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[1212] 3. Resource Matching

[1213] The server checks the waiting taxis in area A and identifies a vehicle suitable for delivering the goods.

[1214] 4. Optimal Route and Task Allocation

[1215] The server assigns the optimal route from area A to area B and a delivery task to the taxi.

[1216] 5. Notices and Instructions

[1217] The terminal (driver) receives notification messages sent from the server and receives delivery tasks and route instructions.

[1218] 6. Execution and Monitoring

[1219] The server monitors the process in real time as the taxi driver picks up the item and delivers it to the specified area B.

[1220] As described above, the present invention can realize efficient allocation of labor in the taxi and logistics industries, and solve problems such as driver shortages and surpluses.

[1221] The processing flow will be explained below.

[1222] Step 1:

[1223] The server collects the current location of taxis and trucks in real time from GPS devices.

[1224] Step 2:

[1225] The server collects historical ride data, package delivery data, and event information from a database.

[1226] Step 3:

[1227] The server obtains real-time traffic data from traffic control systems and map services.

[1228] Step 4:

[1229] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[1230] Step 5:

[1231] The server identifies available vehicles and drivers based on the demand forecast.

[1232] Step 6:

[1233] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[1234] Step 7:

[1235] The server generates notification messages about the assigned tasks and routes and sends them to the driver's terminal.

[1236] Step 8:

[1237] The device (driver) receives the notification message and confirms the task and route instructions.

[1238] Step 9:

[1239] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[1240] Step 10:

[1241] The server monitors the driver's progress in real time, generating alerts and sending response instructions as needed.

[1242] As described above, the system of the present invention can realize efficient allocation of labor in the taxi and logistics fields, and solve the problems of driver shortages and labor surpluses.

[1243] Example 1

[1244] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1245] Efficient allocation of vehicles and personnel is a challenge in the taxi and logistics sectors. Currently, it is difficult to quickly and appropriately reallocate waiting vehicles and driver resources, resulting in frequent mismatches between supply and demand. This reduces driver work efficiency and reduces user satisfaction. Furthermore, a lack of real-time monitoring and optimal route instructions makes traffic congestion and operational delays more likely to occur. Therefore, a system that can solve these issues is needed.

[1246] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1247] In this invention, the server includes means for collecting real-time location information, means for collecting past behavior data and current traffic condition data, means for analyzing the collected data and predicting demand for the next time slot, means for identifying available vehicles and drivers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for sending notifications and instructions to the vehicles and drivers, and means for monitoring the progress of the drivers in real time. This allows for appropriate and efficient allocation of vehicle and driver resources, eliminating mismatches between supply and demand, and enabling improved business efficiency and customer satisfaction.

[1248] "Real-time location information" is data that indicates the specific location of a vehicle or driver at the current time.

[1249] "Past behavior data" is information that records the past behavior history of a vehicle and a driver.

[1250] "Current traffic condition data" refers to data that includes current traffic flow and congestion information in a specific area.

[1251] "Demand forecasting" is the process of calculating traffic demand for a specific time period in the future based on past data and current conditions.

[1252] "Available vehicles and drivers" refers to vehicles and drivers that are currently in operation or on standby and immediately available for work.

[1253] An "optimal route" is a route that takes into account time, distance, traffic conditions, and other factors to reach a destination in the most efficient manner.

[1254] "Task" means a specific task or instruction given to a vehicle and driver.

[1255] A "notification" is a message conveying instructions or information that is sent by the server to a vehicle or driver.

[1256] "Progress" is information indicating how far the vehicle and driver have progressed in completing the specified task.

[1257] "Real-time monitoring" is the process of constantly knowing the current status of the vehicle and driver.

[1258] This invention is a system for efficiently allocating vehicles and personnel in the taxi and logistics sectors. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them to predict demand for the next time slot, identifies available vehicles and drivers, assigns optimal routes and tasks, and sends notifications and instructions to vehicles and drivers, monitoring their progress in real time.

[1259] System Overview

[1260] Data collection

[1261] The server obtains real-time location information from the GPS devices installed in each vehicle. The hardware used for this is a GPS module such as the u-blox NEO-M8N. It also obtains past ride and delivery data from a database such as MySQL. Traffic condition data is obtained in real time from the Google Traffic API, for example.

[1262] Example: The server collects the current location information of taxis in the Tokyo area, ride data around Shinjuku Station for the past month, and current traffic situation data around Shinjuku Station.

[1263] Demand forecasting

[1264] The server analyzes the collected data and runs a demand forecasting algorithm using machine learning models such as TensorFlow. The analysis results are stored in a database such as PostgreSQL.

[1265] Example: Based on data from the past month, the server predicts that there will be an increase in demand for taxis from Shinjuku Station to Roppongi in the next hour.

[1266] Resource Matching

[1267] The server compares the predicted demand with current vehicle location data to identify areas where demand is lacking, then checks available vehicles and drivers and selects the most suitable vehicle and driver.

[1268] Example: The server checks for taxis waiting around Shinjuku Station and identifies the vehicle that is suitable for delivering an item.

[1269] Optimal Routes and Task Allocation

[1270] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle, using the Google Directions API, and assigns specific tasks to each vehicle.

[1271] Example: The server calculates the optimal route for a taxi from Shinjuku Station to Roppongi and assigns a delivery task.

[1272] Notices and Instructions

[1273] The device (driver) receives notification messages sent from the server and receives task and route instructions. The driver checks the notifications on a smartphone or tablet (e.g., Samsung Galaxy Tab).

[1274] Example: A driver receives a notification for a delivery task from Shinjuku Station to Roppongi.

[1275] Execution and Monitoring

[1276] The server monitors the driver's real-time progress as he or she performs the task according to the instructions, and generates alerts and additional instructions based on progress reports from the driver's device.

[1277] Example: The server monitors in real time that the driver has picked up his luggage at Shinjuku Station and is heading to Roppongi.

[1278] In this way, this system can realize efficient labor allocation in the taxi and logistics industries, and solve the problems of driver shortages and surpluses. This system uses TensorFlow as a generative AI model, and examples of its prompts include the following:

[1279] "Predict the demand for taxis from Shinjuku Station to Roppongi for the next hour and allocate appropriate vehicles."

[1280] By inputting such prompt statements into the model, highly accurate demand forecasting and resource matching become possible.

[1281] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1282] Step 1: Data collection

[1283] The server receives real-time vehicle location information from GPS devices. The input is location data provided by the GPS device (e.g., u-blox NEO-M8N). This data is collected at regular intervals and stored in a database. The output is a database entry for each vehicle's latest location.

[1284] Specific operation: Obtain the current location (latitude, longitude) of each vehicle every minute and update it in the "Vehicle Location Data" table.

[1285] The server retrieves historical trip data, delivery data, and event information from a database (e.g., MySQL). The input is historical database queries. This data is aggregated and formatted for demand forecasting. The output is a historical dataset that can be analyzed.

[1286] Specific operation: Extract taxi usage history data for the past month using an SQL query, aggregate it, and store it in the "Past Data" table.

[1287] The server retrieves current traffic situation data from traffic control systems and mapping services (e.g., Google Traffic API). The input is the API request. This data is retrieved in real time and stored for analysis. The output is a dataset of current traffic conditions.

[1288] Specific operation: Obtain the latest traffic congestion information from the traffic API every 5 minutes and store it in the "traffic condition data" table.

[1289] Step 2: Demand forecast

[1290] The server analyzes the collected historical and real-time data and executes a demand forecasting algorithm. The inputs are historical behavior data, current location information, and traffic condition data. A machine learning model (e.g., TensorFlow) is used to predict demand for the next time slot. The output is the demand forecast for the next time slot.

[1291] Specific operation: Using the TensorFlow model, predict taxi demand for the next hour based on data from the past month and current traffic data, and save it in the "Demand forecast data" table.

[1292] Step 3: Resource Matching

[1293] The server compares the predicted demand with the current vehicle location data to identify areas where there is a shortage of demand. The inputs are demand forecast data and current location information data. Based on this data, areas with a supply shortage are identified. The output is a list of areas with a supply shortage.

[1294] Specific operation: Compare the demand forecast results with current vehicle location information and list areas where supply is insufficient.

[1295] The server allocates available vehicles and drivers to the identified areas. The inputs are a list of areas with shortages and vehicle location data. Based on this data, the server selects the most suitable vehicles and drivers. The output is a list of allocated vehicles and drivers.

[1296] Specific operation: Select the vehicle closest to the shortage area and add that vehicle and driver to the "assignment data" table.

[1297] Step 4: Optimal Route and Task Allocation

[1298] The server runs a routing algorithm that takes into account map information and traffic conditions to generate the optimal route for each vehicle. The inputs are the driver's current location, destination, and the latest traffic data. The optimal route is calculated using the Google Directions API. The output is the optimal route information.

[1299] Specific operation: Using the Google Directions API, calculate the optimal route from Shinjuku Station to Roppongi and save it in the "Route Information" table.

[1300] The server assigns specific tasks to each vehicle. The inputs are optimal route information and resource matching results. Based on these, tasks are generated and assigned to vehicles. The output is a task assignment list.

[1301] Specific behavior: Create a delivery task from Shinjuku Station to Roppongi and assign it to the appropriate taxi.

[1302] Step 5: Notification and Instructions

[1303] The terminal (driver) receives notification messages sent from the server and receives task and route instructions. The input is a notification message from the server. This notification is displayed on the terminal and conveyed to the driver reliably. The output is a notification confirmation to the driver.

[1304] Specific operation: A notification message is sent to the driver's device (e.g., smartphone), displaying the delivery task from Shinjuku Station to Roppongi and information about the optimal route.

[1305] Step 6: Running and monitoring

[1306] The server monitors in real time the process of the driver following instructions to carry out the task. The inputs include progress reports and location information from the driver. Based on this, the server monitors and manages the process, issuing alerts or additional instructions as necessary. The output is the progress monitoring results.

[1307] Specific operation: The system monitors the driver's journey from picking up the luggage to heading to Roppongi in real time, and provides instructions on an alternative route if traffic congestion occurs.

[1308] The above is the specific processing flow and operation at each step of this system. This series of steps achieves efficient and optimized resource allocation.

[1309] (Application example 1)

[1310] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] Conventional systems in the taxi and logistics fields have faced challenges such as inefficient vehicle and personnel allocation, low demand forecast accuracy, and difficulty in real-time management. These challenges are particularly evident in inventory management, inbound and outbound operations, and delivery preparation within logistics centers. This has led to problems such as reduced operational efficiency and delivery delays. The present invention aims to solve these challenges and achieve more efficient resource allocation and management.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1313] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and workers based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and workers, means for sending notifications and instructions to vehicles and workers, means for monitoring the progress of vehicles and workers in real time, means for managing inventory status, incoming and outgoing work, and delivery preparation within the logistics center, and means for sending notifications and instructions to staff and robots using smartphones, smart glasses, or robots, thereby enabling efficient allocation and real-time management of vehicles and personnel.

[1314] "Real-time location data" refers to data that is acquired and reflects the current location of vehicles and workers in real time.

[1315] "Demand forecast data" is data for predicting future demand based on past data and current conditions.

[1316] "Traffic condition data" is data that contains information about the current traffic conditions on the roads.

[1317] "Collecting means" refers to devices and methods for acquiring location data, demand forecast data, and traffic condition data.

[1318] The "means for analyzing and predicting demand in the next time period" refers to a method or system for calculating and predicting demand in the next time period using collected data.

[1319] "Means for identifying available vehicles and personnel" refers to a method or system for identifying and selecting currently available vehicles and personnel.

[1320] The "means for assigning optimal routes and tasks" refers to a method or system for instructing the specified vehicles and workers on efficient routes and tasks.

[1321] "Means for sending notifications and issuing instructions" refers to a method or system for transmitting necessary notifications and instructions to vehicles and workers.

[1322] "Means for monitoring progress in real time" refers to a method or system for monitoring task progress of vehicles and workers in real time.

[1323] "Means for managing inventory status, incoming and outgoing work, and delivery preparation within a logistics center" refers to methods and systems for supervising and adjusting inventory status, incoming and outgoing work, and delivery preparation work within a logistics center.

[1324] "Means for sending notifications and instructions using a smartphone, smart glasses, or robot" refers to a method or system for transmitting notifications and instructions to staff or robots via a smart device.

[1325] The present invention is a system for realizing efficient allocation of vehicles and personnel, and in particular, maximizes the work efficiency within a logistics center through real-time demand forecasting and resource management.

[1326] Overall system overview

[1327] This system mainly consists of the following six means:

[1328] 1. Data Collection Methods

[1329] 2. Demand forecasting methods

[1330] 3. Resource Identification Methods

[1331] 4. Task Allocation Method

[1332] 5. Notice and Instructions

[1333] 6. Monitoring Methods

[1334] Server-based data collection method

[1335] The server collects real-time location data, demand forecast data, and traffic data from hardware such as GPS devices, various sensors, and surveillance cameras in the distribution center. This data is then stored in a database.

[1336] Server-based demand forecasting method

[1337] The server analyzes the collected data and uses machine learning models to predict demand for the next time slot. The software used is a machine learning framework such as TensorFlow, which enables highly accurate demand forecasts.

[1338] Resource Identification Method

[1339] The server identifies available vehicles and crews based on predicted demand, matching real-time location data with each crew's schedule and status information.

[1340] Task Allocation Method

[1341] The server then assigns the optimal route and tasks to the identified vehicles and workers using the task allocation means. This process uses the Google Maps API to calculate the optimal route. Specifically, instructions are given taking into account the inventory status within the logistics center, incoming and outgoing work, and delivery preparations.

[1342] Notification and Instructions

[1343] Identified vehicles and workers are then notified and instructed via smartphone, smart glasses, or robot, allowing for quick and clear communication.

[1344] Monitoring Methods

[1345] Finally, the server monitors the progress of vehicles and workers in real time, reporting progress and instantly generating alerts and directing remedial action in the event of any deficiencies or problems.

[1346] Specific examples

[1347] Prompt Sentence Examples

[1348] "Please predict the inbound and outbound demand for Distribution Center A for the next two hours based on historical data, current inventory, weather, and traffic information."

[1349] Example

[1350] At a large logistics center, many delivery tasks are predicted between 3:00 PM and 5:00 PM. The system monitors the inventory status and staff locations in the warehouse in real time and predicts peak demand during this time period. Staff wearing smart glasses receive optimal routes and task instructions in real time, allowing them to work efficiently.

[1351] In this way, the present invention enables efficient allocation of vehicles and workers, greatly improving the operational efficiency of logistics centers.

[1352] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1353] Step 1:

[1354] Data collection

[1355] The server collects real-time location data, demand forecast data, and traffic condition data. This data is obtained from GPS devices, various sensors in the distribution center, and surveillance cameras. Input data includes vehicle location information, inventory status, weather information, traffic information, etc. The server centrally manages this data and stores it in a database.

[1356] Step 2:

[1357] Demand forecasting

[1358] The server analyzes the collected historical and real-time data to predict demand for the next time slot. This process uses machine learning frameworks such as TensorFlow to train a generative AI model and execute a demand forecasting algorithm. Input data includes past ride data, shipping data, weather information, and traffic conditions, and outputs demand forecast data based on this.

[1359] Step 3:

[1360] Resource Identification

[1361] The server identifies available vehicles and workers based on predicted demand. It compares current location information with each worker's schedule and status information to determine which resources are available. It takes real-time location information and worker status information as input data and outputs available resources based on that information.

[1362] Step 4:

[1363] Task assignment

[1364] The server then assigns optimal routes and tasks to the identified vehicles and workers. In this step, it uses the Google Maps API to calculate optimal routes and generates instructions taking into account inventory status within the logistics center, inbound and outbound operations, and delivery preparations. Input data includes information on available vehicles and workers, and the results of optimal route calculations, and it outputs task assignment information based on this.

[1365] Step 5:

[1366] Notices and Instructions

[1367] The server then sends notifications and instructions to the identified vehicles and workers via smartphones, smart glasses, or robots. The server takes input data, such as assigned tasks and route information, and generates and sends notification messages based on them.

[1368] Step 6:

[1369] Progress monitoring

[1370] The server monitors the progress of vehicles and workers in real time. Work progress is reported in real time, and if any deficiencies or problems occur, an alert is immediately generated and countermeasures are instructed. The input data is real-time progress data, and based on that, progress reports and alert information are output.

[1371] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1372] This invention is a system that includes an emotion engine to efficiently allocate vehicles and personnel in the taxi and logistics industries. The system collects real-time GPS location data, demand forecast data, and traffic condition data, analyzes them, and predicts demand for the next time slot. Furthermore, by recognizing the emotions of users (drivers and customers), the system monitors driver fatigue and stress, provides appropriate rest instructions, and optimizes taxi routes and services to improve customer satisfaction. It also evaluates the emotional state of logistics drivers and provides warnings and assistance to promote safe driving.

[1373] System Overview

[1374] 1. Data Collection

[1375] The server collects real-time information about the current location of taxis and trucks from GPS devices, past ride data, package delivery data, and event information from a database, real-time traffic conditions from traffic control systems and map services, and user emotion data using an emotion engine.

[1376] 2. Demand forecast

[1377] The server analyzes the collected historical and real-time data and runs a demand forecasting algorithm to predict demand for the next time period. This prediction is made using a machine learning model, and the generated forecast model and forecast results are stored in a database.

[1378] 3. Resource Matching

[1379] The server compares the predicted demand with the collected vehicle location data to identify areas where supply is insufficient, checks available vehicles and drivers, and selects the most suitable vehicle and driver.

[1380] 4. Optimal Route and Task Allocation

[1381] The server runs algorithms that take into account map information and traffic conditions to generate optimal routes for each vehicle, determine whether the vehicle is delivering goods or transporting people, and assign specific tasks to each vehicle. It also optimizes routes and services by taking into account user sentiment data.

[1382] 5. Notices and Instructions

[1383] The terminal (driver) receives notification messages sent from the server and confirms task and route instructions.

[1384] 6. Execution and Monitoring

[1385] The server monitors in real time whether the driver is performing the task according to the instructions. The driver's device reports the progress, and if necessary, generates an alert and sends response instructions. Utilizing an emotion engine, the server monitors the driver's fatigue and stress state and instructs them to take appropriate breaks. Furthermore, it provides feedback to improve the quality of service based on the customer's emotional state.

[1386] Specific examples

[1387] Example: Transporting goods by taxi and using emotion engines

[1388] 1. Data Collection

[1389] The server collects real-time demand data for a given area and the location of waiting taxis, as well as driver sentiment data.

[1390] 2. Demand forecast

[1391] The server predicts that there will be an increase in demand for deliveries of goods from region A to region B over the next hour.

[1392] 3. Resource Matching

[1393] The server checks the taxis waiting in area A and identifies vehicles suitable for delivering goods. It also evaluates the emotional state of the drivers and prioritizes drivers who are less tired.

[1394] 4. Optimal Route and Task Allocation

[1395] The server assigns the optimal route and delivery task to the taxi from area A to area B. At this time, it takes into account the driver's emotional data to select a safe and efficient route.

[1396] 5. Notices and Instructions

[1397] The terminal (driver) receives the notification message sent from the server and confirms the delivery task and route instructions.

[1398] 6. Execution and Monitoring

[1399] The server monitors in real time the process of the taxi driver receiving the item and delivering it to the designated area B. If the driver's emotional state deteriorates, it will give appropriate rest instructions.

[1400] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[1401] The processing flow will be explained below.

[1402] Step 1:

[1403] The server collects the current location of taxis and trucks in real time from GPS devices.

[1404] Step 2:

[1405] The server collects historical ride data, package delivery data, and event information from a database.

[1406] Step 3:

[1407] The server obtains real-time traffic data from traffic control systems and map services.

[1408] Step 4:

[1409] The server uses an emotion engine to collect emotion data of drivers and customers in real time.

[1410] Step 5:

[1411] The server runs machine learning algorithms to analyze the collected data and predict demand for the next time period.

[1412] Step 6:

[1413] The server identifies available vehicles and drivers based on predicted demand.

[1414] Step 7:

[1415] The server evaluates the driver's fatigue and stress state and selects an appropriate driver.

[1416] Step 8:

[1417] The server assigns optimal routes and tasks to the identified vehicles and drivers.

[1418] Step 9:

[1419] The server generates a notification message about the specified task and route and sends it to the driver's device.

[1420] Step 10:

[1421] The device (driver) receives the notification message and confirms the task and route instructions.

[1422] Step 11:

[1423] The driver performs the task according to the instructions and reports the progress to the server via the terminal.

[1424] Step 12:

[1425] The server monitors the driver and vehicle's progress in real time, generating alerts and sending response instructions as needed.

[1426] Step 13:

[1427] If the driver's emotional state deteriorates, the server will give appropriate rest instructions.

[1428] Step 14:

[1429] The server provides feedback to improve the quality of service based on the emotional state of the customer.

[1430] In this way, the system of the present invention can realize efficient allocation of labor in the taxi and logistics industries, solve the problems of driver shortages and labor surpluses, and improve safety and service quality by taking into account user feelings.

[1431] Example 2

[1432] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1433] The taxi and logistics industries require efficient allocation of vehicles and personnel. Conventional technologies have difficulty in responding to real-time demand forecasts and fluctuations in traffic conditions, and driver fatigue and stress management are insufficient. As a result, service quality has declined, and improving customer satisfaction has become an issue. Furthermore, optimal resource matching is often not possible when transporting goods or people, resulting in a decline in overall efficiency.

[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1435] In this invention, the server includes means for collecting real-time location data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time slot, means for identifying available vehicles and drivers based on the prediction, means for assigning optimal routes and tasks to the identified vehicles and drivers, means for transmitting communication and issuing task instructions to the vehicles and drivers, means for monitoring the progress of the vehicles and drivers in real time, means for collecting and analyzing user emotions, and means for optimizing task instructions based on the emotion data to manage fatigue and improve service quality. This enables efficient allocation of vehicles and personnel and improves driver fatigue and stress management. Furthermore, it can increase customer satisfaction and improve the efficiency of transporting goods and people.

[1436] "Real-time location data" means data that uses a GPS device to instantly obtain and update the vehicle's precise current location.

[1437] "Demand forecast data" is data that predicts the demand for goods and people movement in the next time period based on past data and real-time data.

[1438] "Traffic condition data" refers to data that includes information related to traffic, such as road congestion, accident information, and travel speed.

[1439] "Means of collection" refers to a combination of hardware and software for acquiring various data.

[1440] "Analytical means" are algorithms and software for processing collected data and generating useful information or predictions.

[1441] "Means for identifying available vehicles and drivers" refers to a system for identifying currently available vehicles and drivers and assigning them to optimal positions and tasks.

[1442] The "means for allocating optimal routes and tasks" is a system that determines efficient and timely routes and instructs vehicles and drivers on appropriate tasks.

[1443] "Means for sending communications and providing operational instructions" means a messaging system for communicating operational and route instructions to vehicles and operators.

[1444] "Means for monitoring progress in real time" refers to a system that constantly checks the current location and status of the vehicle and driver and takes any necessary action.

[1445] The "means for collecting and analyzing user emotions" refers to hardware and software for acquiring and analyzing emotional information from the user's facial expressions, voice, etc.

[1446] "Means for optimizing work instructions based on emotional data and improving fatigue management and service quality" is a system that uses emotional information to provide appropriate work instructions and breaks, improving service quality.

[1447] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields. The system collects and analyzes real-time location data, demand forecast data, and traffic condition data to predict demand for the next time slot. It also collects and analyzes user emotion data to manage driver fatigue and improve service quality.

[1448] Data collection

[1449] The server collects real-time vehicle location information from GPS devices, such as Garmin and TomTom. It also collects past ride and package delivery data by querying a MySQL database. Traffic condition data is obtained using the Google Maps API. Furthermore, it uses Affectiva's SDK as an emotion engine to collect driver and customer sentiment data.

[1450] Demand forecasting

[1451] The server uses collected historical data and real-time data to analyze it using TensorFlow machine learning models (e.g., regression models), which predicts the demand for goods and people for the next time period, and stores the results in a MySQL database.

[1452] Resource Matching

[1453] The server compares predicted demand with real-time location data to identify areas where supply is insufficient. It then checks available vehicles and drivers and identifies the most suitable vehicle and driver. It also references emotional data to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[1454] Optimal Routes and Task Allocation

[1455] The server generates optimal routes using the Here Maps API, assigning efficient routes and tasks to each vehicle, whether delivering goods or transporting people, and selecting safe and efficient routes taking into account Affectiva's emotional data.

[1456] Notices and Instructions

[1457] The device (driver) receives notification messages from the server and confirms the assigned tasks and routes. The driver's device has an Android application installed, allowing them to receive real-time instructions and alerts.

[1458] Execution and Monitoring

[1459] The server monitors the driver's progress in real time as he or she follows instructions and performs the task. HTTP requests are used to report progress, and Twilio is used to generate SMS alerts and send response instructions as needed. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue and stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[1460] Specific examples

[1461] Transporting goods by taxi and using emotion engines

[1462] The server collects real-time demand data for a certain area and the location information of waiting taxis. It also collects driver emotional data. It predicts that demand for delivery of goods from area A to area B will increase over the next hour. It checks waiting taxis in area A and identifies vehicles suitable for delivering goods. It evaluates the emotional state of the drivers and prioritizes allocation to drivers who are less tired. It generates an optimal route from area A to area B using the Here Maps API and assigns delivery tasks. Drivers receive notifications from the server through an Android application and check the delivery task and route instructions. It monitors in real time the taxi drivers' ability to pick up goods and deliver them to the specified area B. Meanwhile, if the driver's emotional state deteriorates, appropriate rest instructions are sent via SMS using Twilio.

[1463] Prompt Sentence Examples

[1464] "We want to obtain location and sentiment data of taxi drivers and predict demand for the next hour. What algorithms and devices should we use?"

[1465] The system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality. It also utilizes emotional data to increase user satisfaction.

[1466] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1467] Step 1: Data collection

[1468] The server collects real-time vehicle location data (output) from GPS devices (input). Specifically, it communicates with Garmin and TomTom GPS devices to obtain location information. It also queries and collects past ride and package delivery data (output) from a MySQL database (input). It also uses Google Maps API to obtain traffic condition data (input) and stores this on the server (output). Additionally, it uses Affectiva's SDK as an emotion engine to collect driver and customer emotion data (input) (output).

[1469] Step 2: Demand forecast

[1470] The server uses TensorFlow to analyze the collected historical data and real-time data (input). This analysis is used to predict demand for the next time slot (output). Specifically, the data is analyzed using a machine learning model (regression model), and the results are stored in a MySQL database. This makes it possible to quantify the demand for goods and people movement in the next time slot.

[1471] Step 3: Resource Matching

[1472] The server compares predicted demand data (input) with real-time location data (input) to identify areas where supply is insufficient (output). It checks available vehicles and drivers and identifies the most suitable vehicle and driver (output). In this process, it references emotional data (input) to prioritize drivers who are less tired or stressed. For example, if demand is concentrated in area A, it selects the waiting vehicle closest to area A.

[1473] Step 4: Optimal Route and Task Allocation

[1474] The server generates optimal routes (output) using the Here Maps API. Whether delivering goods or transporting people, it assigns efficient routes and tasks to each vehicle. It also considers Affectiva's emotion data (input) to select safe and efficient routes (output).

[1475] Step 5: Notification and Instructions

[1476] The device (driver) receives notification messages (input) sent from the server and checks the assigned tasks and routes (output). An Android application is installed on the driver's device, allowing it to receive real-time instructions and alerts. Specifically, an app with the function to receive and display notification messages is required.

[1477] Step 6: Running and monitoring

[1478] The server monitors in real time (input) the driver's process of completing tasks according to instructions (output). The driver reports their progress to the server through an Android application, which then sends an HTTP request to the server, which collects the progress data. If necessary, Twilio is used to generate an SMS alert and send instructions on how to respond. Furthermore, Affectiva's emotion engine is used to monitor the driver's emotional state, providing appropriate rest instructions based on fatigue or stress levels. Customer emotion data is also collected and stored in a database as service feedback.

[1479] Through these steps, the system aims to achieve efficient allocation of vehicles and personnel, manage driver fatigue, and improve service quality.

[1480] (Application example 2)

[1481] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1482] In the modern taxi and logistics industry, efficient allocation of vehicles and personnel is required, but there is a lack of systems that take into account traffic conditions, fluctuations in demand, and staff fatigue and stress levels in real time. This can lead to a decline in service quality and safety issues. In addition, the inability to properly manage staff emotional states leads to a decline in work efficiency and customer satisfaction. A system to solve these issues is needed.

[1483] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1484] In this invention, the server includes means for collecting real-time GPS position data, demand forecast data, and traffic condition data, means for analyzing the collected data to predict demand for the next time period, means for identifying available vehicles and staff based on the predicted demand, means for assigning optimal routes and tasks to the identified vehicles and staff, means for sending notifications and giving instructions to the vehicles and staff, means for monitoring the progress of the vehicles and staff in real time, means for monitoring the emotional state of the staff and giving appropriate rest instructions, and means for providing feedback to improve service quality based on the emotional state. This enables efficient allocation of vehicles and staff, improving safety and service quality, and further improving staff work efficiency.

[1485] "Real-time GPS location data" is data used to obtain the current location of vehicles and staff in real time.

[1486] "Demand forecast data" is data used to predict future demand by analyzing collected past data and current conditions.

[1487] "Traffic condition data" refers to data including current traffic congestion and flow, accident information, and the like.

[1488] "Means of collection" refers to devices and systems for collecting various types of data.

[1489] "Means of analyzing and forecasting demand for the next time period" refers to algorithms and software that analyze collected data and forecast future demand.

[1490] "Means for identifying available vehicles and staff" refers to devices or systems for identifying available vehicles and staff from those currently in operation.

[1491] "Means for assigning optimal routes and tasks" refers to devices and systems for instructing identified vehicles and staff on the most efficient routes and tasks.

[1492] "Means for sending notifications and giving instructions" refers to devices and systems for sending notifications and giving instructions to vehicles and staff.

[1493] "Means for monitoring progress in real time" refers to devices and systems for monitoring the work progress of vehicles and staff in real time.

[1494] "Means for monitoring emotional state and issuing appropriate break instructions" refers to devices or systems for monitoring staff's emotional state and issuing break instructions as necessary.

[1495] "Means for providing feedback to improve service quality" refers to a device or system for providing feedback to staff to improve service quality based on data such as emotional state.

[1496] This invention is a system that realizes efficient allocation of vehicles and personnel in the taxi and logistics fields, and a specific implementation method thereof will be described below.

[1497] System configuration and data processing

[1498] This system uses the following hardware and software:

[1499] 1. Hardware:

[1500] Server: Cloud server, database server

[1501] Device: Smartphone (Android / iOS)

[1502] GPS device: Equipment installed in logistics vehicles

[1503] Sensors: devices to measure the emotional state of staff

[1504] 2. Software:

[1505] Emotion Recognition Engine: API

[1506] Machine learning model: Demand forecasting algorithm

[1507] Data collection and analysis

[1508] The server has a means for collecting real-time GPS location data, demand forecast data, and traffic condition data, and then predicts demand for the next time period based on the collected data.

[1509] The terminal (smartphone) receives GPS signals from logistics vehicles to collect current location data and uses sensors to acquire staff emotion data. The server analyzes this data and runs an algorithm to predict future demand.

[1510] Optimal allocation of resources

[1511] The server identifies available vehicles and staff based on predicted demand, assigns optimal routes and tasks, and then sends notifications and instructions to vehicles and staff.

[1512] For example, if a logistics center predicts an increase in shipping demand over the next hour, the server will identify waiting vehicles and less fatigued staff and assign appropriate delivery routes and tasks to each.

[1513] Execution and Monitoring

[1514] The server monitors the progress of vehicles and staff in real time, and also uses an emotion recognition engine to monitor the emotional state of staff and give appropriate break instructions when necessary.

[1515] For example, if Driver A's emotional state is deteriorating and fatigue is building up, the server can instruct him / her to:

[1516] "Judging from your current emotional state, fatigue is building up. If you continue driving, the risk of an accident increases. Please take a 20-minute break at the nearest rest stop."

[1517] Furthermore, based on the emotional state, feedback is provided to improve the quality of service, which allows for more efficient allocation of vehicles and personnel, improving safety, service quality, and staff efficiency.

[1518] Examples of prompt statements

[1519] For example, a prompt for a generative AI model might be entered in the following format:

[1520] "Enter a few lines of Japanese text. Generate a message instructing Driver A to take an appropriate break if he is experiencing a worsening emotional state and fatigue."

[1521] (Example input)

[1522] After monitoring Driver A's emotional state, it was determined that he was highly fatigued. The vehicle's current location was obtained from the location information system, and the next rest stop was approximately 5 km away.

[1523] (Example output)

[1524] Driver A, you are currently very tired, so we recommend that you take a 20-minute break at the rest area 5 km ahead. Refreshing yourself is important for safe driving.

[1525] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1526] Step 1: Data collection

[1527] The server collects GPS location data of logistics vehicles, historical logistics data, real-time traffic condition data, and staff sentiment data.

[1528] Input: Location data from GPS devices, historical database information, traffic API data, emotion recognition engine data

[1529] Output: All collected data

[1530] Specific operation: The server acquires data from each data source and stores it in the integrated database.

[1531] Step 2: Demand forecast

[1532] The server analyzes the collected data and predicts demand for the next time period, using machine learning models to forecast future demand patterns.

[1533] Input: Collected data

[1534] Output: Demand forecast model and forecast results for the next time period

[1535] Specific operation: The server inputs the collected data into a machine learning model and executes a demand forecasting algorithm.

[1536] Step 3: Identify available resources

[1537] The server checks the location and status of vehicles and staff currently in operation and identifies available resources.

[1538] Inputs: Demand forecast results, real-time GPS location data, staff sentiment data

[1539] Output: List of available vehicles and staff

[1540] What it does: The server compares predicted demand with real-time data to identify the best vehicles and staff.

[1541] Step 4: Route and task assignment

[1542] The server assigns optimal routes and tasks, sends notifications to vehicles and staff, and takes emotional data into account to provide safe and efficient instructions.

[1543] Input: list of available vehicles and staff, traffic data

[1544] Output: Optimal route and task instructions for each vehicle and crew member

[1545] Specific operation: The server executes a route calculation algorithm based on the collected data and notifies the user (staff member) of specific instructions.

[1546] Step 5: Running and monitoring

[1547] The server monitors the task execution status of vehicles and staff in real time, checking their emotional state as needed and issuing break instructions as necessary.

[1548] Input: Real-time GPS location data, emotion data

[1549] Output: Task execution status monitoring results, break instructions

[1550] Specific operation: The server tracks the progress of vehicles and staff in real time, notifies and instructs in case of abnormalities, and instructs staff to take breaks based on data provided by the emotion recognition engine.

[1551] Step 6: Provide feedback

[1552] The server evaluates the emotional state and work performance of the staff and provides feedback to improve the quality of service.

[1553] Input: Task execution status monitoring results, emotion data

[1554] Output: Feedback report

[1555] Specific Actions: The server analyzes the collected data and provides specific improvements and recommendations to staff.

[1556] The above are the specific processing steps of this system.

[1557] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1558] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1559] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1560] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1561] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1562] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1563] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1564] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1565] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1566] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1567] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1568] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1569] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1570] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1571] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1572] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1573] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1574] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1575] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1576] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1577] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1578] The following is further disclosed regarding the above embodiment.

[1579] (Claim 1)

[1580] A system for realizing efficient allocation of vehicles and personnel in the taxi and logistics fields,

[1581] a means for collecting real-time GPS location data, demand forecast data, and traffic condition data;

[1582] A means for analyzing the collected data to predict demand for the next time period;

[1583] a means for identifying available vehicles and drivers based on predicted demand;

[1584] a means for assigning optimal routes and tasks to the identified vehicles and drivers;

[1585] means for sending notifications and instructions to the vehicle and driver;

[1586] a means of monitoring the progress of the vehicle and driver in real time;

[1587] A system including:

[1588] (Claim 2)

[1589] The system of claim 1, wherein the system has taxi drivers transport goods and truck drivers transport people.

[1590] (Claim 3)

[1591] 10. The system of claim 1, further comprising means for efficiently reallocating idle or idle vehicles and drivers based on predicted demand.

[1592] "Example 1"

[1593] (Claim 1)

[1594] a means for collecting real-time location information;

[1595] A means of collecting past behavioral data and current traffic situation data;

[1596] A means for analyzing the collected data and predicting demand for the next time period;

[1597] means for identifying available vehicles and drivers based on predicted demand;

[1598] A means for assigning optimal routes and tasks to the identified vehicles and drivers;

[1599] means for sending notifications and instructions to the vehicle and driver;

[1600] a means for monitoring the driver's progress in real time; and

[1601] A system including:

[1602] (Claim 2)

[1603] 10. The system of claim 1, further comprising means for sending notifications to a driver's terminal and displaying specific task and route instructions.

[1604] (Claim 3)

[1605] 10. The system of claim 1, further comprising means for efficiently reallocating idle or gap-time vehicles and drivers based on predicted demand.

[1606] "Application Example 1"

[1607] (Claim 1)

[1608] A system for realizing efficient allocation of vehicles and personnel in the taxi and logistics fields,

[1609] a means for collecting real-time location data, demand forecast data, and traffic condition data;

[1610] A means for analyzing the collected data to predict demand for the next time period;

[1611] a means for identifying available vehicles and personnel based on predicted demand;

[1612] A means for assigning optimal routes and tasks to the identified vehicles and workers;

[1613] means for sending notifications and instructions to vehicles and personnel;

[1614] a means of monitoring the progress of vehicles and workers in real time;

[1615] A means of managing inventory status, inbound and outbound work, and delivery preparation within the distribution center;

[1616] means for sending notifications and instructions to staff and robots using a smartphone, smart glasses, or robot;

[1617] A system including:

[1618] (Claim 2)

[1619] The system according to claim 1, wherein the task is performed based on a taxi driver who transports goods and a truck driver who transports people.

[1620] (Claim 3)

[1621] 10. The system of claim 1, further comprising means for efficiently reallocating idle or idle vehicles and workers based on predicted demand.

[1622] "Example 2: Combining Emotion Engines"

[1623] (Claim 1)

[1624] a means for collecting real-time location data, demand forecast data, and traffic condition data;

[1625] A means for analyzing the collected data to predict demand for the next time period;

[1626] means for identifying available vehicles and operators based on the prediction;

[1627] A means for assigning optimal routes and tasks to the identified vehicles and operators;

[1628] means for transmitting communications and instructions to the vehicle and its operator;

[1629] a means for monitoring the progress of the vehicle and operator in real time;

[1630] A means for collecting and analyzing user emotions;

[1631] A means of optimizing work instructions based on emotion data to improve fatigue management and service quality;

[1632] A system including:

[1633] (Claim 2)

[1634] The system of claim 1, wherein one operator transports an item and another operator transports a person.

[1635] (Claim 3)

[1636] 10. The system of claim 1, further comprising means for effectively reallocating idle or underutilized vehicles and operators based on predicted demand.

[1637] "Application example 2 when combining emotion engines"

[1638] (Claim 1)

[1639] a means for collecting real-time GPS location data, demand forecast data, and traffic condition data;

[1640] A means for analyzing the collected data to predict demand for the next time period;

[1641] a means of identifying available vehicles and staff based on predicted demand;

[1642] A means of assigning optimal routes and tasks to the identified vehicles and staff;

[1643] a means of sending notifications and instructions to vehicles and staff;

[1644] a means of monitoring the progress of vehicles and personnel in real time;

[1645] A means of monitoring staff emotional states and providing appropriate rest instructions;

[1646] a means for providing feedback to improve the quality of service based on the emotional state;

[1647] A system including:

[1648] (Claim 2)

[1649] 10. The system of claim 1, comprising means for transporting objects and means for transporting people.

[1650] (Claim 3)

[1651] 10. The system of claim 1, further comprising means for efficiently reallocating idle or slack vehicles and staff based on predicted demand. [Explanation of symbols]

[1652] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system for realizing efficient allocation of vehicles and personnel in the taxi and logistics fields, a means for collecting real-time GPS location data, demand forecast data, and traffic condition data; A means for analyzing the collected data to predict demand for the next time period; a means for identifying available vehicles and drivers based on predicted demand; A means for assigning optimal routes and tasks to the identified vehicles and drivers; means for sending notifications and instructions to the vehicle and driver; a means of monitoring the progress of the vehicle and driver in real time; A system including:

2. 10. The system of claim 1, wherein the system has taxi drivers transport goods and truck drivers transport people.

3. The system of claim 1 further comprising means for efficiently reallocating idle or idle vehicles and drivers based on predicted demand.

Images