System

Abstract

A system is provided.SOLUTION: Means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data of surrounding facilities, means for collecting event information, means for integrating and preprocessing the collected data, means for predicting demand based on the integrated data, means for generating an optimal dispatch route based on the predicted demand, means for notifying a driver terminal of the generated dispatch route, and means for receiving feedback information from the driver terminal, this system includes a means for updating a demand prediction model, a means for receiving a vehicle allocation request from a user terminal, a means for selecting an optimum driver on the basis of the received vehicle allocation request and position information of the driver, and a means for notifying the selected driver of request information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] As the market for ride-sharing services expands, there is a need to realize efficient vehicle dispatching in response to the increasing demand for transportation. In particular, traffic congestion and congestion are likely to occur in urban areas, posing a challenge, resulting in long waiting times for users. Meanwhile, in areas experiencing depopulation and aging, transportation options are limited, and the ongoing reduction in public transportation reduces the convenience of travel. Against this backdrop, it is necessary to realize efficient vehicle dispatching and optimize the matching of transportation demand and supply. [Means for solving the problem]

[0005] The present invention includes a means for collecting, integrating, and preprocessing traffic condition data, map information data, people distribution data, congestion data at nearby facilities, event information, etc. in real time. It also includes a means for performing demand forecasting based on this data, and generates optimal vehicle dispatch routes based on the predicted demand. The generated vehicle dispatch routes are notified to the driver's terminal, and the demand forecast model is updated by receiving feedback information from the driver's terminal. Furthermore, the system includes a means for receiving dispatch requests from the user's terminal, selecting the optimal driver based on the driver's location information, and notifying the selected driver of the request information. This system optimizes the matching of supply and demand, enabling the provision of an efficient ride-sharing service.

[0006] "Traffic condition data" refers to data that indicates road conditions such as road congestion information, traffic accident information, and travel speed.

[0007] "Map information data" refers to data that indicates geographical information, specifically data that includes road shapes, coordinates, landmarks, and the like.

[0008] "People distribution data" is data that shows the density and movement patterns of people in a particular area.

[0009] "Crowding data for surrounding facilities" is data that shows the number of users and congestion levels at specific facilities such as supermarkets, stations, and event venues.

[0010] "Event information" is information about an event or gathering that takes place on a specific date and time, and is data used to predict traffic demand based on this information.

[0011] "Preprocessing" is the process of checking the consistency of collected data and performing processes such as removing outliers, filling in missing data, and normalizing the data to make it suitable for subsequent data analysis.

[0012] "Demand forecasting" is the process of predicting traffic demand for a certain future time based on past and real-time data.

[0013] A "vehicle dispatch route" is a route that indicates the optimal route from the user's pickup point to the destination.

[0014] A "driver device" is a mobile device such as a smartphone or tablet held by the driver, which has the function of checking the dispatch route and sending feedback.

[0015] A "user terminal" is a mobile terminal such as a smartphone or tablet used by a general user of a ride-sharing service, and is a device that has the function of sending a ride-hailing request.

[0016] "Feedback information" refers to real-time data such as location and progress that the driver sends while actually traveling.

[0017] A "matching algorithm" is a calculation method for selecting the most suitable driver based on the user's ride request and the driver's location information. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention is a system that collects and integrates traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information in real time. Based on this data, it performs demand forecasting, generates efficient vehicle dispatch routes, and notifies drivers. Furthermore, upon receiving a vehicle dispatch request from a user, it selects the most suitable driver and notifies the request information, thereby quickly responding to user needs.

[0040] System Operation

[0041] 1. Data Collection

[0042] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information, allowing the latest situation to be grasped in real time.

[0043] 2. Data integration and preprocessing

[0044] The server consolidates the collected data, corrects inconsistencies, improves data quality by removing outliers and imputing missing data, and normalizes the data to prepare it for input into the AI ​​model.

[0045] 3. Demand forecasting

[0046] The server uses the integrated data to predict demand for the next certain period of time, taking into account factors such as the day of the week, time of day, weather, and events, and identifies areas where travel demand will be high.

[0047] 4. Vehicle routing generation

[0048] The server generates optimal vehicle dispatch routes based on predicted demand data, taking into account current traffic conditions and the driver's location.

[0049] 5. Driver Notification

[0050] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server, allowing the driver to travel efficiently.

[0051] 6. Real-time updates and feedback

[0052] During the journey, the driver's device transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[0053] 7. Receiving requests from users

[0054] Users send a ride request through the app, which includes information such as the departure point, destination, and desired time.

[0055] 8. Driver Selection

[0056] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is notified of the request information and is given instructions on how to get to the departure point.

[0057] Specific examples

[0058] Example 1: Urban commute hours

[0059] The server predicts that demand for rides from business districts to stations will increase at 5 p.m. Ten minutes before the scheduled time, it suggests routes for nearby drivers to wait in front of the station, making it easier for commuters to board rides in front of the station, improving convenience.

[0060] Example 2: When a local event is held

[0061] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates increased demand in the surrounding area. Before the event begins, the server suggests routes for drivers to wait in the area, ensuring smooth transportation for event participants.

[0062] In this way, the present invention can provide an efficient ride-sharing service by combining real-time data collection, demand forecasting, and vehicle route optimization, which can particularly contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas.

[0063] The processing flow will be explained below.

[0064] Step 1: Data collection

[0065] The server periodically collects traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information. Traffic condition data includes road congestion information and travel speeds, and map information data includes coordinate information for roads and landmarks. People distribution data indicates the population density and movement patterns in a specific area, and congestion data at nearby facilities provides the number of users at major spots. Event information includes the date, time, and location of the event.

[0066] Step 2: Data integration and preprocessing

[0067] The server integrates the collected data, detects and removes outliers, fills in missing data, and normalizes the data. If there are inconsistencies in traffic condition data or pedestrian distribution data, it corrects them and converts them into a consistent format. If there are gaps in aerial photograph data or congestion data, it fills in the gaps based on surrounding data. It also standardizes all data so that it can be used by AI models.

[0068] Step 3: Demand forecast

[0069] The server uses the preprocessed data to perform demand forecasts. It inputs the collected data into an AI model to predict traffic demand for the next certain period. For example, the predictive model calculates which areas will experience demand, taking into account specific days of the week, time periods, events, and weather information.

[0070] Step 4: Generate a vehicle routing route

[0071] The server generates optimal vehicle dispatch routes based on predicted demand data. It uses Dijkstra and A algorithms to calculate optimal routes that reflect real-time traffic conditions and each driver's location. The generated routes also take into account the driver's fuel consumption and time efficiency.

[0072] Step 5: Send route to driver

[0073] The terminal (driver's smartphone) receives the dispatch route information sent from the server. The driver follows the displayed route information and heads to the passenger's pickup point. This information is updated regularly, providing the optimal route based on the latest conditions.

[0074] Step 6: Real-time updates and feedback

[0075] The device (the driver's smartphone) sends its current location and progress information to the server in real time. For example, if an unexpected traffic jam or accident occurs, the server recalculates the demand forecast model based on the latest information and re-optimizes the route. This ensures that the driver is always provided with the most up-to-date dispatch route.

[0076] Step 7: Receiving a request from the user

[0077] A user (customer) sends a ride request to the server through a ride-sharing app. This request includes details such as the origin, destination, and desired time, allowing the server to recognize the user's transportation needs.

[0078] Step 8: Driver selection and notification

[0079] The server selects the most suitable driver based on the received ride request, the driver's current location information, and demand forecast data. It applies the Greedy algorithm to select a driver who meets the user's request with the shortest travel distance and time. At the same time, it notifies the selected driver of the request information and provides instructions on how to get to the departure point. This information is displayed on the driver's device, and an appropriate ride is dispatched.

[0080] Example 1

[0081] 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."

[0082] In modern urban and rural areas, real-time vehicle demand forecasting and optimal route generation are required to improve transportation efficiency and travel convenience. However, current systems collect individual data but do not adequately integrate data processing, demand forecasting, and vehicle route optimization. This results in reduced transportation efficiency and inconvenience for users and drivers. Furthermore, there is a lack of systems that can respond to real-time feedback and updates. To address these issues, this invention proposes a system that integrates comprehensive data processing with advanced prediction and optimization methods.

[0083] 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.

[0084] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating the collected data, correcting inconsistencies, and performing preprocessing, means for predicting demand for the next certain period based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and taking into account current traffic conditions and the driver's location, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving real-time update information from the driver terminal, updating the demand forecast model, and re-optimizing the route as necessary, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, and means for notifying the selected driver of the request information and providing directions. This enables data integration processing and real-time prediction and optimization.

[0085] "Traffic condition data" refers to data that includes information on road congestion, traffic accidents, construction works, and the like.

[0086] "Map information data" refers to data including geographical location information, road maps, and building layouts.

[0087] "People distribution data" is data that shows patterns of people gathering and moving in specific areas and at specific times.

[0088] "Congestion data for surrounding facilities" is data that indicates the usage status and congestion level of commercial facilities, public facilities, etc.

[0089] "Event information" is data about public events such as concerts, sports games, and festivals.

[0090] "Means for integrating data, correcting inconsistencies, and preprocessing" refers to means for integrating various collected data into a single format and correcting inconsistencies and missing data.

[0091] The "means for forecasting demand" is a means for forecasting demand for vehicle dispatch within a certain period of time in the future based on the integrated data.

[0092] "Means for generating optimal vehicle dispatch routes" refers to means for calculating and generating the most efficient routes based on predicted demand, real-time traffic conditions, and the driver's location.

[0093] "Driver terminal" refers to a device such as a smartphone or tablet used by the driver, which receives and displays information from the server.

[0094] "Real-time updates" are the latest data generated while on the move, such as the driver's location and progress.

[0095] A "user terminal" refers to a device such as a smartphone or tablet used by a user who uses a vehicle dispatch service, and is a terminal used to send a vehicle dispatch request to the server.

[0096] A "ride request" is a request sent by a user through the app, including information such as the departure point, destination, and desired time.

[0097] The "means for selecting the best driver" is a means for selecting the driver who can most efficiently handle the request based on the ride request and the driver's current location information.

[0098] "Means for notifying request information and providing directions" refers to means for notifying the selected driver of details of the ride request and providing guidance on the optimal route to the specified departure point.

[0099] This invention is a system that collects and integrates multiple data in real time, and based on that data, predicts transportation demand and generates optimal vehicle dispatch routes. This system is composed of a server, terminals, and users, and aims to provide an efficient ride-sharing service.

[0100] Hardware and software used

[0101] The server is the central unit that performs advanced data processing and predictive calculations and utilizes the following software and libraries:

[0102] Data collection: We use Google Maps API, HERE Maps, public open data portals, etc. to collect traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[0103] Data integration and preprocessing: We use the pandas and NumPy libraries to integrate the collected data and correct inconsistencies, thereby imputing missing data and removing outliers.

[0104] Demand forecasting: Based on the integrated data, we use a time series forecasting model (e.g., ARIMA, LSTM) to forecast the demand within the next certain time period.

[0105] Vehicle routing generation: Uses the A algorithm and Dijkstra's algorithm to generate optimal vehicle routing based on predicted demand data, current traffic conditions, and driver location information.

[0106] Notification service: Google Firebase and Apple Push Notification service are used to notify drivers of the generated optimal route information.

[0107] Real-time updates: Using WebSocket or MQTT protocols, the driver's location and progress are sent to the server in real time.

[0108] The terminals (driver terminal and user terminal) are mobile devices such as smartphones and tablets. These terminals have the following functions:

[0109] Driver's device: Receives and displays real-time route information sent from the server. Also, transfers real-time updated information sent from the device to the server.

[0110] User terminal: Sends a ride request to the server. The front-end app is built using React Native or Flutter, and communicates with the back-end via a RESTful API to send requests.

[0111] A user is a person who uses a smartphone or tablet to use a ride-hailing service. The user inputs the departure point, destination, and desired time and sends a request to the server.

[0112] Specific examples

[0113] Example 1: Urban commute hours

[0114] The server predicts that demand for travel from the office district to the station will increase at 5 p.m. Specifically, it uses information that, "According to traffic data, the roads from the office district to the station are usually congested at 5 p.m." The server then suggests a route to nearby drivers 10 minutes in advance, telling them to "wait in front of the station." The driver's device receives this notification, allowing the driver to head to the station efficiently. Commuters can board smoothly in front of the station, improving travel convenience.

[0115] Example 2: When a local event is held

[0116] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates an increase in demand for travel to the surrounding area. Specifically, it uses forecast data that shows that "events in tourist destinations over the weekend will attract large crowds." It then suggests a route to the driver to wait in the vicinity before the event begins, telling them to "wait near the event venue." The driver's device receives the instructions and follows the directions, allowing event participants to reach the event site smoothly.

[0117] Prompt Sentence Examples

[0118] Below are some examples of prompts for the generative AI model:

[0119] "Please forecast major traffic demand this weekend."

[0120] "Generate the optimal route from the office district to the station between 5:00 PM and 6:00 PM."

[0121] "Re-optimize your vehicle routes around the event, taking into account real-time traffic conditions and driver location."

[0122] In this way, the present invention can contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas by collecting data in real time and generating efficient demand forecasts and optimal routes based on that data.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] Data collection

[0126] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information through APIs. It uses Google Maps API, HERE Maps, public open data portals, etc. as input and obtains the necessary data from these services. The output is a collection of raw data obtained from each data source. Specifically, the server sends requests to each API and receives and stores the data returned as a response.

[0127] Step 2:

[0128] Data integration and preprocessing

[0129] The server integrates the collected data, corrects inconsistencies, and performs preprocessing. The input is the raw data from each data source collected in step 1. The output is an integrated and cleaned dataset. Specific operations include removing outliers, imputing missing data, and normalizing the data using the pandas and NumPy libraries. For example, missing values ​​are imputed with surrounding values, and outliers are removed using a specific threshold.

[0130] Step 3:

[0131] Demand forecasting

[0132] The server predicts demand for the next set of hours based on the integrated data. The input is the integrated dataset generated in step 2. The output is a forecast value from the demand forecasting model. Specifically, it uses a time series forecasting model (e.g., ARIMA, LSTM) to make predictions taking into account factors such as the day of the week, time, weather, and event information. For example, it predicts that "demand from the office district to the station will increase at 5 p.m. on Monday."

[0133] Step 4:

[0134] Vehicle routing generation

[0135] The server combines the predicted demand data, current traffic conditions, and the driver's location to generate the optimal vehicle dispatch route. The inputs are the predicted data obtained in step 3, real-time traffic information, and the driver's location information. The output is the optimal vehicle dispatch route. Specifically, it calculates the shortest route using the A algorithm or Dijkstra's algorithm, and adjusts the route by incorporating real-time traffic data.

[0136] Step 5:

[0137] Driver Notification

[0138] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server in real time. The input is the route information generated in step 4. The output is the dispatch route displayed on the driver's terminal. Specifically, the route information is pushed to the driver's smartphone using Google Firebase or Apple Push Notification service.

[0139] Step 6:

[0140] Real-time updates and feedback

[0141] The driver's device transmits real-time location information and progress status to the server during travel. The input is the driver's current location and progress data. The output is real-time updated data received by the server. Specifically, location information is sent to the server with low latency using WebSocket or MQTT protocols, and the server uses this data to update its demand forecasting model and re-optimize routes as needed.

[0142] Step 7:

[0143] Receiving requests from users

[0144] A user sends a ride request to the server via a smartphone app. The input is information such as the departure point, destination, and desired time entered by the user. The output is the ride request received by the server. Specifically, the user enters the destination and desired time on the app screen, and then sends that information to the server via a RESTful API.

[0145] Step 8:

[0146] Driver Selection

[0147] The server selects the most suitable driver based on the received request and the driver's current location information. The input is the ride request and the driver's current location information. The output is the selected driver and notification information. Specifically, it uses a bipartite matching algorithm to select the driver who can most efficiently handle the request, notifies the driver of the request information, and provides directions on how to get there.

[0148] (Application example 1)

[0149] 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."

[0150] Modern food delivery services face many challenges in achieving efficient delivery operations. Among these, generating optimal routes in real time in response to fluctuations in traffic conditions and demand, and quickly selecting drivers are particularly important. However, systems that can handle these variables have not yet been adequately developed, which could significantly reduce driver and customer satisfaction. Furthermore, there is a lack of a way to reoptimize delivery routes based on real-time feedback, which also impacts operational efficiency. A new system is needed to resolve these issues.

[0151] 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.

[0152] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating and pre-processing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, means for improving the delivery efficiency of delivery drivers based on the demand forecast and the optimal route generation in a food delivery service, and means for re-optimizing the delivery route based on real-time feedback information, thereby enabling fast and efficient delivery in a food delivery service.

[0153] 1. "Traffic condition data" refers to all information related to traffic, such as road congestion, accident information, and traffic signal status.

[0154] 2. "Map information data" means data that includes geographical location information and detailed road information.

[0155] 3. "Person distribution data" refers to data that shows the concentration and distribution of people in a particular area.

[0156] 4. "Congestion data for surrounding facilities" refers to data that indicates the degree of congestion and the number of people staying at a specific facility or location.

[0157] 5. "Event Information" refers to information about events or occasions held in a specific area or time.

[0158] 6. "Demand forecasting model" refers to an algorithm or machine learning model that forecasts demand in a specific region or time based on various collected data.

[0159] 7. "Optimal vehicle routing" refers to the best route calculated to reach a destination efficiently.

[0160] 8. "Driver device" refers to a device such as a smartphone or tablet held by the driver.

[0161] 9. "Feedback Information" means location, progress, and other information provided by a driver during a delivery.

[0162] 10. "User terminal" refers to a device such as a smartphone or tablet used by a User to submit an order or request.

[0163] 11. "Vehicle request" refers to the vehicle dispatch request information sent by a User.

[0164] 12. "Demand forecasting" refers to the process of estimating future demand for services based on collected data.

[0165] 13. “Optimization” refers to the process of adjusting parameters or conditions to obtain the best results in order to achieve a specific goal.

[0166] 14. "Real-time feedback" refers to immediate information provided by the driver or user.

[0167] This invention is a system for realizing efficient and prompt delivery operations in food delivery services. Specifically, it collects traffic condition data, map information data, people distribution data, congestion data at surrounding facilities, and event information in real time, and integrates and preprocesses them. It then forecasts demand based on this data, generates optimal vehicle dispatch routes, and notifies drivers. It also receives dispatch requests from users, selects the most suitable driver, and notifies them of the request information. It also reoptimizes delivery routes based on real-time feedback information.

[0168] Specific system configuration and operation

[0169] Data collection

[0170] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information, including information from various APIs on the Internet and GPS devices. The software used includes the Python requests library.

[0171] Data integration and preprocessing

[0172] The server integrates the collected data, corrects inconsistencies, and pre-processes it, including removing outliers, imputing missing data, and normalizing the data. Technologies used here include database management systems (e.g., MySQL) and data processing libraries (e.g., Pandas).

[0173] Demand forecasting

[0174] The server uses generative AI models based on the integrated data to forecast demand, predicting demand for specific time periods and locations and creating efficient delivery plans. The AI ​​models used include TensorFlow and PyTorch.

[0175] Vehicle routing generation

[0176] Based on the demand forecast results, the server generates the optimal vehicle dispatch route, taking into account traffic conditions and driver location information, using a pre-trained routing algorithm and real-time route optimization technology.

[0177] Driver Notification

[0178] The server then notifies the driver of the generated route information, which is then used as a smartphone or tablet, and the driver then travels efficiently based on the route information.

[0179] Real-time updates and feedback

[0180] The server receives feedback from the driver's device, updates the demand forecast model, and re-optimizes the vehicle dispatch route as needed, enabling efficient delivery in real time.

[0181] Receiving requests from users

[0182] Customers can send food delivery requests from their smartphones or tablets, including information such as origin, destination, and desired time.

[0183] Driver Selection

[0184] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is then notified of the request information, ensuring a smooth delivery.

[0185] Specific examples

[0186] Ordering: A user wants a pizza delivered to their home at 6pm.

[0187] Prediction: Based on traffic conditions at 6 p.m. and historical data, the AI ​​model predicts that orders will be concentrated in a particular area at that time.

[0188] Notification: Driver A is notified of the optimal route and picks up the order at the nearest pizza place, and immediately begins delivering it along the specified route.

[0189] Example prompt sentence:

[0190] A user wants a pizza delivered to their home (Address: [Address]) at 6 PM. Based on the traffic conditions and historical data for this time, predict the optimal delivery route and notify the driver.

[0191] This system enables fast and efficient delivery for food delivery services, which will improve service quality and significantly increase the satisfaction of drivers and customers.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1: Data collection The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information. This data is acquired through various APIs and GPS devices. Input includes data acquired from APIs on the Internet, and this data is stored on the server as output.

[0194] Step 2: Data integration and preprocessing. The server integrates the collected data, corrects inconsistencies, and performs preprocessing. This includes removing outliers, imputing missing data, and normalizing the data. The input is the collected raw data, and the output is a preprocessed, high-quality dataset.

[0195] Step 3: Demand Forecasting The server uses a generative AI model based on the integrated data to perform demand forecasting. This predicts demand for specific time periods and locations. The input includes preprocessed data, and the output is the demand forecast result.

[0196] Step 4: Vehicle dispatch route generation The server generates the optimal vehicle dispatch route based on the demand forecast results, taking into account traffic conditions and driver location information. The inputs include demand forecast results, real-time traffic data, and driver location data, and the optimal vehicle dispatch route information is generated as the output.

[0197] Step 5: Notify the driver The server notifies the driver's terminal of the generated vehicle dispatch route information. The input is the optimal route information, and the output is a notification sent to the driver's terminal.

[0198] Step 6: Real-time updates and feedback. The server receives location information and progress information sent from the driver's device, updates the demand forecast model, and re-optimizes the dispatch route. The input includes real-time feedback information from the driver, and the output is an updated demand forecast result and a re-optimized route.

[0199] Step 7: Receiving a request from the user The user sends a request for a ride from their own device. The input includes information on the departure point, destination, and desired time, and the request information is stored in the server as output.

[0200] Step 8: Driver Selection The server selects the most suitable driver based on the received request and driver location information. The input is the ride request information and the driver's location data, and the output is a request notification to the selected driver.

[0201] 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.

[0202] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions.The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[0203] System Operation

[0204] 1. Data Collection

[0205] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information. It also collects user emotional data. Emotional data is collected on the device through the user's voice, text, images, etc.

[0206] 2. Data integration and preprocessing

[0207] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[0208] 3. Demand forecasting

[0209] The server performs demand forecasting based on the preprocessed data. The integrated data is input into an AI model to predict traffic demand for the next certain period of time. Emotional data analyzed by the emotion engine is also reflected in this prediction model. For example, if many users are feeling stressed, it may determine that there is a possibility of increased demand for rides in that area.

[0210] 4. Applying the Emotion Engine

[0211] The device (user's smartphone) sends data such as voice, text, and images input by the user to the emotion engine. The emotion engine analyzes this data and identifies the user's current emotional state. For example, if the user is irritated, that information is sent to the server.

[0212] 5. Vehicle routing generation

[0213] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route. For example, if the user wants to relax, it will suggest a route that avoids congestion.

[0214] 6. Route notification to drivers

[0215] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server, allowing the driver to travel efficiently and providing a service that takes into account the user's emotional state.

[0216] 7. Real-time updates and feedback

[0217] The device (driver's smartphone) sends real-time location information and progress status to the server. The server also receives emotional feedback information and updates the demand forecast model to provide more accurate vehicle dispatch routes.

[0218] 8. Receiving requests from users

[0219] Users can send a ride request to the server through the app. At this time, users can also input their emotional state. For example, information such as "I'm tired" or "I'm in a hurry" can be included in the request.

[0220] 9. Driver Selection and Notification

[0221] The server selects the most suitable driver based on the received request, the driver's current location, demand forecast data, and emotional data. The selected driver is also notified of the user's emotional state and instructed if special measures are required.

[0222] Specific examples

[0223] Example 1: Stress-reducing ride-hailing in urban areas

[0224] The server receives data that indicates that many users feel stressed during the morning commute. Based on this information, the server can provide quieter routes to users who feel stressed, reduce their stress, and select an appropriate driver to provide a relaxing in-car environment for users.

[0225] Example 2: Comfortable transportation at local events

[0226] The server receives emotional data from many users at local event venues, expressing their tiredness. Based on this information, it generates routes with minimal waiting time at the end of the event and prioritizes dispatching vehicles to tired users. In addition, it selects the most suitable vehicle and driver to ensure a comfortable trip.

[0227] In this way, by using an emotion engine in addition to collecting real-time data and forecasting demand, the present invention can provide optimal ride-hailing routes that take into account the user's emotional state, improving the user experience. In particular, by utilizing emotion data, an efficient and satisfying ride-sharing service can be realized in alleviating congestion in urban areas and securing transportation in rural areas.

[0228] The processing flow will be explained below.

[0229] Step 1: Data collection

[0230] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[0231] The device (user's smartphone) sends the user's emotional data, such as voice, text, and images, to the emotion engine, which then transfers it to the server. For example, if the user is feeling stressed, the engine collects their voice data.

[0232] Step 2: Data integration and preprocessing

[0233] The server then integrates the collected data into a single dataset, corrects inconsistencies and gaps, and normalizes the data. It also preprocesses the emotion data to create a consistent format.

[0234] For example, it removes outliers, fills in missing data, and converts all data into an input format for the AI ​​model.

[0235] Step 3: Applying the Emotion Engine

[0236] The device (user's smartphone) sends the voice, text, and image data collected from the user to the emotion engine, which analyzes this data and identifies the user's emotional state.

[0237] The server receives the emotional data analyzed by the emotion engine and determines the user's current emotional state.

[0238] Step 4: Demand forecast

[0239] The server uses the integrated data to predict traffic demand for the next certain period using an AI model, and also incorporates emotion data obtained by the emotion engine into this model.

[0240] For example, if many users in an area where an event is being held express the emotion "tired," it is predicted that demand in that area will increase.

[0241] Step 5: Generate a vehicle routing route

[0242] The server generates optimal vehicle dispatch routes based on predicted demand and user emotional data, and selects the most suitable route and driver based on the emotional data.

[0243] For example, if a user is looking to relax, the system will suggest a route that avoids crowded areas.

[0244] Step 6: Notify your driver of the route

[0245] The terminal (driver's smartphone) receives route information sent from the server and moves according to that route. The driver is also notified of the user's emotional state.

[0246] For example, the server may provide the driver with instructions such as, "The user wants to relax, so please choose a quiet route."

[0247] Step 7: Real-time updates and feedback

[0248] The device (driver's smartphone) transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[0249] For example, if a traffic jam occurs along the way, the server calculates a new optimal route and notifies the driver.

[0250] Step 8: Receiving a request from the user

[0251] A user sends a ride request to the server through a ride-sharing app, which includes the origin, destination, desired time, and emotional state.

[0252] For example, emotional information such as "I'm tired" is also included in the request.

[0253] Step 9: Driver selection and notification

[0254] The server selects the most suitable driver based on the received ride request, the driver's current location information, demand forecast data, and emotional data. The selected driver is notified of the request information and the user's emotional state.

[0255] For example, "because the user is tired, a driver who can arrive quickly" is selected and the request information is notified.

[0256] In this way, the present invention combines real-time data collection and demand forecasting with an emotion engine to provide optimal vehicle dispatch routes that take into account the emotional state of the user. This not only contributes to reducing congestion, particularly in urban areas, and ensuring transportation options in rural areas, but also improves the user experience.

[0257] Example 2

[0258] 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."

[0259] Improving the user experience is crucial for modern ride-sharing services. However, existing systems rely on objective data such as traffic conditions and map information to predict demand and generate dispatch routes, making it difficult to provide services that take into account the user's emotional state. In particular, there is a problem in that appropriate responses are not provided to users experiencing increased stress or fatigue, limiting the improvement of user satisfaction.

[0260] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting user emotion data from voice, text, and image data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and user emotion data, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating the demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request, driver location information, and user emotion data, and means for notifying the selected driver of the request information. This enables demand forecasting and generation of vehicle dispatch routes that take the user's emotional state into consideration.

[0261] "Traffic condition data" refers to data that includes information on current traffic flow, congestion, accidents, and the like.

[0262] "Map information data" refers to data that includes information on geographical locations, topography, road networks, and the like.

[0263] "People distribution data" is data that contains information about the presence and density of people within a particular region or area.

[0264] "Congestion data for surrounding facilities" is data that includes information on the congestion status of commercial facilities, public transportation, tourist spots, etc.

[0265] "Event information" is data that includes information about events or activities that are held at specific dates, times, and locations.

[0266] "Emotional data" refers to data that contains information about people's emotional states, analyzed based on audio, text, and image data.

[0267] "Preprocessing" refers to processes such as removing outliers, filling in missing data, and normalizing data in order to prepare collected data for easier analysis.

[0268] "Demand forecasting" refers to predicting transportation demand for a certain period of time in the future based on collected data.

[0269] "Vehicle dispatch route" refers to the optimal route from the user's boarding point to their destination.

[0270] "Driver device" refers to an electronic device used by a driver, such as a smartphone or tablet.

[0271] "Feedback information" refers to data including information on evaluations of services and areas for improvement provided by drivers and users.

[0272] "User terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[0273] A "ride request" refers to a ride request sent by a user to use a ride-sharing service.

[0274] The "best driver" refers to the most suitable driver based on the received ride request, the driver's current location, demand forecast data, and emotional data.

[0275] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions. The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[0276] The server uses various APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. This allows the server to obtain the latest information in real time. It also collects data such as voice, text, and images from the device, and obtains user emotion data. This is done using NLP and image recognition technologies.

[0277] The collected data is integrated on the server, where it undergoes preprocessing, such as removing outliers, filling in missing data, and normalizing the data. It is expected that Python's pandas library will be used. After preprocessing, the data is input into a demand forecasting model, which uses a generative AI model (such as TensorFlow or PyTorch).

[0278] The demand forecasting model predicts traffic demand for the next set period based on traffic condition data, map information data, emotion data, etc. Based on this prediction result, the server generates the optimal vehicle dispatch route. If the user is emotionally tired, for example, it is possible to suggest routes that avoid congestion or quieter routes by reflecting the emotion data.

[0279] For example, if a user inputs "I'm tired," the server will integrate that emotion data and suggest a quieter route. It also takes into account the driver's location information to select the most suitable driver. During this selection process, the server selects the most suitable driver based on the received ride request, traffic data, and driver location information, and notifies the driver of the request.

[0280] Specifically, the server receives data from the emotion engine indicating that many users are feeling stressed during the morning rush hour. Based on this data, the server notifies users who are feeling stressed by saying, "A quieter route has been selected." The server also notifies the driver's device that, "This user is currently feeling stressed, so please try to drive comfortably."

[0281] As an example of a local event, the server receives emotional data from many users at the event venue, expressing their "tiredness." At the end of the event, the server generates a route that avoids routes that are likely to be crowded and minimizes waiting times. The server notifies the user that "a route for a comfortable trip has been selected," and instructs the driver that "this user is tired, so please be considerate."

[0282] In this way, the present invention can provide an optimal vehicle dispatch route that takes into account the user's emotional state by using an emotion engine in addition to collecting real-time data and forecasting demand.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1: Data collection

[0285] The server uses APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. It also obtains voice, text, and image data from the device (user's smartphone) and uses this to collect user emotion data. This allows the latest information to be obtained in real time. The input is various types of data, and the output is the raw data that combines these.

[0286] Step 2: Data integration and preprocessing

[0287] The server integrates all collected data using libraries such as pandas. During this process, preprocessing such as removing outliers, filling in missing data, and normalizing the data is performed. For example, missing location information data is filled in and the overall data is formatted for easier analysis. The input is the raw data, and the output is the preprocessed data.

[0288] Step 3: Demand forecast

[0289] The server inputs the preprocessed data into an AI model (using, for example, TensorFlow or PyTorch) to predict traffic demand. This model uses traffic condition data, map information data, people distribution data, congestion data at nearby facilities, event information, emotional data, and more. For example, if the emotion engine determines that many users are "feeling stressed," it predicts that demand in that area will increase. The input is the preprocessed data, and the output is the demand forecast results.

[0290] Step 4: Applying the Emotion Engine

[0291] The device (user's smartphone) sends voice, text, and image data to the emotion engine for analysis. NLP and image recognition technologies are used to identify the user's emotional state. For example, if the user inputs "I'm tired," the engine determines that "the user is currently tired" based on that data and sends that information to the server. The input is emotional data from the user, and the output is analyzed emotional information.

[0292] Step 5: Generate a vehicle routing route

[0293] The server generates an optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects a quiet route that avoids congestion or a route that requires immediate attention. For example, if the user sends emotional data indicating that they are "in a hurry," it selects the shortest route and the nearest driver. The input is the demand forecast result and emotional information, and the output is an optimized vehicle dispatch route.

[0294] Step 6: Notify your driver of the route

[0295] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server. For example, the server generates a "specific route to avoid congestion" and notifies the driver, who then follows that route. The input is the optimal dispatch route, and the output is the route display to the driver.

[0296] Step 7: Real-time updates and feedback

[0297] The device (driver's smartphone) sends real-time location information and progress status to the server. The server dynamically adjusts the dispatch route based on this information and updates the demand forecasting model. It also collects feedback from users and reflects that data in the demand forecasting model. The inputs are real-time data and feedback information, and the outputs are an updated demand forecasting model and an optimized route.

[0298] Step 8: Receiving a request from the user

[0299] The user sends a request for a ride to the server using the user terminal. At this time, the user can also input their emotional state. For example, they can send information such as "I'm in a hurry" or "I'm tired," and the data is also provided to the server. The input is the ride request and emotional information, and the output is the request data.

[0300] Step 9: Driver selection and notification

[0301] The server selects the optimal driver based on the received ride request, the current driver's location information, demand forecast data, and emotional data. For example, if it determines that the user is in a hurry, it selects the nearest driver and notifies that driver of the user's emotional state. The inputs are the ride request, the driver's location information, demand forecast data, and emotional data, and the output is the selected driver and notification of the request information.

[0302] (Application example 2)

[0303] 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."

[0304] As ride-sharing services have become more widespread in recent years, there is a demand for systems that can improve passenger travel experiences. It is particularly important to provide services that take into account passengers' emotional states, but current systems have difficulty fully reflecting this. Conventional dispatch systems forecast demand based on traffic conditions, map information, pedestrian distribution, congestion at nearby facilities, and event information. However, they lack mechanisms for collecting and analyzing passenger emotional data to provide optimal dispatch routes and in-car environments. To resolve this technical challenge, a new system is needed.

[0305] 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.

[0306] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting emotional state data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, and means for analyzing the emotional data using a generative AI model and optimizing the corresponding route and in-vehicle environment. This makes it possible to generate an optimal vehicle dispatch route that takes into account the emotional state of passengers and provide a comfortable in-vehicle environment.

[0307] "Traffic condition data" refers to various types of information related to traffic, such as traffic flow, congestion, traffic accident information, and road closure status.

[0308] "Map information data" refers to various information related to maps, such as geographical location information, the layout of road networks and facilities, and route information.

[0309] "Person distribution data" refers to information about the distribution of people, such as the number of people present in a particular area, their travel routes, and the length of their stay.

[0310] "Crowding data for surrounding facilities" refers to information on the congestion status, number of users, waiting times, etc. of specific facilities or locations.

[0311] "Event information" is information about the date, location, scale, and content of an event held in a specific area.

[0312] "Emotional state data" is information indicating the emotional state of a user that is obtained by analyzing the user's voice, text, images, and the like.

[0313] A "demand forecasting model" is an algorithm or mathematical model for predicting future demand based on collected data.

[0314] A "vehicle dispatch route" is a route that optimally guides a user to their destination, and is designed based on traffic conditions and various data.

[0315] A "driver terminal" is an electronic device such as a smartphone or tablet used by a driver to receive information about dispatch routes and demand forecasts.

[0316] A "user terminal" is an electronic device such as a smartphone or tablet used by a user, and is a terminal for transmitting ride requests and emotional state data.

[0317] A "generative AI model" is an artificial intelligence model that is trained to perform specific tasks using large amounts of data.

[0318] A "prompt" is an instruction given to a generative AI model to perform a specific task.

[0319] This invention is a demand forecasting system that collects and integrates real-time traffic conditions, map information, people distribution, congestion at nearby facilities, event information, etc. This system also aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotional state.

[0320] System Overview

[0321] This system consists of the following hardware and software:

[0322] Server: Collects, integrates, pre-processes, forecasts, routes, and updates data.

[0323] User terminal: Collects emotional data and ride requests from users.

[0324] Driver device: Used for route notifications and feedback.

[0325] Operation of each method

[0326] 1. Data Collection

[0327] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. Emotional state data is also collected from the user's device via voice, text, images, etc.

[0328] 2. Data integration and preprocessing

[0329] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[0330] 3. Demand forecasting

[0331] The server then inputs the pre-processed data into an AI model to generate demand forecasts. If many users are feeling stressed, it predicts that demand for rides in that area is likely to increase.

[0332] 4. Applying the Emotion Engine

[0333] Data such as voice, text, and images collected on the user's device are sent to the emotion engine for analysis. For example, if the user is frustrated, that information is sent to the server.

[0334] 5. Vehicle routing generation

[0335] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route.

[0336] 6. Route notification to drivers

[0337] The driver's terminal receives and displays the vehicle dispatch route information transmitted from the server.

[0338] Usage example

[0339] As a specific use case, consider a case where a passenger feels stressed during their commute. The emotion engine detects the stress and transmits the information to the server. The server uses this information to optimize a quieter route that avoids congestion and notifies the driver. This allows the passenger to reach their destination in a relaxed state.

[0340] Example prompt for a generative AI model:

[0341] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[0342] Through the steps described above, the present invention realizes an efficient and satisfying ride-sharing service that integrates real-time data and emotional data.

[0343] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0344] Step 1:

[0345] Data collection

[0346] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information via API. Emotional state data is collected from user devices through voice, text, and images. All of this data is sent to the server. Input data is obtained from various APIs and emotion engines, and output data is integrated, unprocessed raw data.

[0347] Step 2:

[0348] Data integration and preprocessing

[0349] The server removes outliers from the collected data, fills in missing data, and normalizes the data. It also preprocesses emotion data in the same way. The input data is all the collected raw data, and the output data is preprocessed data with outliers removed and normalized. Specifically, it applies a data cleansing algorithm to detect outliers and missing values ​​and fill them in.

[0350] Step 3:

[0351] Demand forecasting

[0352] Based on the preprocessed data, the server uses a generative AI model to perform demand forecasting. The input data is the preprocessed data, and the output data is the demand forecast data for the next fixed time period. Specifically, the integrated data is input into the AI ​​model, and demand forecasting is performed using prompt statements. For example, the demand for rides in each area is predicted according to the prompt statements.

[0353] Step 4:

[0354] Applying the Emotion Engine

[0355] The voice, text, and image data collected on the user's device are sent to the emotion engine for analysis. The analysis results (emotional state data) are sent to the server by the emotion engine. The input data is the user's emotional state data, and the output data is the analyzed emotional state information. Specifically, the emotion engine performs voice tone, facial expression recognition, and text analysis to identify the emotional state.

[0356] Step 5:

[0357] Vehicle routing generation

[0358] The server generates an optimal vehicle dispatch route based on the demand forecast data and emotion data. The input data is the demand forecast data and emotion data, and the output data is optimal vehicle dispatch route information. Specifically, the server uses a route optimization algorithm to generate a route that the user feels comfortable with and selects the optimal driver.

[0359] Step 6:

[0360] Route notification to the driver

[0361] The driver's device receives and displays the dispatch route information sent from the server. The input data is the optimal dispatch route information, and the output data is the route displayed on the driver's device. Specifically, the route information is pushed to the driver's device, and the driver begins traveling based on that information.

[0362] Step 7:

[0363] Receiving feedback information

[0364] The driver's device sends feedback information to the server during travel, including driving data and the user's emotional state. The input data is feedback information, and the output data is data that is reflected in updating the demand forecasting model. Specifically, the driver's device sends real-time location information and the user's reactions to the server.

[0365] Step 8:

[0366] Update demand forecast models

[0367] The server updates the demand forecasting model based on the received feedback information. The input data is the feedback information, and the output data is the updated demand forecasting model. Specifically, the AI ​​model is retrained based on the feedback information to improve the accuracy of the next demand forecast.

[0368] Example prompt sentence:

[0369] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[0370] 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.

[0371] 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.

[0372] 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.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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."

[0386] This invention is a system that collects and integrates traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information in real time. Based on this data, it performs demand forecasting, generates efficient vehicle dispatch routes, and notifies drivers. Furthermore, upon receiving a vehicle dispatch request from a user, it selects the most suitable driver and notifies the request information, thereby quickly responding to user needs.

[0387] System Operation

[0388] 1. Data Collection

[0389] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information, allowing the latest situation to be grasped in real time.

[0390] 2. Data integration and preprocessing

[0391] The server consolidates the collected data, corrects inconsistencies, improves data quality by removing outliers and imputing missing data, and normalizes the data to prepare it for input into the AI ​​model.

[0392] 3. Demand forecasting

[0393] The server uses the integrated data to predict demand for the next certain period of time, taking into account factors such as the day of the week, time of day, weather, and events, and identifies areas where travel demand will be high.

[0394] 4. Vehicle routing generation

[0395] The server generates optimal vehicle dispatch routes based on predicted demand data, taking into account current traffic conditions and the driver's location.

[0396] 5. Driver Notification

[0397] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server, allowing the driver to travel efficiently.

[0398] 6. Real-time updates and feedback

[0399] During the journey, the driver's device transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[0400] 7. Receiving requests from users

[0401] Users send a ride request through the app, which includes information such as the departure point, destination, and desired time.

[0402] 8. Driver Selection

[0403] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is notified of the request information and is given instructions on how to get to the departure point.

[0404] Specific examples

[0405] Example 1: Urban commute hours

[0406] The server predicts that demand for rides from business districts to stations will increase at 5 p.m. Ten minutes before the scheduled time, it suggests routes for nearby drivers to wait in front of the station, making it easier for commuters to board rides in front of the station, improving convenience.

[0407] Example 2: When a local event is held

[0408] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates increased demand in the surrounding area. Before the event begins, the server suggests routes for drivers to wait in the area, ensuring smooth transportation for event participants.

[0409] In this way, the present invention can provide an efficient ride-sharing service by combining real-time data collection, demand forecasting, and vehicle route optimization, which can particularly contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas.

[0410] The processing flow will be explained below.

[0411] Step 1: Data collection

[0412] The server periodically collects traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information. Traffic condition data includes road congestion information and travel speeds, and map information data includes coordinate information for roads and landmarks. People distribution data indicates the population density and movement patterns in a specific area, and congestion data at nearby facilities provides the number of users at major spots. Event information includes the date, time, and location of the event.

[0413] Step 2: Data integration and preprocessing

[0414] The server integrates the collected data, detects and removes outliers, fills in missing data, and normalizes the data. If there are inconsistencies in traffic condition data or pedestrian distribution data, it corrects them and converts them into a consistent format. If there are gaps in aerial photograph data or congestion data, it fills in the gaps based on surrounding data. It also standardizes all data so that it can be used by AI models.

[0415] Step 3: Demand forecast

[0416] The server uses the preprocessed data to perform demand forecasts. It inputs the collected data into an AI model to predict traffic demand for the next certain period. For example, the predictive model calculates which areas will experience demand, taking into account specific days of the week, time periods, events, and weather information.

[0417] Step 4: Generate a vehicle routing route

[0418] The server generates optimal vehicle dispatch routes based on predicted demand data. It uses Dijkstra and A algorithms to calculate optimal routes that reflect real-time traffic conditions and each driver's location. The generated routes also take into account the driver's fuel consumption and time efficiency.

[0419] Step 5: Send route to driver

[0420] The terminal (driver's smartphone) receives the dispatch route information sent from the server. The driver follows the displayed route information and heads to the passenger's pickup point. This information is updated regularly, providing the optimal route based on the latest conditions.

[0421] Step 6: Real-time updates and feedback

[0422] The device (the driver's smartphone) sends its current location and progress information to the server in real time. For example, if an unexpected traffic jam or accident occurs, the server recalculates the demand forecast model based on the latest information and re-optimizes the route. This ensures that the driver is always provided with the most up-to-date dispatch route.

[0423] Step 7: Receiving a request from the user

[0424] A user (customer) sends a ride request to the server through a ride-sharing app. This request includes details such as the origin, destination, and desired time, allowing the server to recognize the user's transportation needs.

[0425] Step 8: Driver selection and notification

[0426] The server selects the most suitable driver based on the received ride request, the driver's current location information, and demand forecast data. It applies the Greedy algorithm to select a driver who meets the user's request with the shortest travel distance and time. At the same time, it notifies the selected driver of the request information and provides instructions on how to get to the departure point. This information is displayed on the driver's device, and an appropriate ride is dispatched.

[0427] Example 1

[0428] 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."

[0429] In modern urban and rural areas, real-time vehicle demand forecasting and optimal route generation are required to improve transportation efficiency and travel convenience. However, current systems collect individual data but do not adequately integrate data processing, demand forecasting, and vehicle route optimization. This results in reduced transportation efficiency and inconvenience for users and drivers. Furthermore, there is a lack of systems that can respond to real-time feedback and updates. To address these issues, this invention proposes a system that integrates comprehensive data processing with advanced prediction and optimization methods.

[0430] 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.

[0431] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating the collected data, correcting inconsistencies, and performing preprocessing, means for predicting demand for the next certain period based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and taking into account current traffic conditions and the driver's location, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving real-time update information from the driver terminal, updating the demand forecast model, and re-optimizing the route as necessary, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, and means for notifying the selected driver of the request information and providing directions. This enables data integration processing and real-time prediction and optimization.

[0432] "Traffic condition data" refers to data that includes information on road congestion, traffic accidents, construction works, and the like.

[0433] "Map information data" refers to data including geographical location information, road maps, and building layouts.

[0434] "People distribution data" is data that shows patterns of people gathering and moving in specific areas and at specific times.

[0435] "Congestion data for surrounding facilities" is data that indicates the usage status and congestion level of commercial facilities, public facilities, etc.

[0436] "Event information" is data about public events such as concerts, sports games, and festivals.

[0437] "Means for integrating data, correcting inconsistencies, and preprocessing" refers to means for integrating various collected data into a single format and correcting inconsistencies and missing data.

[0438] The "means for forecasting demand" is a means for forecasting demand for vehicle dispatch within a certain period of time in the future based on the integrated data.

[0439] "Means for generating optimal vehicle dispatch routes" refers to means for calculating and generating the most efficient routes based on predicted demand, real-time traffic conditions, and the driver's location.

[0440] "Driver terminal" refers to a device such as a smartphone or tablet used by the driver, which receives and displays information from the server.

[0441] "Real-time updates" are the latest data generated while on the move, such as the driver's location and progress.

[0442] A "user terminal" refers to a device such as a smartphone or tablet used by a user who uses a vehicle dispatch service, and is a terminal used to send a vehicle dispatch request to the server.

[0443] A "ride request" is a request sent by a user through the app, including information such as the departure point, destination, and desired time.

[0444] The "means for selecting the best driver" is a means for selecting the driver who can most efficiently handle the request based on the ride request and the driver's current location information.

[0445] "Means for notifying request information and providing directions" refers to means for notifying the selected driver of details of the ride request and providing guidance on the optimal route to the specified departure point.

[0446] This invention is a system that collects and integrates multiple data in real time, and based on that data, predicts transportation demand and generates optimal vehicle dispatch routes. This system is composed of a server, terminals, and users, and aims to provide an efficient ride-sharing service.

[0447] Hardware and software used

[0448] The server is the central unit that performs advanced data processing and predictive calculations and utilizes the following software and libraries:

[0449] Data collection: We use Google Maps API, HERE Maps, public open data portals, etc. to collect traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[0450] Data integration and preprocessing: We use the pandas and NumPy libraries to integrate the collected data and correct inconsistencies, thereby imputing missing data and removing outliers.

[0451] Demand forecasting: Based on the integrated data, we use a time series forecasting model (e.g., ARIMA, LSTM) to forecast the demand within the next certain time period.

[0452] Vehicle routing generation: Uses the A algorithm and Dijkstra's algorithm to generate optimal vehicle routing based on predicted demand data, current traffic conditions, and driver location information.

[0453] Notification service: Google Firebase and Apple Push Notification service are used to notify drivers of the generated optimal route information.

[0454] Real-time updates: Using WebSocket or MQTT protocols, the driver's location and progress are sent to the server in real time.

[0455] The terminals (driver terminal and user terminal) are mobile devices such as smartphones and tablets. These terminals have the following functions:

[0456] Driver's device: Receives and displays real-time route information sent from the server. Also, transfers real-time updated information sent from the device to the server.

[0457] User terminal: Sends a ride request to the server. The front-end app is built using React Native or Flutter, and communicates with the back-end via a RESTful API to send requests.

[0458] A user is a person who uses a smartphone or tablet to use a ride-hailing service. The user inputs the departure point, destination, and desired time and sends a request to the server.

[0459] Specific examples

[0460] Example 1: Urban commute hours

[0461] The server predicts that demand for travel from the office district to the station will increase at 5 p.m. Specifically, it uses information that, "According to traffic data, the roads from the office district to the station are usually congested at 5 p.m." The server then suggests a route to nearby drivers 10 minutes in advance, telling them to "wait in front of the station." The driver's device receives this notification, allowing the driver to head to the station efficiently. Commuters can board smoothly in front of the station, improving travel convenience.

[0462] Example 2: When a local event is held

[0463] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates an increase in demand for travel to the surrounding area. Specifically, it uses forecast data that shows that "events in tourist destinations over the weekend will attract large crowds." It then suggests a route to the driver to wait in the vicinity before the event begins, telling them to "wait near the event venue." The driver's device receives the instructions and follows the directions, allowing event participants to reach the event site smoothly.

[0464] Prompt Sentence Examples

[0465] Below are some examples of prompts for the generative AI model:

[0466] "Please forecast major traffic demand this weekend."

[0467] "Generate the optimal route from the office district to the station between 5:00 PM and 6:00 PM."

[0468] "Re-optimize your vehicle routes around the event, taking into account real-time traffic conditions and driver location."

[0469] In this way, the present invention can contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas by collecting data in real time and generating efficient demand forecasts and optimal routes based on that data.

[0470] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0471] Step 1:

[0472] Data collection

[0473] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information through APIs. It uses Google Maps API, HERE Maps, public open data portals, etc. as input and obtains the necessary data from these services. The output is a collection of raw data obtained from each data source. Specifically, the server sends requests to each API and receives and stores the data returned as a response.

[0474] Step 2:

[0475] Data integration and preprocessing

[0476] The server integrates the collected data, corrects inconsistencies, and performs preprocessing. The input is the raw data from each data source collected in step 1. The output is an integrated and cleaned dataset. Specific operations include removing outliers, imputing missing data, and normalizing the data using the pandas and NumPy libraries. For example, missing values ​​are imputed with surrounding values, and outliers are removed using a specific threshold.

[0477] Step 3:

[0478] Demand forecasting

[0479] The server predicts demand for the next set of hours based on the integrated data. The input is the integrated dataset generated in step 2. The output is a forecast value from the demand forecasting model. Specifically, it uses a time series forecasting model (e.g., ARIMA, LSTM) to make predictions taking into account factors such as the day of the week, time, weather, and event information. For example, it predicts that "demand from the office district to the station will increase at 5 p.m. on Monday."

[0480] Step 4:

[0481] Vehicle routing generation

[0482] The server combines the predicted demand data, current traffic conditions, and the driver's location to generate the optimal vehicle dispatch route. The inputs are the predicted data obtained in step 3, real-time traffic information, and the driver's location information. The output is the optimal vehicle dispatch route. Specifically, it calculates the shortest route using the A algorithm or Dijkstra's algorithm, and adjusts the route by incorporating real-time traffic data.

[0483] Step 5:

[0484] Driver Notification

[0485] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server in real time. The input is the route information generated in step 4. The output is the dispatch route displayed on the driver's terminal. Specifically, the route information is pushed to the driver's smartphone using Google Firebase or Apple Push Notification service.

[0486] Step 6:

[0487] Real-time updates and feedback

[0488] The driver's device transmits real-time location information and progress status to the server during travel. The input is the driver's current location and progress data. The output is real-time updated data received by the server. Specifically, location information is sent to the server with low latency using WebSocket or MQTT protocols, and the server uses this data to update its demand forecasting model and re-optimize routes as needed.

[0489] Step 7:

[0490] Receiving requests from users

[0491] A user sends a ride request to the server via a smartphone app. The input is information such as the departure point, destination, and desired time entered by the user. The output is the ride request received by the server. Specifically, the user enters the destination and desired time on the app screen, and then sends that information to the server via a RESTful API.

[0492] Step 8:

[0493] Driver Selection

[0494] The server selects the most suitable driver based on the received request and the driver's current location information. The input is the ride request and the driver's current location information. The output is the selected driver and notification information. Specifically, it uses a bipartite matching algorithm to select the driver who can most efficiently handle the request, notifies the driver of the request information, and provides directions on how to get there.

[0495] (Application example 1)

[0496] 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."

[0497] Modern food delivery services face many challenges in achieving efficient delivery operations. Among these, generating optimal routes in real time in response to fluctuations in traffic conditions and demand, and quickly selecting drivers are particularly important. However, systems that can handle these variables have not yet been adequately developed, which could significantly reduce driver and customer satisfaction. Furthermore, there is a lack of a way to reoptimize delivery routes based on real-time feedback, which also impacts operational efficiency. A new system is needed to resolve these issues.

[0498] 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.

[0499] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating and pre-processing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, means for improving the delivery efficiency of delivery drivers based on the demand forecast and the optimal route generation in a food delivery service, and means for re-optimizing the delivery route based on real-time feedback information, thereby enabling fast and efficient delivery in a food delivery service.

[0500] 1. "Traffic condition data" refers to all information related to traffic, such as road congestion, accident information, and traffic signal status.

[0501] 2. "Map information data" means data that includes geographical location information and detailed road information.

[0502] 3. "Person distribution data" refers to data that shows the concentration and distribution of people in a particular area.

[0503] 4. "Congestion data for surrounding facilities" refers to data that indicates the degree of congestion and the number of people staying at a specific facility or location.

[0504] 5. "Event Information" refers to information about events or occasions held in a specific area or time.

[0505] 6. "Demand forecasting model" refers to an algorithm or machine learning model that forecasts demand in a specific region or time based on various collected data.

[0506] 7. "Optimal vehicle routing" refers to the best route calculated to reach a destination efficiently.

[0507] 8. "Driver device" refers to a device such as a smartphone or tablet held by the driver.

[0508] 9. "Feedback Information" means location, progress, and other information provided by a driver during a delivery.

[0509] 10. "User terminal" refers to a device such as a smartphone or tablet used by a User to submit an order or request.

[0510] 11. "Vehicle request" refers to the vehicle dispatch request information sent by a User.

[0511] 12. "Demand forecasting" refers to the process of estimating future demand for services based on collected data.

[0512] 13. “Optimization” refers to the process of adjusting parameters or conditions to obtain the best results in order to achieve a specific goal.

[0513] 14. "Real-time feedback" refers to immediate information provided by the driver or user.

[0514] This invention is a system for realizing efficient and prompt delivery operations in food delivery services. Specifically, it collects traffic condition data, map information data, people distribution data, congestion data at surrounding facilities, and event information in real time, and integrates and preprocesses them. It then forecasts demand based on this data, generates optimal vehicle dispatch routes, and notifies drivers. It also receives dispatch requests from users, selects the most suitable driver, and notifies them of the request information. It also reoptimizes delivery routes based on real-time feedback information.

[0515] Specific system configuration and operation

[0516] Data collection

[0517] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information, including information from various APIs on the Internet and GPS devices. The software used includes the Python requests library.

[0518] Data integration and preprocessing

[0519] The server integrates the collected data, corrects inconsistencies, and pre-processes it, including removing outliers, imputing missing data, and normalizing the data. Technologies used here include database management systems (e.g., MySQL) and data processing libraries (e.g., Pandas).

[0520] Demand forecasting

[0521] The server uses generative AI models based on the integrated data to forecast demand, predicting demand for specific time periods and locations and creating efficient delivery plans. The AI ​​models used include TensorFlow and PyTorch.

[0522] Vehicle routing generation

[0523] Based on the demand forecast results, the server generates the optimal vehicle dispatch route, taking into account traffic conditions and driver location information, using a pre-trained routing algorithm and real-time route optimization technology.

[0524] Driver Notification

[0525] The server then notifies the driver of the generated route information, which is then used as a smartphone or tablet, and the driver then travels efficiently based on the route information.

[0526] Real-time updates and feedback

[0527] The server receives feedback from the driver's device, updates the demand forecast model, and re-optimizes the vehicle dispatch route as needed, enabling efficient delivery in real time.

[0528] Receiving requests from users

[0529] Customers can send food delivery requests from their smartphones or tablets, including information such as origin, destination, and desired time.

[0530] Driver Selection

[0531] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is then notified of the request information, ensuring a smooth delivery.

[0532] Specific examples

[0533] Ordering: A user wants a pizza delivered to their home at 6pm.

[0534] Prediction: Based on traffic conditions at 6 p.m. and historical data, the AI ​​model predicts that orders will be concentrated in a particular area at that time.

[0535] Notification: Driver A is notified of the optimal route and picks up the order at the nearest pizza place, and immediately begins delivering it along the specified route.

[0536] Example prompt sentence:

[0537] A user wants a pizza delivered to their home (Address: [Address]) at 6 PM. Based on the traffic conditions and historical data for this time, predict the optimal delivery route and notify the driver.

[0538] This system enables fast and efficient delivery for food delivery services, which will improve service quality and significantly increase the satisfaction of drivers and customers.

[0539] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0540] Step 1: Data collection The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information. This data is acquired through various APIs and GPS devices. Input includes data acquired from APIs on the Internet, and this data is stored on the server as output.

[0541] Step 2: Data integration and preprocessing. The server integrates the collected data, corrects inconsistencies, and performs preprocessing. This includes removing outliers, imputing missing data, and normalizing the data. The input is the collected raw data, and the output is a preprocessed, high-quality dataset.

[0542] Step 3: Demand Forecasting The server uses a generative AI model based on the integrated data to perform demand forecasting. This predicts demand for specific time periods and locations. The input includes preprocessed data, and the output is the demand forecast result.

[0543] Step 4: Vehicle dispatch route generation The server generates the optimal vehicle dispatch route based on the demand forecast results, taking into account traffic conditions and driver location information. The inputs include demand forecast results, real-time traffic data, and driver location data, and the optimal vehicle dispatch route information is generated as the output.

[0544] Step 5: Notify the driver The server notifies the driver's terminal of the generated vehicle dispatch route information. The input is the optimal route information, and the output is a notification sent to the driver's terminal.

[0545] Step 6: Real-time updates and feedback. The server receives location information and progress information sent from the driver's device, updates the demand forecast model, and re-optimizes the dispatch route. The input includes real-time feedback information from the driver, and the output is an updated demand forecast result and a re-optimized route.

[0546] Step 7: Receiving a request from the user The user sends a request for a ride from their own device. The input includes information on the departure point, destination, and desired time, and the request information is stored in the server as output.

[0547] Step 8: Driver Selection The server selects the most suitable driver based on the received request and driver location information. The input is the ride request information and the driver's location data, and the output is a request notification to the selected driver.

[0548] 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.

[0549] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions.The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[0550] System Operation

[0551] 1. Data Collection

[0552] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information. It also collects user emotional data. Emotional data is collected on the device through the user's voice, text, images, etc.

[0553] 2. Data integration and preprocessing

[0554] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[0555] 3. Demand forecasting

[0556] The server performs demand forecasting based on the preprocessed data. The integrated data is input into an AI model to predict traffic demand for the next certain period of time. Emotional data analyzed by the emotion engine is also reflected in this prediction model. For example, if many users are feeling stressed, it may determine that there is a possibility of increased demand for rides in that area.

[0557] 4. Applying the Emotion Engine

[0558] The device (user's smartphone) sends data such as voice, text, and images input by the user to the emotion engine. The emotion engine analyzes this data and identifies the user's current emotional state. For example, if the user is irritated, that information is sent to the server.

[0559] 5. Vehicle routing generation

[0560] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route. For example, if the user wants to relax, it will suggest a route that avoids congestion.

[0561] 6. Route notification to drivers

[0562] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server, allowing the driver to travel efficiently and providing a service that takes into account the user's emotional state.

[0563] 7. Real-time updates and feedback

[0564] The device (driver's smartphone) sends real-time location information and progress status to the server. The server also receives emotional feedback information and updates the demand forecast model to provide more accurate vehicle dispatch routes.

[0565] 8. Receiving requests from users

[0566] Users can send a ride request to the server through the app. At this time, users can also input their emotional state. For example, information such as "I'm tired" or "I'm in a hurry" can be included in the request.

[0567] 9. Driver Selection and Notification

[0568] The server selects the most suitable driver based on the received request, the driver's current location, demand forecast data, and emotional data. The selected driver is also notified of the user's emotional state and instructed if special measures are required.

[0569] Specific examples

[0570] Example 1: Stress-reducing ride-hailing in urban areas

[0571] The server receives data that indicates that many users feel stressed during the morning commute. Based on this information, the server can provide quieter routes to users who feel stressed, reduce their stress, and select an appropriate driver to provide a relaxing in-car environment for users.

[0572] Example 2: Comfortable transportation at local events

[0573] The server receives emotional data from many users at local event venues, expressing their tiredness. Based on this information, it generates routes with minimal waiting time at the end of the event and prioritizes dispatching vehicles to tired users. In addition, it selects the most suitable vehicle and driver to ensure a comfortable trip.

[0574] In this way, by using an emotion engine in addition to collecting real-time data and forecasting demand, the present invention can provide optimal ride-hailing routes that take into account the user's emotional state, improving the user experience. In particular, by utilizing emotion data, an efficient and satisfying ride-sharing service can be realized in alleviating congestion in urban areas and securing transportation in rural areas.

[0575] The processing flow will be explained below.

[0576] Step 1: Data collection

[0577] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[0578] The device (user's smartphone) sends the user's emotional data, such as voice, text, and images, to the emotion engine, which then transfers it to the server. For example, if the user is feeling stressed, the engine collects their voice data.

[0579] Step 2: Data integration and preprocessing

[0580] The server then integrates the collected data into a single dataset, corrects inconsistencies and gaps, and normalizes the data. It also preprocesses the emotion data to create a consistent format.

[0581] For example, it removes outliers, fills in missing data, and converts all data into an input format for the AI ​​model.

[0582] Step 3: Applying the Emotion Engine

[0583] The device (user's smartphone) sends the voice, text, and image data collected from the user to the emotion engine, which analyzes this data and identifies the user's emotional state.

[0584] The server receives the emotional data analyzed by the emotion engine and determines the user's current emotional state.

[0585] Step 4: Demand forecast

[0586] The server uses the integrated data to predict traffic demand for the next certain period using an AI model, and also incorporates emotion data obtained by the emotion engine into this model.

[0587] For example, if many users in an area where an event is being held express the emotion "tired," it is predicted that demand in that area will increase.

[0588] Step 5: Generate a vehicle routing route

[0589] The server generates optimal vehicle dispatch routes based on predicted demand and user emotional data, and selects the most suitable route and driver based on the emotional data.

[0590] For example, if a user is looking to relax, the system will suggest a route that avoids crowded areas.

[0591] Step 6: Notify your driver of the route

[0592] The terminal (driver's smartphone) receives route information sent from the server and moves according to that route. The driver is also notified of the user's emotional state.

[0593] For example, the server may provide the driver with instructions such as, "The user wants to relax, so please choose a quiet route."

[0594] Step 7: Real-time updates and feedback

[0595] The device (driver's smartphone) transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[0596] For example, if a traffic jam occurs along the way, the server calculates a new optimal route and notifies the driver.

[0597] Step 8: Receiving a request from the user

[0598] A user sends a ride request to the server through a ride-sharing app, which includes the origin, destination, desired time, and emotional state.

[0599] For example, emotional information such as "I'm tired" is also included in the request.

[0600] Step 9: Driver selection and notification

[0601] The server selects the most suitable driver based on the received ride request, the driver's current location information, demand forecast data, and emotional data. The selected driver is notified of the request information and the user's emotional state.

[0602] For example, "because the user is tired, a driver who can arrive quickly" is selected and the request information is notified.

[0603] In this way, the present invention combines real-time data collection and demand forecasting with an emotion engine to provide optimal vehicle dispatch routes that take into account the emotional state of the user. This not only contributes to reducing congestion, particularly in urban areas, and ensuring transportation options in rural areas, but also improves the user experience.

[0604] Example 2

[0605] 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."

[0606] Improving the user experience is crucial for modern ride-sharing services. However, existing systems rely on objective data such as traffic conditions and map information to predict demand and generate dispatch routes, making it difficult to provide services that take into account the user's emotional state. In particular, there is a problem in that appropriate responses are not provided to users experiencing increased stress or fatigue, limiting the improvement of user satisfaction.

[0607] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting user emotion data from voice, text, and image data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and user emotion data, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating the demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request, driver location information, and user emotion data, and means for notifying the selected driver of the request information. This enables demand forecasting and generation of vehicle dispatch routes that take the user's emotional state into consideration.

[0608] "Traffic condition data" refers to data that includes information on current traffic flow, congestion, accidents, and the like.

[0609] "Map information data" refers to data that includes information on geographical locations, topography, road networks, and the like.

[0610] "People distribution data" is data that contains information about the presence and density of people within a particular region or area.

[0611] "Congestion data for surrounding facilities" is data that includes information on the congestion status of commercial facilities, public transportation, tourist spots, etc.

[0612] "Event information" is data that includes information about events or activities that are held at specific dates, times, and locations.

[0613] "Emotional data" refers to data that contains information about people's emotional states, analyzed based on audio, text, and image data.

[0614] "Preprocessing" refers to processes such as removing outliers, filling in missing data, and normalizing data in order to prepare collected data for easier analysis.

[0615] "Demand forecasting" refers to predicting transportation demand for a certain period of time in the future based on collected data.

[0616] "Vehicle dispatch route" refers to the optimal route from the user's boarding point to their destination.

[0617] "Driver device" refers to an electronic device used by a driver, such as a smartphone or tablet.

[0618] "Feedback information" refers to data including information on evaluations of services and areas for improvement provided by drivers and users.

[0619] "User terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[0620] A "ride request" refers to a ride request sent by a user to use a ride-sharing service.

[0621] The "best driver" refers to the most suitable driver based on the received ride request, the driver's current location, demand forecast data, and emotional data.

[0622] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions. The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[0623] The server uses various APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. This allows the server to obtain the latest information in real time. It also collects data such as voice, text, and images from the device, and obtains user emotion data. This is done using NLP and image recognition technologies.

[0624] The collected data is integrated on the server, where it undergoes preprocessing, such as removing outliers, filling in missing data, and normalizing the data. It is expected that Python's pandas library will be used. After preprocessing, the data is input into a demand forecasting model, which uses a generative AI model (such as TensorFlow or PyTorch).

[0625] The demand forecasting model predicts traffic demand for the next set period based on traffic condition data, map information data, emotion data, etc. Based on this prediction result, the server generates the optimal vehicle dispatch route. If the user is emotionally tired, for example, it is possible to suggest routes that avoid congestion or quieter routes by reflecting the emotion data.

[0626] For example, if a user inputs "I'm tired," the server will integrate that emotion data and suggest a quieter route. It also takes into account the driver's location information to select the most suitable driver. During this selection process, the server selects the most suitable driver based on the received ride request, traffic data, and driver location information, and notifies the driver of the request.

[0627] Specifically, the server receives data from the emotion engine indicating that many users are feeling stressed during the morning rush hour. Based on this data, the server notifies users who are feeling stressed by saying, "A quieter route has been selected." The server also notifies the driver's device that, "This user is currently feeling stressed, so please try to drive comfortably."

[0628] As an example of a local event, the server receives emotional data from many users at the event venue, expressing their "tiredness." At the end of the event, the server generates a route that avoids routes that are likely to be crowded and minimizes waiting times. The server notifies the user that "a route for a comfortable trip has been selected," and instructs the driver that "this user is tired, so please be considerate."

[0629] In this way, the present invention can provide an optimal vehicle dispatch route that takes into account the user's emotional state by using an emotion engine in addition to collecting real-time data and forecasting demand.

[0630] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0631] Step 1: Data collection

[0632] The server uses APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. It also obtains voice, text, and image data from the device (user's smartphone) and uses this to collect user emotion data. This allows the latest information to be obtained in real time. The input is various types of data, and the output is the raw data that combines these.

[0633] Step 2: Data integration and preprocessing

[0634] The server integrates all collected data using libraries such as pandas. During this process, preprocessing such as removing outliers, filling in missing data, and normalizing the data is performed. For example, missing location information data is filled in and the overall data is formatted for easier analysis. The input is the raw data, and the output is the preprocessed data.

[0635] Step 3: Demand forecast

[0636] The server inputs the preprocessed data into an AI model (using, for example, TensorFlow or PyTorch) to predict traffic demand. This model uses traffic condition data, map information data, people distribution data, congestion data at nearby facilities, event information, emotional data, and more. For example, if the emotion engine determines that many users are "feeling stressed," it predicts that demand in that area will increase. The input is the preprocessed data, and the output is the demand forecast results.

[0637] Step 4: Applying the Emotion Engine

[0638] The device (user's smartphone) sends voice, text, and image data to the emotion engine for analysis. NLP and image recognition technologies are used to identify the user's emotional state. For example, if the user inputs "I'm tired," the engine determines that "the user is currently tired" based on that data and sends that information to the server. The input is emotional data from the user, and the output is analyzed emotional information.

[0639] Step 5: Generate a vehicle routing route

[0640] The server generates an optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects a quiet route that avoids congestion or a route that requires immediate attention. For example, if the user sends emotional data indicating that they are "in a hurry," it selects the shortest route and the nearest driver. The input is the demand forecast result and emotional information, and the output is an optimized vehicle dispatch route.

[0641] Step 6: Notify your driver of the route

[0642] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server. For example, the server generates a "specific route to avoid congestion" and notifies the driver, who then follows that route. The input is the optimal dispatch route, and the output is the route display to the driver.

[0643] Step 7: Real-time updates and feedback

[0644] The device (driver's smartphone) sends real-time location information and progress status to the server. The server dynamically adjusts the dispatch route based on this information and updates the demand forecasting model. It also collects feedback from users and reflects that data in the demand forecasting model. The inputs are real-time data and feedback information, and the outputs are an updated demand forecasting model and an optimized route.

[0645] Step 8: Receiving a request from the user

[0646] The user sends a request for a ride to the server using the user terminal. At this time, the user can also input their emotional state. For example, they can send information such as "I'm in a hurry" or "I'm tired," and the data is also provided to the server. The input is the ride request and emotional information, and the output is the request data.

[0647] Step 9: Driver selection and notification

[0648] The server selects the optimal driver based on the received ride request, the current driver's location information, demand forecast data, and emotional data. For example, if it determines that the user is in a hurry, it selects the nearest driver and notifies that driver of the user's emotional state. The inputs are the ride request, the driver's location information, demand forecast data, and emotional data, and the output is the selected driver and notification of the request information.

[0649] (Application example 2)

[0650] 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."

[0651] As ride-sharing services have become more widespread in recent years, there is a demand for systems that can improve passenger travel experiences. It is particularly important to provide services that take into account passengers' emotional states, but current systems have difficulty fully reflecting this. Conventional dispatch systems forecast demand based on traffic conditions, map information, pedestrian distribution, congestion at nearby facilities, and event information. However, they lack mechanisms for collecting and analyzing passenger emotional data to provide optimal dispatch routes and in-car environments. To resolve this technical challenge, a new system is needed.

[0652] 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.

[0653] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting emotional state data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, and means for analyzing the emotional data using a generative AI model and optimizing the corresponding route and in-vehicle environment. This makes it possible to generate an optimal vehicle dispatch route that takes into account the emotional state of passengers and provide a comfortable in-vehicle environment.

[0654] "Traffic condition data" refers to various types of information related to traffic, such as traffic flow, congestion, traffic accident information, and road closure status.

[0655] "Map information data" refers to various information related to maps, such as geographical location information, the layout of road networks and facilities, and route information.

[0656] "Person distribution data" refers to information about the distribution of people, such as the number of people present in a particular area, their travel routes, and the length of their stay.

[0657] "Crowding data for surrounding facilities" refers to information on the congestion status, number of users, waiting times, etc. of specific facilities or locations.

[0658] "Event information" is information about the date, location, scale, and content of an event held in a specific area.

[0659] "Emotional state data" is information indicating the emotional state of a user that is obtained by analyzing the user's voice, text, images, and the like.

[0660] A "demand forecasting model" is an algorithm or mathematical model for predicting future demand based on collected data.

[0661] A "vehicle dispatch route" is a route that optimally guides a user to their destination, and is designed based on traffic conditions and various data.

[0662] A "driver terminal" is an electronic device such as a smartphone or tablet used by a driver to receive information about dispatch routes and demand forecasts.

[0663] A "user terminal" is an electronic device such as a smartphone or tablet used by a user, and is a terminal for transmitting ride requests and emotional state data.

[0664] A "generative AI model" is an artificial intelligence model that is trained to perform specific tasks using large amounts of data.

[0665] A "prompt" is an instruction given to a generative AI model to perform a specific task.

[0666] This invention is a demand forecasting system that collects and integrates real-time traffic conditions, map information, people distribution, congestion at nearby facilities, event information, etc. This system also aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotional state.

[0667] System Overview

[0668] This system consists of the following hardware and software:

[0669] Server: Collects, integrates, pre-processes, forecasts, routes, and updates data.

[0670] User terminal: Collects emotional data and ride requests from users.

[0671] Driver device: Used for route notifications and feedback.

[0672] Operation of each method

[0673] 1. Data Collection

[0674] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. Emotional state data is also collected from the user's device via voice, text, images, etc.

[0675] 2. Data integration and preprocessing

[0676] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[0677] 3. Demand forecasting

[0678] The server then inputs the pre-processed data into an AI model to generate demand forecasts. If many users are feeling stressed, it predicts that demand for rides in that area is likely to increase.

[0679] 4. Applying the Emotion Engine

[0680] Data such as voice, text, and images collected on the user's device are sent to the emotion engine for analysis. For example, if the user is frustrated, that information is sent to the server.

[0681] 5. Vehicle routing generation

[0682] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route.

[0683] 6. Route notification to drivers

[0684] The driver's terminal receives and displays the vehicle dispatch route information transmitted from the server.

[0685] Usage example

[0686] As a specific use case, consider a case where a passenger feels stressed during their commute. The emotion engine detects the stress and transmits the information to the server. The server uses this information to optimize a quieter route that avoids congestion and notifies the driver. This allows the passenger to reach their destination in a relaxed state.

[0687] Example prompt for a generative AI model:

[0688] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[0689] Through the steps described above, the present invention realizes an efficient and satisfying ride-sharing service that integrates real-time data and emotional data.

[0690] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0691] Step 1:

[0692] Data collection

[0693] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information via API. Emotional state data is collected from user devices through voice, text, and images. All of this data is sent to the server. Input data is obtained from various APIs and emotion engines, and output data is integrated, unprocessed raw data.

[0694] Step 2:

[0695] Data integration and preprocessing

[0696] The server removes outliers from the collected data, fills in missing data, and normalizes the data. It also preprocesses emotion data in the same way. The input data is all the collected raw data, and the output data is preprocessed data with outliers removed and normalized. Specifically, it applies a data cleansing algorithm to detect outliers and missing values ​​and fill them in.

[0697] Step 3:

[0698] Demand forecasting

[0699] Based on the preprocessed data, the server uses a generative AI model to perform demand forecasting. The input data is the preprocessed data, and the output data is the demand forecast data for the next fixed time period. Specifically, the integrated data is input into the AI ​​model, and demand forecasting is performed using prompt statements. For example, the demand for rides in each area is predicted according to the prompt statements.

[0700] Step 4:

[0701] Applying the Emotion Engine

[0702] The voice, text, and image data collected on the user's device are sent to the emotion engine for analysis. The analysis results (emotional state data) are sent to the server by the emotion engine. The input data is the user's emotional state data, and the output data is the analyzed emotional state information. Specifically, the emotion engine performs voice tone, facial expression recognition, and text analysis to identify the emotional state.

[0703] Step 5:

[0704] Vehicle routing generation

[0705] The server generates an optimal vehicle dispatch route based on the demand forecast data and emotion data. The input data is the demand forecast data and emotion data, and the output data is optimal vehicle dispatch route information. Specifically, the server uses a route optimization algorithm to generate a route that the user feels comfortable with and selects the optimal driver.

[0706] Step 6:

[0707] Route notification to the driver

[0708] The driver's device receives and displays the dispatch route information sent from the server. The input data is the optimal dispatch route information, and the output data is the route displayed on the driver's device. Specifically, the route information is pushed to the driver's device, and the driver begins traveling based on that information.

[0709] Step 7:

[0710] Receiving feedback information

[0711] The driver's device sends feedback information to the server during travel, including driving data and the user's emotional state. The input data is feedback information, and the output data is data that is reflected in updating the demand forecasting model. Specifically, the driver's device sends real-time location information and the user's reactions to the server.

[0712] Step 8:

[0713] Update demand forecast models

[0714] The server updates the demand forecasting model based on the received feedback information. The input data is the feedback information, and the output data is the updated demand forecasting model. Specifically, the AI ​​model is retrained based on the feedback information to improve the accuracy of the next demand forecast.

[0715] Example prompt sentence:

[0716] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[0717] 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.

[0718] 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.

[0719] 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.

[0720] [Third embodiment]

[0721] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0722] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0723] 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).

[0724] 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.

[0725] 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.

[0726] 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).

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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."

[0733] This invention is a system that collects and integrates traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information in real time. Based on this data, it performs demand forecasting, generates efficient vehicle dispatch routes, and notifies drivers. Furthermore, upon receiving a vehicle dispatch request from a user, it selects the most suitable driver and notifies the request information, thereby quickly responding to user needs.

[0734] System Operation

[0735] 1. Data Collection

[0736] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information, allowing the latest situation to be grasped in real time.

[0737] 2. Data integration and preprocessing

[0738] The server consolidates the collected data, corrects inconsistencies, improves data quality by removing outliers and imputing missing data, and normalizes the data to prepare it for input into the AI ​​model.

[0739] 3. Demand forecasting

[0740] The server uses the integrated data to predict demand for the next certain period of time, taking into account factors such as the day of the week, time of day, weather, and events, and identifies areas where travel demand will be high.

[0741] 4. Vehicle routing generation

[0742] The server generates optimal vehicle dispatch routes based on predicted demand data, taking into account current traffic conditions and the driver's location.

[0743] 5. Driver Notification

[0744] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server, allowing the driver to travel efficiently.

[0745] 6. Real-time updates and feedback

[0746] During the journey, the driver's device transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[0747] 7. Receiving requests from users

[0748] Users send a ride request through the app, which includes information such as the departure point, destination, and desired time.

[0749] 8. Driver Selection

[0750] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is notified of the request information and is given instructions on how to get to the departure point.

[0751] Specific examples

[0752] Example 1: Urban commute hours

[0753] The server predicts that demand for rides from business districts to stations will increase at 5 p.m. Ten minutes before the scheduled time, it suggests routes for nearby drivers to wait in front of the station, making it easier for commuters to board rides in front of the station, improving convenience.

[0754] Example 2: When a local event is held

[0755] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates increased demand in the surrounding area. Before the event begins, the server suggests routes for drivers to wait in the area, ensuring smooth transportation for event participants.

[0756] In this way, the present invention can provide an efficient ride-sharing service by combining real-time data collection, demand forecasting, and vehicle route optimization, which can particularly contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas.

[0757] The processing flow will be explained below.

[0758] Step 1: Data collection

[0759] The server periodically collects traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information. Traffic condition data includes road congestion information and travel speeds, and map information data includes coordinate information for roads and landmarks. People distribution data indicates the population density and movement patterns in a specific area, and congestion data at nearby facilities provides the number of users at major spots. Event information includes the date, time, and location of the event.

[0760] Step 2: Data integration and preprocessing

[0761] The server integrates the collected data, detects and removes outliers, fills in missing data, and normalizes the data. If there are inconsistencies in traffic condition data or pedestrian distribution data, it corrects them and converts them into a consistent format. If there are gaps in aerial photograph data or congestion data, it fills in the gaps based on surrounding data. It also standardizes all data so that it can be used by AI models.

[0762] Step 3: Demand forecast

[0763] The server uses the preprocessed data to perform demand forecasts. It inputs the collected data into an AI model to predict traffic demand for the next certain period. For example, the predictive model calculates which areas will experience demand, taking into account specific days of the week, time periods, events, and weather information.

[0764] Step 4: Generate a vehicle routing route

[0765] The server generates optimal vehicle dispatch routes based on predicted demand data. It uses Dijkstra and A algorithms to calculate optimal routes that reflect real-time traffic conditions and each driver's location. The generated routes also take into account the driver's fuel consumption and time efficiency.

[0766] Step 5: Send route to driver

[0767] The terminal (driver's smartphone) receives the dispatch route information sent from the server. The driver follows the displayed route information and heads to the passenger's pickup point. This information is updated regularly, providing the optimal route based on the latest conditions.

[0768] Step 6: Real-time updates and feedback

[0769] The device (the driver's smartphone) sends its current location and progress information to the server in real time. For example, if an unexpected traffic jam or accident occurs, the server recalculates the demand forecast model based on the latest information and re-optimizes the route. This ensures that the driver is always provided with the most up-to-date dispatch route.

[0770] Step 7: Receiving a request from the user

[0771] A user (customer) sends a ride request to the server through a ride-sharing app. This request includes details such as the origin, destination, and desired time, allowing the server to recognize the user's transportation needs.

[0772] Step 8: Driver selection and notification

[0773] The server selects the most suitable driver based on the received ride request, the driver's current location information, and demand forecast data. It applies the Greedy algorithm to select a driver who meets the user's request with the shortest travel distance and time. At the same time, it notifies the selected driver of the request information and provides instructions on how to get to the departure point. This information is displayed on the driver's device, and an appropriate ride is dispatched.

[0774] Example 1

[0775] 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."

[0776] In modern urban and rural areas, real-time vehicle demand forecasting and optimal route generation are required to improve transportation efficiency and travel convenience. However, current systems collect individual data but do not adequately integrate data processing, demand forecasting, and vehicle route optimization. This results in reduced transportation efficiency and inconvenience for users and drivers. Furthermore, there is a lack of systems that can respond to real-time feedback and updates. To address these issues, this invention proposes a system that integrates comprehensive data processing with advanced prediction and optimization methods.

[0777] 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.

[0778] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating the collected data, correcting inconsistencies, and performing preprocessing, means for predicting demand for the next certain period based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and taking into account current traffic conditions and the driver's location, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving real-time update information from the driver terminal, updating the demand forecast model, and re-optimizing the route as necessary, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, and means for notifying the selected driver of the request information and providing directions. This enables data integration processing and real-time prediction and optimization.

[0779] "Traffic condition data" refers to data that includes information on road congestion, traffic accidents, construction works, and the like.

[0780] "Map information data" refers to data including geographical location information, road maps, and building layouts.

[0781] "People distribution data" is data that shows patterns of people gathering and moving in specific areas and at specific times.

[0782] "Congestion data for surrounding facilities" is data that indicates the usage status and congestion level of commercial facilities, public facilities, etc.

[0783] "Event information" is data about public events such as concerts, sports games, and festivals.

[0784] "Means for integrating data, correcting inconsistencies, and preprocessing" refers to means for integrating various collected data into a single format and correcting inconsistencies and missing data.

[0785] The "means for forecasting demand" is a means for forecasting demand for vehicle dispatch within a certain period of time in the future based on the integrated data.

[0786] "Means for generating optimal vehicle dispatch routes" refers to means for calculating and generating the most efficient routes based on predicted demand, real-time traffic conditions, and the driver's location.

[0787] "Driver terminal" refers to a device such as a smartphone or tablet used by the driver, which receives and displays information from the server.

[0788] "Real-time updates" are the latest data generated while on the move, such as the driver's location and progress.

[0789] A "user terminal" refers to a device such as a smartphone or tablet used by a user who uses a vehicle dispatch service, and is a terminal used to send a vehicle dispatch request to the server.

[0790] A "ride request" is a request sent by a user through the app, including information such as the departure point, destination, and desired time.

[0791] The "means for selecting the best driver" is a means for selecting the driver who can most efficiently handle the request based on the ride request and the driver's current location information.

[0792] "Means for notifying request information and providing directions" refers to means for notifying the selected driver of details of the ride request and providing guidance on the optimal route to the specified departure point.

[0793] This invention is a system that collects and integrates multiple data in real time, and based on that data, predicts transportation demand and generates optimal vehicle dispatch routes. This system is composed of a server, terminals, and users, and aims to provide an efficient ride-sharing service.

[0794] Hardware and software used

[0795] The server is the central unit that performs advanced data processing and predictive calculations and utilizes the following software and libraries:

[0796] Data collection: We use Google Maps API, HERE Maps, public open data portals, etc. to collect traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[0797] Data integration and preprocessing: We use the pandas and NumPy libraries to integrate the collected data and correct inconsistencies, thereby imputing missing data and removing outliers.

[0798] Demand forecasting: Based on the integrated data, we use a time series forecasting model (e.g., ARIMA, LSTM) to forecast the demand within the next certain time period.

[0799] Vehicle routing generation: Uses the A algorithm and Dijkstra's algorithm to generate optimal vehicle routing based on predicted demand data, current traffic conditions, and driver location information.

[0800] Notification service: Google Firebase and Apple Push Notification service are used to notify drivers of the generated optimal route information.

[0801] Real-time updates: Using WebSocket or MQTT protocols, the driver's location and progress are sent to the server in real time.

[0802] The terminals (driver terminal and user terminal) are mobile devices such as smartphones and tablets. These terminals have the following functions:

[0803] Driver's device: Receives and displays real-time route information sent from the server. Also, transfers real-time updated information sent from the device to the server.

[0804] User terminal: Sends a ride request to the server. The front-end app is built using React Native or Flutter, and communicates with the back-end via a RESTful API to send requests.

[0805] A user is a person who uses a smartphone or tablet to use a ride-hailing service. The user inputs the departure point, destination, and desired time and sends a request to the server.

[0806] Specific examples

[0807] Example 1: Urban commute hours

[0808] The server predicts that demand for travel from the office district to the station will increase at 5 p.m. Specifically, it uses information that, "According to traffic data, the roads from the office district to the station are usually congested at 5 p.m." The server then suggests a route to nearby drivers 10 minutes in advance, telling them to "wait in front of the station." The driver's device receives this notification, allowing the driver to head to the station efficiently. Commuters can board smoothly in front of the station, improving travel convenience.

[0809] Example 2: When a local event is held

[0810] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates an increase in demand for travel to the surrounding area. Specifically, it uses forecast data that shows that "events in tourist destinations over the weekend will attract large crowds." It then suggests a route to the driver to wait in the vicinity before the event begins, telling them to "wait near the event venue." The driver's device receives the instructions and follows the directions, allowing event participants to reach the event site smoothly.

[0811] Prompt Sentence Examples

[0812] Below are some examples of prompts for the generative AI model:

[0813] "Please forecast major traffic demand this weekend."

[0814] "Generate the optimal route from the office district to the station between 5:00 PM and 6:00 PM."

[0815] "Re-optimize your vehicle routes around the event, taking into account real-time traffic conditions and driver location."

[0816] In this way, the present invention can contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas by collecting data in real time and generating efficient demand forecasts and optimal routes based on that data.

[0817] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0818] Step 1:

[0819] Data collection

[0820] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information through APIs. It uses Google Maps API, HERE Maps, public open data portals, etc. as input and obtains the necessary data from these services. The output is a collection of raw data obtained from each data source. Specifically, the server sends requests to each API and receives and stores the data returned as a response.

[0821] Step 2:

[0822] Data integration and preprocessing

[0823] The server integrates the collected data, corrects inconsistencies, and performs preprocessing. The input is the raw data from each data source collected in step 1. The output is an integrated and cleaned dataset. Specific operations include removing outliers, imputing missing data, and normalizing the data using the pandas and NumPy libraries. For example, missing values ​​are imputed with surrounding values, and outliers are removed using a specific threshold.

[0824] Step 3:

[0825] Demand forecasting

[0826] The server predicts demand for the next set of hours based on the integrated data. The input is the integrated dataset generated in step 2. The output is a forecast value from the demand forecasting model. Specifically, it uses a time series forecasting model (e.g., ARIMA, LSTM) to make predictions taking into account factors such as the day of the week, time, weather, and event information. For example, it predicts that "demand from the office district to the station will increase at 5 p.m. on Monday."

[0827] Step 4:

[0828] Vehicle routing generation

[0829] The server combines the predicted demand data, current traffic conditions, and the driver's location to generate the optimal vehicle dispatch route. The inputs are the predicted data obtained in step 3, real-time traffic information, and the driver's location information. The output is the optimal vehicle dispatch route. Specifically, it calculates the shortest route using the A algorithm or Dijkstra's algorithm, and adjusts the route by incorporating real-time traffic data.

[0830] Step 5:

[0831] Driver Notification

[0832] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server in real time. The input is the route information generated in step 4. The output is the dispatch route displayed on the driver's terminal. Specifically, the route information is pushed to the driver's smartphone using Google Firebase or Apple Push Notification service.

[0833] Step 6:

[0834] Real-time updates and feedback

[0835] The driver's device transmits real-time location information and progress status to the server during travel. The input is the driver's current location and progress data. The output is real-time updated data received by the server. Specifically, location information is sent to the server with low latency using WebSocket or MQTT protocols, and the server uses this data to update its demand forecasting model and re-optimize routes as needed.

[0836] Step 7:

[0837] Receiving requests from users

[0838] A user sends a ride request to the server via a smartphone app. The input is information such as the departure point, destination, and desired time entered by the user. The output is the ride request received by the server. Specifically, the user enters the destination and desired time on the app screen, and then sends that information to the server via a RESTful API.

[0839] Step 8:

[0840] Driver Selection

[0841] The server selects the most suitable driver based on the received request and the driver's current location information. The input is the ride request and the driver's current location information. The output is the selected driver and notification information. Specifically, it uses a bipartite matching algorithm to select the driver who can most efficiently handle the request, notifies the driver of the request information, and provides directions on how to get there.

[0842] (Application example 1)

[0843] 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."

[0844] Modern food delivery services face many challenges in achieving efficient delivery operations. Among these, generating optimal routes in real time in response to fluctuations in traffic conditions and demand, and quickly selecting drivers are particularly important. However, systems that can handle these variables have not yet been adequately developed, which could significantly reduce driver and customer satisfaction. Furthermore, there is a lack of a way to reoptimize delivery routes based on real-time feedback, which also impacts operational efficiency. A new system is needed to resolve these issues.

[0845] 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.

[0846] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating and pre-processing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, means for improving the delivery efficiency of delivery drivers based on the demand forecast and the optimal route generation in a food delivery service, and means for re-optimizing the delivery route based on real-time feedback information, thereby enabling fast and efficient delivery in a food delivery service.

[0847] 1. "Traffic condition data" refers to all information related to traffic, such as road congestion, accident information, and traffic signal status.

[0848] 2. "Map information data" means data that includes geographical location information and detailed road information.

[0849] 3. "Person distribution data" refers to data that shows the concentration and distribution of people in a particular area.

[0850] 4. "Congestion data for surrounding facilities" refers to data that indicates the degree of congestion and the number of people staying at a specific facility or location.

[0851] 5. "Event Information" refers to information about events or occasions held in a specific area or time.

[0852] 6. "Demand forecasting model" refers to an algorithm or machine learning model that forecasts demand in a specific region or time based on various collected data.

[0853] 7. "Optimal vehicle routing" refers to the best route calculated to reach a destination efficiently.

[0854] 8. "Driver device" refers to a device such as a smartphone or tablet held by the driver.

[0855] 9. "Feedback Information" means location, progress, and other information provided by a driver during a delivery.

[0856] 10. "User terminal" refers to a device such as a smartphone or tablet used by a User to submit an order or request.

[0857] 11. "Vehicle request" refers to the vehicle dispatch request information sent by a User.

[0858] 12. "Demand forecasting" refers to the process of estimating future demand for services based on collected data.

[0859] 13. “Optimization” refers to the process of adjusting parameters or conditions to obtain the best results in order to achieve a specific goal.

[0860] 14. "Real-time feedback" refers to immediate information provided by the driver or user.

[0861] This invention is a system for realizing efficient and prompt delivery operations in food delivery services. Specifically, it collects traffic condition data, map information data, people distribution data, congestion data at surrounding facilities, and event information in real time, and integrates and preprocesses them. It then forecasts demand based on this data, generates optimal vehicle dispatch routes, and notifies drivers. It also receives dispatch requests from users, selects the most suitable driver, and notifies them of the request information. It also reoptimizes delivery routes based on real-time feedback information.

[0862] Specific system configuration and operation

[0863] Data collection

[0864] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information, including information from various APIs on the Internet and GPS devices. The software used includes the Python requests library.

[0865] Data integration and preprocessing

[0866] The server integrates the collected data, corrects inconsistencies, and pre-processes it, including removing outliers, imputing missing data, and normalizing the data. Technologies used here include database management systems (e.g., MySQL) and data processing libraries (e.g., Pandas).

[0867] Demand forecasting

[0868] The server uses generative AI models based on the integrated data to forecast demand, predicting demand for specific time periods and locations and creating efficient delivery plans. The AI ​​models used include TensorFlow and PyTorch.

[0869] Vehicle routing generation

[0870] Based on the demand forecast results, the server generates the optimal vehicle dispatch route, taking into account traffic conditions and driver location information, using a pre-trained routing algorithm and real-time route optimization technology.

[0871] Driver Notification

[0872] The server then notifies the driver of the generated route information, which is then used as a smartphone or tablet, and the driver then travels efficiently based on the route information.

[0873] Real-time updates and feedback

[0874] The server receives feedback from the driver's device, updates the demand forecast model, and re-optimizes the vehicle dispatch route as needed, enabling efficient delivery in real time.

[0875] Receiving requests from users

[0876] Customers can send food delivery requests from their smartphones or tablets, including information such as origin, destination, and desired time.

[0877] Driver Selection

[0878] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is then notified of the request information, ensuring a smooth delivery.

[0879] Specific examples

[0880] Ordering: A user wants a pizza delivered to their home at 6pm.

[0881] Prediction: Based on traffic conditions at 6 p.m. and historical data, the AI ​​model predicts that orders will be concentrated in a particular area at that time.

[0882] Notification: Driver A is notified of the optimal route and picks up the order at the nearest pizza place, and immediately begins delivering it along the specified route.

[0883] Example prompt sentence:

[0884] A user wants a pizza delivered to their home (Address: [Address]) at 6 PM. Based on the traffic conditions and historical data for this time, predict the optimal delivery route and notify the driver.

[0885] This system enables fast and efficient delivery for food delivery services, which will improve service quality and significantly increase the satisfaction of drivers and customers.

[0886] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0887] Step 1: Data collection The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information. This data is acquired through various APIs and GPS devices. Input includes data acquired from APIs on the Internet, and this data is stored on the server as output.

[0888] Step 2: Data integration and preprocessing. The server integrates the collected data, corrects inconsistencies, and performs preprocessing. This includes removing outliers, imputing missing data, and normalizing the data. The input is the collected raw data, and the output is a preprocessed, high-quality dataset.

[0889] Step 3: Demand Forecasting The server uses a generative AI model based on the integrated data to perform demand forecasting. This predicts demand for specific time periods and locations. The input includes preprocessed data, and the output is the demand forecast result.

[0890] Step 4: Vehicle dispatch route generation The server generates the optimal vehicle dispatch route based on the demand forecast results, taking into account traffic conditions and driver location information. The inputs include demand forecast results, real-time traffic data, and driver location data, and the optimal vehicle dispatch route information is generated as the output.

[0891] Step 5: Notify the driver The server notifies the driver's terminal of the generated vehicle dispatch route information. The input is the optimal route information, and the output is a notification sent to the driver's terminal.

[0892] Step 6: Real-time updates and feedback. The server receives location information and progress information sent from the driver's device, updates the demand forecast model, and re-optimizes the dispatch route. The input includes real-time feedback information from the driver, and the output is an updated demand forecast result and a re-optimized route.

[0893] Step 7: Receiving a request from the user The user sends a request for a ride from their own device. The input includes information on the departure point, destination, and desired time, and the request information is stored in the server as output.

[0894] Step 8: Driver Selection The server selects the most suitable driver based on the received request and driver location information. The input is the ride request information and the driver's location data, and the output is a request notification to the selected driver.

[0895] 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.

[0896] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions.The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[0897] System Operation

[0898] 1. Data Collection

[0899] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information. It also collects user emotional data. Emotional data is collected on the device through the user's voice, text, images, etc.

[0900] 2. Data integration and preprocessing

[0901] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[0902] 3. Demand forecasting

[0903] The server performs demand forecasting based on the preprocessed data. The integrated data is input into an AI model to predict traffic demand for the next certain period of time. Emotional data analyzed by the emotion engine is also reflected in this prediction model. For example, if many users are feeling stressed, it may determine that there is a possibility of increased demand for rides in that area.

[0904] 4. Applying the Emotion Engine

[0905] The device (user's smartphone) sends data such as voice, text, and images input by the user to the emotion engine. The emotion engine analyzes this data and identifies the user's current emotional state. For example, if the user is irritated, that information is sent to the server.

[0906] 5. Vehicle routing generation

[0907] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route. For example, if the user wants to relax, it will suggest a route that avoids congestion.

[0908] 6. Route notification to drivers

[0909] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server, allowing the driver to travel efficiently and providing a service that takes into account the user's emotional state.

[0910] 7. Real-time updates and feedback

[0911] The device (driver's smartphone) sends real-time location information and progress status to the server. The server also receives emotional feedback information and updates the demand forecast model to provide more accurate vehicle dispatch routes.

[0912] 8. Receiving requests from users

[0913] Users can send a ride request to the server through the app. At this time, users can also input their emotional state. For example, information such as "I'm tired" or "I'm in a hurry" can be included in the request.

[0914] 9. Driver Selection and Notification

[0915] The server selects the most suitable driver based on the received request, the driver's current location, demand forecast data, and emotional data. The selected driver is also notified of the user's emotional state and instructed if special measures are required.

[0916] Specific examples

[0917] Example 1: Stress-reducing ride-hailing in urban areas

[0918] The server receives data that indicates that many users feel stressed during the morning commute. Based on this information, the server can provide quieter routes to users who feel stressed, reduce their stress, and select an appropriate driver to provide a relaxing in-car environment for users.

[0919] Example 2: Comfortable transportation at local events

[0920] The server receives emotional data from many users at local event venues, expressing their tiredness. Based on this information, it generates routes with minimal waiting time at the end of the event and prioritizes dispatching vehicles to tired users. In addition, it selects the most suitable vehicle and driver to ensure a comfortable trip.

[0921] In this way, by using an emotion engine in addition to collecting real-time data and forecasting demand, the present invention can provide optimal ride-hailing routes that take into account the user's emotional state, improving the user experience. In particular, by utilizing emotion data, an efficient and satisfying ride-sharing service can be realized in alleviating congestion in urban areas and securing transportation in rural areas.

[0922] The processing flow will be explained below.

[0923] Step 1: Data collection

[0924] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[0925] The device (user's smartphone) sends the user's emotional data, such as voice, text, and images, to the emotion engine, which then transfers it to the server. For example, if the user is feeling stressed, the engine collects their voice data.

[0926] Step 2: Data integration and preprocessing

[0927] The server then integrates the collected data into a single dataset, corrects inconsistencies and gaps, and normalizes the data. It also preprocesses the emotion data to create a consistent format.

[0928] For example, it removes outliers, fills in missing data, and converts all data into an input format for the AI ​​model.

[0929] Step 3: Applying the Emotion Engine

[0930] The device (user's smartphone) sends the voice, text, and image data collected from the user to the emotion engine, which analyzes this data and identifies the user's emotional state.

[0931] The server receives the emotional data analyzed by the emotion engine and determines the user's current emotional state.

[0932] Step 4: Demand forecast

[0933] The server uses the integrated data to predict traffic demand for the next certain period using an AI model, and also incorporates emotion data obtained by the emotion engine into this model.

[0934] For example, if many users in an area where an event is being held express the emotion "tired," it is predicted that demand in that area will increase.

[0935] Step 5: Generate a vehicle routing route

[0936] The server generates optimal vehicle dispatch routes based on predicted demand and user emotional data, and selects the most suitable route and driver based on the emotional data.

[0937] For example, if a user is looking to relax, the system will suggest a route that avoids crowded areas.

[0938] Step 6: Notify your driver of the route

[0939] The terminal (driver's smartphone) receives route information sent from the server and moves according to that route. The driver is also notified of the user's emotional state.

[0940] For example, the server may provide the driver with instructions such as, "The user wants to relax, so please choose a quiet route."

[0941] Step 7: Real-time updates and feedback

[0942] The device (driver's smartphone) transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[0943] For example, if a traffic jam occurs along the way, the server calculates a new optimal route and notifies the driver.

[0944] Step 8: Receiving a request from the user

[0945] A user sends a ride request to the server through a ride-sharing app, which includes the origin, destination, desired time, and emotional state.

[0946] For example, emotional information such as "I'm tired" is also included in the request.

[0947] Step 9: Driver selection and notification

[0948] The server selects the most suitable driver based on the received ride request, the driver's current location information, demand forecast data, and emotional data. The selected driver is notified of the request information and the user's emotional state.

[0949] For example, "because the user is tired, a driver who can arrive quickly" is selected and the request information is notified.

[0950] In this way, the present invention combines real-time data collection and demand forecasting with an emotion engine to provide optimal vehicle dispatch routes that take into account the emotional state of the user. This not only contributes to reducing congestion, particularly in urban areas, and ensuring transportation options in rural areas, but also improves the user experience.

[0951] Example 2

[0952] 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."

[0953] Improving the user experience is crucial for modern ride-sharing services. However, existing systems rely on objective data such as traffic conditions and map information to predict demand and generate dispatch routes, making it difficult to provide services that take into account the user's emotional state. In particular, there is a problem in that appropriate responses are not provided to users experiencing increased stress or fatigue, limiting the improvement of user satisfaction.

[0954] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting user emotion data from voice, text, and image data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and user emotion data, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating the demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request, driver location information, and user emotion data, and means for notifying the selected driver of the request information. This enables demand forecasting and generation of vehicle dispatch routes that take the user's emotional state into consideration.

[0955] "Traffic condition data" refers to data that includes information on current traffic flow, congestion, accidents, and the like.

[0956] "Map information data" refers to data that includes information on geographical locations, topography, road networks, and the like.

[0957] "People distribution data" is data that contains information about the presence and density of people within a particular region or area.

[0958] "Congestion data for surrounding facilities" is data that includes information on the congestion status of commercial facilities, public transportation, tourist spots, etc.

[0959] "Event information" is data that includes information about events or activities that are held at specific dates, times, and locations.

[0960] "Emotional data" refers to data that contains information about people's emotional states, analyzed based on audio, text, and image data.

[0961] "Preprocessing" refers to processes such as removing outliers, filling in missing data, and normalizing data in order to prepare collected data for easier analysis.

[0962] "Demand forecasting" refers to predicting transportation demand for a certain period of time in the future based on collected data.

[0963] "Vehicle dispatch route" refers to the optimal route from the user's boarding point to their destination.

[0964] "Driver device" refers to an electronic device used by a driver, such as a smartphone or tablet.

[0965] "Feedback information" refers to data including information on evaluations of services and areas for improvement provided by drivers and users.

[0966] "User terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[0967] A "ride request" refers to a ride request sent by a user to use a ride-sharing service.

[0968] The "best driver" refers to the most suitable driver based on the received ride request, the driver's current location, demand forecast data, and emotional data.

[0969] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions. The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[0970] The server uses various APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. This allows the server to obtain the latest information in real time. It also collects data such as voice, text, and images from the device, and obtains user emotion data. This is done using NLP and image recognition technologies.

[0971] The collected data is integrated on the server, where it undergoes preprocessing, such as removing outliers, filling in missing data, and normalizing the data. It is expected that Python's pandas library will be used. After preprocessing, the data is input into a demand forecasting model, which uses a generative AI model (such as TensorFlow or PyTorch).

[0972] The demand forecasting model predicts traffic demand for the next set period based on traffic condition data, map information data, emotion data, etc. Based on this prediction result, the server generates the optimal vehicle dispatch route. If the user is emotionally tired, for example, it is possible to suggest routes that avoid congestion or quieter routes by reflecting the emotion data.

[0973] For example, if a user inputs "I'm tired," the server will integrate that emotion data and suggest a quieter route. It also takes into account the driver's location information to select the most suitable driver. During this selection process, the server selects the most suitable driver based on the received ride request, traffic data, and driver location information, and notifies the driver of the request.

[0974] Specifically, the server receives data from the emotion engine indicating that many users are feeling stressed during the morning rush hour. Based on this data, the server notifies users who are feeling stressed by saying, "A quieter route has been selected." The server also notifies the driver's device that, "This user is currently feeling stressed, so please try to drive comfortably."

[0975] As an example of a local event, the server receives emotional data from many users at the event venue, expressing their "tiredness." At the end of the event, the server generates a route that avoids routes that are likely to be crowded and minimizes waiting times. The server notifies the user that "a route for a comfortable trip has been selected," and instructs the driver that "this user is tired, so please be considerate."

[0976] In this way, the present invention can provide an optimal vehicle dispatch route that takes into account the user's emotional state by using an emotion engine in addition to collecting real-time data and forecasting demand.

[0977] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0978] Step 1: Data collection

[0979] The server uses APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. It also obtains voice, text, and image data from the device (user's smartphone) and uses this to collect user emotion data. This allows the latest information to be obtained in real time. The input is various types of data, and the output is the raw data that combines these.

[0980] Step 2: Data integration and preprocessing

[0981] The server integrates all collected data using libraries such as pandas. During this process, preprocessing such as removing outliers, filling in missing data, and normalizing the data is performed. For example, missing location information data is filled in and the overall data is formatted for easier analysis. The input is the raw data, and the output is the preprocessed data.

[0982] Step 3: Demand forecast

[0983] The server inputs the preprocessed data into an AI model (using, for example, TensorFlow or PyTorch) to predict traffic demand. This model uses traffic condition data, map information data, people distribution data, congestion data at nearby facilities, event information, emotional data, and more. For example, if the emotion engine determines that many users are "feeling stressed," it predicts that demand in that area will increase. The input is the preprocessed data, and the output is the demand forecast results.

[0984] Step 4: Applying the Emotion Engine

[0985] The device (user's smartphone) sends voice, text, and image data to the emotion engine for analysis. NLP and image recognition technologies are used to identify the user's emotional state. For example, if the user inputs "I'm tired," the engine determines that "the user is currently tired" based on that data and sends that information to the server. The input is emotional data from the user, and the output is analyzed emotional information.

[0986] Step 5: Generate a vehicle routing route

[0987] The server generates an optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects a quiet route that avoids congestion or a route that requires immediate attention. For example, if the user sends emotional data indicating that they are "in a hurry," it selects the shortest route and the nearest driver. The input is the demand forecast result and emotional information, and the output is an optimized vehicle dispatch route.

[0988] Step 6: Notify your driver of the route

[0989] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server. For example, the server generates a "specific route to avoid congestion" and notifies the driver, who then follows that route. The input is the optimal dispatch route, and the output is the route display to the driver.

[0990] Step 7: Real-time updates and feedback

[0991] The device (driver's smartphone) sends real-time location information and progress status to the server. The server dynamically adjusts the dispatch route based on this information and updates the demand forecasting model. It also collects feedback from users and reflects that data in the demand forecasting model. The inputs are real-time data and feedback information, and the outputs are an updated demand forecasting model and an optimized route.

[0992] Step 8: Receiving a request from the user

[0993] The user sends a request for a ride to the server using the user terminal. At this time, the user can also input their emotional state. For example, they can send information such as "I'm in a hurry" or "I'm tired," and the data is also provided to the server. The input is the ride request and emotional information, and the output is the request data.

[0994] Step 9: Driver selection and notification

[0995] The server selects the optimal driver based on the received ride request, the current driver's location information, demand forecast data, and emotional data. For example, if it determines that the user is in a hurry, it selects the nearest driver and notifies that driver of the user's emotional state. The inputs are the ride request, the driver's location information, demand forecast data, and emotional data, and the output is the selected driver and notification of the request information.

[0996] (Application example 2)

[0997] 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."

[0998] As ride-sharing services have become more widespread in recent years, there is a demand for systems that can improve passenger travel experiences. It is particularly important to provide services that take into account passengers' emotional states, but current systems have difficulty fully reflecting this. Conventional dispatch systems forecast demand based on traffic conditions, map information, pedestrian distribution, congestion at nearby facilities, and event information. However, they lack mechanisms for collecting and analyzing passenger emotional data to provide optimal dispatch routes and in-car environments. To resolve this technical challenge, a new system is needed.

[0999] 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.

[1000] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting emotional state data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, and means for analyzing the emotional data using a generative AI model and optimizing the corresponding route and in-vehicle environment. This makes it possible to generate an optimal vehicle dispatch route that takes into account the emotional state of passengers and provide a comfortable in-vehicle environment.

[1001] "Traffic condition data" refers to various types of information related to traffic, such as traffic flow, congestion, traffic accident information, and road closure status.

[1002] "Map information data" refers to various information related to maps, such as geographical location information, the layout of road networks and facilities, and route information.

[1003] "Person distribution data" refers to information about the distribution of people, such as the number of people present in a particular area, their travel routes, and the length of their stay.

[1004] "Crowding data for surrounding facilities" refers to information on the congestion status, number of users, waiting times, etc. of specific facilities or locations.

[1005] "Event information" is information about the date, location, scale, and content of an event held in a specific area.

[1006] "Emotional state data" is information indicating the emotional state of a user that is obtained by analyzing the user's voice, text, images, and the like.

[1007] A "demand forecasting model" is an algorithm or mathematical model for predicting future demand based on collected data.

[1008] A "vehicle dispatch route" is a route that optimally guides a user to their destination, and is designed based on traffic conditions and various data.

[1009] A "driver terminal" is an electronic device such as a smartphone or tablet used by a driver to receive information about dispatch routes and demand forecasts.

[1010] A "user terminal" is an electronic device such as a smartphone or tablet used by a user, and is a terminal for transmitting ride requests and emotional state data.

[1011] A "generative AI model" is an artificial intelligence model that is trained to perform specific tasks using large amounts of data.

[1012] A "prompt" is an instruction given to a generative AI model to perform a specific task.

[1013] This invention is a demand forecasting system that collects and integrates real-time traffic conditions, map information, people distribution, congestion at nearby facilities, event information, etc. This system also aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotional state.

[1014] System Overview

[1015] This system consists of the following hardware and software:

[1016] Server: Collects, integrates, pre-processes, forecasts, routes, and updates data.

[1017] User terminal: Collects emotional data and ride requests from users.

[1018] Driver device: Used for route notifications and feedback.

[1019] Operation of each method

[1020] 1. Data Collection

[1021] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. Emotional state data is also collected from the user's device via voice, text, images, etc.

[1022] 2. Data integration and preprocessing

[1023] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[1024] 3. Demand forecasting

[1025] The server then inputs the pre-processed data into an AI model to generate demand forecasts. If many users are feeling stressed, it predicts that demand for rides in that area is likely to increase.

[1026] 4. Applying the Emotion Engine

[1027] Data such as voice, text, and images collected on the user's device are sent to the emotion engine for analysis. For example, if the user is frustrated, that information is sent to the server.

[1028] 5. Vehicle routing generation

[1029] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route.

[1030] 6. Route notification to drivers

[1031] The driver's terminal receives and displays the vehicle dispatch route information transmitted from the server.

[1032] Usage example

[1033] As a specific use case, consider a case where a passenger feels stressed during their commute. The emotion engine detects the stress and transmits the information to the server. The server uses this information to optimize a quieter route that avoids congestion and notifies the driver. This allows the passenger to reach their destination in a relaxed state.

[1034] Example prompt for a generative AI model:

[1035] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[1036] Through the steps described above, the present invention realizes an efficient and satisfying ride-sharing service that integrates real-time data and emotional data.

[1037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1038] Step 1:

[1039] Data collection

[1040] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information via API. Emotional state data is collected from user devices through voice, text, and images. All of this data is sent to the server. Input data is obtained from various APIs and emotion engines, and output data is integrated, unprocessed raw data.

[1041] Step 2:

[1042] Data integration and preprocessing

[1043] The server removes outliers from the collected data, fills in missing data, and normalizes the data. It also preprocesses emotion data in the same way. The input data is all the collected raw data, and the output data is preprocessed data with outliers removed and normalized. Specifically, it applies a data cleansing algorithm to detect outliers and missing values ​​and fill them in.

[1044] Step 3:

[1045] Demand forecasting

[1046] Based on the preprocessed data, the server uses a generative AI model to perform demand forecasting. The input data is the preprocessed data, and the output data is the demand forecast data for the next fixed time period. Specifically, the integrated data is input into the AI ​​model, and demand forecasting is performed using prompt statements. For example, the demand for rides in each area is predicted according to the prompt statements.

[1047] Step 4:

[1048] Applying the Emotion Engine

[1049] The voice, text, and image data collected on the user's device are sent to the emotion engine for analysis. The analysis results (emotional state data) are sent to the server by the emotion engine. The input data is the user's emotional state data, and the output data is the analyzed emotional state information. Specifically, the emotion engine performs voice tone, facial expression recognition, and text analysis to identify the emotional state.

[1050] Step 5:

[1051] Vehicle routing generation

[1052] The server generates an optimal vehicle dispatch route based on the demand forecast data and emotion data. The input data is the demand forecast data and emotion data, and the output data is optimal vehicle dispatch route information. Specifically, the server uses a route optimization algorithm to generate a route that the user feels comfortable with and selects the optimal driver.

[1053] Step 6:

[1054] Route notification to the driver

[1055] The driver's device receives and displays the dispatch route information sent from the server. The input data is the optimal dispatch route information, and the output data is the route displayed on the driver's device. Specifically, the route information is pushed to the driver's device, and the driver begins traveling based on that information.

[1056] Step 7:

[1057] Receiving feedback information

[1058] The driver's device sends feedback information to the server during travel, including driving data and the user's emotional state. The input data is feedback information, and the output data is data that is reflected in updating the demand forecasting model. Specifically, the driver's device sends real-time location information and the user's reactions to the server.

[1059] Step 8:

[1060] Update demand forecast models

[1061] The server updates the demand forecasting model based on the received feedback information. The input data is the feedback information, and the output data is the updated demand forecasting model. Specifically, the AI ​​model is retrained based on the feedback information to improve the accuracy of the next demand forecast.

[1062] Example prompt sentence:

[1063] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[1064] 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.

[1065] 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.

[1066] 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.

[1067] [Fourth embodiment]

[1068] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1069] 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.

[1070] 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).

[1071] 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.

[1072] 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.

[1073] 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).

[1074] 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.

[1075] 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.

[1076] 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.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] 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."

[1081] This invention is a system that collects and integrates traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information in real time. Based on this data, it performs demand forecasting, generates efficient vehicle dispatch routes, and notifies drivers. Furthermore, upon receiving a vehicle dispatch request from a user, it selects the most suitable driver and notifies the request information, thereby quickly responding to user needs.

[1082] System Operation

[1083] 1. Data Collection

[1084] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information, allowing the latest situation to be grasped in real time.

[1085] 2. Data integration and preprocessing

[1086] The server consolidates the collected data, corrects inconsistencies, improves data quality by removing outliers and imputing missing data, and normalizes the data to prepare it for input into the AI ​​model.

[1087] 3. Demand forecasting

[1088] The server uses the integrated data to predict demand for the next certain period of time, taking into account factors such as the day of the week, time of day, weather, and events, and identifies areas where travel demand will be high.

[1089] 4. Vehicle routing generation

[1090] The server generates optimal vehicle dispatch routes based on predicted demand data, taking into account current traffic conditions and the driver's location.

[1091] 5. Driver Notification

[1092] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server, allowing the driver to travel efficiently.

[1093] 6. Real-time updates and feedback

[1094] During the journey, the driver's device transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[1095] 7. Receiving requests from users

[1096] Users send a ride request through the app, which includes information such as the departure point, destination, and desired time.

[1097] 8. Driver Selection

[1098] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is notified of the request information and is given instructions on how to get to the departure point.

[1099] Specific examples

[1100] Example 1: Urban rush hour

[1101] The server predicts that demand for rides from business districts to stations will increase at 5 p.m. Ten minutes before the scheduled time, it suggests routes for nearby drivers to wait in front of the station, making it easier for commuters to board rides in front of the station, improving convenience.

[1102] Example 2: When a local event is held

[1103] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates increased demand in the surrounding area. Before the event begins, the server suggests routes for drivers to wait in the area, ensuring smooth transportation for event participants.

[1104] In this way, the present invention can provide an efficient ride-sharing service by combining real-time data collection, demand forecasting, and vehicle route optimization, which can particularly contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas.

[1105] The processing flow will be explained below.

[1106] Step 1: Data collection

[1107] The server periodically collects traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information. Traffic condition data includes road congestion information and travel speeds, and map information data includes coordinate information for roads and landmarks. People distribution data indicates the population density and movement patterns in a specific area, and congestion data at nearby facilities provides the number of users at major spots. Event information includes the date, time, and location of the event.

[1108] Step 2: Data integration and preprocessing

[1109] The server integrates the collected data, detects and removes outliers, fills in missing data, and normalizes the data. If there are inconsistencies in traffic condition data or pedestrian distribution data, it corrects them and converts them into a consistent format. If there are gaps in aerial photograph data or congestion data, it fills in the gaps based on surrounding data. It also standardizes all data so that it can be used by AI models.

[1110] Step 3: Demand forecast

[1111] The server uses the preprocessed data to perform demand forecasts. It inputs the collected data into an AI model to predict traffic demand for the next certain period. For example, the predictive model calculates which areas will experience demand, taking into account specific days of the week, time periods, events, and weather information.

[1112] Step 4: Generate a vehicle routing route

[1113] The server generates optimal vehicle dispatch routes based on predicted demand data. It uses Dijkstra and A algorithms to calculate optimal routes that reflect real-time traffic conditions and each driver's location. The generated routes also take into account the driver's fuel consumption and time efficiency.

[1114] Step 5: Send route to driver

[1115] The terminal (driver's smartphone) receives the dispatch route information sent from the server. The driver follows the displayed route information and heads to the passenger's pickup point. This information is updated regularly, providing the optimal route based on the latest conditions.

[1116] Step 6: Real-time updates and feedback

[1117] The device (the driver's smartphone) sends its current location and progress information to the server in real time. For example, if an unexpected traffic jam or accident occurs, the server recalculates the demand forecast model based on the latest information and re-optimizes the route. This ensures that the driver is always provided with the most up-to-date dispatch route.

[1118] Step 7: Receiving a request from the user

[1119] A user sends a ride request to the server through a ride-sharing app. This request includes details such as the origin, destination, and desired time, allowing the server to recognize the user's transportation needs.

[1120] Step 8: Driver selection and notification

[1121] The server selects the most suitable driver based on the received ride request, the driver's current location information, and demand forecast data. It applies the Greedy algorithm to select a driver who meets the user's request with the shortest travel distance and time. At the same time, it notifies the selected driver of the request information and provides instructions on how to get to the departure point. This information is displayed on the driver's device, and an appropriate ride is dispatched.

[1122] Example 1

[1123] 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."

[1124] In modern urban and rural areas, real-time vehicle demand forecasting and optimal route generation are required to improve transportation efficiency and travel convenience. However, current systems collect individual data but do not adequately integrate data processing, demand forecasting, and vehicle route optimization. This results in reduced transportation efficiency and inconvenience for users and drivers. Furthermore, there is a lack of systems that can respond to real-time feedback and updates. To address these issues, this invention proposes a system that integrates comprehensive data processing with advanced prediction and optimization methods.

[1125] 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.

[1126] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating the collected data, correcting inconsistencies, and performing preprocessing, means for predicting demand for the next certain period based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and taking into account current traffic conditions and the driver's location, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving real-time update information from the driver terminal, updating the demand forecast model, and re-optimizing the route as necessary, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, and means for notifying the selected driver of the request information and providing directions. This enables data integration processing and real-time prediction and optimization.

[1127] "Traffic condition data" refers to data that includes information on road congestion, traffic accidents, construction works, and the like.

[1128] "Map information data" refers to data including geographical location information, road maps, and building layouts.

[1129] "People distribution data" is data that shows patterns of people gathering and moving in specific areas and at specific times.

[1130] "Congestion data for surrounding facilities" is data that indicates the usage status and congestion level of commercial facilities, public facilities, etc.

[1131] "Event information" is data about public events such as concerts, sports games, and festivals.

[1132] "Means for integrating data, correcting inconsistencies, and preprocessing" refers to means for integrating various collected data into a single format and correcting inconsistencies and missing data.

[1133] The "means for forecasting demand" is a means for forecasting demand for vehicle dispatch within a certain period of time in the future based on the integrated data.

[1134] "Means for generating optimal vehicle dispatch routes" refers to means for calculating and generating the most efficient routes based on predicted demand, real-time traffic conditions, and the driver's location.

[1135] "Driver terminal" refers to a device such as a smartphone or tablet used by the driver, which receives and displays information from the server.

[1136] "Real-time updates" are the latest data generated while on the move, such as the driver's location and progress.

[1137] A "user terminal" refers to a device such as a smartphone or tablet used by a user who uses a vehicle dispatch service, and is a terminal used to send a vehicle dispatch request to the server.

[1138] A "ride request" is a request sent by a user through the app, including information such as the departure point, destination, and desired time.

[1139] The "means for selecting the best driver" is a means for selecting the driver who can most efficiently handle the request based on the ride request and the driver's current location information.

[1140] "Means for notifying request information and providing directions" refers to means for notifying the selected driver of details of the ride request and providing guidance on the optimal route to the specified departure point.

[1141] This invention is a system that collects and integrates multiple data in real time, and based on that data, predicts transportation demand and generates optimal vehicle dispatch routes. This system is composed of a server, terminals, and users, and aims to provide an efficient ride-sharing service.

[1142] Hardware and software used

[1143] The server is the central unit that performs advanced data processing and predictive calculations and utilizes the following software and libraries:

[1144] Data collection: We use Google Maps API, HERE Maps, public open data portals, etc. to collect traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[1145] Data integration and preprocessing: We use the pandas and NumPy libraries to integrate the collected data and correct inconsistencies, thereby imputing missing data and removing outliers.

[1146] Demand forecasting: Based on the integrated data, we use a time series forecasting model (e.g., ARIMA, LSTM) to forecast the demand within the next certain time period.

[1147] Vehicle routing generation: Uses the A algorithm and Dijkstra's algorithm to generate optimal vehicle routing based on predicted demand data, current traffic conditions, and driver location information.

[1148] Notification service: Google Firebase and Apple Push Notification service are used to notify drivers of the generated optimal route information.

[1149] Real-time updates: Using WebSocket or MQTT protocols, the driver's location and progress are sent to the server in real time.

[1150] The terminals (driver terminal and user terminal) are mobile devices such as smartphones and tablets. These terminals have the following functions:

[1151] Driver's device: Receives and displays real-time route information sent from the server. Also, transfers real-time updated information sent from the device to the server.

[1152] User terminal: Sends a ride request to the server. The front-end app is built using React Native or Flutter, and communicates with the back-end via a RESTful API to send requests.

[1153] A user is a person who uses a smartphone or tablet to use a ride-hailing service. The user inputs the departure point, destination, and desired time and sends a request to the server.

[1154] Specific examples

[1155] Example 1: Urban commute hours

[1156] The server predicts that demand for travel from the office district to the station will increase at 5 p.m. Specifically, it uses information that, "According to traffic data, the roads from the office district to the station are usually congested at 5 p.m." The server then suggests a route to nearby drivers 10 minutes in advance, telling them to "wait in front of the station." The driver's device receives this notification, allowing the driver to head to the station efficiently. Commuters can board smoothly in front of the station, improving travel convenience.

[1157] Example 2: When a local event is held

[1158] The server predicts that a large-scale event will be held in a local tourist destination over the weekend, and anticipates an increase in demand for travel to the surrounding area. Specifically, it uses forecast data that shows that "events in tourist destinations over the weekend will attract large crowds." It then suggests a route to the driver to wait in the vicinity before the event begins, telling them to "wait near the event venue." The driver's device receives the instructions and follows the directions, allowing event participants to reach the event site smoothly.

[1159] Prompt Sentence Examples

[1160] Below are some examples of prompts for the generative AI model:

[1161] "Please forecast major traffic demand this weekend."

[1162] "Generate the optimal route from the office district to the station between 5:00 PM and 6:00 PM."

[1163] "Re-optimize your vehicle routes around the event, taking into account real-time traffic conditions and driver location."

[1164] In this way, the present invention can contribute to easing traffic congestion in urban areas and ensuring transportation options in rural areas by collecting data in real time and generating efficient demand forecasts and optimal routes based on that data.

[1165] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1166] Step 1:

[1167] Data collection

[1168] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information through APIs. It uses Google Maps API, HERE Maps, public open data portals, etc. as input and obtains the necessary data from these services. The output is a collection of raw data obtained from each data source. Specifically, the server sends requests to each API and receives and stores the data returned as a response.

[1169] Step 2:

[1170] Data integration and preprocessing

[1171] The server integrates the collected data, corrects inconsistencies, and performs preprocessing. The input is the raw data from each data source collected in step 1. The output is an integrated and cleaned dataset. Specific operations include removing outliers, imputing missing data, and normalizing the data using the pandas and NumPy libraries. For example, missing values ​​are imputed with surrounding values, and outliers are removed using a specific threshold.

[1172] Step 3:

[1173] Demand forecasting

[1174] The server predicts demand for the next set of hours based on the integrated data. The input is the integrated dataset generated in step 2. The output is a forecast value from the demand forecasting model. Specifically, it uses a time series forecasting model (e.g., ARIMA, LSTM) to make predictions taking into account factors such as the day of the week, time, weather, and event information. For example, it predicts that "demand from the office district to the station will increase at 5 p.m. on Monday."

[1175] Step 4:

[1176] Vehicle routing generation

[1177] The server combines the predicted demand data, current traffic conditions, and the driver's location to generate the optimal vehicle dispatch route. The inputs are the predicted data obtained in step 3, real-time traffic information, and the driver's location information. The output is the optimal vehicle dispatch route. Specifically, it calculates the shortest route using the A algorithm or Dijkstra's algorithm, and adjusts the route by incorporating real-time traffic data.

[1178] Step 5:

[1179] Driver Notification

[1180] The terminal (driver's smartphone) receives and displays the optimal route information sent from the server in real time. The input is the route information generated in step 4. The output is the dispatch route displayed on the driver's terminal. Specifically, the route information is pushed to the driver's smartphone using Google Firebase or Apple Push Notification service.

[1181] Step 6:

[1182] Real-time updates and feedback

[1183] The driver's device transmits real-time location information and progress status to the server during travel. The input is the driver's current location and progress data. The output is real-time updated data received by the server. Specifically, location information is sent to the server with low latency using WebSocket or MQTT protocols, and the server uses this data to update its demand forecasting model and re-optimize routes as needed.

[1184] Step 7:

[1185] Receiving requests from users

[1186] A user sends a ride request to the server via a smartphone app. The input is information such as the departure point, destination, and desired time entered by the user. The output is the ride request received by the server. Specifically, the user enters the destination and desired time on the app screen, and then sends that information to the server via a RESTful API.

[1187] Step 8:

[1188] Driver Selection

[1189] The server selects the most suitable driver based on the received request and the driver's current location information. The input is the ride request and the driver's current location information. The output is the selected driver and notification information. Specifically, it uses a bipartite matching algorithm to select the driver who can most efficiently handle the request, notifies the driver of the request information, and provides directions on how to get there.

[1190] (Application example 1)

[1191] 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."

[1192] Modern food delivery services face many challenges in achieving efficient delivery operations. Among these, generating optimal routes in real time in response to fluctuations in traffic conditions and demand, and quickly selecting drivers are particularly important. However, systems that can handle these variables have not yet been adequately developed, which could significantly reduce driver and customer satisfaction. Furthermore, there is a lack of a way to reoptimize delivery routes based on real-time feedback, which also impacts operational efficiency. A new system is needed to resolve these issues.

[1193] 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.

[1194] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for integrating and pre-processing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, means for improving the delivery efficiency of delivery drivers based on the demand forecast and the optimal route generation in a food delivery service, and means for re-optimizing the delivery route based on real-time feedback information, thereby enabling fast and efficient delivery in a food delivery service.

[1195] 1. "Traffic condition data" refers to all information related to traffic, such as road congestion, accident information, and traffic signal status.

[1196] 2. "Map information data" means data that includes geographical location information and detailed road information.

[1197] 3. "Person distribution data" refers to data that shows the concentration and distribution of people in a particular area.

[1198] 4. "Congestion data for surrounding facilities" refers to data that indicates the degree of congestion and the number of people staying at a specific facility or location.

[1199] 5. "Event Information" refers to information about events or occasions held in a specific area or time.

[1200] 6. "Demand forecasting model" refers to an algorithm or machine learning model that forecasts demand in a specific region or time based on various collected data.

[1201] 7. "Optimal vehicle routing" refers to the best route calculated to reach a destination efficiently.

[1202] 8. "Driver device" refers to a device such as a smartphone or tablet held by the driver.

[1203] 9. "Feedback Information" means location, progress, and other information provided by a driver during a delivery.

[1204] 10. "User terminal" refers to a device such as a smartphone or tablet used by a User to submit an order or request.

[1205] 11. "Vehicle request" refers to the vehicle dispatch request information sent by a User.

[1206] 12. "Demand forecasting" refers to the process of estimating future demand for services based on collected data.

[1207] 13. “Optimization” refers to the process of adjusting parameters or conditions to obtain the best results in order to achieve a specific goal.

[1208] 14. "Real-time feedback" refers to immediate information provided by the driver or user.

[1209] This invention is a system for realizing efficient and prompt delivery operations in food delivery services. Specifically, it collects traffic condition data, map information data, people distribution data, congestion data at surrounding facilities, and event information in real time, and integrates and preprocesses them. It then forecasts demand based on this data, generates optimal vehicle dispatch routes, and notifies drivers. It also receives dispatch requests from users, selects the most suitable driver, and notifies them of the request information. It also reoptimizes delivery routes based on real-time feedback information.

[1210] Specific system configuration and operation

[1211] Data collection

[1212] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information, including information from various APIs on the Internet and GPS devices. The software used includes the Python requests library.

[1213] Data integration and preprocessing

[1214] The server integrates the collected data, corrects inconsistencies, and pre-processes it, including removing outliers, imputing missing data, and normalizing the data. Technologies used here include database management systems (e.g., MySQL) and data processing libraries (e.g., Pandas).

[1215] Demand forecasting

[1216] The server uses generative AI models based on the integrated data to forecast demand, predicting demand for specific time periods and locations and creating efficient delivery plans. The AI ​​models used include TensorFlow and PyTorch.

[1217] Vehicle routing generation

[1218] Based on the demand forecast results, the server generates the optimal vehicle dispatch route, taking into account traffic conditions and driver location information, using a pre-trained routing algorithm and real-time route optimization technology.

[1219] Driver Notification

[1220] The server then notifies the driver of the generated route information, which is then used as a smartphone or tablet, and the driver travels efficiently based on the route information.

[1221] Real-time updates and feedback

[1222] The server receives feedback from the driver's device, updates the demand forecast model, and re-optimizes the vehicle dispatch route as needed, enabling efficient delivery in real time.

[1223] Receiving requests from users

[1224] Customers can send food delivery requests from their smartphones or tablets, including information such as origin, destination, and desired time.

[1225] Driver Selection

[1226] The server selects the most suitable driver based on the received request and the driver's location information. The selected driver is then notified of the request information, ensuring a smooth delivery.

[1227] Specific examples

[1228] Ordering: A user wants a pizza delivered to their home at 6pm.

[1229] Prediction: Based on traffic conditions at 6 p.m. and historical data, the AI ​​model predicts that orders will be concentrated in a particular area at that time.

[1230] Notification: Driver A is notified of the optimal route and picks up the order at the nearest pizza place, immediately starting delivery along the specified route.

[1231] Example prompt sentence:

[1232] A user wants a pizza delivered to their home (Address: [Address]) at 6 PM. Based on the traffic conditions and historical data for this time, predict the optimal delivery route and notify the driver.

[1233] This system enables fast and efficient delivery for food delivery services, which will improve service quality and significantly increase the satisfaction of drivers and customers.

[1234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1235] Step 1: Data collection The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information. This data is acquired through various APIs and GPS devices. Input includes data acquired from APIs on the Internet, and this data is stored on the server as output.

[1236] Step 2: Data integration and preprocessing. The server integrates the collected data, corrects inconsistencies, and performs preprocessing. This includes removing outliers, imputing missing data, and normalizing the data. The input is the collected raw data, and the output is a preprocessed, high-quality dataset.

[1237] Step 3: Demand Forecasting The server uses a generative AI model based on the integrated data to perform demand forecasting. This predicts demand for specific time periods and locations. The input includes preprocessed data, and the output is the demand forecast result.

[1238] Step 4: Vehicle dispatch route generation The server generates the optimal vehicle dispatch route based on the demand forecast results, taking into account traffic conditions and driver location information. The inputs include demand forecast results, real-time traffic data, and driver location data, and the optimal vehicle dispatch route information is generated as the output.

[1239] Step 5: Notify the driver The server notifies the driver's terminal of the generated vehicle dispatch route information. The input is the optimal route information, and the output is a notification sent to the driver's terminal.

[1240] Step 6: Real-time updates and feedback. The server receives location information and progress information sent from the driver's device, updates the demand forecast model, and re-optimizes the dispatch route. The input includes real-time feedback information from the driver, and the output is an updated demand forecast result and a re-optimized route.

[1241] Step 7: Receiving a request from the user The user sends a request for a ride from their own device. The input includes information on the departure point, destination, and desired time, and the request information is stored in the server as output.

[1242] Step 8: Driver Selection The server selects the most suitable driver based on the received request and driver location information. The input is the ride request information and the driver's location data, and the output is a request notification to the selected driver.

[1243] 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.

[1244] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions.The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[1245] System Operation

[1246] 1. Data Collection

[1247] The server periodically collects traffic data, map information, pedestrian distribution data, congestion data at nearby facilities, and event information. It also collects user emotional data. Emotional data is collected on the device through the user's voice, text, images, etc.

[1248] 2. Data integration and preprocessing

[1249] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[1250] 3. Demand forecasting

[1251] The server performs demand forecasting based on the preprocessed data. The integrated data is input into an AI model to predict traffic demand for the next certain period of time. Emotional data analyzed by the emotion engine is also reflected in this prediction model. For example, if many users are feeling stressed, it may determine that there is a possibility of increased demand for rides in that area.

[1252] 4. Applying the Emotion Engine

[1253] The device (user's smartphone) sends data such as voice, text, and images input by the user to the emotion engine. The emotion engine analyzes this data and identifies the user's current emotional state. For example, if the user is irritated, that information is sent to the server.

[1254] 5. Vehicle routing generation

[1255] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route. For example, if the user wants to relax, it will suggest a route that avoids congestion.

[1256] 6. Route notification to drivers

[1257] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server, allowing the driver to travel efficiently and providing a service that takes into account the user's emotional state.

[1258] 7. Real-time updates and feedback

[1259] The device (driver's smartphone) sends real-time location information and progress status to the server. The server also receives emotional feedback information and updates the demand forecast model to provide more accurate vehicle dispatch routes.

[1260] 8. Receiving requests from users

[1261] Users can send a ride request to the server through the app. At this time, users can also input their emotional state. For example, information such as "I'm tired" or "I'm in a hurry" can be included in the request.

[1262] 9. Driver Selection and Notification

[1263] The server selects the most suitable driver based on the received request, the driver's current location, demand forecast data, and emotional data. The selected driver is also notified of the user's emotional state and instructed if special measures are required.

[1264] Specific examples

[1265] Example 1: Stress-reducing ride-hailing in urban areas

[1266] The server receives data that indicates that many users feel stressed during the morning commute. Based on this information, the server can provide quieter routes to users who feel stressed, reduce their stress, and select an appropriate driver to provide a relaxing in-car environment for users.

[1267] Example 2: Comfortable transportation at local events

[1268] The server receives emotional data from many users at local event venues, expressing their tiredness. Based on this information, it generates routes with minimal waiting time at the end of the event and prioritizes dispatching vehicles to tired users. In addition, it selects the most suitable vehicle and driver to ensure a comfortable trip.

[1269] In this way, by using an emotion engine in addition to collecting real-time data and forecasting demand, the present invention can provide optimal ride-hailing routes that take into account the user's emotional state, improving the user experience. In particular, by utilizing emotion data, an efficient and satisfying ride-sharing service can be realized in alleviating congestion in urban areas and securing transportation in rural areas.

[1270] The processing flow will be explained below.

[1271] Step 1: Data collection

[1272] The server periodically collects traffic data, map information data, people distribution data, congestion data at nearby facilities, and event information.

[1273] The device (user's smartphone) sends the user's emotional data, such as voice, text, and images, to the emotion engine, which then transfers it to the server. For example, if the user is feeling stressed, the engine collects their voice data.

[1274] Step 2: Data integration and preprocessing

[1275] The server then integrates the collected data into a single dataset, corrects inconsistencies and gaps, and normalizes the data. It also preprocesses the emotion data to create a consistent format.

[1276] For example, it removes outliers, fills in missing data, and converts all data into an input format for the AI ​​model.

[1277] Step 3: Applying the Emotion Engine

[1278] The device (user's smartphone) sends the voice, text, and image data collected from the user to the emotion engine, which analyzes this data and identifies the user's emotional state.

[1279] The server receives the emotional data analyzed by the emotion engine and determines the user's current emotional state.

[1280] Step 4: Demand forecast

[1281] The server uses the integrated data to predict traffic demand for the next certain period using an AI model, and also incorporates emotion data obtained by the emotion engine into this model.

[1282] For example, if many users in an area where an event is being held express the emotion "tired," it is predicted that demand in that area will increase.

[1283] Step 5: Generate a vehicle routing route

[1284] The server generates optimal vehicle dispatch routes based on predicted demand and user emotional data, and selects the most suitable route and driver based on the emotional data.

[1285] For example, if a user is looking to relax, the system will suggest a route that avoids crowded areas.

[1286] Step 6: Notify your driver of the route

[1287] The terminal (driver's smartphone) receives route information sent from the server and moves according to that route. The driver is also notified of the user's emotional state.

[1288] For example, the server may provide the driver with instructions such as, "The user wants to relax, so please choose a quiet route."

[1289] Step 7: Real-time updates and feedback

[1290] The device (driver's smartphone) transmits real-time location and progress information to the server, which uses this information to update the demand forecasting model and re-optimize the route as needed.

[1291] For example, if a traffic jam occurs along the way, the server calculates a new optimal route and notifies the driver.

[1292] Step 8: Receiving a request from the user

[1293] A user sends a ride request to the server through a ride-sharing app, which includes the origin, destination, desired time, and emotional state.

[1294] For example, emotional information such as "I'm tired" is also included in the request.

[1295] Step 9: Driver selection and notification

[1296] The server selects the most suitable driver based on the received ride request, the driver's current location information, demand forecast data, and emotional data. The selected driver is notified of the request information and the user's emotional state.

[1297] For example, "because the user is tired, a driver who can arrive quickly" is selected and the request information is notified.

[1298] In this way, the present invention combines real-time data collection and demand forecasting with an emotion engine to provide optimal vehicle dispatch routes that take into account the emotional state of the user. This not only contributes to reducing congestion, particularly in urban areas, and ensuring transportation options in rural areas, but also improves the user experience.

[1299] Example 2

[1300] 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."

[1301] Improving the user experience is crucial for modern ride-sharing services. However, existing systems rely on objective data such as traffic conditions and map information to predict demand and generate dispatch routes, making it difficult to provide services that take into account the user's emotional state. In particular, there is a problem in that appropriate responses are not provided to users experiencing increased stress or fatigue, limiting the improvement of user satisfaction.

[1302] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting user emotion data from voice, text, and image data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand and user emotion data, means for notifying the driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating the demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request, driver location information, and user emotion data, and means for notifying the selected driver of the request information. This enables demand forecasting and generation of vehicle dispatch routes that take the user's emotional state into consideration.

[1303] "Traffic condition data" refers to data that includes information on current traffic flow, congestion, accidents, and the like.

[1304] "Map information data" refers to data that includes information on geographical locations, topography, road networks, and the like.

[1305] "People distribution data" is data that contains information about the presence and density of people within a particular region or area.

[1306] "Congestion data for surrounding facilities" is data that includes information on the congestion status of commercial facilities, public transportation, tourist spots, etc.

[1307] "Event information" is data that includes information about events or activities that are held at specific dates, times, and locations.

[1308] "Emotional data" refers to data that contains information about people's emotional states, analyzed based on audio, text, and image data.

[1309] "Preprocessing" refers to processes such as removing outliers, filling in missing data, and normalizing data in order to prepare collected data for easier analysis.

[1310] "Demand forecasting" refers to predicting transportation demand for a certain period of time in the future based on collected data.

[1311] "Vehicle dispatch route" refers to the optimal route from the user's boarding point to their destination.

[1312] "Driver device" refers to an electronic device used by a driver, such as a smartphone or tablet.

[1313] "Feedback information" refers to data including information on evaluations of services and areas for improvement provided by drivers and users.

[1314] "User terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[1315] A "ride request" refers to a ride request sent by a user to use a ride-sharing service.

[1316] The "best driver" refers to the most suitable driver based on the received ride request, the driver's current location, demand forecast data, and emotional data.

[1317] This invention combines a demand forecasting system that collects and integrates multiple pieces of information in real time, such as traffic condition data, map information data, people distribution data, congestion data at nearby facilities, and event information, with an emotion engine that recognizes user emotions. The system aims to improve the user experience by optimizing vehicle dispatch routes taking into account the user's emotional state.

[1318] The server uses various APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. This allows the server to obtain the latest information in real time. It also collects data such as voice, text, and images from the device, and obtains user emotion data. This is done using NLP and image recognition technologies.

[1319] The collected data is integrated on the server, where it undergoes preprocessing, such as removing outliers, filling in missing data, and normalizing the data. It is expected that Python's pandas library will be used. After preprocessing, the data is input into a demand forecasting model, which uses a generative AI model (such as TensorFlow or PyTorch).

[1320] The demand forecasting model predicts traffic demand for the next set period based on traffic condition data, map information data, emotion data, etc. Based on this prediction result, the server generates the optimal vehicle dispatch route. If the user is emotionally tired, for example, it is possible to suggest routes that avoid congestion or quieter routes by reflecting the emotion data.

[1321] For example, if a user inputs "I'm tired," the server will integrate that emotion data and suggest a quieter route. It also takes into account the driver's location information to select the most suitable driver. During this selection process, the server selects the most suitable driver based on the received ride request, traffic data, and driver location information, and notifies the driver of the request.

[1322] Specifically, the server receives data from the emotion engine indicating that many users are feeling stressed during the morning rush hour. Based on this data, the server notifies users who are feeling stressed by saying, "A quieter route has been selected." The server also notifies the driver's device that, "This user is currently feeling stressed, so please try to drive comfortably."

[1323] As an example of a local event, the server receives emotional data from many users at the event venue, expressing their "tiredness." At the end of the event, the server generates a route that avoids routes that are likely to be crowded and minimizes waiting times. The server notifies the user that "a route for a comfortable trip has been selected," and instructs the driver that "this user is tired, so please be considerate."

[1324] In this way, the present invention can provide an optimal vehicle dispatch route that takes into account the user's emotional state by using an emotion engine in addition to collecting real-time data and forecasting demand.

[1325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1326] Step 1: Data collection

[1327] The server uses APIs and sensor devices to collect traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. It also obtains voice, text, and image data from the device (user's smartphone) and uses this to collect user emotion data. This allows the latest information to be obtained in real time. The input is various types of data, and the output is the raw data that combines these.

[1328] Step 2: Data integration and preprocessing

[1329] The server integrates all collected data using libraries such as pandas. During this process, preprocessing such as removing outliers, filling in missing data, and normalizing the data is performed. For example, missing location information data is filled in and the overall data is formatted for easier analysis. The input is the raw data, and the output is the preprocessed data.

[1330] Step 3: Demand forecast

[1331] The server inputs the preprocessed data into an AI model (using, for example, TensorFlow or PyTorch) to predict traffic demand. This model uses traffic condition data, map information data, people distribution data, congestion data at nearby facilities, event information, emotional data, and more. For example, if the emotion engine determines that many users are "feeling stressed," it predicts that demand in that area will increase. The input is the preprocessed data, and the output is the demand forecast results.

[1332] Step 4: Applying the Emotion Engine

[1333] The device (user's smartphone) sends voice, text, and image data to the emotion engine for analysis. NLP and image recognition technologies are used to identify the user's emotional state. For example, if the user inputs "I'm tired," the engine determines that "the user is currently tired" based on that data and sends that information to the server. The input is emotional data from the user, and the output is analyzed emotional information.

[1334] Step 5: Generate a vehicle routing route

[1335] The server generates an optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects a quiet route that avoids congestion or a route that requires immediate attention. For example, if the user sends emotional data indicating that they are "in a hurry," it selects the shortest route and the nearest driver. The input is the demand forecast result and emotional information, and the output is an optimized vehicle dispatch route.

[1336] Step 6: Notify your driver of the route

[1337] The terminal (driver's smartphone) receives and displays the dispatch route information sent from the server. For example, the server generates a "specific route to avoid congestion" and notifies the driver, who then follows that route. The input is the optimal dispatch route, and the output is the route display to the driver.

[1338] Step 7: Real-time updates and feedback

[1339] The device (driver's smartphone) sends real-time location information and progress status to the server. The server dynamically adjusts the dispatch route based on this information and updates the demand forecasting model. It also collects feedback from users and reflects that data in the demand forecasting model. The inputs are real-time data and feedback information, and the outputs are an updated demand forecasting model and an optimized route.

[1340] Step 8: Receiving a request from the user

[1341] The user sends a request for a ride to the server using the user terminal. At this time, the user can also input their emotional state. For example, they can send information such as "I'm in a hurry" or "I'm tired," and the data is also provided to the server. The input is the ride request and emotional information, and the output is the request data.

[1342] Step 9: Driver selection and notification

[1343] The server selects the optimal driver based on the received ride request, the current driver's location information, demand forecast data, and emotional data. For example, if it determines that the user is in a hurry, it selects the nearest driver and notifies that driver of the user's emotional state. The inputs are the ride request, the driver's location information, demand forecast data, and emotional data, and the output is the selected driver and notification of the request information.

[1344] (Application example 2)

[1345] 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."

[1346] As ride-sharing services have become more widespread in recent years, there is a demand for systems that can improve passenger travel experiences. It is particularly important to provide services that take into account passengers' emotional states, but current systems have difficulty fully reflecting this. Conventional dispatch systems forecast demand based on traffic conditions, map information, pedestrian distribution, congestion at nearby facilities, and event information. However, they lack mechanisms for collecting and analyzing passenger emotional data to provide optimal dispatch routes and in-car environments. To resolve this technical challenge, a new system is needed.

[1347] 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.

[1348] In this invention, the server includes means for collecting traffic condition data, means for collecting map information data, means for collecting people distribution data, means for collecting congestion data at surrounding facilities, means for collecting event information, means for collecting emotional state data, means for integrating and preprocessing the collected data, means for performing demand forecasting based on the integrated data, means for generating an optimal vehicle dispatch route based on the predicted demand, means for notifying a driver terminal of the generated vehicle dispatch route, means for receiving feedback information from the driver terminal and updating a demand forecasting model, means for receiving a vehicle dispatch request from a user terminal, means for selecting an optimal driver based on the received vehicle dispatch request and driver location information, means for notifying the selected driver of the request information, and means for analyzing the emotional data using a generative AI model and optimizing the corresponding route and in-vehicle environment. This makes it possible to generate an optimal vehicle dispatch route that takes into account the emotional state of passengers and provide a comfortable in-vehicle environment.

[1349] "Traffic condition data" refers to various types of information related to traffic, such as traffic flow, congestion, traffic accident information, and road closure status.

[1350] "Map information data" refers to various information related to maps, such as geographical location information, the layout of road networks and facilities, and route information.

[1351] "Person distribution data" refers to information about the distribution of people, such as the number of people present in a particular area, their travel routes, and the length of their stay.

[1352] "Crowding data for surrounding facilities" refers to information on the congestion status, number of users, waiting times, etc. of specific facilities or locations.

[1353] "Event information" is information about the date, location, scale, and content of an event held in a specific area.

[1354] "Emotional state data" is information indicating the emotional state of a user that is obtained by analyzing the user's voice, text, images, and the like.

[1355] A "demand forecasting model" is an algorithm or mathematical model for predicting future demand based on collected data.

[1356] A "vehicle dispatch route" is a route that optimally guides a user to their destination, and is designed based on traffic conditions and various data.

[1357] A "driver terminal" is an electronic device such as a smartphone or tablet used by a driver to receive information about dispatch routes and demand forecasts.

[1358] A "user terminal" is an electronic device such as a smartphone or tablet used by a user, and is a terminal for transmitting ride requests and emotional state data.

[1359] A "generative AI model" is an artificial intelligence model that is trained to perform specific tasks using large amounts of data.

[1360] A "prompt" is an instruction given to a generative AI model to perform a specific task.

[1361] This invention is a demand forecasting system that collects and integrates real-time traffic conditions, map information, people distribution, congestion at nearby facilities, event information, etc. This system also aims to improve the user experience by combining it with an emotion engine that recognizes the user's emotional state.

[1362] System Overview

[1363] This system consists of the following hardware and software:

[1364] Server: Collects, integrates, pre-processes, forecasts, routes, and updates data.

[1365] User terminal: Collects emotional data and ride requests from users.

[1366] Driver device: Used for route notifications and feedback.

[1367] Operation of each method

[1368] 1. Data Collection

[1369] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information. Emotional state data is also collected from the user's device via voice, text, images, etc.

[1370] 2. Data integration and preprocessing

[1371] The server integrates all collected data, removes outliers, fills in missing data, and normalizes the data. The same preprocessing is performed on emotion data.

[1372] 3. Demand forecasting

[1373] The server then inputs the pre-processed data into an AI model to generate demand forecasts. If many users are feeling stressed, it predicts that demand for rides in that area is likely to increase.

[1374] 4. Applying the Emotion Engine

[1375] Data such as voice, text, and images collected on the user's device are sent to the emotion engine for analysis. For example, if the user is frustrated, that information is sent to the server.

[1376] 5. Vehicle routing generation

[1377] The server generates the optimal vehicle dispatch route based on the predicted demand data and the user's emotional data. Based on the emotional data, it selects the most suitable driver and the most comfortable route.

[1378] 6. Route notification to drivers

[1379] The driver's terminal receives and displays the vehicle dispatch route information transmitted from the server.

[1380] Usage example

[1381] As a specific use case, consider a case where a passenger feels stressed during their commute. The emotion engine detects the stress and transmits the information to the server. The server uses this information to optimize a quieter route that avoids congestion and notifies the driver. This allows the passenger to reach their destination in a relaxed state.

[1382] Example prompt for a generative AI model:

[1383] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[1384] Through the steps described above, the present invention realizes an efficient and satisfying ride-sharing service that integrates real-time data and emotional data.

[1385] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1386] Step 1:

[1387] Data collection

[1388] The server periodically collects traffic data, map information, people distribution data, congestion data at nearby facilities, and event information via API. Emotional state data is collected from user devices through voice, text, and images. All of this data is sent to the server. Input data is obtained from various APIs and emotion engines, and output data is integrated, unprocessed raw data.

[1389] Step 2:

[1390] Data integration and preprocessing

[1391] The server removes outliers from the collected data, fills in missing data, and normalizes the data. It also preprocesses emotion data in the same way. The input data is all the collected raw data, and the output data is preprocessed data with outliers removed and normalized. Specifically, it applies a data cleansing algorithm to detect outliers and missing values ​​and fill them in.

[1392] Step 3:

[1393] Demand forecasting

[1394] Based on the preprocessed data, the server uses a generative AI model to perform demand forecasting. The input data is the preprocessed data, and the output data is the demand forecast data for the next fixed time period. Specifically, the integrated data is input into the AI ​​model, and demand forecasting is performed using prompt statements. For example, the demand for rides in each area is predicted according to the prompt statements.

[1395] Step 4:

[1396] Applying the Emotion Engine

[1397] The voice, text, and image data collected on the user's device are sent to the emotion engine for analysis. The analysis results (emotional state data) are sent to the server by the emotion engine. The input data is the user's emotional state data, and the output data is the analyzed emotional state information. Specifically, the emotion engine performs voice tone, facial expression recognition, and text analysis to identify the emotional state.

[1398] Step 5:

[1399] Vehicle routing generation

[1400] The server generates an optimal vehicle dispatch route based on the demand forecast data and emotion data. The input data is the demand forecast data and emotion data, and the output data is optimal vehicle dispatch route information. Specifically, the server uses a route optimization algorithm to generate a route that the user feels comfortable with and selects the optimal driver.

[1401] Step 6:

[1402] Route notification to the driver

[1403] The driver's device receives and displays the dispatch route information sent from the server. The input data is the optimal dispatch route information, and the output data is the route displayed on the driver's device. Specifically, the route information is pushed to the driver's device, and the driver begins traveling based on that information.

[1404] Step 7:

[1405] Receiving feedback information

[1406] The driver's device sends feedback information to the server during travel, including driving data and the user's emotional state. The input data is feedback information, and the output data is data that is reflected in updating the demand forecasting model. Specifically, the driver's device sends real-time location information and the user's reactions to the server.

[1407] Step 8:

[1408] Update demand forecast models

[1409] The server updates the demand forecasting model based on the received feedback information. The input data is the feedback information, and the output data is the updated demand forecasting model. Specifically, the AI ​​model is retrained based on the feedback information to improve the accuracy of the next demand forecast.

[1410] Example prompt sentence:

[1411] "The next passenger's emotional data is stress. Please suggest the best route and in-car environment for this passenger."

[1412] 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.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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).

[1419] 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.

[1420] 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."

[1421] 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.

[1422] 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).

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] The following is further disclosed regarding the above embodiment.

[1434] (Claim 1)

[1435] a means for collecting traffic condition data;

[1436] A means for collecting map inform...

Claims

1. a means for collecting traffic condition data; A means for collecting map information data; a means for collecting human distribution data; A means for collecting congestion data of surrounding facilities; a means for collecting event information; a means of integrating and pre-processing the collected data; a means for performing demand forecasting based on the integrated data; means for generating optimal vehicle routing based on the predicted demand; a means for notifying a driver terminal of the generated vehicle dispatch route; a means for receiving feedback information from the driver terminal and updating the demand forecasting model; A means for receiving a dispatch request from a user terminal; A means for selecting the most suitable driver based on the received dispatch request and the driver's location information; a means for notifying the selected driver of the request information; A system including:

2. 2. The system according to claim 1, wherein the means for performing the demand forecasting applies a model for forecasting traffic demand for the next certain period of time based on collected traffic condition data, pedestrian distribution data, congestion data at surrounding facilities, and event information.

3. 2. The system according to claim 1, wherein the means for generating the optimal vehicle dispatch route calculates the optimal route based on traffic condition data and driver location information that are updated in real time.

Images