system

Abstract

We provide the system. [Solution] The present invention relates to a system that, when an employee goes out or on a business trip, inputs information such as departure point, destination, date and time, number of accompanying persons, meeting schedule, presence or absence of luggage, and desired conditions. The system automatically acquires information from various passenger service providers and rental car services, past settlement data, location information services, satellite office information, weather and road information, etc., and uses generative AI to automatically select and propose the optimal means of transportation, route, and meeting location from multiple perspectives such as cost, time required, number of transfers, convenience, feasibility of holding the meeting, past performance, congestion prediction, and individual preferences. The system is characterized by simultaneously achieving optimization of business efficiency and travel costs for individual employees and the entire group.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence associated with a description related to a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] The problems this invention aims to solve are: employees traveling for business or leisure must individually research and compare multiple transportation services, transit information websites, rental car services, past expense data, location information services, and the availability of satellite offices and telephone booths to determine the optimal means of transportation and route to their destination, which consumes a great deal of time and effort; when traveling with multiple companions or when meetings are scheduled during travel, employees are often unable to rationally and objectively select the optimal means of transportation, route, and meeting location, instead relying on the experience and subjective judgment of senior colleagues or superiors, resulting in inefficient choices; and the costs and time spent on travel and leisure for the entire group are not adequately optimized. To solve these problems, this invention aims to automatically collect necessary information from various external services and internal databases, and analyze and compare it comprehensively and from multiple perspectives using generative AI, thereby optimizing the selection of means of transportation, routes, and meeting locations for individual employees and the entire group, and simultaneously improving work efficiency and reducing costs. [Means for solving the problem]

[0005] As a means of solving the problem, the system comprises an input unit for inputting employee travel schedule information, an information acquisition unit for acquiring transportation route information provided by various passenger service providers, rental car service usage information, past settlement data of group companies and the company itself, location information service data, and availability information of satellite offices and telephone booths, and an optimization processing unit that, based on the information obtained from the input unit and the information acquisition unit, uses generative AI to score from multiple perspectives such as the number of accompanying persons, destination, departure point, departure date and time, meeting schedule, past travel history, cost, duration, number of transfers, convenience, and feasibility of holding the meeting, and automatically selects and proposes the optimal means of transportation, route, and meeting location along the route. The optimization processing unit operates with generative AI as a requirement, comprehensively compares and analyzes multiple candidate means of transportation and meeting location, automating the selection of means of transportation and meeting location for employee travel, thereby simultaneously achieving operational efficiency and cost optimization. [Brief explanation of the drawing]

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0007] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0008] First, let's explain the terminology used in the following explanation.

[0009] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0010] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0011] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0012] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" may mean only A, only B, or a combination of A and B. In addition, in this specification, when three or more items are expressed in a connected manner using "and / or", the same concept as that for "A and / or B" applies.

[0014] [First Embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] As shown in FIG. 1, the data processing system 10 includes a data processing apparatus 12 and a smart device 14. An example of the data processing apparatus 12 includes a server.

[0017] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of the "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, RAM 30, and 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) and the like.

[0018] The smart device 14 includes a computer 36, a reception apparatus 38, an output apparatus 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, RAM 48, and storage 50 are connected to a bus 52. The reception apparatus 38, output apparatus 40, camera 42 and communication I / F 44 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A receives user input via contact of an indicator (for example, a pen or a finger) by detecting the contact of the indicator. The microphone 38B receives user input via voice by detecting the user's voice. The control unit 46A in the processor 46 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.

[0020] The output device 40 includes a display 40A, a speaker 40B, and the like, and presents data to the user 20 by outputting the data in a representation form perceptible to the user 20 (for example, voice 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 voice in accordance with instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to the network 54. The communication I / Fs 44 and 26 manage the exchange of various types of information between the processor 46 and the processor 28 via the network 54.

[0022] Figure 2 illustrates an example of the main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0024] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0027] (Example 1)

[0028] The flow of a specific process in Example 1 will now be described. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0029] (Embodiments for carrying out the present invention)

[0030] Embodiments for carrying out the present invention will be described in more specific and detail. The system of the present invention consists of a server and a terminal (smartphone, tablet, laptop, etc.) and automatically suggests the optimal means of transportation, route, and meeting place along the way when an employee is out of the office or on a business trip.

[0031] First, the terminal is equipped with a user interface, allowing employees to input detailed travel plans using a dedicated application or web browser on the terminal. These plans include departure point, destination, departure date and time, number of accompanying persons, whether there are meetings scheduled and their times, whether there is luggage, preferred mode of transportation (e.g., public transport, rental car, taxi, shared bicycle, etc.), budget limit, priorities during travel (e.g., "I want to prioritize the meeting," "I want to keep costs down," "I want to reduce the number of transfers," etc.), and past preferences or allergies regarding modes of transportation (e.g., "I get carsick easily," "I have difficulty walking long distances," etc.). For example, employee A can input detailed conditions such as "Departing from headquarters at 9:00 AM on July 1st, arriving at destination B by 12:00 PM, traveling with 5 people, having an online meeting at 1:00 PM, having a lot of luggage, and wanting to minimize transfers as much as possible."

[0032] Information entered on the terminal is transmitted to the server via the communication unit. The server side is equipped with an information acquisition unit, which automatically and in real time acquires necessary information by linking with APIs from various passenger service providers (e.g., railway companies, bus companies, airlines, taxi companies, shared bicycle operators, etc.), transit information site APIs, rental car service APIs, databases of group companies' and the company's own settlement systems, location information service APIs, satellite office and telephone booth reservation systems, weather information service APIs, road traffic information service APIs, and so on. For example, it comprehensively collects a wide range of information, such as train service status, delay information, congestion forecasts, bus timetables, flight seat availability, rental car availability (vehicle types, rates, pick-up and return locations), taxi availability, shared bicycle station locations and availability, past expense data from similar outings (e.g., "means of transport, costs, and travel time to destination B over the past 3 years"), availability and facilities (Wi-Fi, private rooms, power outlets, monitors, etc.) for satellite offices and telephone booths, weather forecasts (rainfall, snowfall, temperature, wind speed, etc.), and road congestion and construction information.

[0033] The information acquisition unit retrieves multiple transportation options and route candidates, for example, if employee A and five others are heading to destination B. These options include public transport routes such as "a route transferring from train A to train B (60 minutes, 1200 yen, 1 transfer, moderate congestion)" and "a route transferring from bus C to train D (80 minutes, 900 yen, 2 transfers, low congestion)," rental cars such as "a standard car (5-seater, 6000 yen, 70 minutes, rental location: station front office, return location: office near destination)," taxis such as "65 minutes, 9000 yen, 10 minutes waiting time until a taxi becomes available," and shared bicycles such as "120 minutes, 500 yen, 1 transfer, 5 bicycles available at the station." In addition, past expense data will be collected, such as "July 2023: Train use, cost 1300 yen, travel time 65 minutes," "December 2022: Rental car use, cost 6500 yen, travel time 75 minutes," and "March 2023: Bus use, cost 1000 yen, travel time 90 minutes." Furthermore, detailed information on satellite offices and telephone booths will be collected, such as "Satellite office at station X: Available at 13:00, equipped with Wi-Fi, private room, and monitor," "Telephone booth at station Y: Fully occupied at 13:00," and "Satellite office near destination B: Available at 13:00, Wi-Fi only."

[0034] This information is sent to the optimization processing unit on the server. The optimization processing unit is implemented with a generative AI as a requirement, and it integrates the input employee travel schedule information with various data collected by the information acquisition unit, performing scoring and optimization from multiple perspectives. For example, if there are many people traveling together, the generative AI will prioritize the cost-effectiveness and convenience of using a rental car and compare it with the total cost and travel time if public transportation is used individually. For example, if the total cost for 5 people using the train is 6,000 yen and a rental car is also 6,000 yen, the AI ​​will prioritize suggesting a rental car, taking into account the amount of luggage, the number of transfers, and the ease of conversation and document review during the journey. It will also analyze past settlement data and take into account the means of transportation actually used under similar conditions, their evaluation, whether there were any problems, and feedback from employees (for example, "The rental car was delayed due to traffic," "The train was very crowded," etc.).

[0035] The generative AI, when a meeting is scheduled during travel, considers the availability of satellite offices and telephone booths at each station along the route and suggests the best place to stop for the meeting. For example, if a meeting is scheduled for 13:00, it will select the optimal meeting location based on information such as "There is a satellite office at station X that is available at 13:00," "The telephone booths at station Y are all occupied," and "There is availability at a satellite office near destination B at 13:00," taking into account the travel route, travel time before and after the meeting, the availability of facilities, and ease of booking. Furthermore, the generative AI also takes weather and road traffic information into account, flexibly responding to real-time changes in conditions, such as "Heavy rain is expected, so avoid walking or cycling" or "The highway is congested, so renting a car is not recommended."

[0036] One way to utilize generative AI is to first comprehensively generate multiple transportation options, routes, and meeting location candidates. For each, it automatically extracts multifaceted evaluation indicators such as cost, travel time, number of transfers, convenience, ease of luggage transport, feasibility of holding the meeting, consistency with past performance, congestion prediction, weather information, road conditions, availability of facilities, ease of booking, employee preferences and allergies, and the group's overall travel cost optimization policy. Next, based on these evaluation indicators, the generative AI uses natural language processing and machine learning models to propose the optimal combination of transportation, route, and meeting location, taking into account employee preferences, past trends, and the group's overall optimization policy. For example, the generative AI automatically generates several specific suggestions such as, "The most efficient option is for five people to rent a car and hold the 1pm meeting at the satellite office near station X," "The best option is to use public transportation and get off at station Y to use a telephone booth," or "It is recommended to take a taxi and hold the meeting at the satellite office near destination B." Furthermore, generative AI can continuously learn from employee feedback and actual usage data, thereby improving the accuracy of future suggestions.

[0037] Furthermore, generative AI can instantly recalculate and re-propose optimal routes, modes of transportation, and meeting locations in real time, even when information changes, such as when the number of accompanying persons suddenly increases or decreases, when the meeting schedule changes, or when the weather suddenly changes. For example, if heavy rain is predicted just before departure, the generative AI will take into account the risk of delays on public transportation and the safety of using a rental car, and re-select the optimal means of transportation. Also, if the meeting is extended during travel, it can instantly search for the availability of the next satellite office and suggest getting off midway or changing the route. For example, if the meeting runs longer than planned, it can flexibly propose alternatives depending on the situation, such as getting off at the next station and using a different satellite office, or switching to a taxi as the mode of transportation.

[0038] The main functions implemented on the server side include an information acquisition unit, an optimization processing unit, an execution environment for generative AI, a module for linking with external services, a module for accumulating and analyzing historical data, a real-time information update module, and a user feedback management module. The main functions implemented on the terminal side include a user interface, an input unit for outing schedule information, a communication unit with the server, a display unit for suggestion results, a user feedback input unit, a reservation operation unit, and a notification function. For example, information entered on the terminal is sent to the server, where the generative AI performs optimization processing, and the results are sent back to the terminal, where a list of "recommended modes of transport," "recommended routes," and "recommended meeting locations" is displayed. Furthermore, it is possible for the user to make reservations for selected modes of transport and meeting locations on the terminal side, and this reservation information is also centrally managed on the server side. For example, reservations for rental cars, satellite offices, and public transport tickets can all be made in one place.

[0039] Furthermore, for example, if multiple employees are traveling to the same destination, the generative AI can comprehensively analyze everyone's schedules, departure points, and meeting appointments to suggest the most efficient meeting place, departure time, and mode of transportation. For instance, if four people are traveling to the same destination from different starting points, the AI ​​can automatically generate multiple scenarios, such as meeting at an intermediate station and renting a car, everyone using public transport, or sharing a taxi, and then present the optimal solution. It can also optimize the overall travel cost and time for the group. For example, it can set a goal of reducing the group's overall travel expenses by 10% annually and then suggest the most suitable mode of transportation to achieve that goal.

[0040] Furthermore, generative AI can learn from employees' past travel history and feedback, automatically reflecting individual preferences and constraints in its suggestions. For example, it might recognize that "Employee A is prone to motion sickness on buses," "Employee B prefers rental cars when carrying a lot of luggage," or "Employee C strongly desires a private room for meetings." If Employee A should avoid buses, the system will prioritize suggesting routes that exclude buses. In addition, the generative AI can immediately offer alternatives in the event of travel problems (e.g., "the train is delayed," "the rental car return location is full"). For example, if a train is delayed, it will suggest switching to the next connecting train or taking a taxi; if the rental car return location is full, it will suggest returning the car to a nearby branch.

[0041] Thus, in the embodiments of the present invention, the roles of the server and terminal are clearly defined, and generative AI is used as an essential core technology. By utilizing generative AI in all situations, such as collecting information from external services and internal databases, scoring from multiple perspectives, optimization, real-time re-suggestions, learning from user feedback, reflecting individual preferences, and presenting alternative solutions in case of trouble, the selection of means of transportation, routes, and meeting locations for outings and business trips is automated and optimized, thereby simultaneously achieving improved work efficiency and cost reduction for individual employees and the entire group.

[0042] (System Configuration)

[0043] The system according to this embodiment comprises a user interface unit, an outing schedule information input unit, an information acquisition unit, an optimization processing unit, a generation AI collaboration unit, a proposal result display unit, a reservation management unit, a user feedback management unit, a communication unit, and a database management unit. The user interface unit provides screens and input forms for employees to operate on terminals such as smartphones, tablets, and laptops, and realizes a variety of interfaces, such as displaying maps of departure and destination locations, selecting dates and times in calendar format, adding and deleting companions, inputting meeting schedules, selecting whether or not to have luggage and desired modes of transportation, referring to past travel history, explanations of characteristics and precautions for each mode of transportation, and interactive input via voice input or chatbot. The outing schedule information input unit organizes and structures detailed outing schedule information received from the user interface unit, such as departure point, destination, departure date and time, number of accompanying persons, meeting schedule, whether or not there is luggage, preferred mode of transportation, budget, priorities, individual preferences, and constraints. It then sends specific conditions to the server, such as "Depart from headquarters at 9:00 on July 1st, arrive at destination B by 12:00 with 5 people, online meeting at 13:00, lots of luggage, want to minimize transfers, bus is not an option."

[0044] The information acquisition unit is located on a server and connects with a wide range of external and internal information sources, including APIs from various passenger service providers, transit information websites, rental car services, taxi dispatch services, shared bicycle operators, airlines, databases of group companies' and the company's own settlement systems, location information services, reservation systems for satellite offices and telephone booths, weather information services, and road traffic information services, to acquire necessary data in real time. For example, it comprehensively collects information such as train operation status and delay information, bus timetables and congestion forecasts, rental car vehicle availability and fares, taxi dispatch status, shared bicycle station locations and availability, airline seat availability and fares, settlement data and usage history from similar trips in the past, availability, facilities, and operating hours of satellite offices and telephone booths, weather forecasts, rainfall, snowfall, temperature, wind speed, and road congestion and construction information. Furthermore, for example, if five employees are heading to destination B, the options are: taking train A and transferring to train B (60 minutes, 1200 yen, 1 transfer, moderate congestion), taking bus C and transferring to train D (80 minutes, 900 yen, 2 transfers, low congestion), renting a standard car (5-seater, 6000 yen, 70 minutes, pick-up location: station front office, return location: office near destination), taking a taxi (65 minutes, 9000 yen, 10 minutes waiting time for dispatch), and using a shared bicycle (120 minutes, The system retrieves multiple transportation options, routes, and meeting locations, including the following: cost of 500 yen, one transfer, and 5 available spaces at the station; past expense data (July 2023: train fare 1300 yen, travel time 65 minutes; December 2022: rental car fare 6500 yen, travel time 75 minutes); and satellite offices and telephone booths (Station X satellite office available at 13:00 with Wi-Fi, private room, and monitor; Station Y telephone booths fully occupied at 13:00; nearby satellite office at Destination B available at 13:00 with Wi-Fi only).

[0045] The optimization processing unit integrates diverse data obtained from the information acquisition unit and conditions from the outing schedule information input unit, and works in conjunction with the generation AI collaboration unit to perform scoring and optimization from multiple perspectives. For example, if there are many accompanying persons, it prioritizes the cost-effectiveness and convenience of using a rental car and compares it with the total cost and travel time if public transportation is used individually. It also analyzes past settlement data and takes into account the means of transportation actually used under similar conditions, their evaluation, whether or not there were any problems, and feedback from employees. If there is a meeting scheduled during travel, it considers the availability of each station along the route and nearby satellite offices and telephone booths, and suggests the best place to stop to hold the meeting. It also takes weather information and road traffic information into account, and flexibly responds to real-time changes in conditions, such as avoiding walking or cycling if heavy rain is expected, or not recommending the use of a rental car if there is congestion. For example, if the total cost for 5 people using the train is 6,000 yen and the cost of a rental car is 6,000 yen, it will prioritize suggesting a rental car, taking into account the amount of luggage, the number of transfers, and the ease of conversation and document review during travel. Furthermore, through the Generative AI Integration Department, the system learns from employees' past travel history and feedback, automatically reflecting individual preferences and constraints in its suggestions. For example, it might recognize that Employee A is prone to motion sickness on buses, Employee B prefers rental cars when carrying a lot of luggage, or Employee C strongly desires a private room for meetings.

[0046] The Generative AI Collaboration Unit generates prompt statements for the Generative AI based on the information and conditions passed from the Optimization Processing Unit, and performs multifaceted analysis and proposal generation by the AI. For example, it generates a specific prompt statement for the Generative AI such as "Departure point: Head office, Destination: Destination B, Departure date and time: July 1st, 9am, Desired arrival time: 12pm, Number of accompanying persons: 5, Meeting scheduled: Online meeting at 1pm, Lots of luggage, Want to reduce the number of transfers, Bus not allowed, Past travel history: Train 1300 yen, 65 minutes, Rental car 6500 yen, 75 minutes, Satellite office information: Station X available at 1pm, Wi-Fi, private room with monitor, Station Y fully booked at 1pm, Near Destination B available at 1pm, Wi-Fi only, Weather: Heavy rain forecast, Roads: Traffic congestion, Consider all conditions and propose the optimal means of transportation, route, and meeting place," and feeds it to the AI. Based on this information, the generative AI automatically extracts a multifaceted evaluation index, including cost, travel time, number of transfers, convenience, ease of luggage transport, feasibility of holding the meeting, consistency with past performance, congestion forecast, weather information, road conditions, availability of facilities, ease of booking, employee preferences and allergies, and the group's overall travel cost optimization policy, and proposes the optimal combination of transportation, route, and meeting location. For example, it automatically generates multiple specific suggestions such as, "The most efficient option is for five people to rent a car and hold the 1pm meeting at the satellite office near Station X," "The best option is to use public transportation and get off at Station Y to use the telephone booth," or "It is recommended to take a taxi and hold the meeting at the satellite office near Destination B."

[0047] The suggestion result display unit clearly displays the optimal transportation, route, and meeting location suggestions obtained from the generation AI collaboration unit and the optimization processing unit on the terminal screen. For example, for each recommended transportation method, it presents information such as cost, travel time, number of transfers, congestion level, ease of luggage transport, meeting location facilities, and reservation status in a way that is easy for the user to understand intuitively, using comparison tables, graphs, route displays on maps, timeline displays, voice guidance, and chatbot explanations. Furthermore, operation buttons such as "Proceed to Reservation," "View Details," and "Compare with Other Options" are provided for each suggestion, allowing the user to easily select the next action.

[0048] The reservation management department centrally manages reservations for transportation and meeting locations selected by users. For example, it automatically executes reservations for rental cars, satellite offices, public transport tickets, taxis, and shared bicycles in conjunction with external services, and notifies users when reservations are complete. It also enables changes and cancellations of reservation status, confirmation of reservation details and sending of reminders, bulk reservations for multiple people, and group sharing of reservation details.

[0049] The User Feedback Management Department collects feedback from users after they leave the office or go on business trips regarding their means of transportation, meeting locations, routes, facilities, congestion levels, handling of problems, and overall satisfaction, and stores this information in the Database Management Department. For example, it collects specific opinions and evaluations such as "The rental car was delayed due to traffic," "The Wi-Fi at the satellite office was unstable," "The train was extremely crowded," and "The taxi dispatch was delayed," and uses this information through the Generative AI Integration Department to improve the accuracy of future proposals.

[0050] The communications department is responsible for sending and receiving data between terminals and servers, between servers and external services, and between different parts of the server, ensuring secure communication, real-time information updates, retry processing in case of failures, communication log management, data encryption, and user authentication. The database management department centrally manages information such as travel schedules, acquired data, past settlement history, reservation information, user feedback, AI training data, and system logs, and performs high-speed searches, aggregations, analyses, backups, and restores as needed.

[0051] A specific example of a prompt statement to be fed into a generative AI when implementing the present invention is: "Departure point: Head office, Destination: Destination B, Departure date and time: July 1st, 9am, Desired arrival time: 12pm, Number of accompanying persons: 5, Meeting scheduled: Online meeting at 1pm, Lots of luggage, Want to reduce the number of transfers, Bus not allowed, Past travel history: Train 1300 yen, 65 minutes, Rental car 6500 yen, 75 minutes, Satellite office information: Station X available at 1pm, Wi-Fi, private room with monitor, Station Y fully booked at 1pm, Near Destination B available at 1pm, Wi-Fi only, Weather: Heavy rain Examples of problems include: "Consider the forecast, road conditions (traffic congestion), and propose the optimal mode of transport, route, and meeting location," "Four people are traveling to the same destination C from different starting points. Considering each person's starting point, available departure time, meeting schedule, luggage status, past travel history, satellite office availability, weather, and road conditions, propose the most efficient meeting place, departure time, mode of transport, and meeting location," and "If the meeting is extended during travel, immediately search for the availability of the next satellite office and propose the best alternative, including stopovers or route changes."

[0052] As described above, the system according to this embodiment comprises a user interface unit, an outing schedule information input unit, an information acquisition unit, an optimization processing unit, a generative AI collaboration unit, a proposal result display unit, a reservation management unit, a user feedback management unit, a communication unit, and a database management unit, each of which is responsible for specific and diverse functions. By utilizing generative AI as an essential core technology, the system automates and optimizes the selection of means of transportation, routes, and meeting locations for outings and business trips, simultaneously achieving improved work efficiency and cost reduction for individual employees and the entire group.

[0053] (Implementation Steps)

[0054] Step 1: Enter information about your planned outings. Employees use a dedicated application on their terminal or a web browser to input detailed information about their travel plans, including departure point, destination, departure date and time, number of companions, whether or not they have a meeting scheduled and its time, whether or not they have luggage, preferred mode of transportation, budget limit, priorities during the trip, and past preferences and constraints regarding modes of transportation. For example, they can input detailed conditions such as "Departing from headquarters at 9:00 on July 1st, arriving at destination B by 12:00 with 5 people, online meeting at 13:00, lots of luggage, want to minimize transfers, bus not allowed."

[0055] Step 2: Automatic acquisition of external and internal data The information acquisition unit on the server connects with APIs from various passenger service providers, transit information websites, rental car services, taxi dispatch services, shared bicycle operators, airlines, databases of group companies' and the company's own settlement systems, location information services, satellite office and telephone booth reservation systems, weather information services, and road traffic information services to acquire necessary data in real time. For example, it comprehensively collects information such as train operation status and delay information, bus timetables and congestion forecasts, rental car vehicle availability and fares, taxi dispatch availability, shared bicycle station locations and availability, airline seat availability and fares, settlement data and usage history from similar trips in the past, availability, facilities, and operating hours of satellite offices and telephone booths, weather forecasts, rainfall, snowfall, temperature, wind speed, and road congestion and construction information.

[0056] Step 3: Generating candidates for transportation, routes, and meeting locations. The information acquisition unit integrates diverse data collected with conditions from the outing schedule information input unit to comprehensively generate multiple modes of transportation and routes, such as public transport, rental cars, taxis, shared bicycles, and airplanes, as well as candidate meeting locations such as satellite offices and telephone booths. For example, it lists several specific options such as "Route from train A to train B (60 minutes, 1200 yen, 1 transfer, moderate congestion)", "Rental car (5-seater, 6000 yen, 70 minutes, rental location: station front office, return location: office near destination)", and "Station X satellite office available at 13:00, equipped with Wi-Fi, private room, and monitor".

[0057] Step 4: Optimization and scoring using generative AI The optimization processing unit, through the generative AI collaboration unit, automatically extracts and scores multifaceted evaluation indicators for candidate modes of transport, routes, and meeting locations, including cost, travel time, number of transfers, convenience, ease of luggage transport, feasibility of holding the meeting, consistency with past performance, congestion prediction, weather information, road conditions, availability of facilities, ease of booking, employee preferences and allergies, and the group's overall travel cost optimization policy, and then performs optimization. Specific examples of prompts to be fed into a generative AI include: "Departure point: Head office, Destination: Destination B, Departure date and time: July 1st, 9am, Desired arrival time: 12pm, Number of accompanying persons: 5, Meeting scheduled: Online meeting at 1pm, Lots of luggage, Want to minimize transfers, Bus not an option, Past travel history: Train 1300 yen, 65 minutes; Rental car 6500 yen, 75 minutes; Satellite office information: Station X available at 1pm, Wi-Fi, private room with monitor, Station Y fully booked at 1pm, Near Destination B available at 1pm, Wi-Fi only, Weather: Heavy rain forecast, Roads: Traffic congestion, Consider all conditions and suggest the optimal means of transportation, route, and meeting location."

[0058] Step 5: Generating and displaying the optimal suggestion Based on the scoring results calculated by the generative AI, the optimal combination of transportation, route, and meeting location is automatically selected and displayed clearly on the terminal screen. For example, for each recommended mode of transportation, cost, travel time, number of transfers, congestion level, ease of luggage transport, meeting location facilities, and reservation status are presented using comparison tables, graphs, route displays on maps, timeline displays, voice guidance, and chatbot explanations. Operation buttons such as "Proceed to Reservation," "View Details," and "Compare with Other Options" are provided for each suggestion.

[0059] Step 6: Book, execute, and collect feedback The reservation management department centrally executes booking operations for transportation and meeting locations selected by users and notifies users of the booking completion information. After travel or meetings take place, the user feedback management department collects feedback on transportation, meeting locations, routes, facilities, congestion levels, handling of problems, and overall satisfaction, and stores it in the database management department. For example, specific opinions and evaluations such as "The rental car was delayed due to traffic," "The Wi-Fi at the satellite office was unstable," and "The train was extremely crowded" are collected and used to improve the accuracy of future proposals.

[0060] (Specific use cases)

[0061] For example, suppose five employees are scheduled to travel from headquarters to a client office in an urban area. They need to depart headquarters at 9:00 AM and arrive at their destination by 12:00 PM, with an online meeting scheduled for 1:00 PM. Several employees have a lot of luggage and want to minimize the number of transfers, and they also have a physical reason for wanting to avoid bus travel. The user interface of the terminal allows users to input detailed information about the planned trip, such as departure point, destination, departure date and time, number of people traveling together, meeting schedule, whether or not they have luggage, preferred mode of transport and any restrictions, budget limit, and past preferences for modes of transport. For example, the conditions might be: "Departure point: Headquarters, Destination: Urban client office, Departure date and time: July 1st, 9:00 AM, Desired arrival time: 12:00 PM, Number of people traveling together: 5, Meeting schedule: 1:00 PM online meeting, Lots of luggage, Desire to minimize transfers, Bus not allowed, Budget limit: 2000 yen per person."

[0062] The information acquisition unit obtains real-time information such as multiple route information from the nearest station to the head office to the nearest station to the destination, travel time, fare, number of transfers, and congestion forecast from railway company APIs; bus route information from bus company APIs; available vehicles, vehicle types, rates, and rental / return times at branches near the head office from rental car service APIs; number of available taxis, estimated waiting times, and fares from taxi dispatch service APIs; station locations and number of available bicycles from shared bicycle operators' APIs; seat availability and fares for intercity travel from airline APIs; travel methods, costs, travel time, and usage history for similar outings over the past three years from the settlement systems of group companies and the company itself; availability, facility information, and available time slots around the destination and along the route from satellite office and telephone booth reservation systems; rain forecasts, temperature, and wind speed for the day from weather information service APIs; and congestion and construction information for expressways and major arterial roads from road traffic information service APIs.

[0063] The optimization processing unit integrates this information and, through the generative AI collaboration unit, automatically extracts and scores multifaceted evaluation indicators such as cost, travel time, number of transfers, congestion level, ease of luggage transport, feasibility of holding meetings, consistency with past performance, weather and road conditions, availability of facilities, ease of booking, employee preferences and constraints, and the group's overall travel cost optimization policy. For example, if the total cost for five people using the train is 6,000 yen and the cost of renting a car is also 6,000 yen, the system will prioritize suggesting a rental car, taking into account factors such as the amount of luggage, the number of transfers, the ease of conversation and document review during travel, the impact of weather, and the risk of traffic congestion. If a meeting is scheduled during travel, the availability of satellite offices and telephone booths along the route will be considered. For example, information such as "A satellite office at Station X is available at 13:00 and is equipped with Wi-Fi, a private room, and a monitor" or "A satellite office near the destination is available at 13:00 and only has Wi-Fi" will be used to select the optimal meeting location, taking into account the travel route, travel time before and after the meeting, the level of facilities available, and the ease of making a reservation.

[0064] An example of a prompt message to be fed into a generative AI would be: "Departure point: Head office, Destination: Urban customer office, Departure date and time: July 1st, 9am, Desired arrival time: 12pm, Number of accompanying persons: 5, Meeting scheduled: Online meeting at 1pm, Lots of luggage, Want to minimize transfers, Bus not allowed, Budget limit: 2000 yen per person, Past travel history: Train 1300 yen, 65 minutes, Rental car 6500 yen, 75 minutes, Satellite office information: Station X available at 1pm, Wi-Fi, private room with monitor, Near destination available at 1pm, Wi-Fi only, Weather: Heavy rain forecast, Roads: Traffic congestion, Consider all conditions and suggest the optimal means of transportation, route, and meeting location."

[0065] Based on this information, the generative AI automatically generates multiple specific suggestions, such as "The most efficient way to meet at 1pm is for five people to rent a car and hold the meeting at the satellite office near Station X," "The best option is to use public transport, get off at Station Y, and use a telephone booth," or "It is recommended to take a taxi and hold the meeting at a satellite office near the destination." The suggestion result display section presents information for each recommended mode of transport, including cost, travel time, number of transfers, congestion level, ease of luggage transport, meeting location facilities, and reservation status, using comparison tables, graphs, route displays on maps, timeline displays, voice guidance, and chatbot explanations. Each suggestion is accompanied by operation buttons such as "Proceed to reservation," "View details," and "Compare with other options." The reservation management section collectively executes the reservation operations for the user's selected mode of transport and meeting location, and notifies the user of the reservation completion information. After travel or meetings, the User Feedback Management Department collects feedback on transportation methods, meeting locations, routes, facilities, congestion levels, handling of problems, and overall satisfaction. This feedback is stored in the Database Management Department and can be used to improve the accuracy of future proposals.

[0066] (Application Example 1) The flow of a specific process in Application Example 1 will be explained below. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] (Embodiments for carrying out the present invention)

[0068] Embodiments for implementing the present invention will be described in great detail and comprehensively, assuming actual operation at a logistics center. The system of the present invention consists of a delivery person information input unit, a cargo information input unit, an information acquisition unit, an optimization processing unit, a generation AI collaboration unit, a proposal result display unit, a reservation management unit, a user feedback management unit, a database management unit, a communication unit, and the like, and these units work together in cooperation.

[0069] The delivery driver information input section allows for the input and management of detailed attributes and circumstances for each delivery driver. For example, it can record details such as: Delivery driver A is available to work from 8 am to 5 pm, has a bad back and wants to avoid long hours of driving or carrying heavy objects; Delivery driver B is available for night shifts, has over 10 years of driving experience, holds a forklift license, and has extensive experience driving refrigerated trucks; and Delivery driver C is a newcomer with little experience and prefers to work in pairs with an instructor. It can record individual health conditions, qualifications, experience, desired working hours, past accident history, desired break times, strengths and weaknesses in tasks, allergies and chronic illnesses, and even past evaluations and feedback. For example, it can reflect constraints to ensure both safety and efficiency on site, such as: Delivery driver A has a history of leaving work early due to worsening back pain; must take a break every two hours during long-distance driving; and cannot load or unload refrigerated cargo.

[0070] The cargo information input section allows for the input and management of detailed attributes for each cargo. For example, cargo P1 could be "refrigerated, 30kg weight, delivery destination A, desired delivery time 10am, cannot be loaded on the top shelf," cargo P2 could be "precision equipment, must not be subjected to impact, delivery destination B, desired delivery time 11am, special cushioning material required," cargo P3 could be "heavy item, 50kg weight, delivery destination C, desired delivery time 12pm, forklift loading / unloading recommended," and cargo P4 could be "small and lightweight, delivery destination D, desired delivery time 1pm, can be loaded with other cargo." Detailed information such as temperature control, weight, size, delivery destination, desired delivery time, precautions during loading and unloading, whether it can be loaded with other cargo, loading order, and special handling conditions can be entered. For example, cargo P1 and P2 cannot be loaded together in the same vehicle, P3 requires a forklift, and P4 can be loaded simultaneously with other cargo, reflecting complex constraints at the site.

[0071] The information acquisition unit obtains data in real time from a variety of external and internal sources. For example, it obtains data from the traffic information API such as "A-B is normally open, B-C is congested, and C-D is closed due to an accident," from the weather API such as "rain throughout the area, low temperatures, and a strong wind warning in effect," from the vehicle management system such as "one truck with a load capacity of 100 is available, one van with a load capacity of 60 is under maintenance, and one refrigerated truck is reserved," from the rest stop management system such as "rest stop X is available, transshipment base Y is available, and rest stop Z is full," from the historical database such as "the center-ABCD route normally takes 180 minutes, B-C has a history of frequent congestion and accidents, and C-D has a history of frequent transshipment delays," as well as comprehensively obtains information such as the available time slots and congestion status of delivery destinations, the availability of unloading space at delivery destinations, the equipment status of transshipment bases (presence or absence of forklifts, refrigeration storage capability, staff presence), road construction information, and emergency detour information. For example, delivery destination A could be described as "accepting deliveries only between 9 am and 11 am, with space for two vehicles to unload, and high congestion," delivery destination B as "accepting deliveries at all times, with a forklift always on-site," and delivery destination C as "accepting deliveries only in the afternoon, with space for one vehicle to unload, and low congestion," reflecting information that is relevant to the actual situation on site.

[0072] The optimization processing unit integrates the vast amount of information obtained from the delivery person information input unit, the cargo information input unit, and the information acquisition unit, and comprehensively generates candidate delivery routes, delivery methods, and intermediate rest stops and transshipment points through the generation AI collaboration unit. For example, the system automatically generates multiple specific delivery routes, vehicles, rest stops, and transshipment combinations that reflect on-site constraints and preferences, cargo characteristics, vehicle status, traffic, weather, and equipment conditions, and past trouble history. These could include using a truck in the order of center to A, A to B, B to C, and C to D, stopping at rest stop X between A and B, and transshipping goods to a van at transshipment point Y to avoid congestion between B and C before heading to C; using the reverse order of center to D, D to C, C to B, and B to A to efficiently deliver according to the desired delivery time; delivering refrigerated goods to A and B in advance using a refrigerated vehicle, and delivering the remaining goods to C and D by truck; having a worker with back pain only drive and load / unload up to A, with other workers handling the section between B and D; and having new delivery worker C work only between B and C in pairs with an instructor, with forklift operations only performed at B.

[0073] The Generative AI Collaboration Unit generates prompts for the Generative AI based on information and conditions passed from the Optimization Processing Unit, and performs multifaceted analysis and proposal generation by the AI. For example, it generates prompts such as, "Three delivery personnel: A has a chronic backache, B has a forklift license, and C is a newcomer. Four packages: P1 requires refrigeration, P2 is precision equipment, P3 is heavy, and P4 is small and lightweight. Delivery destinations are A and D, with preferred delivery times for each. One truck with a capacity of 100, one van with a capacity of 60 is under maintenance, and one refrigerated truck is reserved. The weather is rainy, there is congestion between B and C, and the road between C and D is closed. Rest area X is available, transshipment base Y is available, and rest area Z is full. Past data shows frequent delays between B and C, and frequent transshipment delays between C and D. Propose the optimal delivery route, vehicles, and rest / transshipment points that balance worker health, on-time delivery, efficiency, and safety," and feeds these prompts to the AI. The generative AI scores and optimizes from multiple perspectives, including cost, time required, worker burden, adherence to delivery times, avoidance of weather and traffic risks, health and safety, cargo characteristics, consistency with past performance, and on-site constraints and preferences, to automatically select the optimal combination of delivery route, vehicle, and rest / transfer points.

[0074] The suggestion results display unit clearly shows the optimal delivery route, vehicle, rest stop, and transshipment point suggestions obtained from the generation AI collaboration unit and the optimization processing unit on the terminal screens of administrators and delivery personnel. For example, for each recommended route, it presents information such as cost, required time, on-time delivery rate, workload of workers, timing of rest stops and transshipments, traffic congestion and bad weather risks, unloading procedures at each delivery destination, transshipment work details, temperature control plan for refrigerated cargo, shock countermeasures for precision equipment, forklift work assignments, and instructor pair operation schedules using comparison tables, route displays on maps, timeline displays, voice guidance, and chatbot explanations. Furthermore, operation buttons such as "Proceed to booking," "View details," and "Compare with other options" are provided for each suggestion, allowing users to easily select their next action.

[0075] The reservation management department centrally manages the reservation operations for delivery routes, vehicles, rest stops, and transshipment points selected by users. For example, it automatically performs tasks such as booking trucks, refrigerated trucks, rest stops, and transshipment points, notifying delivery destinations of delivery times in advance, making bulk reservations for multiple people, sharing reservation details among groups, changing or canceling reservation status, confirming reservation details and sending reminders, and automatically suggesting rebooking or alternative options in emergencies, all in conjunction with external services, and notifying users when a reservation is complete.

[0076] The User Feedback Management Department collects feedback from delivery personnel and managers after delivery regarding the usability of rest areas and transshipment points, driving comfort of vehicles, ease of loading and unloading cargo, response to problems caused by traffic jams or weather, effectiveness of temperature control for refrigerated cargo, whether or not precision equipment was damaged, efficiency of forklift operations, effectiveness of paired instructor operations, and overall satisfaction, and stores this feedback in the Database Management Department. For example, it collects specific opinions and evaluations such as "Rest area X was comfortable," "Transshipment work was smooth," "Traffic jam avoidance was effective," "The truck driver's seat was cramped," "There was insufficient unloading space at the delivery destination," "Temperature control of refrigerated cargo was inadequate," "Precision equipment was damaged," and "Training for new delivery personnel was effective," and uses this feedback to improve the accuracy of future suggestions through the Generative AI Collaboration Department.

[0077] The Database Management Department centrally manages delivery personnel information, package information, various acquired data, past delivery history, reservation information, user feedback, AI training data, system logs, etc., and performs high-speed searches, aggregations, analyses, backups, restores, data anonymization, and access control as needed. The Communications Department is responsible for sending and receiving data between terminals and servers, between servers and external services, and between various departments within the server, and realizes secure communication, real-time information updates, retry processing in case of failures, communication log management, data encryption, user authentication, and monitoring and fault detection of API integrations.

[0078] For example, under the following conditions: 3 delivery personnel, 4 packages, delivery destinations A and D, 1 truck with a load capacity of 100, 1 van with a load capacity of 60 (currently under maintenance), 1 refrigerated truck reserved, deliveries required at 10am for A, 11am for B, 12pm for C, and 1pm for D, rainy weather, traffic congestion between B and C, road closure between C and D, rest area X available, transshipment base Y available, rest area Z full, worker with back pain unable to drive long distances, past data shows frequent delays between B and C, and frequent transshipment delays between C and D, the system The system automatically generates an optimal delivery plan, such as "Center → A (stop at rest area X) → B (transfer to van at transshipment base Y) → C → D, adhering to all delivery times, reducing the burden on workers, avoiding traffic jams, taking full precautions against rain, delivering refrigerated goods to A and B in advance using refrigerated vehicles, shock-resistant measures taken for precision equipment, forklift operations performed at B, and new delivery personnel working in pairs with instructors between B and C," and manages everything from booking and execution to feedback in a seamless manner.

[0079] Thus, in the embodiments of the present invention, by comprehensively and specifically considering various conditions and constraints that may occur at the logistics center site, sudden changes in circumstances, the health and wishes of workers, the characteristics of cargo, traffic, weather, equipment, past performance, etc., and utilizing generative AI as an essential core technology, it is possible to simultaneously achieve increased efficiency in delivery operations, improved delivery quality, enhanced safety and health of workers, cost reduction, and strengthened on-site responsiveness.

[0080] (System Configuration)

[0081] The system according to this embodiment includes a delivery person information input unit, a cargo information input unit, an information acquisition unit, an optimization processing unit, a generation AI collaboration unit, a proposal result display unit, a reservation management unit, a user feedback management unit, a database management unit, and a communication unit. The delivery person information input unit inputs and manages detailed attributes and circumstances for each delivery person. For example, it can record details such as: delivery person A can work from 8 am to 5 pm, has back pain and wants to avoid long hours of driving or carrying heavy objects; delivery person B can work at night, has more than 10 years of driving experience, holds a forklift license and has extensive experience driving refrigerated trucks; and delivery person C is a newcomer with little experience and it is preferable for them to work in a pair with an instructor. It can record details such as individual health status, qualifications, experience, desired working hours, past accident history, desired break timing, strengths and weaknesses in work, allergies and chronic illnesses, and past evaluations and feedback. For example, it can reflect detailed constraints to balance safety and efficiency on site, such as: delivery person A has a history of leaving early due to worsening back pain; must take a break every two hours during long-distance driving; and cannot load or unload refrigerated cargo.

[0082] The cargo information input section allows for the input and management of detailed attributes for each cargo. For example, cargo P1 requires refrigeration, weighs 30kg, is delivered to destination A, has a desired delivery time of 10am, and cannot be loaded on the top shelf; cargo P2 is precision equipment, must not be subjected to impact, is delivered to destination B, has a desired delivery time of 11am, and requires special cushioning material; cargo P3 is heavy, weighs 50kg, is delivered to destination C, has a desired delivery time of 12pm, and forklift loading / unloading is recommended; cargo P4 is small and lightweight, is delivered to destination D, has a desired delivery time of 1pm, and can be loaded with other cargo. Detailed information such as temperature control, weight, size, delivery destination, desired delivery time, precautions during loading and unloading, whether it can be loaded with other cargo, loading order, and special handling conditions can be entered. For example, cargo P1 and P2 cannot be loaded together in the same vehicle, P3 requires a forklift, and P4 can be loaded simultaneously with other cargo, reflecting complex constraints on site.

[0083] The information acquisition unit acquires data in real time from a variety of external and internal sources. For example, it obtains data from the traffic information API, such as: between A and B it is normally open, between B and C it is congested, and between C and D it is closed due to an accident; from the weather API it is raining throughout the area, temperatures are dropping, and a strong wind warning is in effect; from the vehicle management system it has one truck with a load capacity of 100 available, one van with a load capacity of 60 under maintenance, and one refrigerated truck reserved; from the rest stop management it has rest stop X available, transshipment base Y available, and rest stop Z full; from the past database it has obtained data such as: the center-ABCD route is normally 180 minutes, there have been many traffic jams and accidents between B and C in the past, transshipment delays have been frequent between C and D in the past, and it comprehensively acquires information such as the available acceptance times and congestion status of delivery destinations, the availability of unloading space at delivery destinations, the equipment status of transshipment bases (availability of forklifts, refrigeration storage capabilities, staff presence), road construction information, and emergency detour information. For example, delivery destination A may only accept deliveries between 9 am and 11 am, have space for two trucks to unload, and be highly congested; delivery destination B may accept deliveries at any time, have a forklift on-site; and delivery destination C may only accept deliveries in the afternoon, have space for one truck to unload, and be less congested. This information can reflect the actual situation on site.

[0084] The optimization processing unit integrates the vast amount of information obtained from the delivery person information input unit, the cargo information input unit, and the information acquisition unit, and comprehensively generates candidate delivery routes, delivery methods, and intermediate rest stops and transshipment points through the generation AI collaboration unit. For example, it could use a truck in the order of center to A, A to B, B to C, and C to D, stopping at rest stop X between A and B, and to avoid congestion between B and C, transferring the cargo to a van at transshipment point Y before heading to C. Alternatively, it could use the reverse order from center to D, D to C, C to B, and B to A, depending on the desired delivery date. The system automatically generates multiple specific delivery route, vehicle, rest, and transshipment combinations that reflect on-site constraints and preferences, cargo characteristics, vehicle status, traffic, weather, equipment conditions, and past trouble history. Examples include: a plan to efficiently manage routes according to the time; a plan to deliver refrigerated goods to A and B first using refrigerated trucks, and the remaining goods to C and D using regular trucks; a plan where a worker with back pain is only responsible for driving and loading / unloading to A, with other workers handling the section between B and D; and a plan where new delivery worker C is paired with an instructor and only responsible for the section between B and C, with forklift operations performed only at B.

[0085] The Generative AI Collaboration Unit generates prompts for the Generative AI based on information and conditions passed from the Optimization Processing Unit, and performs multifaceted analysis and proposal generation by the AI. For example, it generates prompts such as, "Three delivery personnel, A has a backache, B has a forklift license, C is a newcomer. Four packages, P1 must be refrigerated, P2 is precision equipment, P3 is heavy, P4 is small and lightweight. Delivery destinations A and D, each with a desired delivery time. One truck with a load capacity of 100, one van with a load capacity of 60 is under maintenance, one refrigerated truck is reserved. Weather is rainy, there is congestion between B and C, and the road between C and D is closed. Rest area X is available, transshipment base Y is available, rest area Z is full. Past data shows frequent delays between B and C, and frequent transshipment delays between C and D. Propose the optimal delivery route, vehicles, and rest / transshipment points that balance worker health, strict adherence to delivery times, efficiency, and safety," and feeds these prompts to the AI. The generative AI scores and optimizes from multiple perspectives, including cost, time required, worker burden, adherence to delivery times, avoidance of weather and traffic risks, health and safety, cargo characteristics, consistency with past performance, and on-site constraints and preferences, to automatically select the optimal combination of delivery route, vehicle, and rest / transfer points.

[0086] The suggestion results display unit clearly shows the optimal delivery route, vehicle, rest stop, and transshipment point suggestions obtained from the generation AI collaboration unit and the optimization processing unit on the terminal screens of administrators and delivery personnel. For example, for each recommended route, it presents information such as cost, required time, on-time delivery rate, workload of workers, timing of rest stops and transshipments, traffic congestion and bad weather risks, unloading procedures at each delivery destination, transshipment work details, temperature control plans for refrigerated cargo, shock countermeasures for precision equipment, forklift work assignments, and instructor pair operation schedules through comparison tables, route displays on maps, timeline displays, voice guidance, and chatbot explanations. Furthermore, operation buttons such as "Proceed to booking," "View details," and "Compare with other options" are provided for each suggestion, allowing users to easily select the next action.

[0087] The reservation management unit centrally manages the reservation operations for delivery routes, vehicles, rest stops, and transshipment points selected by the user. For example, it automatically performs tasks such as booking trucks, refrigerated trucks, rest stops, and transshipment points, notifying delivery destinations of delivery times in advance, making bulk reservations for multiple people, sharing reservation details among groups, changing or canceling reservation status, confirming reservation details and sending reminders, and automatically suggesting rebooking or alternative options in emergencies, all in conjunction with external services, and notifying users when the reservation is complete.

[0088] The User Feedback Management Department collects feedback from delivery personnel and managers after delivery regarding the usability of rest areas and transshipment points, driving comfort of vehicles, ease of loading and unloading cargo, response to problems caused by traffic jams or weather, effectiveness of temperature control for refrigerated cargo, whether or not precision equipment was damaged, efficiency of forklift operations, effectiveness of paired instructor operations, and overall satisfaction. This feedback is then stored in the Database Management Department. For example, it collects specific opinions and evaluations such as "Rest area X was comfortable," "Transshipment work was smooth," "Traffic jam avoidance was effective," "The truck driver's seat was cramped," "There was insufficient unloading space at the delivery destination," "Temperature control of refrigerated cargo was inadequate," "Precision equipment was damaged," and "Training for new delivery personnel was effective." This feedback is then used through the Generative AI Collaboration Department to improve the accuracy of future suggestions.

[0089] The Database Management Department centrally manages delivery personnel information, package information, various acquired data, past delivery history, reservation information, user feedback, AI training data, system logs, etc., and performs high-speed searches, aggregations, analyses, backups, restores, data anonymization, and access control as needed. The Communications Department is responsible for sending and receiving data between terminals and servers, between servers and external services, and between various departments within the server, and realizes secure communication, real-time information updates, retry processing in case of failures, communication log management, data encryption, user authentication, and monitoring and fault detection of API integrations.

[0090] Specific examples of prompt messages to be fed into the AI ​​when implementing this invention include: "Three delivery personnel: A has a backache, B has a forklift license, and C is a newcomer. Four packages: P1 requires refrigeration, P2 is precision equipment, P3 is a heavy item, and P4 is small and lightweight. Delivery destinations are A and D, with preferred delivery times for each. One truck with a capacity of 100 and one van with a capacity of 60 are under maintenance, and one refrigerated truck is reserved. The weather is rainy, there is traffic congestion between B and C, and the road between C and D is closed. Rest area X is available, transshipment point Y is available, and rest area Z is full. Past data shows frequent delays between B and C, and frequent transshipment delays between C and D. Propose the optimal delivery route, vehicles, and rest / transshipment points that balance worker health, on-time delivery, efficiency, and safety." Thus, the system according to this embodiment comprehensively and specifically considers diverse on-site conditions and constraints, sudden changes in circumstances, the health and wishes of workers, the characteristics of cargo, traffic, weather, equipment, and past performance, and utilizes generative AI as an essential core technology to simultaneously achieve increased efficiency in delivery operations, improved delivery quality, enhanced worker safety and health, cost reduction, and strengthened on-site flexibility.

[0091] (Implementation Steps)

[0092] Step 1: Enter detailed information about the delivery person. In the delivery driver information input section, detailed information is entered for each delivery driver, including their name, available working hours, health status (e.g., back pain, allergies, chronic illnesses), qualifications (e.g., forklift license, refrigerated truck driving experience), driving history, past accident history, desired break times, strengths and weaknesses in specific tasks, past evaluations and feedback, preference for being paired with a trainer, and whether they are a newcomer or not. For example, delivery driver A may be listed as "available to work from 8am to 5pm, has back pain, cannot drive long distances, cannot load or unload refrigerated goods," delivery driver B as "available to work at night, holds a forklift license, and has extensive experience driving refrigerated trucks," and delivery driver C as "newcomer, prefers to work in a trainer's pair." This comprehensive information is registered to ensure both safety and efficiency on site.

[0093] Step 2: Enter detailed luggage information In the cargo information input section, detailed information such as the type of cargo, weight, size, delivery destination, desired delivery time, need for temperature control, fragility, precautions during loading, whether it can be mixed with other cargo, loading order, and special handling conditions are entered for each cargo. For example, cargo P1 could be "refrigerated, weight 30kg, delivery destination A, desired delivery time 10am, cannot be placed on the top shelf," cargo P2 could be "precision equipment, must not be subjected to impact, delivery destination B, desired delivery time 11am, special cushioning material required," cargo P3 could be "heavy item, weight 50kg, delivery destination C, desired delivery time 12pm, forklift loading / unloading recommended," and cargo P4 could be "small and lightweight, delivery destination D, desired delivery time 1pm, can be mixed with other cargo," allowing for the reflection of complex constraints on site.

[0094] Step 3: Real-time acquisition of external and internal information The information acquisition unit comprehensively acquires information in real time, including road conditions from the traffic information API (for example, normal conditions between A and B, congestion between B and C, and road closure due to an accident between C and D), weather information from the weather API (rain throughout the area, temperature drops, strong wind warning), vehicle usage status from the vehicle management system (1 truck with a load capacity of 100 available, 1 van with a load capacity of 60 under maintenance, 1 refrigerated truck reserved), availability of rest areas and transshipment bases from the rest spot management system (rest area X available, transshipment base Y available, rest area Z full), delivery route history and trouble history from the past database (frequent congestion and accidents between B and C in the past, frequent transshipment delays between C and D), available time slots and congestion status at delivery destinations, availability of unloading space at delivery destinations, equipment status of transshipment bases, road construction information, and emergency detour information.

[0095] Step 4: Comprehensive generation of delivery plan candidates The optimization processing unit integrates delivery driver information, cargo information, and various acquired external and internal information to comprehensively generate multiple delivery route, vehicle assignment, and rest / transfer point combinations that reflect on-site constraints and preferences, cargo characteristics, vehicle status, traffic, weather, and equipment conditions, and past trouble history. For example, it generates a variety of candidates that reflect the complex operations on site, such as using a truck in the order of center to A, A to B, B to C, and C to D, stopping at rest area X between A and B, and transferring cargo to a van at transshipment point Y to avoid congestion between B and C before heading to C; delivering refrigerated cargo to A and B first using a refrigerated vehicle, and delivering the remaining cargo to C and D by truck; and having new delivery drivers work only between B and C in pairs with instructors, and performing forklift operations only at B.

[0096] Step 5: Optimization and scoring using generative AI The generation AI collaboration unit generates prompt messages for the generation AI based on delivery person information, cargo information, various acquired information, and delivery plan candidates passed from the optimization processing unit, and performs multifaceted analysis, scoring, and optimization by the AI. A concrete example of a prompt message is: "There are 3 delivery people; A has a bad back, B has a forklift license, and C is a newcomer. There are 4 packages; P1 requires refrigeration, P2 is precision equipment, P3 is a heavy item, and P4 is small and lightweight. Delivery destinations are A and D, with desired delivery times for each. One truck has a load capacity of 100, one van has a load capacity of 60 and is under maintenance, and one refrigerated truck is reserved. The weather is rainy, there is congestion between B and C, and the road between C and D is closed. Rest area X is available, transshipment base Y is available, and rest area Z is full. Past data shows frequent delays between B and C, and frequent transshipment delays between C and D. Propose the optimal delivery route, vehicles, and rest / transshipment points that balance worker health, strict adherence to delivery times, efficiency, and safety." The AI ​​scores and optimizes from multiple perspectives, including cost, time required, worker burden, adherence to delivery times, avoidance of weather and traffic risks, health and safety, cargo characteristics, consistency with past performance, and on-site constraints and requests, to automatically select the optimal delivery route, vehicle, and rest / transfer point combination.

[0097] Step 6: Display, reserve, and collect feedback on the best proposal. The Proposal Results Display Unit clearly displays the optimal delivery route, vehicle, rest stop, and transshipment point suggestions obtained from the Generation AI Integration Unit and the Optimization Processing Unit on the terminal screens of administrators and delivery personnel. For each recommended route, it presents information such as cost, required time, on-time delivery rate, workload of workers, timing of rest stops and transshipments, traffic congestion and bad weather risks, unloading procedures at each delivery destination, transshipment work details, temperature control plans for refrigerated cargo, shock countermeasures for precision equipment, forklift work assignments, and instructor pair operation schedules through comparison tables, route displays on maps, timeline displays, voice guidance, and chatbot explanations. The Reservation Management Unit centrally manages the reservation operations for delivery routes, vehicles, rest stops, and transshipment points selected by the user, and notifies the user of reservation completion information. The User Feedback Management Department collects feedback from delivery personnel and managers after delivery regarding the usability of rest areas and transshipment points, driving comfort of vehicles, ease of loading and unloading cargo, response to problems caused by traffic jams or weather, effectiveness of temperature control for refrigerated cargo, whether or not precision equipment was damaged, efficiency of forklift operations, effectiveness of paired instructor operation, and overall satisfaction. This feedback is stored in the Database Management Department and used to improve the accuracy of future proposals.

[0098] (Specific use cases)

[0099] For example, consider a scenario at a logistics center with 3 delivery personnel, 5 packages, and delivery destinations A, B, C, D, and E. Each package has different attributes, such as requiring refrigeration, being precision equipment, heavy, small and light, or a standard item. Each destination also has a specified desired delivery time. Delivery personnel A suffers from lower back pain and must avoid long-distance driving and carrying heavy items. Delivery personnel B holds a forklift license and has extensive experience driving refrigerated trucks. Delivery personnel C is a newcomer and should ideally work in a training pair. Available vehicles include one truck with a 100kg load capacity, one van with a 60kg load capacity (under maintenance), and one refrigerated truck (reserved). The weather is rainy throughout the area, there is traffic congestion between B and C, and the road between C and D is closed due to an accident. Rest area X is available, transshipment point Y is available, and rest area Z is full. Past delivery data shows frequent delays between B and C, and frequent transshipment delays between C and D. Delivery destination A accepts deliveries only between 9 am and 11 am and has space for two vehicles to unload; delivery destination B accepts deliveries at any time and has a forklift on-site; delivery destination C accepts deliveries only in the afternoon and has space for one vehicle to unload; delivery destination D is often congested; and delivery destination E accepts only regular items.

[0100] Under these circumstances, the delivery person information input unit inputs detailed information about each delivery person, including their available working hours, health status, qualifications, experience, preferences, past evaluations, and feedback. The cargo information input unit inputs information about each cargo, including its attributes, delivery destination, desired delivery time, temperature control, loading order, whether it can be mixed with other cargo, and any special handling conditions. The information acquisition unit acquires information in real time from traffic information APIs, weather APIs, vehicle management systems, rest stop management, historical databases, available time slots and congestion status at delivery destinations, equipment status at transshipment centers, road construction information, and emergency detour information.

[0101] The optimization processing unit integrates this information to comprehensively generate multiple delivery routes, vehicle assignments, and rest / transfer point combinations that reflect on-site constraints and preferences, cargo characteristics, vehicle status, traffic, weather, and equipment conditions, and past trouble history. For example, it generates a variety of candidates that reflect the complex operations of the site, such as a plan to use trucks in the order of center to A, A to B, B to C, C to D, and D to E, stopping at rest area X between A and B, and transferring cargo to a refrigerated truck at transshipment point Y to avoid congestion between B and C before heading to C; a plan to deliver refrigerated cargo to A and B first by refrigerated truck, and deliver the remaining cargo to C, D, and E by truck; and a plan where new delivery personnel are paired with instructors and only work between B and C, and forklift operations are performed only at B.

[0102] The AI ​​generation and integration unit generates prompt messages for the AI ​​based on delivery person information, cargo information, various acquired information, and delivery plan candidates passed from the optimization processing unit, and performs multifaceted analysis, scoring, and optimization using the AI. A concrete example of a prompt message is: "There are 3 delivery people; A has a bad back, B has a forklift license, and C is a newcomer. There are 5 packages; P1 requires refrigeration, P2 is precision equipment, P3 is a heavy item, P4 is small and light, and P5 is a regular item. Delivery destinations are A and E, with preferred delivery times for each. One truck has a load capacity of 100, one van has a load capacity of 60 and is under maintenance, and one refrigerated truck is reserved. The weather is rainy, there is congestion between B and C, and the road between C and D is closed. Rest area X is available, transshipment base Y is available, and rest area Z is full. Past data shows frequent delays between B and C, and frequent transshipment delays between C and D. Propose the optimal delivery route, vehicles, and rest / transshipment points that balance worker health, strict adherence to delivery times, efficiency, and safety."

[0103] The AI ​​generates and optimizes based on a multifaceted approach, including cost, time required, worker burden, adherence to delivery times, avoidance of weather and traffic risks, health and safety, cargo characteristics, consistency with past performance, and on-site constraints and preferences, automatically selecting the optimal delivery route, vehicle, and rest / transfer point combination. The suggested results display section presents each recommended route with information such as cost, time required, adherence to delivery times, worker burden, timing of rest and transshipment, traffic congestion and bad weather risks, unloading procedures at each delivery destination, transshipment details, temperature control plans for refrigerated cargo, shock protection for precision equipment, forklift assignments, and instructor pair schedules, using comparison tables, map-based route displays, timeline displays, voice guidance, and chatbot explanations. The reservation management section centrally manages reservations for the delivery routes, vehicles, rest stops, and transshipment points selected by the user, and notifies the user of reservation completion information. The User Feedback Management Department collects feedback from delivery personnel and managers after delivery regarding the usability of rest areas and transshipment points, driving comfort of vehicles, ease of loading and unloading cargo, response to problems caused by traffic jams or weather, effectiveness of temperature control for refrigerated cargo, whether or not precision equipment was damaged, efficiency of forklift operations, effectiveness of paired instructor operation, and overall satisfaction. This feedback is stored in the Database Management Department and can be used to improve the accuracy of future suggestions.

[0104] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0106] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] For example, the data collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart device 14 and processes it with the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0108] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0109] [Second Embodiment]

[0110] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0111] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and communication interface 44 are also connected to the bus 52.

[0114] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0116] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0117] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0118] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0119] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0120] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the identification processing unit 290 using these models.

[0121] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is realized by the data processing device 12 and the smart glasses 214. 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".

[0122] (Example 1)

[0123] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0124] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0125] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Furthermore, the processing by the data processing system 10 described above is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart glasses 214 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0128] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0129] [Third Embodiment]

[0130] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, display 343, and communication interface 44 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0139] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0140] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0141] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the headset terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0142] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0143] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0144] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the headset terminal 314 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0147] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0148] [Fourth Embodiment]

[0149] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, controlled object 443, and communication interface 44 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0159] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0160] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0161] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0162] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0163] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0164] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0165] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.

[0166] For example, the data collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the robot 414 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and controlled object 443 of the robot 414 and the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0167] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0168] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0169] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0170] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0171] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0172] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0173] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0174] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0175] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0176] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0177] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0178] 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.

[0179] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0180] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0181] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0182] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0183] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0184] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0185] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0186] Furthermore, the following additional information is disclosed regarding the above explanation.

[0187] (Claim 1)

[0188] The system comprises a delivery driver information input unit, a cargo information input unit, an information acquisition unit, an optimization processing unit, a generative AI integration unit, a proposal result display unit, a reservation management unit, and a user feedback management unit. The delivery driver information input unit inputs information such as each delivery driver's schedule, health status, preferences, and constraints. The cargo information input unit inputs information such as cargo type, size, weight, delivery destination, and desired delivery time. The information acquisition unit acquires information such as traffic conditions, weather, vehicle availability, rest stops and transshipment points, and past delivery performance data in real time from external and internal sources. The optimization processing unit integrates the information obtained from the delivery driver information input unit, cargo information input unit, and information acquisition unit, and integrates it with the generative AI integration unit. This system features a comprehensive generation of delivery routes, delivery methods, and potential rest stops and transshipment points through a mobile unit. It scores and optimizes these options from multiple perspectives, including cost, time required, worker burden, adherence to delivery times, avoidance of weather and traffic risks, health and safety, and consistency with past performance. The system automatically selects the optimal combination of delivery route, vehicle, and rest / transshipment points. The proposed results display unit clearly presents the results, the reservation management unit automatically makes reservations for necessary vehicles, rest stops, and transshipment points, and the user feedback management unit collects evaluations and opinions from workers after delivery to improve the accuracy of future proposals. This system operates with the essential function of a generative AI. (Claim 2)

[0189] The system according to claim 1, wherein the optimization processing unit uses generative AI to comprehensively analyze factors such as the health status and preferences of delivery personnel, the size and weight of packages, desired delivery times at each destination, weather, traffic conditions, vehicle load capacity and availability, the need for breaks and transshipments, past delivery performance, and worker constraints, and proposes combinations of delivery routes, vehicles, breaks, and transshipment points that, for example, prioritize routes that avoid long-distance driving and heavy loading / unloading for workers with back pain, while strictly adhering to delivery times, avoiding traffic jams and bad weather, and simultaneously reducing the burden on workers and improving efficiency. (Claim 3)

[0190] The system according to claim 1, wherein the User Feedback Management Department collects feedback from workers after delivery on various aspects such as the usability of rest areas and transshipment points, the driving comfort of the vehicle, the ease of loading and unloading cargo, the response to problems caused by traffic congestion or weather, and overall satisfaction, and the Generative AI Collaboration Department incorporates this feedback as training data to continuously improve the accuracy of suggesting delivery routes, vehicles, rest areas, and transshipment points for future deliveries. [Explanation of Symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The system comprises an input unit for inputting employee travel plans, an information acquisition unit for acquiring transportation route information provided by various passenger service providers, rental car service usage information, past settlement data of group companies and the company itself, location information service data, and availability information for satellite offices and telephone booths, and an optimization processing unit that, based on the information obtained from the input unit and the information acquisition unit, uses generative AI to score from multiple perspectives such as the number of accompanying persons, destination, departure point, departure date and time, meeting schedule, past travel history, cost, duration, number of transfers, convenience, and feasibility of holding the meeting, and automatically selects and proposes the optimal means of transportation, route, and meeting location along the route, wherein the optimization processing unit operates with generative AI as a requirement, comprehensively compares and analyzes multiple candidate means of transportation and meeting location, automates the selection of means of transportation and meeting location for employee travel, and simultaneously achieves operational efficiency and cost optimization.

2. The system according to claim 1, wherein the optimization processing unit, when the number of accompanying persons exceeds a predetermined number, compares the cost and time required when using public transportation individually with the cost and time required when using a rental car jointly with multiple persons using a generative AI, selects the most suitable mode of transportation from the standpoint of cost and convenience, and further, if there is a meeting scheduled along the travel route, proposes the most suitable stopover location for holding the meeting, taking into account the availability of satellite offices and telephone booths.

3. The system according to claim 1, wherein the information acquisition unit acquires historical information such as destination, departure point, number of accompanying persons, date and time of use, means of use, cost, and duration from the past settlement databases of group companies and the company itself, and the optimization processing unit comprehensively analyzes this past performance data and real-time acquired transportation route information, rental car information, and satellite office information using a generative AI, and proposes realistic and performance-oriented means of transportation and meeting locations based on past performance.

Images