system

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving customer queries and analyzing them using a natural-language processing model to generate appropriate responses; means for inputting truck availabilities, departure times, and route information and generating an optimal dispatch schedule using a generative AI model; means for obtaining truck location information from a GPS device and providing the location information in real-time; and means for analyzing dispatch problems using a natural-language processing model and generating solutions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The present invention aims to improve the overall efficiency of vehicle dispatching operations by reducing human error and providing efficient dispatch schedules. Another objective is to improve customer satisfaction by providing real-time truck location information and prompt customer response. In particular, it is necessary to reduce the complexity and burden of vehicle dispatching operations by efficiently utilizing a variety of data and optimizing vehicle dispatching using a generative AI model. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. Specifically, the system includes: means for receiving customer inquiries, analyzing them using a natural language processing model, and generating an appropriate response; means for inputting truck availability, departure time, and route information and creating an optimal vehicle dispatch schedule using a generative AI model; means for acquiring truck location information from a GPS device and providing the location information in real time; means for analyzing vehicle dispatch problems using a natural language processing model and generating solutions; and means for collecting and analyzing past dispatch data and extracting trends and patterns (Claim 1). The system also includes means for receiving customer inquiries in text form, analyzing them using a natural language processing model, and returning text-based responses (Claim 2). The system also includes means for automatically generating an optimal vehicle dispatch schedule using a generative AI model, taking into account truck availability, departure time, and route information (Claim 3). These means improve the efficiency of vehicle dispatch operations, reduce human error, provide real-time truck location information, and respond to customers quickly.

[0006] "Customer inquiry response" is a function that receives text-based inquiries from customers, analyzes them using a natural language processing model, generates appropriate responses, and returns them to the customers.

[0007] "Vehicle dispatch schedule optimization" is a function that inputs truck availability, departure time, and route information and uses a generative AI model to create an optimal vehicle dispatch schedule.

[0008] "Truck location information provision" is a function that obtains truck location information from a GPS device and provides that information in real time.

[0009] "Troubleshooting" is a function that uses natural language processing models to analyze dispatch problems, generate appropriate solutions, and assist in problem-solving.

[0010] "Past data analysis" is a function that collects past dispatch data, analyzes it using a generative AI model, and extracts trends and patterns that can be used to plan future dispatches.

[0011] A "generative AI model" is a model that uses machine learning and artificial intelligence techniques to generate optimal solutions when data is input.

[0012] A "natural language processing model" is an artificial intelligence model that analyzes text data and generates appropriate responses or results.

[0013] "Optimization" is the process of achieving the most efficient and effective results while satisfying multiple specified conditions.

[0014] "GPS Device" means a device that uses the Global Positioning System to determine the location of an object in real time.

[0015] "Real-time" refers to updating and providing information immediately without delay. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[0038] Responding to customer inquiries

[0039] The user uses a terminal to input a text-based inquiry about dispatching a vehicle. For example, the user might input a query such as "I would like to check tomorrow's delivery status." The server receives this query and analyzes it using a natural language processing model. The server then generates an answer and sends it back to the user's terminal, replying, "Delivery is scheduled for tomorrow at 2:00 PM."

[0040] Vehicle scheduling optimization

[0041] The user sends a delivery request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The server receives the request and retrieves truck availability, past schedules, departure times, and routes from a database. The server then uses a generative AI model to create an optimal delivery schedule and notifies the user, "A delivery will be made at 10:00 AM on Monday."

[0042] Providing truck location information

[0043] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives this request and obtains real-time location information from the GPS device installed in the truck. For example, it provides the user with information such as, "The truck is currently traveling on a major street in the city."

[0044] Troubleshooting and Support

[0045] A user reports a problem with a delivery from their device. For example, they send a report saying, "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model. It generates a solution, such as "Contact the nearest repair shop?", and provides it to the user.

[0046] Analysis of past dispatch data

[0047] The server periodically collects past dispatch data from the database. The collected data is passed to the generative AI model for analysis. For example, from dispatch data from the past year, the server may discover a trend that "weekend dispatch requests are on the rise." The server then creates a report of these results and provides it to the user. Based on this, the user can formulate future dispatch plans.

[0048] As described above, the system of the present invention uses generative AI models and natural language processing models to achieve a wide range of functions, including responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data. This enables more efficient dispatch work, reduces human error, provides faster customer service, and improves customer satisfaction.

[0049] The processing flow will be explained below.

[0050] Responding to customer inquiries

[0051] Step 1:

[0052] The user uses the terminal to input and send the inquiry.

[0053] Step 2:

[0054] The server receives the query and passes it to a natural language processing model.

[0055] Step 3:

[0056] The server analyzes the content of the query using a natural language processing model.

[0057] Step 4:

[0058] The server generates an appropriate answer based on the analysis results.

[0059] Step 5:

[0060] The server generates a response and sends it back to the user's terminal.

[0061] Step 6:

[0062] The user checks the answer on the device.

[0063] Vehicle scheduling optimization

[0064] Step 1:

[0065] The user sends a request for a ride through the terminal.

[0066] Step 2:

[0067] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[0068] Step 3:

[0069] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[0070] Step 4:

[0071] The server transmits the optimized vehicle dispatch schedule to the user's terminal.

[0072] Step 5:

[0073] The user checks the dispatch schedule on the terminal.

[0074] Providing truck location information

[0075] Step 1:

[0076] The user sends a request for truck location information from the terminal.

[0077] Step 2:

[0078] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[0079] Step 3:

[0080] The server analyzes the location information and determines the current location of the truck.

[0081] Step 4:

[0082] The server sends real-time updated location information to the user's device.

[0083] Step 5:

[0084] The user checks the real-time location information on the device.

[0085] Troubleshooting and Support

[0086] Step 1:

[0087] A user reports a problem with a ride from their device.

[0088] Step 2:

[0089] A server receives the report and uses natural language processing models to analyze the problem.

[0090] Step 3:

[0091] The server generates an appropriate solution based on the analysis results.

[0092] Step 4:

[0093] The server sends the generated solution to the user's terminal.

[0094] Step 5:

[0095] The user checks the solution on the device and takes appropriate action.

[0096] Analysis of past dispatch data

[0097] Step 1:

[0098] The server periodically collects past dispatch data from the database.

[0099] Step 2:

[0100] The server passes the collected data to a generative AI model for analysis.

[0101] Step 3:

[0102] The server extracts trends and patterns based on the analysis results of the generated AI model.

[0103] Step 4:

[0104] The server creates a report of the results obtained and sends it to the user's terminal.

[0105] Step 5:

[0106] Users can review the reports and use them to plan future vehicle dispatches.

[0107] Example 1

[0108] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0109] Modern dispatch operations require efficient customer service, optimized schedules, real-time location information, fast troubleshooting, and historical data analysis. However, there is no system in place to consistently and efficiently accomplish these tasks. Most companies perform these processes manually, which is prone to human error and slow response times.

[0110] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0111] In this invention, the server includes a means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, a means for inputting vehicle availability, departure times, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model, and a means for acquiring vehicle location information from a positioning device and providing the location information in real time, thereby enabling more efficient dispatch arrangement work, reducing human error, and providing faster customer responses.

[0112] "Customer inquiries" are actions in which a user inputs questions or requests regarding vehicle dispatch in text format and sends them to the system.

[0113] A "natural language processing model" is a type of artificial intelligence technology for understanding and analyzing text data and generating appropriate responses.

[0114] A "generative AI model" is an artificial intelligence method for generating new information and optimal schedules based on input data.

[0115] "Vehicle availability" refers to the status and availability of vehicles available for dispatch during a specific time period.

[0116] The "departure time" is the specific time when a vehicle departs from a specified location during a vehicle dispatch operation.

[0117] "Route information" is data relating to the route that a vehicle will take to travel to the delivery destination.

[0118] A "positioning device" is a device that uses satellites to determine the current location of a vehicle.

[0119] "Location information" is data that indicates the current location of a vehicle.

[0120] "Dispatch issues" refers to reports of troubles or trivialities that arise during the dispatch process.

[0121] "Past dispatch data" is a data set that includes the history of past dispatch operations, schedules, and other related information.

[0122] "Trends and patterns" refer to specific movements or regularities found in past data.

[0123] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has a wide range of functions, such as responding to customer inquiries, optimizing dispatch schedules, providing vehicle location information, troubleshooting, and analyzing past dispatch data.

[0124] Responding to customer inquiries

[0125] The user uses the device to input a text-based inquiry about dispatching a vehicle. For example, the user might input, "I'd like to check tomorrow's delivery status." The device then sends this text data to the server. The server then passes the received inquiry to a natural language processing model (e.g., natural language processing AI) for analysis. The server then sends the generated answer back to the user's device, which then displays to the user, "Delivery is scheduled for tomorrow at 2:00 PM."

[0126] Vehicle scheduling optimization

[0127] The user sends a vehicle dispatch request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The terminal then sends this request data to the server. The server receives the request and retrieves vehicle availability, past schedules, departure times, and routes from a database (e.g., a relational database management system). This information is passed to a generative AI model (e.g., an AI generation model) to generate an optimal vehicle dispatch schedule. The generated vehicle dispatch schedule is then sent to the user's terminal, which displays "A vehicle will be dispatched at 10:00 AM on Monday."

[0128] Providing vehicle location information

[0129] The user sends a request from the device saying, "I want to know the current location of the vehicle." The device then sends this request to the server. The server receives the request and obtains real-time location information from a positioning device (e.g., a GPS device). The server then sends the obtained location information to the user's device. The device then displays to the user, "The vehicle is currently traveling on a major street in the city."

[0130] Troubleshooting and Support

[0131] The user reports a problem with a delivery vehicle from their device. For example, they report that "the delivery vehicle has stalled." The device sends this report to the server. The server receives the report and analyzes the problem using a natural language processing model (e.g., natural language processing AI). The server then generates a solution based on the analysis results and sends it to the user's device. The device then displays a message to the user asking, "Would you like to contact the nearest repair shop?"

[0132] Analysis of past dispatch data

[0133] The server periodically collects past dispatch data from a database (e.g., a relational database management system). The collected data is passed to a generative AI model (e.g., an AI-generated model) for analysis. For example, from dispatch data from the past year, a trend may be discovered that "weekend dispatch requests are on the rise." The results are compiled in a report format and provided to the user. The user can use this information to formulate future dispatch plans.

[0134] Examples and prompts

[0135] Here are some examples of specific prompts:

[0136] 1. Customer Inquiry Response:

[0137] User input prompt: "Please let me know the status of tomorrow's delivery."

[0138] Server-generated response: "Estimated delivery time is tomorrow at 2 PM."

[0139] 2. Vehicle scheduling optimization:

[0140] User input prompt: "I would like delivery by next Monday morning."

[0141] Server notification: "Your ride will arrive at 10 AM on Monday."

[0142] 3. Vehicle location information provision:

[0143] User input prompt: "What is the current vehicle location?"

[0144] Server response: "The vehicle is currently traveling on a major city street."

[0145] 4. Troubleshooting and Support:

[0146] User input prompt: "My delivery vehicle has stalled. What should I do?"

[0147] Server offers solution: "Would you like to contact your local repair shop?"

[0148] 5. Analysis of historical trip data:

[0149] Server internal process prompt (runs weekly): "Analyze the past year's dispatch data and report the trends."

[0150] Server generates report: "We're seeing an increase in weekend ride requests."

[0151] Using these functions, the system of the present invention can improve the efficiency of vehicle dispatch arrangement work, reduce human errors, and provide quick customer service.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Responding to customer inquiries

[0154] Step 1:

[0155] A user uses a terminal to input a text-based inquiry about dispatching. For example, the user inputs an inquiry such as "I would like to check tomorrow's delivery status." This input is sent to the server as text data by the terminal (input: user's inquiry text, output: text data sent to the server).

[0156] Step 2:

[0157] The server passes the received query to a natural language processing model. Specifically, the server calls the natural language processing model (e.g., natural language processing AI) and has it analyze the text data (input: query text from the user, data processing: text analysis, output: analysis results).

[0158] Step 3:

[0159] The server returns the generated answer to the user's device. Specifically, it sends the analysis results to the device, which then displays them to the user (input: analysis results, output: display of answer on device). For example, it displays "Expected delivery time is tomorrow at 2:00 PM."

[0160] Vehicle scheduling optimization

[0161] Step 1:

[0162] The user sends a request for a ride from the terminal. For example, the user enters "I would like delivery by Monday morning next week." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[0163] Step 2:

[0164] The server receives the request and retrieves information from the database. Specifically, the server retrieves vehicle availability, departure time, and route information from a relational database management system (input: database query, data processing: data extraction, output: vehicle information).

[0165] Step 3:

[0166] The server passes the extracted information to a generative AI model, which then generates an optimal vehicle dispatch schedule based on this information (input: vehicle information, data calculation: vehicle dispatch schedule generation, output: optimal vehicle dispatch schedule).

[0167] Step 4:

[0168] The server sends the generated vehicle dispatch schedule to the user's terminal, which displays it (input: optimal vehicle dispatch schedule, output: schedule notification displayed on terminal). For example, it displays "Vehicle dispatch will be at 10:00 AM on Monday."

[0169] Providing vehicle location information

[0170] Step 1:

[0171] The user sends a request from the terminal saying, "I want to know the current location of the vehicle." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[0172] Step 2:

[0173] The server receives the request and retrieves real-time location information from the positioning device. Specifically, the server retrieves location information from the GPS device (input: GPS device data request, data processing: location information retrieval, output: real-time location information).

[0174] Step 3:

[0175] The server sends the acquired location information to the user's device, which then displays it to the user (input: real-time location information, output: display of location information on device). For example, it displays "The vehicle is currently traveling on a major street in the city."

[0176] Troubleshooting and Support

[0177] Step 1:

[0178] A user reports a problem with a delivery vehicle from a terminal. For example, the user reports that "the delivery vehicle has stalled." This report is sent to the server by the terminal (input: user's problem report text, output: report data sent to the server).

[0179] Step 2:

[0180] The server receives the report and analyzes the problem using a natural language processing model. Specifically, the server analyzes the problem text data using a natural language processing model (input: problem report text, data processing: text analysis, output: analysis results).

[0181] Step 3:

[0182] The server generates a solution based on the analysis results and sends it to the user's device. The device displays it to the user (input: solution data, output: solution display on device). For example, it displays "Would you like to contact the nearest repair shop?"

[0183] Analysis of past dispatch data

[0184] Step 1:

[0185] The server periodically collects past dispatch data from the database. Specifically, the server extracts data from the relational database management system (input: database query, data processing: data extraction, output: past dataset).

[0186] Step 2:

[0187] The server passes the collected data to the generative AI model for analysis. The generative AI model analyzes the data and extracts specific trends and patterns (input: past data sets, data calculation: data analysis, output: trends and patterns).

[0188] Step 3:

[0189] The server compiles the analysis results into a report and provides it to the user. Specifically, it creates a report and sends it to the terminal, which then displays it to the user (input: analysis results, output: report display). For example, it might display something like, "There is a trend of increasing requests for car dispatches on weekends."

[0190] Based on the above steps, the system of the present invention efficiently and effectively supports vehicle dispatch operations.

[0191] (Application example 1)

[0192] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0193] Modern food delivery technology requires efficient delivery schedule generation, real-time location information, rapid response to customer inquiries, and rapid solutions when problems arise. However, existing systems struggle to provide these functions in an integrated manner. Furthermore, they lack a mechanism for effectively utilizing past delivery data to improve future operations. Therefore, developing an effective system that improves the efficiency of food delivery operations and customer satisfaction is a challenge.

[0194] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0195] In this invention, the server includes means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, means for inputting delivery availability, departure times, and route information, and creating an optimal delivery schedule using a generative AI model, means for acquiring delivery vehicle location information from a GPS device and providing the location information in real time, means for analyzing delivery-related issues using a natural language processing model and generating solutions, means for collecting and analyzing past delivery data and extracting trends and patterns, means for customers to input text-based food delivery inquiries and generating appropriate responses, means for checking available delivery personnel based on delivery requests and generating an optimal delivery schedule, means for providing driver GPS data to customers in real time, means for analyzing issues reported by delivery drivers and proposing solutions, and means for periodically analyzing delivery data and generating valuable insights. This enables efficiency improvements in food delivery operations, provision of real-time location information, rapid customer response, early resolution of problems when they occur, and effective use of past data.

[0196] "Customer" means any person or entity that uses the food delivery service.

[0197] An "Inquiry" is a question or request from a Customer seeking information or support related to food delivery.

[0198] A "natural language processing model" is an artificial intelligence technology for understanding, analyzing, and generating responses to human language.

[0199] "Delivery services" refers to the general business of delivering food and other products ordered by customers to designated locations.

[0200] "Delivery Schedule" refers to the planned delivery time slots and sequence to optimize delivery operations.

[0201] A "generative AI model" is an artificial intelligence technology that uses underlying data and algorithms to automatically perform specific tasks.

[0202] "Departure time" refers to the time when the delivery person begins delivery from the designated departure point.

[0203] "Route information" refers to information about the route or path that a delivery vehicle will take to reach a designated delivery point.

[0204] A "GPS device" is a device that uses satellites to obtain location information in real time.

[0205] A "delivery vehicle" is a vehicle such as a car, motorcycle, or bicycle used to perform delivery operations.

[0206] "Real-time" refers to the time between when information is acquired and when it is processed with minimal delay.

[0207] "Location information" means information indicating the current geographic location of a vehicle or item as determined by a GPS device.

[0208] "Problem" refers to an unexpected event or obstacle that occurs in the delivery process.

[0209] A "solution" is a specific method or means for solving the problem that has occurred.

[0210] "Historical Delivery Data" means all records and information relating to previous delivery transactions.

[0211] A "trend or pattern" is a consistent movement or recurring feature observed in historical data.

[0212] "Delivery Request" means a request that includes details of the Customer's desired delivery (e.g., date, time, location, etc.).

[0213] A "delivery person" is a person whose role is to deliver customer orders to a specified location.

[0214] "Insights" refers to useful discoveries and knowledge gained through data analysis.

[0215] This invention is a system aimed at improving the efficiency of food delivery operations and customer satisfaction. This system includes a wide range of functions, such as responding to customer inquiries, generating optimal delivery schedules, providing real-time location information, troubleshooting, and analyzing past data. These functions are realized using generative AI models and natural language processing models.

[0216] The system includes the following means:

[0217] 1. Customer inquiry response methods:

[0218] The server receives inquiries about food delivery entered by users through their devices and analyzes the inquiries using a natural language processing model. Based on the analysis results, it generates an appropriate answer and sends it back to the user's device. For example, if a user inquires, "I want to know the status of my order," the server generates the answer, "The delivery is currently on its way and is expected to arrive in 15 minutes."

[0219] 2. Delivery schedule optimization measures:

[0220] When a user submits their desired delivery time, departure time, and route information, the server uses a generative AI model to automatically generate an optimal delivery schedule based on available delivery staff. For example, if a user requests delivery at 10 a.m., the server will notify them that the delivery will be made at the specified time.

[0221] 3. Real-time location information provision methods:

[0222] If a user wants to know the current location of a delivery person, the server uses a GPS device to obtain real-time location information of the delivery vehicle and provides it to the user. For example, the server may provide information such as, "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[0223] 4. Troubleshooting methods:

[0224] If a delivery driver reports a problem during a delivery, the server uses natural language processing models to analyze the problem and suggest a solution. For example, if a driver reports that their bike has stalled, the server might suggest, "Would you like to contact the nearest repair shop?"

[0225] 5. How to analyze past delivery data:

[0226] The server periodically collects past delivery data and inputs it into a generative AI model for analysis. This allows trends and patterns in delivery operations to be extracted and used to improve operations in the future. For example, a trend such as "orders increase on weekend nights" could be extracted from data from the past year, and delivery schedules could be adjusted based on this result.

[0227] Specific examples

[0228] Responding to customer inquiries

[0229] When a user asks "What's the status of my order?":

[0230] Customer: "I want to know the status of my order."

[0231] System: "Delivery is currently on its way. Expected arrival in 15 minutes."

[0232] Optimizing delivery schedules

[0233] If a user requests delivery at 10:00 AM, the server generates an optimal delivery schedule based on information about available delivery staff.

[0234] Real-time location information

[0235] When a user requests the current location of a delivery person, the server uses a GPS device to provide real-time location information, such as "The delivery person is currently traveling on a major road and is expected to arrive in 10 minutes."

[0236] troubleshooting

[0237] If a delivery driver reports that their bike has stalled, the system will suggest, "Would you like to contact the nearest repair shop?"

[0238] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0239] Step 1:

[0240] Receiving and analyzing customer inquiries

[0241] A user inputs a text-based inquiry about food delivery through a terminal. The input text is sent to the server, which receives it. The received text is analyzed using a natural language processing model to understand the content of the inquiry. For example, if a user inputs the inquiry "I want to know the status of my order," the server analyzes this text and understands that the user is requesting information about the current status of the order.

[0242] Input: The query text sent by the user from the terminal

[0243] Output: Analysis result of inquiry (e.g. "I want to know the status of my order")

[0244] Step 2:

[0245] Generating the right answers

[0246] The server uses a generative AI model to generate an appropriate response based on the analyzed inquiry. For example, in response to an inquiry such as "I want to know the status of my order," the server generates a response such as "It's currently on its way and is expected to arrive in 15 minutes." This response is then sent back to the user's device and provided in real time.

[0247] Input: Analysis result of inquiry content

[0248] Output: The generated answer (e.g., "The delivery is currently on its way and should arrive in 15 minutes.")

[0249] Step 3:

[0250] Optimizing delivery schedules

[0251] The user inputs the desired delivery time and other conditions and sends them from the device to the server. The server uses a generative AI model to generate an optimal delivery schedule, taking into account the availability of delivery services, departure times, and route information. For example, if a user requests delivery at 10:00 a.m., the server checks the available delivery personnel and proposes the optimal schedule.

[0252] Input: User-entered desired delivery time, delivery request

[0253] Output: Optimized delivery schedule (e.g. "Deliver at 10 AM")

[0254] Step 4:

[0255] Providing real-time location information

[0256] The user sends a request from their device to find out the current location of the delivery person. The server uses a GPS device to obtain the real-time location information of the delivery vehicle and provides that information to the user. For example, the server may notify the user that "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[0257] Input: User location request

[0258] Output: Real-time location information (e.g. "The delivery person is currently driving on a major road. They are expected to arrive in 10 minutes.")

[0259] Step 5:

[0260] troubleshooting

[0261] A delivery driver reports a problem during a delivery. For example, if the driver reports that their bike has stalled, the information is sent from the device to the server. The server uses a natural language processing model to analyze the problem and propose a solution. The server generates a solution, such as "Should we contact the nearest repair shop?" and notifies the delivery driver.

[0262] Input: Driver problem report

[0263] Output: Proposed solution (e.g., "Contact your local repair shop?")

[0264] Step 6:

[0265] Analysis of past delivery data

[0266] The server periodically collects past delivery data from a database and passes it to the generative AI model for analysis. From the results of this analysis, trends and patterns in delivery operations can be extracted. For example, the server can extract trends such as "orders increase on weekend nights" and use this as a focus point for adjusting future delivery schedules.

[0267] Input: Past delivery data

[0268] Output: Extracted trends and patterns (e.g., "Orders increase on weekend nights")

[0269] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0270] This invention relates to a system that further improves the optimization and efficiency of vehicle dispatching operations by combining an emotion engine. This system not only handles customer inquiries, optimizes dispatch schedules, provides truck location information, troubleshoots, and analyzes past dispatch data, but also recognizes user emotions and responds appropriately.

[0271] Responding to customer inquiries

[0272] The user inputs and sends a text-based inquiry using a terminal. For example, a query such as "I want to know the current location of the delivery truck." The server receives this inquiry and analyzes it using a natural language processing model and emotion engine. The server understands not only the content of the inquiry but also the user's emotions, and returns an appropriate response such as "The truck is currently traveling on a major road and is expected to make its delivery as scheduled."

[0273] Vehicle scheduling optimization

[0274] The user sends a dispatch request using a terminal. For example, they request, "I would like delivery by Monday morning next week." The server receives this request and combines the generative AI model with an emotion engine to create an optimal dispatch schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will dispatch the vehicle at 10 a.m. on Monday. Don't worry."

[0275] Providing truck location information

[0276] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives the request and analyzes it by combining real-time location information obtained from the GPS device with the emotion engine. For example, it provides the user with reassuring information such as, "The truck is currently traveling on a major street in the city. Don't worry."

[0277] Troubleshooting and Support

[0278] The user reports a problem with a delivery vehicle from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and an emotion engine. It then provides the user with a solution that takes emotion into account, such as "Would you like to contact the nearest repair shop? We will respond immediately."

[0279] Analysis of past dispatch data

[0280] The server periodically collects past dispatch data from a database. The collected data is analyzed using a generative AI model and an emotion engine to extract trends and patterns. For example, it provides advice to users such as, "According to data from the past year, weekend dispatch requests are on the rise, so please plan your trip well in advance."

[0281] The system of the present invention combines functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past data with an emotion engine to realize a more advanced and efficient dispatch operation that can also respond to user emotions. This will improve the efficiency of dispatch operations, reduce human error, provide quicker customer service, and improve customer satisfaction.

[0282] The processing flow will be explained below.

[0283] Responding to customer inquiries

[0284] Step 1:

[0285] The user uses the terminal to input and send the inquiry.

[0286] Step 2:

[0287] The server receives the query and passes it to a natural language processing model.

[0288] Step 3:

[0289] The server analyzes the content of the query using a natural language processing model.

[0290] Step 4:

[0291] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[0292] Step 5:

[0293] The server generates an appropriate answer based on the results of the emotion engine and analysis.

[0294] Step 6:

[0295] The server generates a response and sends it back to the user's terminal.

[0296] Step 7:

[0297] The user checks the answer on the device.

[0298] Vehicle scheduling optimization

[0299] Step 1:

[0300] The user sends a request for a ride through the terminal.

[0301] Step 2:

[0302] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[0303] Step 3:

[0304] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[0305] Step 4:

[0306] The vehicle dispatch schedule created by the server is passed to the emotion engine to recognize the user's emotions.

[0307] Step 5:

[0308] The server considers the results of the emotion engine and generates emotion-sensitive notifications along with optimized vehicle dispatch schedules.

[0309] Step 6:

[0310] The server sends the notification to the user's device.

[0311] Step 7:

[0312] The user checks the ride schedule and notifications on the device.

[0313] Providing truck location information

[0314] Step 1:

[0315] The user sends a request for truck location information from the terminal.

[0316] Step 2:

[0317] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[0318] Step 3:

[0319] The server analyzes the location information obtained.

[0320] Step 4:

[0321] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[0322] Step 5:

[0323] The server takes into account the results of the emotion engine and generates appropriate location information.

[0324] Step 6:

[0325] The server transmits the generated location information to the user's device.

[0326] Step 7:

[0327] The user checks the real-time location information on the device.

[0328] Troubleshooting and Support

[0329] Step 1:

[0330] A user reports a problem with a ride from their device.

[0331] Step 2:

[0332] A server receives the report and uses natural language processing models to analyze the problem.

[0333] Step 3:

[0334] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[0335] Step 4:

[0336] The server uses the generative AI model to generate an appropriate solution.

[0337] Step 5:

[0338] The server considers the results of the emotion engine and provides a solution to the user.

[0339] Step 6:

[0340] The server sends the generated solution to the user's terminal.

[0341] Step 7:

[0342] The user checks the solution on the device and takes appropriate action.

[0343] Analysis of past dispatch data

[0344] Step 1:

[0345] The server periodically collects past dispatch data from the database.

[0346] Step 2:

[0347] The server passes the collected data to a generative AI model for analysis.

[0348] Step 3:

[0349] The server passes the analysis results to the emotion engine, which extracts trends and patterns.

[0350] Step 4:

[0351] The server generates an appropriate report based on the results obtained.

[0352] Step 5:

[0353] The server considers the results of the emotion engine and generates an emotion-sensitive report.

[0354] Step 6:

[0355] The server sends the generated report to the user's terminal.

[0356] Step 7:

[0357] Users can review the reports and use them to plan future vehicle dispatches.

[0358] Example 2

[0359] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0360] Conventional vehicle dispatch systems have problems such as delays in response and human error when responding to customer inquiries, optimizing truck dispatch schedules, providing location information, troubleshooting, analyzing past data, etc. Furthermore, they lack the ability to respond to customer emotions, making it difficult to improve customer satisfaction.

[0361] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model and an emotion engine; means for acquiring truck location information from a GPS device, analyzing it in combination with the emotion engine, and providing the location information in real time; means for analyzing vehicle dispatch problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting and analyzing past vehicle dispatch data, extracting trends and patterns, and providing advice. This enables quick and efficient responses that take customer emotions into consideration.

[0362] A "customer inquiry" is an act in which a customer requests information from the system.

[0363] A "natural language processing model" is a computer model for analyzing and understanding human language.

[0364] An "emotion engine" is a technology that identifies and analyzes emotions from input text or voice.

[0365] An "appropriate response" is accurate and useful information provided by the system in response to a customer inquiry.

[0366] A "dispatch schedule" refers to the operation plan for trucks and vehicles.

[0367] A "generative AI model" is a system that generates data and information using generative artificial intelligence algorithms.

[0368] "GPS Device" means a device for obtaining geographic location information.

[0369] "Real-time location information" refers to information that indicates a specific geographic location at the current time.

[0370] "Troubleshooting" is the process of resolving problems or issues that arise.

[0371] A "solution" is a specific response to a specific problem.

[0372] "Past vehicle dispatch data" refers to historical information regarding previous vehicle dispatches.

[0373] "Trends and patterns" refer to general trends or recurring characteristics found in the data.

[0374] "Advice" refers to advice or recommendations for a particular situation or problem.

[0375] This invention relates to a system that utilizes an emotion engine and generative AI models to optimize and streamline vehicle dispatch operations, demonstrating superior performance in responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[0376] First, when responding to a customer inquiry, the user makes a text-based inquiry from their device. The content of this inquiry is sent to the server, which analyzes it using a natural language processing model (e.g., GPT-4) and an emotion engine. For example, if a user types, "I want to know the current location of the delivery truck," the server understands the inquiry and the user's emotion, and provides a reassuring answer such as, "The truck is currently traveling on a major road, and we expect the delivery to be completed as scheduled."

[0377] Next, to optimize the vehicle dispatch schedule, the user sends a dispatch request from their device. For example, if they request "I would like delivery by Monday morning next week," the server receives this request and uses a generative AI model (e.g., OpenAI API) and an emotion engine to optimize truck availability, departure time, and route information. The optimized schedule is then provided to the user as a response such as, "We will dispatch a vehicle at 10 a.m. on Monday. Don't worry."

[0378] To provide truck location information, the user inquires about the current location from their device. For example, if they type "I want to know the current location of the truck," the server receives this request and obtains real-time location information from the GPS device. The server then analyzes the location information using an emotion engine and returns a reassuring response to the user, such as "The truck is currently traveling on a major street in the city. Don't worry."

[0379] Furthermore, for troubleshooting and support, users can report problems with dispatching from their terminals. For example, if a user reports that their delivery truck has stalled, the server will analyze the problem using a natural language processing model and an emotion engine, and provide the user with a solution that takes emotion into consideration, such as, "Would you like to contact the nearest repair shop? We will respond immediately."

[0380] Finally, for analyzing past ride-hailing data, the server periodically collects past data and analyzes it using a generative AI model and emotion engine. Based on the results of this analysis, the system provides advice to users, such as, "According to data from the past year, weekend ride-hailing requests are on the rise, so please plan your trip well in advance."

[0381] As described above, this invention enables efficient and highly accurate vehicle dispatching operations while taking into consideration the feelings of customers. By using this system, it is possible to improve the efficiency of vehicle dispatching operations, reduce human error, respond quickly to customers, and improve customer satisfaction.

[0382] Example prompt sentence:

[0383] "I want to know the current location of the delivery truck."

[0384] "I would like delivery next Monday morning."

[0385] "I want to know the current location of the truck."

[0386] "The delivery truck stalled."

[0387] "According to data from the past year"

[0388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0389] Responding to customer inquiries

[0390] Step 1:

[0391] The user inputs the inquiry from the terminal.

[0392] Input: The user enters "I want to know the current location of the delivery truck" into the inquiry form on the terminal.

[0393] Operation: Enter the input content in text format and press the send button.

[0394] Step 2:

[0395] The device sends the input to the server.

[0396] Input: Enquiry ("I want to know the current location of the delivery truck").

[0397] Action: The device formats the input as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[0398] Step 3:

[0399] The server receives the query.

[0400] Input: HTTP request.

[0401] Operation: The server receives the request and extracts the inquiry as text data. Output: Text data ("I want to know the current location of the delivery truck").

[0402] Step 4:

[0403] The server analyzes the data using a natural language processing model and emotion engine.

[0404] Input: Text data of the inquiry.

[0405] How it works: The server uses a natural language processing model (e.g., GPT-4) to analyze the query content and also analyzes the user's emotions using an emotion engine. Output: Analysis results (understanding of the query content and emotions).

[0406] Step 5:

[0407] The server generates an answer based on the analysis results.

[0408] Input: Analysis results.

[0409] Action: The server generates a reassuring answer: "The truck is currently traveling on the main road and is expected to make the delivery on time." Output: The generated answer.

[0410] Step 6:

[0411] The server sends the response to the terminal.

[0412] Input: The generated answer.

[0413] Action: The server sends the answer to the device as an HTTP response. Output: The HTTP response received by the device.

[0414] Step 7:

[0415] The user receives the response at the terminal.

[0416] Input: HTTP response.

[0417] Action: The terminal displays the received answer and the user confirms it. Output: The user is relieved.

[0418] Vehicle scheduling optimization

[0419] Step 1:

[0420] The user inputs a ride request into the terminal.

[0421] Input: The user inputs "I would like delivery by Monday morning next week" into the terminal.

[0422] Operation: Enter the input content in text format and press the send button.

[0423] Step 2:

[0424] The device sends a request to the server.

[0425] Input: Ride request ("I'd like delivery next Monday morning").

[0426] Action: The device formats the request as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[0427] Step 3:

[0428] The server receives the request.

[0429] Input: HTTP request.

[0430] Operation: The server receives the request and extracts the request content as text data. Output: Text data ("Delivery requested by Monday morning next week").

[0431] Step 4:

[0432] The server optimizes the schedule using generative AI models and emotion engines.

[0433] Input: Text data of a ride request.

[0434] Action: The server uses generative AI models (e.g. OpenAI API) and emotion engines to optimize truck availability, departure times, and route information. Output: An optimized schedule.

[0435] Step 5:

[0436] The server generates an optimized schedule.

[0437] Input: Optimized schedule.

[0438] Operation: The server generates an optimal schedule with the message "The car will be dispatched at 10:00 AM on Monday. Don't worry." Output: The generated schedule answer.

[0439] Step 6:

[0440] The server sends the optimization schedule to the terminal.

[0441] Input: Generated schedule answers.

[0442] Operation: The server sends this schedule to the terminal as an HTTP response. Output: The HTTP response received by the terminal.

[0443] Step 7:

[0444] The user checks the schedule on the device.

[0445] Input: HTTP response.

[0446] Operation: The terminal displays the received schedule and the user confirms it. Output: The user feels reassured.

[0447] (Application example 2)

[0448] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0449] In food delivery services, responding to customer inquiries, optimizing delivery schedules, providing delivery personnel with location information, troubleshooting, and analyzing past delivery data are all important factors. However, conventional systems struggle to respond appropriately while taking customer emotions into account, limiting the improvement of customer satisfaction. Furthermore, it is difficult to centrally manage these factors and achieve efficient delivery operations. To address these challenges, this invention provides an advanced system that uses an emotion engine and a generative AI model.

[0450] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal dispatch schedule using a generative AI model; means for acquiring truck location information from a GPS device, providing the location information in real time, and providing information in a manner that takes user peace of mind into account; means for analyzing dispatch-related problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting past dispatch data, analyzing it using the generative AI model and an emotion engine, and extracting trends and patterns. This enables quick and appropriate responses that take customer emotions into account, thereby improving the efficiency of food delivery operations and customer satisfaction.

[0451] "Customer inquiries" refers to questions or requests made by customers through the food delivery service's application, such as checking delivery status or reporting problems.

[0452] "Natural language processing models" refer to the algorithms and techniques that computers use to understand and analyze human language.

[0453] "Emotion engine" refers to software or algorithms that analyze and recognize user emotions and are used to determine a user's emotional state through text or voice data.

[0454] An "appropriate response" means a response that contains the most appropriate and useful information based on the customer's inquiry and their feelings at the time.

[0455] "Truck availability" refers to information indicating whether a truck to be used for delivery is currently available.

[0456] "Departure time" refers to data indicating the scheduled time for delivery to begin.

[0457] "Route information" refers to information including the optimal route to the delivery destination and data on intermediate points.

[0458] A "generative AI model" refers to an algorithm or framework for generating new data or information using AI technology.

[0459] "Optimal vehicle dispatch schedule" refers to the most efficient and economical vehicle dispatch plan, taking into account the availability of each truck, departure time, route information, etc.

[0460] "GPS device" refers to equipment and technology used to obtain global location information.

[0461] "Providing location information in real time" means instantly obtaining current location information and providing it to customers on the spot.

[0462] "Providing information in a manner that takes into consideration the user's sense of security" refers to a method of providing information that aims to alleviate the user's emotions and anxiety, and includes messages that are intended to give the user a sense of security.

[0463] "Dispatch issues" refer to various troubles and problems related to delivery operations and truck operations.

[0464] "Solution generation" refers to the process of providing the most appropriate response or fix to an issue that has arisen.

[0465] "Historical Trip Data" refers to historical data relating to all trips ever made.

[0466] "Extracting trends and patterns" refers to the analytical process of finding patterns and commonalities from large amounts of data.

[0467] This invention is a system that aims to improve the efficiency and customer satisfaction of food delivery services. This system optimizes the management of vehicle dispatch operations by combining an emotion engine and a generative AI model.

[0468] Responding to customer inquiries

[0469] The user inputs a query using a terminal and sends it to the server. For example, a query such as "I would like to know the delivery status of the pizza I just ordered." The server receives this query and analyzes it using a natural language processing model (e.g., BERT) and an emotion engine (e.g., IBM Watson Tone Analyzer). The server generates an appropriate answer based on the query and replies to the user after taking their emotions into consideration. This allows the user to feel that their emotions are understood and gives them a sense of security.

[0470] Optimizing delivery schedules

[0471] A user sends a delivery request using a terminal. For example, they request, "I would like delivery tomorrow morning." The server receives this request and combines the generative AI model with the emotion engine to create an optimal delivery schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will deliver tomorrow at 10 a.m. Don't worry." In this way, by using the emotion engine, it is possible to provide a delivery schedule that takes into account the user's emotions.

[0472] Real-time delivery location information

[0473] The user sends a request from their device saying, "I want to know the current location of the delivery person." The server receives the request and analyzes the real-time location information obtained from the GPS device in combination with the emotion engine. For example, it provides the user with reassuring information such as, "The delivery person is currently traveling on a major road. Don't worry." This not only allows the user to check the delivery status in real time, but also gives them a sense of security.

[0474] Troubleshooting and Support

[0475] A user reports a delivery problem from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and emotion engine. They then provide the user with a solution that takes their emotions into account, such as "Would you like to contact your nearest repair shop? We will take care of it right away." In this way, using the emotion engine can ease the user's anxiety and enable a prompt response.

[0476] Analysis of past delivery data

[0477] The server periodically collects past delivery data from a database. The collected data is analyzed using a generative AI model and emotion engine to extract delivery trends and patterns. For example, the system provides advice to users such as, "According to data from the past year, weekend delivery requests are on the rise, so please plan your deliveries well in advance." This enables efficient planning of delivery operations.

[0478] Examples of prompt statements

[0479] Customer inquiry prompt:

[0480] input:

[0481] "I'd like to know the status of the delivery of the pizza I just ordered."

[0482] Prompt for delivery schedule optimization:

[0483] input:

[0484] "I would like delivery tomorrow morning."

[0485] In this way, by combining an emotion engine and a generative AI model, the system of the present invention effectively realizes customer service and delivery schedule optimization, real-time location information provision, troubleshooting, and historical data analysis in food delivery services, thereby improving customer satisfaction and streamlining operations.

[0486] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0487] Step 1:

[0488] The terminal receives an inquiry from a customer. The customer uses the terminal to input and send an inquiry such as, "I'd like to know the delivery status of the pizza I just ordered." The input text data is then sent from the terminal to the server.

[0489] Step 2:

[0490] The server receives the customer's inquiry. The server uses a natural language processing model (e.g., BERT) to analyze the received inquiry. The BERT model is used to extract the intent of the inquiry and determine the appropriate action accordingly. In this process, the input text data is analyzed to identify the type and content of the inquiry.

[0491] Step 3:

[0492] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the content of the customer's inquiry. The analysis results provide information to determine the customer's emotional state. Specifically, it analyzes text data and outputs the customer's emotional state, such as whether they are feeling stressed or relieved.

[0493] Step 4:

[0494] The server generates an appropriate response based on the content of the inquiry and the results of sentiment analysis. A generative AI model is used to create a response that takes into account the customer's emotions. For example, a response that provides reassuring information such as, "The delivery person is currently driving on a major road. Don't worry," is generated. Here, a response text is generated based on the analysis results and sent back from the server to the device.

[0495] Step 5:

[0496] The server collects truck availability, departure times, and route information, and uses a generative AI model to create an optimal delivery schedule. Specifically, this information is passed as input to the system, and the generative AI model calculates the optimal schedule by taking various factors into account. The output includes the delivery schedule and the reasons for it.

[0497] Step 6:

[0498] The server obtains the truck's real-time location information from the GPS device. The obtained location information is quickly transmitted to the server. The emotion engine then processes the information in a way that increases the user's sense of security. The output is a description of the delivery situation, such as "The delivery person is currently driving on a major road. Don't worry."

[0499] Step 7:

[0500] When a user reports a delivery problem to the server, the server analyzes the problem using a natural language processing model and an emotion engine. For example, if a user reports that "the delivery truck stalled," the server analyzes the report and generates a proposal that takes into account specific solutions, such as contacting the nearest repair shop. The output is a proposal such as "Would you like to contact the nearest repair shop? We will respond immediately."

[0501] Step 8:

[0502] The server periodically collects past dispatch data from a database and analyzes it using a generative AI model and emotion engine. This analysis extracts delivery trends and patterns. For example, it can input data from the past year and output trends such as "weekend delivery requests are on the rise." Advice based on the analysis results is provided to the user.

[0503] Through the above processing steps, the system of the present invention realizes improved efficiency in food delivery operations and increased customer satisfaction.

[0504] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0505] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0506] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0507] [Second embodiment]

[0508] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0509] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0510] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0511] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0512] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0513] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0514] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0515] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0516] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0517] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0518] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0519] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0520] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[0521] Responding to customer inquiries

[0522] The user uses a terminal to input a text-based inquiry about dispatching a vehicle. For example, the user might input a query such as "I would like to check tomorrow's delivery status." The server receives this query and analyzes it using a natural language processing model. The server then generates an answer and sends it back to the user's terminal, replying, "Delivery is scheduled for tomorrow at 2:00 PM."

[0523] Vehicle scheduling optimization

[0524] The user sends a delivery request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The server receives the request and retrieves truck availability, past schedules, departure times, and routes from a database. The server then uses a generative AI model to create an optimal delivery schedule and notifies the user, "A delivery will be made at 10:00 AM on Monday."

[0525] Providing truck location information

[0526] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives this request and obtains real-time location information from the GPS device installed in the truck. For example, it provides the user with information such as, "The truck is currently traveling on a major street in the city."

[0527] Troubleshooting and Support

[0528] A user reports a problem with a delivery from their device. For example, they send a report saying, "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model. It generates a solution, such as "Contact the nearest repair shop?", and provides it to the user.

[0529] Analysis of past dispatch data

[0530] The server periodically collects past dispatch data from the database. The collected data is passed to the generative AI model for analysis. For example, from dispatch data from the past year, the server may discover a trend that "weekend dispatch requests are on the rise." The server then creates a report of these results and provides it to the user. Based on this, the user can formulate future dispatch plans.

[0531] As described above, the system of the present invention uses generative AI models and natural language processing models to achieve a wide range of functions, including responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data. This enables more efficient dispatch work, reduces human error, provides faster customer service, and improves customer satisfaction.

[0532] The processing flow will be explained below.

[0533] Responding to customer inquiries

[0534] Step 1:

[0535] The user uses the terminal to input and send the inquiry.

[0536] Step 2:

[0537] The server receives the query and passes it to a natural language processing model.

[0538] Step 3:

[0539] The server analyzes the content of the query using a natural language processing model.

[0540] Step 4:

[0541] The server generates an appropriate answer based on the analysis results.

[0542] Step 5:

[0543] The server generates a response and sends it back to the user's terminal.

[0544] Step 6:

[0545] The user checks the answer on the device.

[0546] Vehicle scheduling optimization

[0547] Step 1:

[0548] The user sends a request for a ride through the terminal.

[0549] Step 2:

[0550] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[0551] Step 3:

[0552] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[0553] Step 4:

[0554] The server transmits the optimized vehicle dispatch schedule to the user's terminal.

[0555] Step 5:

[0556] The user checks the dispatch schedule on the terminal.

[0557] Providing truck location information

[0558] Step 1:

[0559] The user sends a request for truck location information from the terminal.

[0560] Step 2:

[0561] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[0562] Step 3:

[0563] The server analyzes the location information and determines the current location of the truck.

[0564] Step 4:

[0565] The server sends real-time updated location information to the user's device.

[0566] Step 5:

[0567] The user checks the real-time location information on the device.

[0568] Troubleshooting and Support

[0569] Step 1:

[0570] A user reports a problem with a ride from their device.

[0571] Step 2:

[0572] A server receives the report and uses natural language processing models to analyze the problem.

[0573] Step 3:

[0574] The server generates an appropriate solution based on the analysis results.

[0575] Step 4:

[0576] The server sends the generated solution to the user's terminal.

[0577] Step 5:

[0578] The user checks the solution on the device and takes appropriate action.

[0579] Analysis of past dispatch data

[0580] Step 1:

[0581] The server periodically collects past dispatch data from the database.

[0582] Step 2:

[0583] The server passes the collected data to a generative AI model for analysis.

[0584] Step 3:

[0585] The server extracts trends and patterns based on the analysis results of the generated AI model.

[0586] Step 4:

[0587] The server creates a report of the results obtained and sends it to the user's terminal.

[0588] Step 5:

[0589] Users can review the reports and use them to plan future vehicle dispatches.

[0590] Example 1

[0591] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] Modern dispatch operations require efficient customer service, optimized schedules, real-time location information, fast troubleshooting, and historical data analysis. However, there is no system in place to consistently and efficiently accomplish these tasks. Most companies perform these processes manually, which is prone to human error and slow response times.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0594] In this invention, the server includes a means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, a means for inputting vehicle availability, departure times, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model, and a means for acquiring vehicle location information from a positioning device and providing the location information in real time, thereby enabling more efficient dispatch arrangement work, reducing human error, and providing faster customer responses.

[0595] "Customer inquiries" are actions in which a user inputs questions or requests regarding vehicle dispatch in text format and sends them to the system.

[0596] A "natural language processing model" is a type of artificial intelligence technology for understanding and analyzing text data and generating appropriate responses.

[0597] A "generative AI model" is an artificial intelligence method for generating new information and optimal schedules based on input data.

[0598] "Vehicle availability" refers to the status and availability of vehicles available for dispatch during a specific time period.

[0599] The "departure time" is the specific time when a vehicle departs from a specified location during a vehicle dispatch operation.

[0600] "Route information" is data relating to the route that a vehicle will take to travel to the delivery destination.

[0601] A "positioning device" is a device that uses satellites to determine the current location of a vehicle.

[0602] "Location information" is data that indicates the current location of a vehicle.

[0603] "Dispatch issues" refers to reports of troubles or trivialities that arise during the dispatch process.

[0604] "Past dispatch data" is a data set that includes the history of past dispatch operations, schedules, and other related information.

[0605] "Trends and patterns" refer to specific movements or regularities found in past data.

[0606] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has a wide range of functions, such as responding to customer inquiries, optimizing dispatch schedules, providing vehicle location information, troubleshooting, and analyzing past dispatch data.

[0607] Responding to customer inquiries

[0608] The user uses the device to input a text-based inquiry about dispatching a vehicle. For example, the user might input, "I'd like to check tomorrow's delivery status." The device then sends this text data to the server. The server then passes the received inquiry to a natural language processing model (e.g., natural language processing AI) for analysis. The server then sends the generated answer back to the user's device, which then displays to the user, "Delivery is scheduled for tomorrow at 2:00 PM."

[0609] Vehicle scheduling optimization

[0610] The user sends a vehicle dispatch request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The terminal then sends this request data to the server. The server receives the request and retrieves vehicle availability, past schedules, departure times, and routes from a database (e.g., a relational database management system). This information is passed to a generative AI model (e.g., an AI generation model) to generate an optimal vehicle dispatch schedule. The generated vehicle dispatch schedule is then sent to the user's terminal, which displays "A vehicle will be dispatched at 10:00 AM on Monday."

[0611] Providing vehicle location information

[0612] The user sends a request from the device saying, "I want to know the current location of the vehicle." The device then sends this request to the server. The server receives the request and obtains real-time location information from a positioning device (e.g., a GPS device). The server then sends the obtained location information to the user's device. The device then displays to the user, "The vehicle is currently traveling on a major street in the city."

[0613] Troubleshooting and Support

[0614] The user reports a problem with a delivery vehicle from their device. For example, they report that "the delivery vehicle has stalled." The device sends this report to the server. The server receives the report and analyzes the problem using a natural language processing model (e.g., natural language processing AI). The server then generates a solution based on the analysis results and sends it to the user's device. The device then displays a message to the user asking, "Would you like to contact the nearest repair shop?"

[0615] Analysis of past dispatch data

[0616] The server periodically collects past dispatch data from a database (e.g., a relational database management system). The collected data is passed to a generative AI model (e.g., an AI-generated model) for analysis. For example, from dispatch data from the past year, a trend may be discovered that "weekend dispatch requests are on the rise." The results are compiled in a report format and provided to the user. The user can use this information to formulate future dispatch plans.

[0617] Examples and prompts

[0618] Here are some examples of specific prompts:

[0619] 1. Customer Inquiry Response:

[0620] User input prompt: "Please let me know the status of tomorrow's delivery."

[0621] Server-generated response: "Estimated delivery time is tomorrow at 2 PM."

[0622] 2. Vehicle scheduling optimization:

[0623] User input prompt: "I would like delivery by next Monday morning."

[0624] Server notification: "Your ride will arrive at 10 AM on Monday."

[0625] 3. Vehicle location information provision:

[0626] User input prompt: "What is the current vehicle location?"

[0627] Server response: "The vehicle is currently traveling on a major city street."

[0628] 4. Troubleshooting and Support:

[0629] User input prompt: "My delivery vehicle has stalled. What should I do?"

[0630] Server offers solution: "Would you like to contact your local repair shop?"

[0631] 5. Analysis of historical trip data:

[0632] Server internal process prompt (runs weekly): "Analyze the past year's dispatch data and report the trends."

[0633] Server generates report: "We're seeing an increase in weekend ride requests."

[0634] Using these functions, the system of the present invention can improve the efficiency of vehicle dispatch arrangement work, reduce human errors, and provide quick customer service.

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Responding to customer inquiries

[0637] Step 1:

[0638] A user uses a terminal to input a text-based inquiry about dispatching. For example, the user inputs an inquiry such as "I would like to check tomorrow's delivery status." This input is sent to the server as text data by the terminal (input: user's inquiry text, output: text data sent to the server).

[0639] Step 2:

[0640] The server passes the received query to a natural language processing model. Specifically, the server calls the natural language processing model (e.g., natural language processing AI) and has it analyze the text data (input: query text from the user, data processing: text analysis, output: analysis results).

[0641] Step 3:

[0642] The server returns the generated answer to the user's device. Specifically, it sends the analysis results to the device, which then displays them to the user (input: analysis results, output: display of answer on device). For example, it displays "Expected delivery time is tomorrow at 2:00 PM."

[0643] Vehicle scheduling optimization

[0644] Step 1:

[0645] The user sends a request for a ride from the terminal. For example, the user enters "I would like delivery by Monday morning next week." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[0646] Step 2:

[0647] The server receives the request and retrieves information from the database. Specifically, the server retrieves vehicle availability, departure time, and route information from a relational database management system (input: database query, data processing: data extraction, output: vehicle information).

[0648] Step 3:

[0649] The server passes the extracted information to a generative AI model, which then generates an optimal vehicle dispatch schedule based on this information (input: vehicle information, data calculation: vehicle dispatch schedule generation, output: optimal vehicle dispatch schedule).

[0650] Step 4:

[0651] The server sends the generated vehicle dispatch schedule to the user's terminal, which displays it (input: optimal vehicle dispatch schedule, output: schedule notification displayed on terminal). For example, it displays "Vehicle dispatch will be at 10:00 AM on Monday."

[0652] Providing vehicle location information

[0653] Step 1:

[0654] The user sends a request from the terminal saying, "I want to know the current location of the vehicle." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[0655] Step 2:

[0656] The server receives the request and retrieves real-time location information from the positioning device. Specifically, the server retrieves location information from the GPS device (input: GPS device data request, data processing: location information retrieval, output: real-time location information).

[0657] Step 3:

[0658] The server sends the acquired location information to the user's device, which then displays it to the user (input: real-time location information, output: display of location information on device). For example, it displays "The vehicle is currently traveling on a major street in the city."

[0659] Troubleshooting and Support

[0660] Step 1:

[0661] A user reports a problem with a delivery vehicle from a terminal. For example, the user reports that "the delivery vehicle has stalled." This report is sent to the server by the terminal (input: user's problem report text, output: report data sent to the server).

[0662] Step 2:

[0663] The server receives the report and analyzes the problem using a natural language processing model. Specifically, the server analyzes the problem text data using a natural language processing model (input: problem report text, data processing: text analysis, output: analysis results).

[0664] Step 3:

[0665] The server generates a solution based on the analysis results and sends it to the user's device. The device displays it to the user (input: solution data, output: solution display on device). For example, it displays "Would you like to contact the nearest repair shop?"

[0666] Analysis of past dispatch data

[0667] Step 1:

[0668] The server periodically collects past dispatch data from the database. Specifically, the server extracts data from the relational database management system (input: database query, data processing: data extraction, output: past dataset).

[0669] Step 2:

[0670] The server passes the collected data to the generative AI model for analysis. The generative AI model analyzes the data and extracts specific trends and patterns (input: past data sets, data calculation: data analysis, output: trends and patterns).

[0671] Step 3:

[0672] The server compiles the analysis results into a report and provides it to the user. Specifically, it creates a report and sends it to the terminal, which then displays it to the user (input: analysis results, output: report display). For example, it might display something like, "There is a trend of increasing requests for car dispatches on weekends."

[0673] Based on the above steps, the system of the present invention efficiently and effectively supports vehicle dispatch operations.

[0674] (Application example 1)

[0675] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0676] Modern food delivery technology requires efficient delivery schedule generation, real-time location information, rapid response to customer inquiries, and rapid solutions when problems arise. However, existing systems struggle to provide these functions in an integrated manner. Furthermore, they lack a mechanism for effectively utilizing past delivery data to improve future operations. Therefore, developing an effective system that improves the efficiency of food delivery operations and customer satisfaction is a challenge.

[0677] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0678] In this invention, the server includes means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, means for inputting delivery availability, departure times, and route information, and creating an optimal delivery schedule using a generative AI model, means for acquiring delivery vehicle location information from a GPS device and providing the location information in real time, means for analyzing delivery-related issues using a natural language processing model and generating solutions, means for collecting and analyzing past delivery data and extracting trends and patterns, means for customers to input text-based food delivery inquiries and generating appropriate responses, means for checking available delivery personnel based on delivery requests and generating an optimal delivery schedule, means for providing driver GPS data to customers in real time, means for analyzing issues reported by delivery drivers and proposing solutions, and means for periodically analyzing delivery data and generating valuable insights. This enables efficiency improvements in food delivery operations, provision of real-time location information, rapid customer response, early resolution of problems when they occur, and effective use of past data.

[0679] "Customer" means any person or entity that uses the food delivery service.

[0680] An "Inquiry" is a question or request from a Customer seeking information or support related to food delivery.

[0681] A "natural language processing model" is an artificial intelligence technology for understanding, analyzing, and generating responses to human language.

[0682] "Delivery services" refers to the general business of delivering food and other products ordered by customers to designated locations.

[0683] "Delivery Schedule" refers to the planned delivery time slots and sequence to optimize delivery operations.

[0684] A "generative AI model" is an artificial intelligence technology that uses underlying data and algorithms to automatically perform specific tasks.

[0685] "Departure time" refers to the time when the delivery person begins delivery from the designated departure point.

[0686] "Route information" refers to information about the route or path that a delivery vehicle will take to reach a designated delivery point.

[0687] A "GPS device" is a device that uses satellites to obtain location information in real time.

[0688] A "delivery vehicle" is a vehicle such as a car, motorcycle, or bicycle used to perform delivery operations.

[0689] "Real-time" refers to the time between when information is acquired and when it is processed with minimal delay.

[0690] "Location information" means information indicating the current geographic location of a vehicle or item as determined by a GPS device.

[0691] "Problem" refers to an unexpected event or obstacle that occurs in the delivery process.

[0692] A "solution" is a specific method or means for solving the problem that has occurred.

[0693] "Historical Delivery Data" means all records and information relating to previous delivery transactions.

[0694] A "trend or pattern" is a consistent movement or recurring feature observed in historical data.

[0695] "Delivery Request" means a request that includes details of the Customer's desired delivery (e.g., date, time, location, etc.).

[0696] A "delivery person" is a person whose role is to deliver customer orders to a specified location.

[0697] "Insights" refers to useful discoveries and knowledge gained through data analysis.

[0698] This invention is a system aimed at improving the efficiency of food delivery operations and customer satisfaction. This system includes a wide range of functions, such as responding to customer inquiries, generating optimal delivery schedules, providing real-time location information, troubleshooting, and analyzing past data. These functions are realized using generative AI models and natural language processing models.

[0699] The system includes the following means:

[0700] 1. Customer inquiry response methods:

[0701] The server receives inquiries about food delivery entered by users through their devices and analyzes the inquiries using a natural language processing model. Based on the analysis results, it generates an appropriate answer and sends it back to the user's device. For example, if a user inquires, "I want to know the status of my order," the server generates the answer, "The delivery is currently on its way and is expected to arrive in 15 minutes."

[0702] 2. Delivery schedule optimization measures:

[0703] When a user submits their desired delivery time, departure time, and route information, the server uses a generative AI model to automatically generate an optimal delivery schedule based on available delivery staff. For example, if a user requests delivery at 10 a.m., the server will notify them that the delivery will be made at the specified time.

[0704] 3. Real-time location information provision methods:

[0705] If a user wants to know the current location of a delivery person, the server uses a GPS device to obtain real-time location information of the delivery vehicle and provides it to the user. For example, the server may provide information such as, "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[0706] 4. Troubleshooting methods:

[0707] If a delivery driver reports a problem during a delivery, the server uses natural language processing models to analyze the problem and suggest a solution. For example, if a driver reports that their bike has stalled, the server might suggest, "Would you like to contact the nearest repair shop?"

[0708] 5. How to analyze past delivery data:

[0709] The server periodically collects past delivery data and inputs it into a generative AI model for analysis. This allows trends and patterns in delivery operations to be extracted and used to improve operations in the future. For example, a trend such as "orders increase on weekend nights" could be extracted from data from the past year, and delivery schedules could be adjusted based on this result.

[0710] Specific examples

[0711] Responding to customer inquiries

[0712] When a user asks "What's the status of my order?":

[0713] Customer: "I want to know the status of my order."

[0714] System: "Delivery is currently on its way. Expected arrival in 15 minutes."

[0715] Optimizing delivery schedules

[0716] If a user requests delivery at 10:00 AM, the server generates an optimal delivery schedule based on information about available delivery staff.

[0717] Real-time location information

[0718] When a user requests the current location of a delivery person, the server uses a GPS device to provide real-time location information, such as "The delivery person is currently traveling on a major road and is expected to arrive in 10 minutes."

[0719] troubleshooting

[0720] If a delivery driver reports that their bike has stalled, the system will suggest, "Would you like to contact the nearest repair shop?"

[0721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0722] Step 1:

[0723] Receiving and analyzing customer inquiries

[0724] A user inputs a text-based inquiry about food delivery through a terminal. The input text is sent to the server, which receives it. The received text is analyzed using a natural language processing model to understand the content of the inquiry. For example, if a user inputs the inquiry "I want to know the status of my order," the server analyzes this text and understands that the user is requesting information about the current status of the order.

[0725] Input: The query text sent by the user from the terminal

[0726] Output: Analysis result of inquiry (e.g. "I want to know the status of my order")

[0727] Step 2:

[0728] Generating the right answers

[0729] The server uses a generative AI model to generate an appropriate response based on the analyzed inquiry. For example, in response to an inquiry such as "I want to know the status of my order," the server generates a response such as "It's currently on its way and is expected to arrive in 15 minutes." This response is then sent back to the user's device and provided in real time.

[0730] Input: Analysis result of inquiry content

[0731] Output: The generated answer (e.g., "The delivery is currently on its way and should arrive in 15 minutes.")

[0732] Step 3:

[0733] Optimizing delivery schedules

[0734] The user inputs the desired delivery time and other conditions and sends them from the device to the server. The server uses a generative AI model to generate an optimal delivery schedule, taking into account the availability of delivery services, departure times, and route information. For example, if a user requests delivery at 10:00 a.m., the server checks the available delivery personnel and proposes the optimal schedule.

[0735] Input: User-entered desired delivery time, delivery request

[0736] Output: Optimized delivery schedule (e.g. "Deliver at 10 AM")

[0737] Step 4:

[0738] Providing real-time location information

[0739] The user sends a request from their device to find out the current location of the delivery person. The server uses a GPS device to obtain the real-time location information of the delivery vehicle and provides that information to the user. For example, the server may notify the user that "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[0740] Input: User location request

[0741] Output: Real-time location information (e.g. "The delivery person is currently driving on a major road. They are expected to arrive in 10 minutes.")

[0742] Step 5:

[0743] troubleshooting

[0744] A delivery driver reports a problem during a delivery. For example, if the driver reports that their bike has stalled, the information is sent from the device to the server. The server uses a natural language processing model to analyze the problem and propose a solution. The server generates a solution, such as "Should we contact the nearest repair shop?" and notifies the delivery driver.

[0745] Input: Driver problem report

[0746] Output: Proposed solution (e.g., "Contact your local repair shop?")

[0747] Step 6:

[0748] Analysis of past delivery data

[0749] The server periodically collects past delivery data from a database and passes it to the generative AI model for analysis. From the results of this analysis, trends and patterns in delivery operations can be extracted. For example, the server can extract trends such as "orders increase on weekend nights" and use this as a focus point for adjusting future delivery schedules.

[0750] Input: Past delivery data

[0751] Output: Extracted trends and patterns (e.g., "Orders increase on weekend nights")

[0752] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0753] This invention relates to a system that further improves the optimization and efficiency of vehicle dispatching operations by combining an emotion engine. This system not only handles customer inquiries, optimizes dispatch schedules, provides truck location information, troubleshoots, and analyzes past dispatch data, but also recognizes user emotions and responds appropriately.

[0754] Responding to customer inquiries

[0755] The user inputs and sends a text-based inquiry using a terminal. For example, a query such as "I want to know the current location of the delivery truck." The server receives this inquiry and analyzes it using a natural language processing model and emotion engine. The server understands not only the content of the inquiry but also the user's emotions, and returns an appropriate response such as "The truck is currently traveling on a major road and is expected to make its delivery as scheduled."

[0756] Vehicle scheduling optimization

[0757] The user sends a dispatch request using a terminal. For example, they request, "I would like delivery by Monday morning next week." The server receives this request and combines the generative AI model with an emotion engine to create an optimal dispatch schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will dispatch the vehicle at 10 a.m. on Monday. Don't worry."

[0758] Providing truck location information

[0759] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives the request and analyzes it by combining real-time location information obtained from the GPS device with the emotion engine. For example, it provides the user with reassuring information such as, "The truck is currently traveling on a major street in the city. Don't worry."

[0760] Troubleshooting and Support

[0761] The user reports a problem with a delivery vehicle from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and an emotion engine. It then provides the user with a solution that takes emotion into account, such as "Would you like to contact the nearest repair shop? We will respond immediately."

[0762] Analysis of past dispatch data

[0763] The server periodically collects past dispatch data from a database. The collected data is analyzed using a generative AI model and an emotion engine to extract trends and patterns. For example, it provides advice to users such as, "According to data from the past year, weekend dispatch requests are on the rise, so please plan your trip well in advance."

[0764] The system of the present invention combines functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past data with an emotion engine to realize a more advanced and efficient dispatch operation that can also respond to user emotions. This will improve the efficiency of dispatch operations, reduce human error, provide quicker customer service, and improve customer satisfaction.

[0765] The processing flow will be explained below.

[0766] Responding to customer inquiries

[0767] Step 1:

[0768] The user uses the terminal to input and send the inquiry.

[0769] Step 2:

[0770] The server receives the query and passes it to a natural language processing model.

[0771] Step 3:

[0772] The server analyzes the content of the query using a natural language processing model.

[0773] Step 4:

[0774] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[0775] Step 5:

[0776] The server generates an appropriate answer based on the results of the emotion engine and analysis.

[0777] Step 6:

[0778] The server generates a response and sends it back to the user's terminal.

[0779] Step 7:

[0780] The user checks the answer on the device.

[0781] Vehicle scheduling optimization

[0782] Step 1:

[0783] The user sends a request for a ride through the terminal.

[0784] Step 2:

[0785] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[0786] Step 3:

[0787] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[0788] Step 4:

[0789] The vehicle dispatch schedule created by the server is passed to the emotion engine to recognize the user's emotions.

[0790] Step 5:

[0791] The server considers the results of the emotion engine and generates emotion-sensitive notifications along with optimized vehicle dispatch schedules.

[0792] Step 6:

[0793] The server sends the notification to the user's device.

[0794] Step 7:

[0795] The user checks the ride schedule and notifications on the device.

[0796] Providing truck location information

[0797] Step 1:

[0798] The user sends a request for truck location information from the terminal.

[0799] Step 2:

[0800] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[0801] Step 3:

[0802] The server analyzes the location information obtained.

[0803] Step 4:

[0804] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[0805] Step 5:

[0806] The server takes into account the results of the emotion engine and generates appropriate location information.

[0807] Step 6:

[0808] The server transmits the generated location information to the user's device.

[0809] Step 7:

[0810] The user checks the real-time location information on the device.

[0811] Troubleshooting and Support

[0812] Step 1:

[0813] A user reports a problem with a ride from their device.

[0814] Step 2:

[0815] A server receives the report and uses natural language processing models to analyze the problem.

[0816] Step 3:

[0817] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[0818] Step 4:

[0819] The server uses the generative AI model to generate an appropriate solution.

[0820] Step 5:

[0821] The server considers the results of the emotion engine and provides a solution to the user.

[0822] Step 6:

[0823] The server sends the generated solution to the user's terminal.

[0824] Step 7:

[0825] The user checks the solution on the device and takes appropriate action.

[0826] Analysis of past dispatch data

[0827] Step 1:

[0828] The server periodically collects past dispatch data from the database.

[0829] Step 2:

[0830] The server passes the collected data to a generative AI model for analysis.

[0831] Step 3:

[0832] The server passes the analysis results to the emotion engine, which extracts trends and patterns.

[0833] Step 4:

[0834] The server generates an appropriate report based on the results obtained.

[0835] Step 5:

[0836] The server considers the results of the emotion engine and generates an emotion-sensitive report.

[0837] Step 6:

[0838] The server sends the generated report to the user's terminal.

[0839] Step 7:

[0840] Users can review the reports and use them to plan future vehicle dispatches.

[0841] Example 2

[0842] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0843] Conventional vehicle dispatch systems have problems such as delays in response and human error when responding to customer inquiries, optimizing truck dispatch schedules, providing location information, troubleshooting, analyzing past data, etc. Furthermore, they lack the ability to respond to customer emotions, making it difficult to improve customer satisfaction.

[0844] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model and an emotion engine; means for acquiring truck location information from a GPS device, analyzing it in combination with the emotion engine, and providing the location information in real time; means for analyzing vehicle dispatch problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting and analyzing past vehicle dispatch data, extracting trends and patterns, and providing advice. This enables quick and efficient responses that take customer emotions into consideration.

[0845] A "customer inquiry" is an act in which a customer requests information from the system.

[0846] A "natural language processing model" is a computer model for analyzing and understanding human language.

[0847] An "emotion engine" is a technology that identifies and analyzes emotions from input text or voice.

[0848] An "appropriate response" is accurate and useful information provided by the system in response to a customer inquiry.

[0849] A "dispatch schedule" refers to the operation plan for trucks and vehicles.

[0850] A "generative AI model" is a system that generates data and information using generative artificial intelligence algorithms.

[0851] "GPS Device" means a device for obtaining geographic location information.

[0852] "Real-time location information" refers to information that indicates a specific geographic location at the current time.

[0853] "Troubleshooting" is the process of resolving problems or issues that arise.

[0854] A "solution" is a specific response to a specific problem.

[0855] "Past vehicle dispatch data" refers to historical information regarding previous vehicle dispatches.

[0856] "Trends and patterns" refer to general trends or recurring characteristics found in the data.

[0857] "Advice" refers to advice or recommendations for a particular situation or problem.

[0858] This invention relates to a system that utilizes an emotion engine and generative AI models to optimize and streamline vehicle dispatch operations, demonstrating superior performance in responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[0859] First, when responding to a customer inquiry, the user makes a text-based inquiry from their device. The content of this inquiry is sent to the server, which analyzes it using a natural language processing model (e.g., GPT-4) and an emotion engine. For example, if a user types, "I want to know the current location of the delivery truck," the server understands the inquiry and the user's emotion, and provides a reassuring answer such as, "The truck is currently traveling on a major road, and we expect the delivery to be completed as scheduled."

[0860] Next, to optimize the vehicle dispatch schedule, the user sends a dispatch request from their device. For example, if they request "I would like delivery by Monday morning next week," the server receives this request and uses a generative AI model (e.g., OpenAI API) and an emotion engine to optimize truck availability, departure time, and route information. The optimized schedule is then provided to the user as a response such as, "We will dispatch a vehicle at 10 a.m. on Monday. Don't worry."

[0861] To provide truck location information, the user inquires about the current location from their device. For example, if they type "I want to know the current location of the truck," the server receives this request and obtains real-time location information from the GPS device. The server then analyzes the location information using an emotion engine and returns a reassuring response to the user, such as "The truck is currently traveling on a major street in the city. Don't worry."

[0862] Furthermore, for troubleshooting and support, users can report problems with dispatching from their terminals. For example, if a user reports that their delivery truck has stalled, the server will analyze the problem using a natural language processing model and an emotion engine, and provide the user with a solution that takes emotion into consideration, such as, "Would you like to contact the nearest repair shop? We will respond immediately."

[0863] Finally, for analyzing past ride-hailing data, the server periodically collects past data and analyzes it using a generative AI model and emotion engine. Based on the results of this analysis, the system provides advice to users, such as, "According to data from the past year, weekend ride-hailing requests are on the rise, so please plan your trip well in advance."

[0864] As described above, this invention enables efficient and highly accurate vehicle dispatching operations while taking into consideration the feelings of customers. By using this system, it is possible to improve the efficiency of vehicle dispatching operations, reduce human error, respond quickly to customers, and improve customer satisfaction.

[0865] Example prompt sentence:

[0866] "I want to know the current location of the delivery truck."

[0867] "I would like delivery next Monday morning."

[0868] "I want to know the current location of the truck."

[0869] "The delivery truck stalled."

[0870] "According to data from the past year"

[0871] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0872] Responding to customer inquiries

[0873] Step 1:

[0874] The user inputs the inquiry from the terminal.

[0875] Input: The user enters "I want to know the current location of the delivery truck" into the inquiry form on the terminal.

[0876] Operation: Enter the input content in text format and press the send button.

[0877] Step 2:

[0878] The device sends the input to the server.

[0879] Input: Enquiry ("I want to know the current location of the delivery truck").

[0880] Action: The device formats the input as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[0881] Step 3:

[0882] The server receives the query.

[0883] Input: HTTP request.

[0884] Operation: The server receives the request and extracts the inquiry as text data. Output: Text data ("I want to know the current location of the delivery truck").

[0885] Step 4:

[0886] The server analyzes the data using a natural language processing model and emotion engine.

[0887] Input: Text data of the inquiry.

[0888] How it works: The server uses a natural language processing model (e.g., GPT-4) to analyze the query content and also analyzes the user's emotions using an emotion engine. Output: Analysis results (understanding of the query content and emotions).

[0889] Step 5:

[0890] The server generates an answer based on the analysis results.

[0891] Input: Analysis results.

[0892] Action: The server generates a reassuring answer: "The truck is currently traveling on the main road and is expected to make the delivery on time." Output: The generated answer.

[0893] Step 6:

[0894] The server sends the response to the terminal.

[0895] Input: The generated answer.

[0896] Action: The server sends the answer to the device as an HTTP response. Output: The HTTP response received by the device.

[0897] Step 7:

[0898] The user receives the response at the terminal.

[0899] Input: HTTP response.

[0900] Action: The terminal displays the received answer and the user confirms it. Output: The user is relieved.

[0901] Vehicle scheduling optimization

[0902] Step 1:

[0903] The user inputs a ride request into the terminal.

[0904] Input: The user inputs "I would like delivery by Monday morning next week" into the terminal.

[0905] Operation: Enter the input content in text format and press the send button.

[0906] Step 2:

[0907] The device sends a request to the server.

[0908] Input: Ride request ("I'd like delivery next Monday morning").

[0909] Action: The device formats the request as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[0910] Step 3:

[0911] The server receives the request.

[0912] Input: HTTP request.

[0913] Operation: The server receives the request and extracts the request content as text data. Output: Text data ("Delivery requested by Monday morning next week").

[0914] Step 4:

[0915] The server optimizes the schedule using generative AI models and emotion engines.

[0916] Input: Text data of a ride request.

[0917] Action: The server uses generative AI models (e.g. OpenAI API) and emotion engines to optimize truck availability, departure times, and route information. Output: An optimized schedule.

[0918] Step 5:

[0919] The server generates an optimized schedule.

[0920] Input: Optimized schedule.

[0921] Operation: The server generates an optimal schedule with the message "The car will be dispatched at 10:00 AM on Monday. Don't worry." Output: The generated schedule answer.

[0922] Step 6:

[0923] The server sends the optimization schedule to the terminal.

[0924] Input: Generated schedule answers.

[0925] Operation: The server sends this schedule to the terminal as an HTTP response. Output: The HTTP response received by the terminal.

[0926] Step 7:

[0927] The user checks the schedule on the device.

[0928] Input: HTTP response.

[0929] Operation: The terminal displays the received schedule and the user confirms it. Output: The user feels reassured.

[0930] (Application example 2)

[0931] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0932] In food delivery services, responding to customer inquiries, optimizing delivery schedules, providing delivery personnel with location information, troubleshooting, and analyzing past delivery data are all important factors. However, conventional systems struggle to respond appropriately while taking customer emotions into account, limiting the improvement of customer satisfaction. Furthermore, it is difficult to centrally manage these factors and achieve efficient delivery operations. To address these challenges, this invention provides an advanced system that uses an emotion engine and a generative AI model.

[0933] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal dispatch schedule using a generative AI model; means for acquiring truck location information from a GPS device, providing the location information in real time, and providing information in a manner that takes user peace of mind into account; means for analyzing dispatch-related problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting past dispatch data, analyzing it using the generative AI model and an emotion engine, and extracting trends and patterns. This enables quick and appropriate responses that take customer emotions into account, thereby improving the efficiency of food delivery operations and customer satisfaction.

[0934] "Customer inquiries" refers to questions or requests made by customers through the food delivery service's application, such as checking delivery status or reporting problems.

[0935] "Natural language processing models" refer to the algorithms and techniques that computers use to understand and analyze human language.

[0936] "Emotion engine" refers to software or algorithms that analyze and recognize user emotions and are used to determine a user's emotional state through text or voice data.

[0937] An "appropriate response" means a response that contains the most appropriate and useful information based on the customer's inquiry and their feelings at the time.

[0938] "Truck availability" refers to information indicating whether a truck to be used for delivery is currently available.

[0939] "Departure time" refers to data indicating the scheduled time for delivery to begin.

[0940] "Route information" refers to information including the optimal route to the delivery destination and data on intermediate points.

[0941] A "generative AI model" refers to an algorithm or framework for generating new data or information using AI technology.

[0942] "Optimal vehicle dispatch schedule" refers to the most efficient and economical vehicle dispatch plan, taking into account the availability of each truck, departure time, route information, etc.

[0943] "GPS device" refers to equipment and technology used to obtain global location information.

[0944] "Providing location information in real time" means instantly obtaining current location information and providing it to customers on the spot.

[0945] "Providing information in a manner that takes into consideration the user's sense of security" refers to a method of providing information that aims to alleviate the user's emotions and anxiety, and includes messages that are intended to give the user a sense of security.

[0946] "Dispatch issues" refer to various troubles and problems related to delivery operations and truck operations.

[0947] "Solution generation" refers to the process of providing the most appropriate response or fix to an issue that has arisen.

[0948] "Historical Trip Data" refers to historical data relating to all trips ever made.

[0949] "Extracting trends and patterns" refers to the analytical process of finding patterns and commonalities from large amounts of data.

[0950] This invention is a system that aims to improve the efficiency and customer satisfaction of food delivery services. This system optimizes the management of vehicle dispatch operations by combining an emotion engine and a generative AI model.

[0951] Responding to customer inquiries

[0952] The user inputs a query using a terminal and sends it to the server. For example, a query such as "I would like to know the delivery status of the pizza I just ordered." The server receives this query and analyzes it using a natural language processing model (e.g., BERT) and an emotion engine (e.g., IBM Watson Tone Analyzer). The server generates an appropriate answer based on the query and replies to the user after taking their emotions into consideration. This allows the user to feel that their emotions are understood and gives them a sense of security.

[0953] Optimizing delivery schedules

[0954] A user sends a delivery request using a terminal. For example, they request, "I would like delivery tomorrow morning." The server receives this request and combines the generative AI model with the emotion engine to create an optimal delivery schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will deliver tomorrow at 10 a.m. Don't worry." In this way, by using the emotion engine, it is possible to provide a delivery schedule that takes into account the user's emotions.

[0955] Real-time delivery location information

[0956] The user sends a request from their device saying, "I want to know the current location of the delivery person." The server receives the request and analyzes the real-time location information obtained from the GPS device in combination with the emotion engine. For example, it provides the user with reassuring information such as, "The delivery person is currently traveling on a major road. Don't worry." This not only allows the user to check the delivery status in real time, but also gives them a sense of security.

[0957] Troubleshooting and Support

[0958] A user reports a delivery problem from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and emotion engine. They then provide the user with a solution that takes their emotions into account, such as "Would you like to contact your nearest repair shop? We will take care of it right away." In this way, using the emotion engine can ease the user's anxiety and enable a prompt response.

[0959] Analysis of past delivery data

[0960] The server periodically collects past delivery data from a database. The collected data is analyzed using a generative AI model and emotion engine to extract delivery trends and patterns. For example, the system provides advice to users such as, "According to data from the past year, weekend delivery requests are on the rise, so please plan your deliveries well in advance." This enables efficient planning of delivery operations.

[0961] Examples of prompt statements

[0962] Customer inquiry prompt:

[0963] input:

[0964] "I'd like to know the status of the delivery of the pizza I just ordered."

[0965] Prompt for delivery schedule optimization:

[0966] input:

[0967] "I would like delivery tomorrow morning."

[0968] In this way, by combining an emotion engine and a generative AI model, the system of the present invention effectively realizes customer service and delivery schedule optimization, real-time location information provision, troubleshooting, and historical data analysis in food delivery services, thereby improving customer satisfaction and streamlining operations.

[0969] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0970] Step 1:

[0971] The terminal receives an inquiry from a customer. The customer uses the terminal to input and send an inquiry such as, "I'd like to know the delivery status of the pizza I just ordered." The input text data is then sent from the terminal to the server.

[0972] Step 2:

[0973] The server receives the customer's inquiry. The server uses a natural language processing model (e.g., BERT) to analyze the received inquiry. The BERT model is used to extract the intent of the inquiry and determine the appropriate action accordingly. In this process, the input text data is analyzed to identify the type and content of the inquiry.

[0974] Step 3:

[0975] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the content of the customer's inquiry. The analysis results provide information to determine the customer's emotional state. Specifically, it analyzes text data and outputs the customer's emotional state, such as whether they are feeling stressed or relieved.

[0976] Step 4:

[0977] The server generates an appropriate response based on the content of the inquiry and the results of sentiment analysis. A generative AI model is used to create a response that takes into account the customer's emotions. For example, a response that provides reassuring information such as, "The delivery person is currently driving on a major road. Don't worry," is generated. Here, a response text is generated based on the analysis results and sent back from the server to the device.

[0978] Step 5:

[0979] The server collects truck availability, departure times, and route information, and uses a generative AI model to create an optimal delivery schedule. Specifically, this information is passed as input to the system, and the generative AI model calculates the optimal schedule by taking various factors into account. The output includes the delivery schedule and the reasons for it.

[0980] Step 6:

[0981] The server obtains the truck's real-time location information from the GPS device. The obtained location information is quickly transmitted to the server. The emotion engine then processes the information in a way that increases the user's sense of security. The output is a description of the delivery situation, such as "The delivery person is currently driving on a major road. Don't worry."

[0982] Step 7:

[0983] When a user reports a delivery problem to the server, the server analyzes the problem using a natural language processing model and an emotion engine. For example, if a user reports that "the delivery truck stalled," the server analyzes the report and generates a proposal that takes into account specific solutions, such as contacting the nearest repair shop. The output is a proposal such as "Would you like to contact the nearest repair shop? We will respond immediately."

[0984] Step 8:

[0985] The server periodically collects past dispatch data from a database and analyzes it using a generative AI model and emotion engine. This analysis extracts delivery trends and patterns. For example, it can input data from the past year and output trends such as "weekend delivery requests are on the rise." Advice based on the analysis results is provided to the user.

[0986] Through the above processing steps, the system of the present invention realizes improved efficiency in food delivery operations and increased customer satisfaction.

[0987] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0988] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0989] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0990] [Third embodiment]

[0991] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0992] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0993] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0994] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0995] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0996] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0997] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0998] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0999] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1000] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1001] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1002] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1003] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[1004] Responding to customer inquiries

[1005] The user uses a terminal to input a text-based inquiry about dispatching a vehicle. For example, the user might input a query such as "I would like to check tomorrow's delivery status." The server receives this query and analyzes it using a natural language processing model. The server then generates an answer and sends it back to the user's terminal, replying, "Delivery is scheduled for tomorrow at 2:00 PM."

[1006] Vehicle scheduling optimization

[1007] The user sends a delivery request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The server receives the request and retrieves truck availability, past schedules, departure times, and routes from a database. The server then uses a generative AI model to create an optimal delivery schedule and notifies the user, "A delivery will be made at 10:00 AM on Monday."

[1008] Providing truck location information

[1009] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives this request and obtains real-time location information from the GPS device installed in the truck. For example, it provides the user with information such as, "The truck is currently traveling on a major street in the city."

[1010] Troubleshooting and Support

[1011] A user reports a problem with a delivery from their device. For example, they send a report saying, "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model. It generates a solution, such as "Contact the nearest repair shop?", and provides it to the user.

[1012] Analysis of past dispatch data

[1013] The server periodically collects past dispatch data from the database. The collected data is passed to the generative AI model for analysis. For example, from dispatch data from the past year, the server may discover a trend that "weekend dispatch requests are on the rise." The server then creates a report of these results and provides it to the user. Based on this, the user can formulate future dispatch plans.

[1014] As described above, the system of the present invention uses generative AI models and natural language processing models to achieve a wide range of functions, including responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data. This enables more efficient dispatch work, reduces human error, provides faster customer service, and improves customer satisfaction.

[1015] The processing flow will be explained below.

[1016] Responding to customer inquiries

[1017] Step 1:

[1018] The user uses the terminal to input and send the inquiry.

[1019] Step 2:

[1020] The server receives the query and passes it to a natural language processing model.

[1021] Step 3:

[1022] The server analyzes the content of the query using a natural language processing model.

[1023] Step 4:

[1024] The server generates an appropriate answer based on the analysis results.

[1025] Step 5:

[1026] The server generates a response and sends it back to the user's terminal.

[1027] Step 6:

[1028] The user checks the answer on the device.

[1029] Vehicle scheduling optimization

[1030] Step 1:

[1031] The user sends a request for a ride through the terminal.

[1032] Step 2:

[1033] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[1034] Step 3:

[1035] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[1036] Step 4:

[1037] The server transmits the optimized vehicle dispatch schedule to the user's terminal.

[1038] Step 5:

[1039] The user checks the dispatch schedule on the terminal.

[1040] Providing truck location information

[1041] Step 1:

[1042] The user sends a request for truck location information from the terminal.

[1043] Step 2:

[1044] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[1045] Step 3:

[1046] The server analyzes the location information and determines the current location of the truck.

[1047] Step 4:

[1048] The server sends real-time updated location information to the user's device.

[1049] Step 5:

[1050] The user checks the real-time location information on the device.

[1051] Troubleshooting and Support

[1052] Step 1:

[1053] A user reports a problem with a ride from their device.

[1054] Step 2:

[1055] A server receives the report and uses natural language processing models to analyze the problem.

[1056] Step 3:

[1057] The server generates an appropriate solution based on the analysis results.

[1058] Step 4:

[1059] The server sends the generated solution to the user's terminal.

[1060] Step 5:

[1061] The user checks the solution on the device and takes appropriate action.

[1062] Analysis of past dispatch data

[1063] Step 1:

[1064] The server periodically collects past dispatch data from the database.

[1065] Step 2:

[1066] The server passes the collected data to a generative AI model for analysis.

[1067] Step 3:

[1068] The server extracts trends and patterns based on the analysis results of the generated AI model.

[1069] Step 4:

[1070] The server creates a report of the results obtained and sends it to the user's terminal.

[1071] Step 5:

[1072] Users can review the reports and use them to plan future vehicle dispatches.

[1073] Example 1

[1074] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1075] Modern dispatch operations require efficient customer service, optimized schedules, real-time location information, fast troubleshooting, and historical data analysis. However, there is no system in place to consistently and efficiently accomplish these tasks. Most companies perform these processes manually, which is prone to human error and slow response times.

[1076] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1077] In this invention, the server includes a means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, a means for inputting vehicle availability, departure times, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model, and a means for acquiring vehicle location information from a positioning device and providing the location information in real time, thereby enabling more efficient dispatch arrangement work, reducing human error, and providing faster customer responses.

[1078] "Customer inquiries" are actions in which a user inputs questions or requests regarding vehicle dispatch in text format and sends them to the system.

[1079] A "natural language processing model" is a type of artificial intelligence technology for understanding and analyzing text data and generating appropriate responses.

[1080] A "generative AI model" is an artificial intelligence method for generating new information and optimal schedules based on input data.

[1081] "Vehicle availability" refers to the status and availability of vehicles available for dispatch during a specific time period.

[1082] The "departure time" is the specific time when a vehicle departs from a specified location during a vehicle dispatch operation.

[1083] "Route information" is data relating to the route that a vehicle will take to travel to the delivery destination.

[1084] A "positioning device" is a device that uses satellites to determine the current location of a vehicle.

[1085] "Location information" is data that indicates the current location of a vehicle.

[1086] "Dispatch issues" refers to reports of troubles or trivialities that arise during the dispatch process.

[1087] "Past dispatch data" is a data set that includes the history of past dispatch operations, schedules, and other related information.

[1088] "Trends and patterns" refer to specific movements or regularities found in past data.

[1089] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has a wide range of functions, such as responding to customer inquiries, optimizing dispatch schedules, providing vehicle location information, troubleshooting, and analyzing past dispatch data.

[1090] Responding to customer inquiries

[1091] The user uses the device to input a text-based inquiry about dispatching a vehicle. For example, the user might input, "I'd like to check tomorrow's delivery status." The device then sends this text data to the server. The server then passes the received inquiry to a natural language processing model (e.g., natural language processing AI) for analysis. The server then sends the generated answer back to the user's device, which then displays to the user, "Delivery is scheduled for tomorrow at 2:00 PM."

[1092] Vehicle scheduling optimization

[1093] The user sends a vehicle dispatch request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The terminal then sends this request data to the server. The server receives the request and retrieves vehicle availability, past schedules, departure times, and routes from a database (e.g., a relational database management system). This information is passed to a generative AI model (e.g., an AI generation model) to generate an optimal vehicle dispatch schedule. The generated vehicle dispatch schedule is then sent to the user's terminal, which displays "A vehicle will be dispatched at 10:00 AM on Monday."

[1094] Providing vehicle location information

[1095] The user sends a request from the device saying, "I want to know the current location of the vehicle." The device then sends this request to the server. The server receives the request and obtains real-time location information from a positioning device (e.g., a GPS device). The server then sends the obtained location information to the user's device. The device then displays to the user, "The vehicle is currently traveling on a major street in the city."

[1096] Troubleshooting and Support

[1097] The user reports a problem with a delivery vehicle from their device. For example, they report that "the delivery vehicle has stalled." The device sends this report to the server. The server receives the report and analyzes the problem using a natural language processing model (e.g., natural language processing AI). The server then generates a solution based on the analysis results and sends it to the user's device. The device then displays a message to the user asking, "Would you like to contact the nearest repair shop?"

[1098] Analysis of past dispatch data

[1099] The server periodically collects past dispatch data from a database (e.g., a relational database management system). The collected data is passed to a generative AI model (e.g., an AI-generated model) for analysis. For example, from dispatch data from the past year, a trend may be discovered that "weekend dispatch requests are on the rise." The results are compiled in a report format and provided to the user. The user can use this information to formulate future dispatch plans.

[1100] Examples and prompts

[1101] Here are some examples of specific prompts:

[1102] 1. Customer Inquiry Response:

[1103] User input prompt: "Please let me know the status of tomorrow's delivery."

[1104] Server-generated response: "Estimated delivery time is tomorrow at 2 PM."

[1105] 2. Vehicle scheduling optimization:

[1106] User input prompt: "I would like delivery by next Monday morning."

[1107] Server notification: "Your ride will arrive at 10 AM on Monday."

[1108] 3. Vehicle location information provision:

[1109] User input prompt: "What is the current vehicle location?"

[1110] Server response: "The vehicle is currently traveling on a major city street."

[1111] 4. Troubleshooting and Support:

[1112] User input prompt: "My delivery vehicle has stalled. What should I do?"

[1113] Server offers solution: "Would you like to contact your local repair shop?"

[1114] 5. Analysis of historical trip data:

[1115] Server internal process prompt (runs weekly): "Analyze the past year's dispatch data and report the trends."

[1116] Server generates report: "We're seeing an increase in weekend ride requests."

[1117] Using these functions, the system of the present invention can improve the efficiency of vehicle dispatch arrangement work, reduce human errors, and provide quick customer service.

[1118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1119] Responding to customer inquiries

[1120] Step 1:

[1121] A user uses a terminal to input a text-based inquiry about dispatching. For example, the user inputs an inquiry such as "I would like to check tomorrow's delivery status." This input is sent to the server as text data by the terminal (input: user's inquiry text, output: text data sent to the server).

[1122] Step 2:

[1123] The server passes the received query to a natural language processing model. Specifically, the server calls the natural language processing model (e.g., natural language processing AI) and has it analyze the text data (input: query text from the user, data processing: text analysis, output: analysis results).

[1124] Step 3:

[1125] The server returns the generated answer to the user's device. Specifically, it sends the analysis results to the device, which then displays them to the user (input: analysis results, output: display of answer on device). For example, it displays "Expected delivery time is tomorrow at 2:00 PM."

[1126] Vehicle scheduling optimization

[1127] Step 1:

[1128] The user sends a request for a ride from the terminal. For example, the user enters "I would like delivery by Monday morning next week." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[1129] Step 2:

[1130] The server receives the request and retrieves information from the database. Specifically, the server retrieves vehicle availability, departure time, and route information from a relational database management system (input: database query, data processing: data extraction, output: vehicle information).

[1131] Step 3:

[1132] The server passes the extracted information to a generative AI model, which then generates an optimal vehicle dispatch schedule based on this information (input: vehicle information, data calculation: vehicle dispatch schedule generation, output: optimal vehicle dispatch schedule).

[1133] Step 4:

[1134] The server sends the generated vehicle dispatch schedule to the user's terminal, which displays it (input: optimal vehicle dispatch schedule, output: schedule notification displayed on terminal). For example, it displays "Vehicle dispatch will be at 10:00 AM on Monday."

[1135] Providing vehicle location information

[1136] Step 1:

[1137] The user sends a request from the terminal saying, "I want to know the current location of the vehicle." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[1138] Step 2:

[1139] The server receives the request and retrieves real-time location information from the positioning device. Specifically, the server retrieves location information from the GPS device (input: GPS device data request, data processing: location information retrieval, output: real-time location information).

[1140] Step 3:

[1141] The server sends the acquired location information to the user's device, which then displays it to the user (input: real-time location information, output: display of location information on device). For example, it displays "The vehicle is currently traveling on a major street in the city."

[1142] Troubleshooting and Support

[1143] Step 1:

[1144] A user reports a problem with a delivery vehicle from a terminal. For example, the user reports that "the delivery vehicle has stalled." This report is sent to the server by the terminal (input: user's problem report text, output: report data sent to the server).

[1145] Step 2:

[1146] The server receives the report and analyzes the problem using a natural language processing model. Specifically, the server analyzes the problem text data using a natural language processing model (input: problem report text, data processing: text analysis, output: analysis results).

[1147] Step 3:

[1148] The server generates a solution based on the analysis results and sends it to the user's device. The device displays it to the user (input: solution data, output: solution display on device). For example, it displays "Would you like to contact the nearest repair shop?"

[1149] Analysis of past dispatch data

[1150] Step 1:

[1151] The server periodically collects past dispatch data from the database. Specifically, the server extracts data from the relational database management system (input: database query, data processing: data extraction, output: past dataset).

[1152] Step 2:

[1153] The server passes the collected data to the generative AI model for analysis. The generative AI model analyzes the data and extracts specific trends and patterns (input: past data sets, data calculation: data analysis, output: trends and patterns).

[1154] Step 3:

[1155] The server compiles the analysis results into a report and provides it to the user. Specifically, it creates a report and sends it to the terminal, which then displays it to the user (input: analysis results, output: report display). For example, it might display something like, "There is a trend of increasing requests for car dispatches on weekends."

[1156] Based on the above steps, the system of the present invention efficiently and effectively supports vehicle dispatch operations.

[1157] (Application example 1)

[1158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1159] Modern food delivery technology requires efficient delivery schedule generation, real-time location information, rapid response to customer inquiries, and rapid solutions when problems arise. However, existing systems struggle to provide these functions in an integrated manner. Furthermore, they lack a mechanism for effectively utilizing past delivery data to improve future operations. Therefore, developing an effective system that improves the efficiency of food delivery operations and customer satisfaction is a challenge.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1161] In this invention, the server includes means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, means for inputting delivery availability, departure times, and route information, and creating an optimal delivery schedule using a generative AI model, means for acquiring delivery vehicle location information from a GPS device and providing the location information in real time, means for analyzing delivery-related issues using a natural language processing model and generating solutions, means for collecting and analyzing past delivery data and extracting trends and patterns, means for customers to input text-based food delivery inquiries and generating appropriate responses, means for checking available delivery personnel based on delivery requests and generating an optimal delivery schedule, means for providing driver GPS data to customers in real time, means for analyzing issues reported by delivery drivers and proposing solutions, and means for periodically analyzing delivery data and generating valuable insights. This enables efficiency improvements in food delivery operations, provision of real-time location information, rapid customer response, early resolution of problems when they occur, and effective use of past data.

[1162] "Customer" means any person or entity that uses the food delivery service.

[1163] An "Inquiry" is a question or request from a Customer seeking information or support related to food delivery.

[1164] A "natural language processing model" is an artificial intelligence technology for understanding, analyzing, and generating responses to human language.

[1165] "Delivery services" refers to the general business of delivering food and other products ordered by customers to designated locations.

[1166] "Delivery Schedule" refers to the planned delivery time slots and sequence to optimize delivery operations.

[1167] A "generative AI model" is an artificial intelligence technology that uses underlying data and algorithms to automatically perform specific tasks.

[1168] "Departure time" refers to the time when the delivery person begins delivery from the designated departure point.

[1169] "Route information" refers to information about the route or path that a delivery vehicle will take to reach a designated delivery point.

[1170] A "GPS device" is a device that uses satellites to obtain location information in real time.

[1171] A "delivery vehicle" is a vehicle such as a car, motorcycle, or bicycle used to perform delivery operations.

[1172] "Real-time" refers to the time between when information is acquired and when it is processed with minimal delay.

[1173] "Location information" means information indicating the current geographic location of a vehicle or item as determined by a GPS device.

[1174] "Problem" refers to an unexpected event or obstacle that occurs in the delivery process.

[1175] A "solution" is a specific method or means for solving the problem that has occurred.

[1176] "Historical Delivery Data" means all records and information relating to previous delivery transactions.

[1177] A "trend or pattern" is a consistent movement or recurring feature observed in historical data.

[1178] "Delivery Request" means a request that includes details of the Customer's desired delivery (e.g., date, time, location, etc.).

[1179] A "delivery person" is a person whose role is to deliver customer orders to a specified location.

[1180] "Insights" refers to useful discoveries and knowledge gained through data analysis.

[1181] This invention is a system aimed at improving the efficiency of food delivery operations and customer satisfaction. This system includes a wide range of functions, such as responding to customer inquiries, generating optimal delivery schedules, providing real-time location information, troubleshooting, and analyzing past data. These functions are realized using generative AI models and natural language processing models.

[1182] The system includes the following means:

[1183] 1. Customer inquiry response methods:

[1184] The server receives inquiries about food delivery entered by users through their devices and analyzes the inquiries using a natural language processing model. Based on the analysis results, it generates an appropriate answer and sends it back to the user's device. For example, if a user inquires, "I want to know the status of my order," the server generates the answer, "The delivery is currently on its way and is expected to arrive in 15 minutes."

[1185] 2. Delivery schedule optimization measures:

[1186] When a user submits their desired delivery time, departure time, and route information, the server uses a generative AI model to automatically generate an optimal delivery schedule based on available delivery staff. For example, if a user requests delivery at 10 a.m., the server will notify them that the delivery will be made at the specified time.

[1187] 3. Real-time location information provision methods:

[1188] If a user wants to know the current location of a delivery person, the server uses a GPS device to obtain real-time location information of the delivery vehicle and provides it to the user. For example, the server may provide information such as, "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[1189] 4. Troubleshooting methods:

[1190] If a delivery driver reports a problem during a delivery, the server uses natural language processing models to analyze the problem and suggest a solution. For example, if a driver reports that their bike has stalled, the server might suggest, "Would you like to contact the nearest repair shop?"

[1191] 5. How to analyze past delivery data:

[1192] The server periodically collects past delivery data and inputs it into a generative AI model for analysis. This allows trends and patterns in delivery operations to be extracted and used to improve operations in the future. For example, a trend such as "orders increase on weekend nights" could be extracted from data from the past year, and delivery schedules could be adjusted based on this result.

[1193] Specific examples

[1194] Responding to customer inquiries

[1195] When a user asks "What's the status of my order?":

[1196] Customer: "I want to know the status of my order."

[1197] System: "Delivery is currently on its way. Expected arrival in 15 minutes."

[1198] Optimizing delivery schedules

[1199] If a user requests delivery at 10:00 AM, the server generates an optimal delivery schedule based on information about available delivery staff.

[1200] Real-time location information

[1201] When a user requests the current location of a delivery person, the server uses a GPS device to provide real-time location information, such as "The delivery person is currently traveling on a major road and is expected to arrive in 10 minutes."

[1202] troubleshooting

[1203] If a delivery driver reports that their bike has stalled, the system will suggest, "Would you like to contact the nearest repair shop?"

[1204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1205] Step 1:

[1206] Receiving and analyzing customer inquiries

[1207] A user inputs a text-based inquiry about food delivery through a terminal. The input text is sent to the server, which receives it. The received text is analyzed using a natural language processing model to understand the content of the inquiry. For example, if a user inputs the inquiry "I want to know the status of my order," the server analyzes this text and understands that the user is requesting information about the current status of the order.

[1208] Input: The query text sent by the user from the terminal

[1209] Output: Analysis result of inquiry (e.g. "I want to know the status of my order")

[1210] Step 2:

[1211] Generating the right answers

[1212] The server uses a generative AI model to generate an appropriate response based on the analyzed inquiry. For example, in response to an inquiry such as "I want to know the status of my order," the server generates a response such as "It's currently on its way and is expected to arrive in 15 minutes." This response is then sent back to the user's device and provided in real time.

[1213] Input: Analysis result of inquiry content

[1214] Output: The generated answer (e.g., "The delivery is currently on its way and should arrive in 15 minutes.")

[1215] Step 3:

[1216] Optimizing delivery schedules

[1217] The user inputs the desired delivery time and other conditions and sends them from the device to the server. The server uses a generative AI model to generate an optimal delivery schedule, taking into account the availability of delivery services, departure times, and route information. For example, if a user requests delivery at 10:00 a.m., the server checks the available delivery personnel and proposes the optimal schedule.

[1218] Input: User-entered desired delivery time, delivery request

[1219] Output: Optimized delivery schedule (e.g. "Deliver at 10 AM")

[1220] Step 4:

[1221] Providing real-time location information

[1222] The user sends a request from their device to find out the current location of the delivery person. The server uses a GPS device to obtain the real-time location information of the delivery vehicle and provides that information to the user. For example, the server may notify the user that "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[1223] Input: User location request

[1224] Output: Real-time location information (e.g. "The delivery person is currently driving on a major road. They are expected to arrive in 10 minutes.")

[1225] Step 5:

[1226] troubleshooting

[1227] A delivery driver reports a problem during a delivery. For example, if the driver reports that their bike has stalled, the information is sent from the device to the server. The server uses a natural language processing model to analyze the problem and propose a solution. The server generates a solution, such as "Should we contact the nearest repair shop?" and notifies the delivery driver.

[1228] Input: Driver problem report

[1229] Output: Proposed solution (e.g., "Contact your local repair shop?")

[1230] Step 6:

[1231] Analysis of past delivery data

[1232] The server periodically collects past delivery data from a database and passes it to the generative AI model for analysis. From the results of this analysis, trends and patterns in delivery operations can be extracted. For example, the server can extract trends such as "orders increase on weekend nights" and use this as a focus point for adjusting future delivery schedules.

[1233] Input: Past delivery data

[1234] Output: Extracted trends and patterns (e.g., "Orders increase on weekend nights")

[1235] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1236] This invention relates to a system that further improves the optimization and efficiency of vehicle dispatching operations by combining an emotion engine. This system not only handles customer inquiries, optimizes dispatch schedules, provides truck location information, troubleshoots, and analyzes past dispatch data, but also recognizes user emotions and responds appropriately.

[1237] Responding to customer inquiries

[1238] The user inputs and sends a text-based inquiry using a terminal. For example, a query such as "I want to know the current location of the delivery truck." The server receives this inquiry and analyzes it using a natural language processing model and emotion engine. The server understands not only the content of the inquiry but also the user's emotions, and returns an appropriate response such as "The truck is currently traveling on a major road and is expected to make its delivery as scheduled."

[1239] Vehicle scheduling optimization

[1240] The user sends a dispatch request using a terminal. For example, they request, "I would like delivery by Monday morning next week." The server receives this request and combines the generative AI model with an emotion engine to create an optimal dispatch schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will dispatch the vehicle at 10 a.m. on Monday. Don't worry."

[1241] Providing truck location information

[1242] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives the request and analyzes it by combining real-time location information obtained from the GPS device with the emotion engine. For example, it provides the user with reassuring information such as, "The truck is currently traveling on a major street in the city. Don't worry."

[1243] Troubleshooting and Support

[1244] The user reports a problem with a delivery vehicle from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and an emotion engine. It then provides the user with a solution that takes emotion into account, such as "Would you like to contact the nearest repair shop? We will respond immediately."

[1245] Analysis of past dispatch data

[1246] The server periodically collects past dispatch data from a database. The collected data is analyzed using a generative AI model and an emotion engine to extract trends and patterns. For example, it provides advice to users such as, "According to data from the past year, weekend dispatch requests are on the rise, so please plan your trip well in advance."

[1247] The system of the present invention combines functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past data with an emotion engine to realize a more advanced and efficient dispatch operation that can also respond to user emotions. This will improve the efficiency of dispatch operations, reduce human error, provide quicker customer service, and improve customer satisfaction.

[1248] The processing flow will be explained below.

[1249] Responding to customer inquiries

[1250] Step 1:

[1251] The user uses the terminal to input and send the inquiry.

[1252] Step 2:

[1253] The server receives the query and passes it to a natural language processing model.

[1254] Step 3:

[1255] The server analyzes the content of the query using a natural language processing model.

[1256] Step 4:

[1257] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[1258] Step 5:

[1259] The server generates an appropriate answer based on the results of the emotion engine and analysis.

[1260] Step 6:

[1261] The server generates a response and sends it back to the user's terminal.

[1262] Step 7:

[1263] The user checks the answer on the device.

[1264] Vehicle scheduling optimization

[1265] Step 1:

[1266] The user sends a request for a ride through the terminal.

[1267] Step 2:

[1268] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[1269] Step 3:

[1270] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[1271] Step 4:

[1272] The vehicle dispatch schedule created by the server is passed to the emotion engine to recognize the user's emotions.

[1273] Step 5:

[1274] The server considers the results of the emotion engine and generates emotion-sensitive notifications along with optimized vehicle dispatch schedules.

[1275] Step 6:

[1276] The server sends the notification to the user's device.

[1277] Step 7:

[1278] The user checks the ride schedule and notifications on the device.

[1279] Providing truck location information

[1280] Step 1:

[1281] The user sends a request for truck location information from the terminal.

[1282] Step 2:

[1283] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[1284] Step 3:

[1285] The server analyzes the location information obtained.

[1286] Step 4:

[1287] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[1288] Step 5:

[1289] The server takes into account the results of the emotion engine and generates appropriate location information.

[1290] Step 6:

[1291] The server transmits the generated location information to the user's device.

[1292] Step 7:

[1293] The user checks the real-time location information on the device.

[1294] Troubleshooting and Support

[1295] Step 1:

[1296] A user reports a problem with a ride from their device.

[1297] Step 2:

[1298] A server receives the report and uses natural language processing models to analyze the problem.

[1299] Step 3:

[1300] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[1301] Step 4:

[1302] The server uses the generative AI model to generate an appropriate solution.

[1303] Step 5:

[1304] The server considers the results of the emotion engine and provides a solution to the user.

[1305] Step 6:

[1306] The server sends the generated solution to the user's terminal.

[1307] Step 7:

[1308] The user checks the solution on the device and takes appropriate action.

[1309] Analysis of past dispatch data

[1310] Step 1:

[1311] The server periodically collects past dispatch data from the database.

[1312] Step 2:

[1313] The server passes the collected data to a generative AI model for analysis.

[1314] Step 3:

[1315] The server passes the analysis results to the emotion engine, which extracts trends and patterns.

[1316] Step 4:

[1317] The server generates an appropriate report based on the results obtained.

[1318] Step 5:

[1319] The server considers the results of the emotion engine and generates an emotion-sensitive report.

[1320] Step 6:

[1321] The server sends the generated report to the user's terminal.

[1322] Step 7:

[1323] Users can review the reports and use them to plan future vehicle dispatches.

[1324] Example 2

[1325] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1326] Conventional vehicle dispatch systems have problems such as delays in response and human error when responding to customer inquiries, optimizing truck dispatch schedules, providing location information, troubleshooting, analyzing past data, etc. Furthermore, they lack the ability to respond to customer emotions, making it difficult to improve customer satisfaction.

[1327] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model and an emotion engine; means for acquiring truck location information from a GPS device, analyzing it in combination with the emotion engine, and providing the location information in real time; means for analyzing vehicle dispatch problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting and analyzing past vehicle dispatch data, extracting trends and patterns, and providing advice. This enables quick and efficient responses that take customer emotions into consideration.

[1328] A "customer inquiry" is an act in which a customer requests information from the system.

[1329] A "natural language processing model" is a computer model for analyzing and understanding human language.

[1330] An "emotion engine" is a technology that identifies and analyzes emotions from input text or voice.

[1331] An "appropriate response" is accurate and useful information provided by the system in response to a customer inquiry.

[1332] A "dispatch schedule" refers to the operation plan for trucks and vehicles.

[1333] A "generative AI model" is a system that generates data and information using generative artificial intelligence algorithms.

[1334] "GPS Device" means a device for obtaining geographic location information.

[1335] "Real-time location information" refers to information that indicates a specific geographic location at the current time.

[1336] "Troubleshooting" is the process of resolving problems or issues that arise.

[1337] A "solution" is a specific response to a specific problem.

[1338] "Past vehicle dispatch data" refers to historical information regarding previous vehicle dispatches.

[1339] "Trends and patterns" refer to general trends or recurring characteristics found in the data.

[1340] "Advice" refers to advice or recommendations for a particular situation or problem.

[1341] This invention relates to a system that utilizes an emotion engine and generative AI models to optimize and streamline vehicle dispatch operations, demonstrating superior performance in responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[1342] First, when responding to a customer inquiry, the user makes a text-based inquiry from their device. The content of this inquiry is sent to the server, which analyzes it using a natural language processing model (e.g., GPT-4) and an emotion engine. For example, if a user types, "I want to know the current location of the delivery truck," the server understands the inquiry and the user's emotion, and provides a reassuring answer such as, "The truck is currently traveling on a major road, and we expect the delivery to be completed as scheduled."

[1343] Next, to optimize the vehicle dispatch schedule, the user sends a dispatch request from their device. For example, if they request "I would like delivery by Monday morning next week," the server receives this request and uses a generative AI model (e.g., OpenAI API) and an emotion engine to optimize truck availability, departure time, and route information. The optimized schedule is then provided to the user as a response such as, "We will dispatch a vehicle at 10 a.m. on Monday. Don't worry."

[1344] To provide truck location information, the user inquires about the current location from their device. For example, if they type "I want to know the current location of the truck," the server receives this request and obtains real-time location information from the GPS device. The server then analyzes the location information using an emotion engine and returns a reassuring response to the user, such as "The truck is currently traveling on a major street in the city. Don't worry."

[1345] Furthermore, for troubleshooting and support, users can report problems with dispatching from their terminals. For example, if a user reports that their delivery truck has stalled, the server will analyze the problem using a natural language processing model and an emotion engine, and provide the user with a solution that takes emotion into consideration, such as, "Would you like to contact the nearest repair shop? We will respond immediately."

[1346] Finally, for analyzing past ride-hailing data, the server periodically collects past data and analyzes it using a generative AI model and emotion engine. Based on the results of this analysis, the system provides advice to users, such as, "According to data from the past year, weekend ride-hailing requests are on the rise, so please plan your trip well in advance."

[1347] As described above, this invention enables efficient and highly accurate vehicle dispatching operations while taking into consideration the feelings of customers. By using this system, it is possible to improve the efficiency of vehicle dispatching operations, reduce human error, respond quickly to customers, and improve customer satisfaction.

[1348] Example prompt sentence:

[1349] "I want to know the current location of the delivery truck."

[1350] "I would like delivery next Monday morning."

[1351] "I want to know the current location of the truck."

[1352] "The delivery truck stalled."

[1353] "According to data from the past year"

[1354] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1355] Responding to customer inquiries

[1356] Step 1:

[1357] The user inputs the inquiry from the terminal.

[1358] Input: The user enters "I want to know the current location of the delivery truck" into the inquiry form on the terminal.

[1359] Operation: Enter the input content in text format and press the send button.

[1360] Step 2:

[1361] The device sends the input to the server.

[1362] Input: Enquiry ("I want to know the current location of the delivery truck").

[1363] Action: The device formats the input as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[1364] Step 3:

[1365] The server receives the query.

[1366] Input: HTTP request.

[1367] Operation: The server receives the request and extracts the inquiry as text data. Output: Text data ("I want to know the current location of the delivery truck").

[1368] Step 4:

[1369] The server analyzes the data using a natural language processing model and emotion engine.

[1370] Input: Text data of the inquiry.

[1371] How it works: The server uses a natural language processing model (e.g., GPT-4) to analyze the query content and also analyzes the user's emotions using an emotion engine. Output: Analysis results (understanding of the query content and emotions).

[1372] Step 5:

[1373] The server generates an answer based on the analysis results.

[1374] Input: Analysis results.

[1375] Action: The server generates a reassuring answer: "The truck is currently traveling on the main road and is expected to make the delivery on time." Output: The generated answer.

[1376] Step 6:

[1377] The server sends the response to the terminal.

[1378] Input: The generated answer.

[1379] Action: The server sends the answer to the device as an HTTP response. Output: The HTTP response received by the device.

[1380] Step 7:

[1381] The user receives the response at the terminal.

[1382] Input: HTTP response.

[1383] Action: The terminal displays the received answer and the user confirms it. Output: The user is relieved.

[1384] Vehicle scheduling optimization

[1385] Step 1:

[1386] The user inputs a ride request into the terminal.

[1387] Input: The user inputs "I would like delivery by Monday morning next week" into the terminal.

[1388] Operation: Enter the input content in text format and press the send button.

[1389] Step 2:

[1390] The device sends a request to the server.

[1391] Input: Ride request ("I'd like delivery next Monday morning").

[1392] Action: The device formats the request as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[1393] Step 3:

[1394] The server receives the request.

[1395] Input: HTTP request.

[1396] Operation: The server receives the request and extracts the request content as text data. Output: Text data ("Delivery requested by Monday morning next week").

[1397] Step 4:

[1398] The server optimizes the schedule using generative AI models and emotion engines.

[1399] Input: Text data of a ride request.

[1400] Action: The server uses generative AI models (e.g. OpenAI API) and emotion engines to optimize truck availability, departure times, and route information. Output: An optimized schedule.

[1401] Step 5:

[1402] The server generates an optimized schedule.

[1403] Input: Optimized schedule.

[1404] Operation: The server generates an optimal schedule with the message "The car will be dispatched at 10:00 AM on Monday. Don't worry." Output: The generated schedule answer.

[1405] Step 6:

[1406] The server sends the optimization schedule to the terminal.

[1407] Input: Generated schedule answers.

[1408] Operation: The server sends this schedule to the terminal as an HTTP response. Output: The HTTP response received by the terminal.

[1409] Step 7:

[1410] The user checks the schedule on the device.

[1411] Input: HTTP response.

[1412] Operation: The terminal displays the received schedule and the user confirms it. Output: The user feels reassured.

[1413] (Application example 2)

[1414] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1415] In food delivery services, responding to customer inquiries, optimizing delivery schedules, providing delivery personnel with location information, troubleshooting, and analyzing past delivery data are all important factors. However, conventional systems struggle to respond appropriately while taking customer emotions into account, limiting the improvement of customer satisfaction. Furthermore, it is difficult to centrally manage these factors and achieve efficient delivery operations. To address these challenges, this invention provides an advanced system that uses an emotion engine and a generative AI model.

[1416] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal dispatch schedule using a generative AI model; means for acquiring truck location information from a GPS device, providing the location information in real time, and providing information in a manner that takes user peace of mind into account; means for analyzing dispatch-related problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting past dispatch data, analyzing it using the generative AI model and an emotion engine, and extracting trends and patterns. This enables quick and appropriate responses that take customer emotions into account, thereby improving the efficiency of food delivery operations and customer satisfaction.

[1417] "Customer inquiries" refers to questions or requests made by customers through the food delivery service's application, such as checking delivery status or reporting problems.

[1418] "Natural language processing models" refer to the algorithms and techniques that computers use to understand and analyze human language.

[1419] "Emotion engine" refers to software or algorithms that analyze and recognize user emotions and are used to determine a user's emotional state through text or voice data.

[1420] An "appropriate response" means a response that contains the most appropriate and useful information based on the customer's inquiry and their feelings at the time.

[1421] "Truck availability" refers to information indicating whether a truck to be used for delivery is currently available.

[1422] "Departure time" refers to data indicating the scheduled time for delivery to begin.

[1423] "Route information" refers to information including the optimal route to the delivery destination and data on intermediate points.

[1424] A "generative AI model" refers to an algorithm or framework for generating new data or information using AI technology.

[1425] "Optimal vehicle dispatch schedule" refers to the most efficient and economical vehicle dispatch plan, taking into account the availability of each truck, departure time, route information, etc.

[1426] "GPS device" refers to equipment and technology used to obtain global location information.

[1427] "Providing location information in real time" means instantly obtaining current location information and providing it to customers on the spot.

[1428] "Providing information in a manner that takes into consideration the user's sense of security" refers to a method of providing information that aims to alleviate the user's emotions and anxiety, and includes messages that are intended to give the user a sense of security.

[1429] "Dispatch issues" refer to various troubles and problems related to delivery operations and truck operations.

[1430] "Solution generation" refers to the process of providing the most appropriate response or fix to an issue that has arisen.

[1431] "Historical Trip Data" refers to historical data relating to all trips ever made.

[1432] "Extracting trends and patterns" refers to the analytical process of finding patterns and commonalities from large amounts of data.

[1433] This invention is a system that aims to improve the efficiency and customer satisfaction of food delivery services. This system optimizes the management of vehicle dispatch operations by combining an emotion engine and a generative AI model.

[1434] Responding to customer inquiries

[1435] The user inputs a query using a terminal and sends it to the server. For example, a query such as "I would like to know the delivery status of the pizza I just ordered." The server receives this query and analyzes it using a natural language processing model (e.g., BERT) and an emotion engine (e.g., IBM Watson Tone Analyzer). The server generates an appropriate answer based on the query and replies to the user after taking their emotions into consideration. This allows the user to feel that their emotions are understood and gives them a sense of security.

[1436] Optimizing delivery schedules

[1437] A user sends a delivery request using a terminal. For example, they request, "I would like delivery tomorrow morning." The server receives this request and combines the generative AI model with the emotion engine to create an optimal delivery schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will deliver tomorrow at 10 a.m. Don't worry." In this way, by using the emotion engine, it is possible to provide a delivery schedule that takes into account the user's emotions.

[1438] Real-time delivery location information

[1439] The user sends a request from their device saying, "I want to know the current location of the delivery person." The server receives the request and analyzes the real-time location information obtained from the GPS device in combination with the emotion engine. For example, it provides the user with reassuring information such as, "The delivery person is currently traveling on a major road. Don't worry." This not only allows the user to check the delivery status in real time, but also gives them a sense of security.

[1440] Troubleshooting and Support

[1441] A user reports a delivery problem from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and emotion engine. They then provide the user with a solution that takes their emotions into account, such as "Would you like to contact your nearest repair shop? We will take care of it right away." In this way, using the emotion engine can ease the user's anxiety and enable a prompt response.

[1442] Analysis of past delivery data

[1443] The server periodically collects past delivery data from a database. The collected data is analyzed using a generative AI model and emotion engine to extract delivery trends and patterns. For example, the system provides advice to users such as, "According to data from the past year, weekend delivery requests are on the rise, so please plan your deliveries well in advance." This enables efficient planning of delivery operations.

[1444] Examples of prompt statements

[1445] Customer inquiry prompt:

[1446] input:

[1447] "I'd like to know the status of the delivery of the pizza I just ordered."

[1448] Prompt for delivery schedule optimization:

[1449] input:

[1450] "I would like delivery tomorrow morning."

[1451] In this way, by combining an emotion engine and a generative AI model, the system of the present invention effectively realizes customer service and delivery schedule optimization, real-time location information provision, troubleshooting, and historical data analysis in food delivery services, thereby improving customer satisfaction and streamlining operations.

[1452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1453] Step 1:

[1454] The terminal receives an inquiry from a customer. The customer uses the terminal to input and send an inquiry such as, "I'd like to know the delivery status of the pizza I just ordered." The input text data is then sent from the terminal to the server.

[1455] Step 2:

[1456] The server receives the customer's inquiry. The server uses a natural language processing model (e.g., BERT) to analyze the received inquiry. The BERT model is used to extract the intent of the inquiry and determine the appropriate action accordingly. In this process, the input text data is analyzed to identify the type and content of the inquiry.

[1457] Step 3:

[1458] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the content of the customer's inquiry. The analysis results provide information to determine the customer's emotional state. Specifically, it analyzes text data and outputs the customer's emotional state, such as whether they are feeling stressed or relieved.

[1459] Step 4:

[1460] The server generates an appropriate response based on the content of the inquiry and the results of sentiment analysis. A generative AI model is used to create a response that takes into account the customer's emotions. For example, a response that provides reassuring information such as, "The delivery person is currently driving on a major road. Don't worry," is generated. Here, a response text is generated based on the analysis results and sent back from the server to the device.

[1461] Step 5:

[1462] The server collects truck availability, departure times, and route information, and uses a generative AI model to create an optimal delivery schedule. Specifically, this information is passed as input to the system, and the generative AI model calculates the optimal schedule by taking various factors into account. The output includes the delivery schedule and the reasons for it.

[1463] Step 6:

[1464] The server obtains the truck's real-time location information from the GPS device. The obtained location information is quickly transmitted to the server. The emotion engine then processes the information in a way that increases the user's sense of security. The output is a description of the delivery situation, such as "The delivery person is currently driving on a major road. Don't worry."

[1465] Step 7:

[1466] When a user reports a delivery problem to the server, the server analyzes the problem using a natural language processing model and an emotion engine. For example, if a user reports that "the delivery truck stalled," the server analyzes the report and generates a proposal that takes into account specific solutions, such as contacting the nearest repair shop. The output is a proposal such as "Would you like to contact the nearest repair shop? We will respond immediately."

[1467] Step 8:

[1468] The server periodically collects past dispatch data from a database and analyzes it using a generative AI model and emotion engine. This analysis extracts delivery trends and patterns. For example, it can input data from the past year and output trends such as "weekend delivery requests are on the rise." Advice based on the analysis results is provided to the user.

[1469] Through the above processing steps, the system of the present invention realizes improved efficiency in food delivery operations and increased customer satisfaction.

[1470] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1471] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1472] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1473] [Fourth embodiment]

[1474] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1475] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1476] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1477] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1478] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1479] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1480] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1481] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1482] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1483] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1484] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1485] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1486] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1487] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[1488] Responding to customer inquiries

[1489] The user uses a terminal to input a text-based inquiry about dispatching a vehicle. For example, the user might input a query such as "I would like to check tomorrow's delivery status." The server receives this query and analyzes it using a natural language processing model. The server then generates an answer and sends it back to the user's terminal, replying, "Delivery is scheduled for tomorrow at 2:00 PM."

[1490] Vehicle scheduling optimization

[1491] The user sends a delivery request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The server receives the request and retrieves truck availability, past schedules, departure times, and routes from a database. The server then uses a generative AI model to create an optimal delivery schedule and notifies the user, "A delivery will be made at 10:00 AM on Monday."

[1492] Providing truck location information

[1493] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives this request and obtains real-time location information from the GPS device installed in the truck. For example, it provides the user with information such as, "The truck is currently traveling on a major street in the city."

[1494] Troubleshooting and Support

[1495] A user reports a problem with a delivery from their device. For example, they send a report saying, "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model. It generates a solution, such as "Contact the nearest repair shop?", and provides it to the user.

[1496] Analysis of past dispatch data

[1497] The server periodically collects past dispatch data from the database. The collected data is passed to the generative AI model for analysis. For example, from dispatch data from the past year, the server may discover a trend that "weekend dispatch requests are on the rise." The server then creates a report of these results and provides it to the user. Based on this, the user can formulate future dispatch plans.

[1498] As described above, the system of the present invention uses generative AI models and natural language processing models to achieve a wide range of functions, including responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data. This enables more efficient dispatch work, reduces human error, provides faster customer service, and improves customer satisfaction.

[1499] The processing flow will be explained below.

[1500] Responding to customer inquiries

[1501] Step 1:

[1502] The user uses the terminal to input and send the inquiry.

[1503] Step 2:

[1504] The server receives the query and passes it to a natural language processing model.

[1505] Step 3:

[1506] The server analyzes the content of the query using a natural language processing model.

[1507] Step 4:

[1508] The server generates an appropriate answer based on the analysis results.

[1509] Step 5:

[1510] The server generates a response and sends it back to the user's terminal.

[1511] Step 6:

[1512] The user checks the answer on the device.

[1513] Vehicle scheduling optimization

[1514] Step 1:

[1515] The user sends a request for a ride through the terminal.

[1516] Step 2:

[1517] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[1518] Step 3:

[1519] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[1520] Step 4:

[1521] The server transmits the optimized vehicle dispatch schedule to the user's terminal.

[1522] Step 5:

[1523] The user checks the dispatch schedule on the terminal.

[1524] Providing truck location information

[1525] Step 1:

[1526] The user sends a request for truck location information from the terminal.

[1527] Step 2:

[1528] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[1529] Step 3:

[1530] The server analyzes the location information and determines the current location of the truck.

[1531] Step 4:

[1532] The server sends real-time updated location information to the user's device.

[1533] Step 5:

[1534] The user checks the real-time location information on the device.

[1535] Troubleshooting and Support

[1536] Step 1:

[1537] A user reports a problem with a ride from their device.

[1538] Step 2:

[1539] A server receives the report and uses natural language processing models to analyze the problem.

[1540] Step 3:

[1541] The server generates an appropriate solution based on the analysis results.

[1542] Step 4:

[1543] The server sends the generated solution to the user's terminal.

[1544] Step 5:

[1545] The user checks the solution on the device and takes appropriate action.

[1546] Analysis of past dispatch data

[1547] Step 1:

[1548] The server periodically collects past dispatch data from the database.

[1549] Step 2:

[1550] The server passes the collected data to a generative AI model for analysis.

[1551] Step 3:

[1552] The server extracts trends and patterns based on the analysis results of the generated AI model.

[1553] Step 4:

[1554] The server creates a report of the results obtained and sends it to the user's terminal.

[1555] Step 5:

[1556] Users can review the reports and use them to plan future vehicle dispatches.

[1557] Example 1

[1558] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1559] Modern dispatch operations require efficient customer service, optimized schedules, real-time location information, fast troubleshooting, and historical data analysis. However, there is no system in place to consistently and efficiently accomplish these tasks. Most companies perform these processes manually, which is prone to human error and slow response times.

[1560] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1561] In this invention, the server includes a means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, a means for inputting vehicle availability, departure times, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model, and a means for acquiring vehicle location information from a positioning device and providing the location information in real time, thereby enabling more efficient dispatch arrangement work, reducing human error, and providing faster customer responses.

[1562] "Customer inquiries" are actions in which a user inputs questions or requests regarding vehicle dispatch in text format and sends them to the system.

[1563] A "natural language processing model" is a type of artificial intelligence technology for understanding and analyzing text data and generating appropriate responses.

[1564] A "generative AI model" is an artificial intelligence method for generating new information and optimal schedules based on input data.

[1565] "Vehicle availability" refers to the status and availability of vehicles available for dispatch during a specific time period.

[1566] The "departure time" is the specific time when a vehicle departs from a specified location during a vehicle dispatch operation.

[1567] "Route information" is data relating to the route that a vehicle will take to travel to the delivery destination.

[1568] A "positioning device" is a device that uses satellites to determine the current location of a vehicle.

[1569] "Location information" is data that indicates the current location of a vehicle.

[1570] "Dispatch issues" refers to reports of troubles or trivialities that arise during the dispatch process.

[1571] "Past dispatch data" is a data set that includes the history of past dispatch operations, schedules, and other related information.

[1572] "Trends and patterns" refer to specific movements or regularities found in past data.

[1573] The present invention relates to a system for optimizing and streamlining vehicle dispatch operations. This system has a wide range of functions, such as responding to customer inquiries, optimizing dispatch schedules, providing vehicle location information, troubleshooting, and analyzing past dispatch data.

[1574] Responding to customer inquiries

[1575] The user uses the device to input a text-based inquiry about dispatching a vehicle. For example, the user might input, "I'd like to check tomorrow's delivery status." The device then sends this text data to the server. The server then passes the received inquiry to a natural language processing model (e.g., natural language processing AI) for analysis. The server then sends the generated answer back to the user's device, which then displays to the user, "Delivery is scheduled for tomorrow at 2:00 PM."

[1576] Vehicle scheduling optimization

[1577] The user sends a vehicle dispatch request through their terminal. For example, they input information such as "I would like delivery by Monday morning next week." The terminal then sends this request data to the server. The server receives the request and retrieves vehicle availability, past schedules, departure times, and routes from a database (e.g., a relational database management system). This information is passed to a generative AI model (e.g., an AI generation model) to generate an optimal vehicle dispatch schedule. The generated vehicle dispatch schedule is then sent to the user's terminal, which displays "A vehicle will be dispatched at 10:00 AM on Monday."

[1578] Providing vehicle location information

[1579] The user sends a request from the device saying, "I want to know the current location of the vehicle." The device then sends this request to the server. The server receives the request and obtains real-time location information from a positioning device (e.g., a GPS device). The server then sends the obtained location information to the user's device. The device then displays to the user, "The vehicle is currently traveling on a major street in the city."

[1580] Troubleshooting and Support

[1581] The user reports a problem with a delivery vehicle from their device. For example, they report that "the delivery vehicle has stalled." The device sends this report to the server. The server receives the report and analyzes the problem using a natural language processing model (e.g., natural language processing AI). The server then generates a solution based on the analysis results and sends it to the user's device. The device then displays a message to the user asking, "Would you like to contact the nearest repair shop?"

[1582] Analysis of past dispatch data

[1583] The server periodically collects past dispatch data from a database (e.g., a relational database management system). The collected data is passed to a generative AI model (e.g., an AI-generated model) for analysis. For example, from dispatch data from the past year, a trend may be discovered that "weekend dispatch requests are on the rise." The results are compiled in a report format and provided to the user. The user can use this information to formulate future dispatch plans.

[1584] Examples and prompts

[1585] Here are some examples of specific prompts:

[1586] 1. Customer Inquiry Response:

[1587] User input prompt: "Please let me know the status of tomorrow's delivery."

[1588] Server-generated response: "Estimated delivery time is tomorrow at 2 PM."

[1589] 2. Vehicle scheduling optimization:

[1590] User input prompt: "I would like delivery by next Monday morning."

[1591] Server notification: "Your ride will arrive at 10 AM on Monday."

[1592] 3. Vehicle location information provision:

[1593] User input prompt: "What is the current vehicle location?"

[1594] Server response: "The vehicle is currently traveling on a major city street."

[1595] 4. Troubleshooting and Support:

[1596] User input prompt: "My delivery vehicle has stalled. What should I do?"

[1597] Server offers solution: "Would you like to contact your local repair shop?"

[1598] 5. Analysis of historical trip data:

[1599] Server internal process prompt (runs weekly): "Analyze the past year's dispatch data and report the trends."

[1600] Server generates report: "We're seeing an increase in weekend ride requests."

[1601] Using these functions, the system of the present invention can improve the efficiency of vehicle dispatch arrangement work, reduce human errors, and provide quick customer service.

[1602] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1603] Responding to customer inquiries

[1604] Step 1:

[1605] A user uses a terminal to input a text-based inquiry about dispatching. For example, the user inputs an inquiry such as "I would like to check tomorrow's delivery status." This input is sent to the server as text data by the terminal (input: user's inquiry text, output: text data sent to the server).

[1606] Step 2:

[1607] The server passes the received query to a natural language processing model. Specifically, the server calls the natural language processing model (e.g., natural language processing AI) and has it analyze the text data (input: query text from the user, data processing: text analysis, output: analysis results).

[1608] Step 3:

[1609] The server returns the generated answer to the user's device. Specifically, it sends the analysis results to the device, which then displays them to the user (input: analysis results, output: display of answer on device). For example, it displays "Expected delivery time is tomorrow at 2:00 PM."

[1610] Vehicle scheduling optimization

[1611] Step 1:

[1612] The user sends a request for a ride from the terminal. For example, the user enters "I would like delivery by Monday morning next week." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[1613] Step 2:

[1614] The server receives the request and retrieves information from the database. Specifically, the server retrieves vehicle availability, departure time, and route information from a relational database management system (input: database query, data processing: data extraction, output: vehicle information).

[1615] Step 3:

[1616] The server passes the extracted information to a generative AI model, which then generates an optimal vehicle dispatch schedule based on this information (input: vehicle information, data calculation: vehicle dispatch schedule generation, output: optimal vehicle dispatch schedule).

[1617] Step 4:

[1618] The server sends the generated vehicle dispatch schedule to the user's terminal, which displays it (input: optimal vehicle dispatch schedule, output: schedule notification displayed on terminal). For example, it displays "Vehicle dispatch will be at 10:00 AM on Monday."

[1619] Providing vehicle location information

[1620] Step 1:

[1621] The user sends a request from the terminal saying, "I want to know the current location of the vehicle." This request is sent to the server by the terminal (input: user's request text, output: request data sent to the server).

[1622] Step 2:

[1623] The server receives the request and retrieves real-time location information from the positioning device. Specifically, the server retrieves location information from the GPS device (input: GPS device data request, data processing: location information retrieval, output: real-time location information).

[1624] Step 3:

[1625] The server sends the acquired location information to the user's device, which then displays it to the user (input: real-time location information, output: display of location information on device). For example, it displays "The vehicle is currently traveling on a major street in the city."

[1626] Troubleshooting and Support

[1627] Step 1:

[1628] A user reports a problem with a delivery vehicle from a terminal. For example, the user reports that "the delivery vehicle has stalled." This report is sent to the server by the terminal (input: user's problem report text, output: report data sent to the server).

[1629] Step 2:

[1630] The server receives the report and analyzes the problem using a natural language processing model. Specifically, the server analyzes the problem text data using a natural language processing model (input: problem report text, data processing: text analysis, output: analysis results).

[1631] Step 3:

[1632] The server generates a solution based on the analysis results and sends it to the user's device. The device displays it to the user (input: solution data, output: solution display on device). For example, it displays "Would you like to contact the nearest repair shop?"

[1633] Analysis of past dispatch data

[1634] Step 1:

[1635] The server periodically collects past dispatch data from the database. Specifically, the server extracts data from the relational database management system (input: database query, data processing: data extraction, output: past dataset).

[1636] Step 2:

[1637] The server passes the collected data to the generative AI model for analysis. The generative AI model analyzes the data and extracts specific trends and patterns (input: past data sets, data calculation: data analysis, output: trends and patterns).

[1638] Step 3:

[1639] The server compiles the analysis results into a report and provides it to the user. Specifically, it creates a report and sends it to the terminal, which then displays it to the user (input: analysis results, output: report display). For example, it might display something like, "There is a trend of increasing requests for car dispatches on weekends."

[1640] Based on the above steps, the system of the present invention efficiently and effectively supports vehicle dispatch operations.

[1641] (Application example 1)

[1642] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1643] Modern food delivery technology requires efficient delivery schedule generation, real-time location information, rapid response to customer inquiries, and rapid solutions when problems arise. However, existing systems struggle to provide these functions in an integrated manner. Furthermore, they lack a mechanism for effectively utilizing past delivery data to improve future operations. Therefore, developing an effective system that improves the efficiency of food delivery operations and customer satisfaction is a challenge.

[1644] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1645] In this invention, the server includes means for receiving inquiries from customers, analyzing them using a natural language processing model, and generating appropriate responses, means for inputting delivery availability, departure times, and route information, and creating an optimal delivery schedule using a generative AI model, means for acquiring delivery vehicle location information from a GPS device and providing the location information in real time, means for analyzing delivery-related issues using a natural language processing model and generating solutions, means for collecting and analyzing past delivery data and extracting trends and patterns, means for customers to input text-based food delivery inquiries and generating appropriate responses, means for checking available delivery personnel based on delivery requests and generating an optimal delivery schedule, means for providing driver GPS data to customers in real time, means for analyzing issues reported by delivery drivers and proposing solutions, and means for periodically analyzing delivery data and generating valuable insights. This enables efficiency improvements in food delivery operations, provision of real-time location information, rapid customer response, early resolution of problems when they occur, and effective use of past data.

[1646] "Customer" means any person or entity that uses the food delivery service.

[1647] An "Inquiry" is a question or request from a Customer seeking information or support related to food delivery.

[1648] A "natural language processing model" is an artificial intelligence technology for understanding, analyzing, and generating responses to human language.

[1649] "Delivery services" refers to the general business of delivering food and other products ordered by customers to designated locations.

[1650] "Delivery Schedule" refers to the planned delivery time slots and sequence to optimize delivery operations.

[1651] A "generative AI model" is an artificial intelligence technology that uses underlying data and algorithms to automatically perform specific tasks.

[1652] "Departure time" refers to the time when the delivery person begins delivery from the designated departure point.

[1653] "Route information" refers to information about the route or path that a delivery vehicle will take to reach a designated delivery point.

[1654] A "GPS device" is a device that uses satellites to obtain location information in real time.

[1655] A "delivery vehicle" is a vehicle such as a car, motorcycle, or bicycle used to perform delivery operations.

[1656] "Real-time" refers to the time between when information is acquired and when it is processed with minimal delay.

[1657] "Location information" means information indicating the current geographic location of a vehicle or item as determined by a GPS device.

[1658] "Problem" refers to an unexpected event or obstacle that occurs in the delivery process.

[1659] A "solution" is a specific method or means for solving the problem that has occurred.

[1660] "Historical Delivery Data" means all records and information relating to previous delivery transactions.

[1661] A "trend or pattern" is a consistent movement or recurring feature observed in historical data.

[1662] "Delivery Request" means a request that includes details of the Customer's desired delivery (e.g., date, time, location, etc.).

[1663] A "delivery person" is a person whose role is to deliver customer orders to a specified location.

[1664] "Insights" refers to useful discoveries and knowledge gained through data analysis.

[1665] This invention is a system aimed at improving the efficiency of food delivery operations and customer satisfaction. This system includes a wide range of functions, such as responding to customer inquiries, generating optimal delivery schedules, providing real-time location information, troubleshooting, and analyzing past data. These functions are realized using generative AI models and natural language processing models.

[1666] The system includes the following means:

[1667] 1. Customer inquiry response methods:

[1668] The server receives inquiries about food delivery entered by users through their devices and analyzes the inquiries using a natural language processing model. Based on the analysis results, it generates an appropriate answer and sends it back to the user's device. For example, if a user inquires, "I want to know the status of my order," the server generates the answer, "The delivery is currently on its way and is expected to arrive in 15 minutes."

[1669] 2. Delivery schedule optimization measures:

[1670] When a user submits their desired delivery time, departure time, and route information, the server uses a generative AI model to automatically generate an optimal delivery schedule based on available delivery staff. For example, if a user requests delivery at 10 a.m., the server will notify them that the delivery will be made at the specified time.

[1671] 3. Real-time location information provision methods:

[1672] If a user wants to know the current location of a delivery person, the server uses a GPS device to obtain real-time location information of the delivery vehicle and provides it to the user. For example, the server may provide information such as, "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[1673] 4. Troubleshooting methods:

[1674] If a delivery driver reports a problem during a delivery, the server uses natural language processing models to analyze the problem and suggest a solution. For example, if a driver reports that their bike has stalled, the server might suggest, "Would you like to contact the nearest repair shop?"

[1675] 5. How to analyze past delivery data:

[1676] The server periodically collects past delivery data and inputs it into a generative AI model for analysis. This allows trends and patterns in delivery operations to be extracted and used to improve operations in the future. For example, a trend such as "orders increase on weekend nights" could be extracted from data from the past year, and delivery schedules could be adjusted based on this result.

[1677] Specific examples

[1678] Responding to customer inquiries

[1679] When a user asks "What's the status of my order?":

[1680] Customer: "I want to know the status of my order."

[1681] System: "Delivery is currently on its way. Expected arrival in 15 minutes."

[1682] Optimizing delivery schedules

[1683] If a user requests delivery at 10:00 AM, the server generates an optimal delivery schedule based on information about available delivery staff.

[1684] Real-time location information

[1685] When a user requests the current location of a delivery person, the server uses a GPS device to provide real-time location information, such as "The delivery person is currently traveling on a major road and is expected to arrive in 10 minutes."

[1686] troubleshooting

[1687] If a delivery driver reports that their bike has stalled, the system will suggest, "Would you like to contact the nearest repair shop?"

[1688] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1689] Step 1:

[1690] Receiving and analyzing customer inquiries

[1691] A user inputs a text-based inquiry about food delivery through a terminal. The input text is sent to the server, which receives it. The received text is analyzed using a natural language processing model to understand the content of the inquiry. For example, if a user inputs the inquiry "I want to know the status of my order," the server analyzes this text and understands that the user is requesting information about the current status of the order.

[1692] Input: The query text sent by the user from the terminal

[1693] Output: Analysis result of inquiry (e.g. "I want to know the status of my order")

[1694] Step 2:

[1695] Generating the right answers

[1696] The server uses a generative AI model to generate an appropriate response based on the analyzed inquiry. For example, in response to an inquiry such as "I want to know the status of my order," the server generates a response such as "It's currently on its way and is expected to arrive in 15 minutes." This response is then sent back to the user's device and provided in real time.

[1697] Input: Analysis result of inquiry content

[1698] Output: The generated answer (e.g., "The delivery is currently on its way and should arrive in 15 minutes.")

[1699] Step 3:

[1700] Optimizing delivery schedules

[1701] The user inputs the desired delivery time and other conditions and sends them from the device to the server. The server uses a generative AI model to generate an optimal delivery schedule, taking into account the availability of delivery services, departure times, and route information. For example, if a user requests delivery at 10:00 a.m., the server checks the available delivery personnel and proposes the optimal schedule.

[1702] Input: User-entered desired delivery time, delivery request

[1703] Output: Optimized delivery schedule (e.g. "Deliver at 10 AM")

[1704] Step 4:

[1705] Providing real-time location information

[1706] The user sends a request from their device to find out the current location of the delivery person. The server uses a GPS device to obtain the real-time location information of the delivery vehicle and provides that information to the user. For example, the server may notify the user that "The delivery person is currently driving on a major road and is expected to arrive in 10 minutes."

[1707] Input: User location request

[1708] Output: Real-time location information (e.g. "The delivery person is currently driving on a major road. They are expected to arrive in 10 minutes.")

[1709] Step 5:

[1710] troubleshooting

[1711] A delivery driver reports a problem during a delivery. For example, if the driver reports that their bike has stalled, the information is sent from the device to the server. The server uses a natural language processing model to analyze the problem and propose a solution. The server generates a solution, such as "Should we contact the nearest repair shop?" and notifies the delivery driver.

[1712] Input: Driver problem report

[1713] Output: Proposed solution (e.g., "Contact your local repair shop?")

[1714] Step 6:

[1715] Analysis of past delivery data

[1716] The server periodically collects past delivery data from a database and passes it to the generative AI model for analysis. From the results of this analysis, trends and patterns in delivery operations can be extracted. For example, the server can extract trends such as "orders increase on weekend nights" and use this as a focus point for adjusting future delivery schedules.

[1717] Input: Past delivery data

[1718] Output: Extracted trends and patterns (e.g., "Orders increase on weekend nights")

[1719] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1720] This invention relates to a system that further improves the optimization and efficiency of vehicle dispatching operations by combining an emotion engine. This system not only handles customer inquiries, optimizes dispatch schedules, provides truck location information, troubleshoots, and analyzes past dispatch data, but also recognizes user emotions and responds appropriately.

[1721] Responding to customer inquiries

[1722] The user inputs and sends a text-based inquiry using a terminal. For example, a query such as "I want to know the current location of the delivery truck." The server receives this inquiry and analyzes it using a natural language processing model and emotion engine. The server understands not only the content of the inquiry but also the user's emotions, and returns an appropriate response such as "The truck is currently traveling on a major road and is expected to make its delivery as scheduled."

[1723] Vehicle scheduling optimization

[1724] The user sends a dispatch request using a terminal. For example, they request, "I would like delivery by Monday morning next week." The server receives this request and combines the generative AI model with an emotion engine to create an optimal dispatch schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will dispatch the vehicle at 10 a.m. on Monday. Don't worry."

[1725] Providing truck location information

[1726] The user sends a request from their device saying, "I want to know the current location of the truck." The server receives the request and analyzes it by combining real-time location information obtained from the GPS device with the emotion engine. For example, it provides the user with reassuring information such as, "The truck is currently traveling on a major street in the city. Don't worry."

[1727] Troubleshooting and Support

[1728] The user reports a problem with a delivery vehicle from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and an emotion engine. It then provides the user with a solution that takes emotion into account, such as "Would you like to contact the nearest repair shop? We will respond immediately."

[1729] Analysis of past dispatch data

[1730] The server periodically collects past dispatch data from a database. The collected data is analyzed using a generative AI model and an emotion engine to extract trends and patterns. For example, it provides advice to users such as, "According to data from the past year, weekend dispatch requests are on the rise, so please plan your trip well in advance."

[1731] The system of the present invention combines functions such as responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past data with an emotion engine to realize a more advanced and efficient dispatch operation that can also respond to user emotions. This will improve the efficiency of dispatch operations, reduce human error, provide quicker customer service, and improve customer satisfaction.

[1732] The processing flow will be explained below.

[1733] Responding to customer inquiries

[1734] Step 1:

[1735] The user uses the terminal to input and send the inquiry.

[1736] Step 2:

[1737] The server receives the query and passes it to a natural language processing model.

[1738] Step 3:

[1739] The server analyzes the content of the query using a natural language processing model.

[1740] Step 4:

[1741] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[1742] Step 5:

[1743] The server generates an appropriate answer based on the results of the emotion engine and analysis.

[1744] Step 6:

[1745] The server generates a response and sends it back to the user's terminal.

[1746] Step 7:

[1747] The user checks the answer on the device.

[1748] Vehicle scheduling optimization

[1749] Step 1:

[1750] The user sends a request for a ride through the terminal.

[1751] Step 2:

[1752] The server receives the request and retrieves truck availability, departure times, and route information from a database.

[1753] Step 3:

[1754] The server uses the generative AI model to create an optimal vehicle dispatch schedule.

[1755] Step 4:

[1756] The vehicle dispatch schedule created by the server is passed to the emotion engine to recognize the user's emotions.

[1757] Step 5:

[1758] The server considers the results of the emotion engine and generates emotion-sensitive notifications along with optimized vehicle dispatch schedules.

[1759] Step 6:

[1760] The server sends the notification to the user's device.

[1761] Step 7:

[1762] The user checks the ride schedule and notifications on the device.

[1763] Providing truck location information

[1764] Step 1:

[1765] The user sends a request for truck location information from the terminal.

[1766] Step 2:

[1767] The server receives the request and retrieves the location information from the GPS device installed in the truck.

[1768] Step 3:

[1769] The server analyzes the location information obtained.

[1770] Step 4:

[1771] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[1772] Step 5:

[1773] The server takes into account the results of the emotion engine and generates appropriate location information.

[1774] Step 6:

[1775] The server transmits the generated location information to the user's device.

[1776] Step 7:

[1777] The user checks the real-time location information on the device.

[1778] Troubleshooting and Support

[1779] Step 1:

[1780] A user reports a problem with a ride from their device.

[1781] Step 2:

[1782] A server receives the report and uses natural language processing models to analyze the problem.

[1783] Step 3:

[1784] The server passes the analysis results to the emotion engine to recognize the user's emotions.

[1785] Step 4:

[1786] The server uses the generative AI model to generate an appropriate solution.

[1787] Step 5:

[1788] The server considers the results of the emotion engine and provides a solution to the user.

[1789] Step 6:

[1790] The server sends the generated solution to the user's terminal.

[1791] Step 7:

[1792] The user checks the solution on the device and takes appropriate action.

[1793] Analysis of past dispatch data

[1794] Step 1:

[1795] The server periodically collects past dispatch data from the database.

[1796] Step 2:

[1797] The server passes the collected data to a generative AI model for analysis.

[1798] Step 3:

[1799] The server passes the analysis results to the emotion engine, which extracts trends and patterns.

[1800] Step 4:

[1801] The server generates an appropriate report based on the results obtained.

[1802] Step 5:

[1803] The server considers the results of the emotion engine and generates an emotion-sensitive report.

[1804] Step 6:

[1805] The server sends the generated report to the user's terminal.

[1806] Step 7:

[1807] Users can review the reports and use them to plan future vehicle dispatches.

[1808] Example 2

[1809] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1810] Conventional vehicle dispatch systems have problems such as delays in response and human error when responding to customer inquiries, optimizing truck dispatch schedules, providing location information, troubleshooting, analyzing past data, etc. Furthermore, they lack the ability to respond to customer emotions, making it difficult to improve customer satisfaction.

[1811] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal vehicle dispatch schedule using a generative AI model and an emotion engine; means for acquiring truck location information from a GPS device, analyzing it in combination with the emotion engine, and providing the location information in real time; means for analyzing vehicle dispatch problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting and analyzing past vehicle dispatch data, extracting trends and patterns, and providing advice. This enables quick and efficient responses that take customer emotions into consideration.

[1812] A "customer inquiry" is an act in which a customer requests information from the system.

[1813] A "natural language processing model" is a computer model for analyzing and understanding human language.

[1814] An "emotion engine" is a technology that identifies and analyzes emotions from input text or voice.

[1815] An "appropriate response" is accurate and useful information provided by the system in response to a customer inquiry.

[1816] A "dispatch schedule" refers to the operation plan for trucks and vehicles.

[1817] A "generative AI model" is a system that generates data and information using generative artificial intelligence algorithms.

[1818] "GPS Device" means a device for obtaining geographic location information.

[1819] "Real-time location information" refers to information that indicates a specific geographic location at the current time.

[1820] "Troubleshooting" is the process of resolving problems or issues that arise.

[1821] A "solution" is a specific response to a specific problem.

[1822] "Past vehicle dispatch data" refers to historical information regarding previous vehicle dispatches.

[1823] "Trends and patterns" refer to general trends or recurring characteristics found in the data.

[1824] "Advice" refers to advice or recommendations for a particular situation or problem.

[1825] This invention relates to a system that utilizes an emotion engine and generative AI models to optimize and streamline vehicle dispatch operations, demonstrating superior performance in responding to customer inquiries, optimizing dispatch schedules, providing truck location information, troubleshooting, and analyzing past dispatch data.

[1826] First, when responding to a customer inquiry, the user makes a text-based inquiry from their device. The content of this inquiry is sent to the server, which analyzes it using a natural language processing model (e.g., GPT-4) and an emotion engine. For example, if a user types, "I want to know the current location of the delivery truck," the server understands the inquiry and the user's emotion, and provides a reassuring answer such as, "The truck is currently traveling on a major road, and we expect the delivery to be completed as scheduled."

[1827] Next, to optimize the vehicle dispatch schedule, the user sends a dispatch request from their device. For example, if they request "I would like delivery by Monday morning next week," the server receives this request and uses a generative AI model (e.g., OpenAI API) and an emotion engine to optimize truck availability, departure time, and route information. The optimized schedule is then provided to the user as a response such as, "We will dispatch a vehicle at 10 a.m. on Monday. Don't worry."

[1828] To provide truck location information, the user inquires about the current location from their device. For example, if they type "I want to know the current location of the truck," the server receives this request and obtains real-time location information from the GPS device. The server then analyzes the location information using an emotion engine and returns a reassuring response to the user, such as "The truck is currently traveling on a major street in the city. Don't worry."

[1829] Furthermore, for troubleshooting and support, users can report problems with dispatching from their terminals. For example, if a user reports that their delivery truck has stalled, the server will analyze the problem using a natural language processing model and an emotion engine, and provide the user with a solution that takes emotion into consideration, such as, "Would you like to contact the nearest repair shop? We will respond immediately."

[1830] Finally, for analyzing past ride-hailing data, the server periodically collects past data and analyzes it using a generative AI model and emotion engine. Based on the results of this analysis, the system provides advice to users, such as, "According to data from the past year, weekend ride-hailing requests are on the rise, so please plan your trip well in advance."

[1831] As described above, this invention enables efficient and highly accurate vehicle dispatching operations while taking into consideration the feelings of customers. By using this system, it is possible to improve the efficiency of vehicle dispatching operations, reduce human error, respond quickly to customers, and improve customer satisfaction.

[1832] Example prompt sentence:

[1833] "I want to know the current location of the delivery truck."

[1834] "I would like delivery next Monday morning."

[1835] "I want to know the current location of the truck."

[1836] "The delivery truck stalled."

[1837] "According to data from the past year"

[1838] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1839] Responding to customer inquiries

[1840] Step 1:

[1841] The user inputs the inquiry from the terminal.

[1842] Input: The user enters "I want to know the current location of the delivery truck" into the inquiry form on the terminal.

[1843] Operation: Enter the input content in text format and press the send button.

[1844] Step 2:

[1845] The device sends the input to the server.

[1846] Input: Enquiry ("I want to know the current location of the delivery truck").

[1847] Action: The device formats the input as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[1848] Step 3:

[1849] The server receives the query.

[1850] Input: HTTP request.

[1851] Operation: The server receives the request and extracts the inquiry as text data. Output: Text data ("I want to know the current location of the delivery truck").

[1852] Step 4:

[1853] The server analyzes the data using a natural language processing model and emotion engine.

[1854] Input: Text data of the inquiry.

[1855] How it works: The server uses a natural language processing model (e.g., GPT-4) to analyze the query content and also analyzes the user's emotions using an emotion engine. Output: Analysis results (understanding of the query content and emotions).

[1856] Step 5:

[1857] The server generates an answer based on the analysis results.

[1858] Input: Analysis results.

[1859] Action: The server generates a reassuring answer: "The truck is currently traveling on the main road and is expected to make the delivery on time." Output: The generated answer.

[1860] Step 6:

[1861] The server sends the response to the terminal.

[1862] Input: The generated answer.

[1863] Action: The server sends the answer to the device as an HTTP response. Output: The HTTP response received by the device.

[1864] Step 7:

[1865] The user receives the response at the terminal.

[1866] Input: HTTP response.

[1867] Action: The terminal displays the received answer and the user confirms it. Output: The user is relieved.

[1868] Vehicle scheduling optimization

[1869] Step 1:

[1870] The user inputs a ride request into the terminal.

[1871] Input: The user inputs "I would like delivery by Monday morning next week" into the terminal.

[1872] Operation: Enter the input content in text format and press the send button.

[1873] Step 2:

[1874] The device sends a request to the server.

[1875] Input: Ride request ("I'd like delivery next Monday morning").

[1876] Action: The device formats the request as an HTTP request and sends it to the specified endpoint on the server. Output: The HTTP request received by the server.

[1877] Step 3:

[1878] The server receives the request.

[1879] Input: HTTP request.

[1880] Operation: The server receives the request and extracts the request content as text data. Output: Text data ("Delivery requested by Monday morning next week").

[1881] Step 4:

[1882] The server optimizes the schedule using generative AI models and emotion engines.

[1883] Input: Text data of a ride request.

[1884] Action: The server uses generative AI models (e.g. OpenAI API) and emotion engines to optimize truck availability, departure times, and route information. Output: An optimized schedule.

[1885] Step 5:

[1886] The server generates an optimized schedule.

[1887] Input: Optimized schedule.

[1888] Operation: The server generates an optimal schedule with the message "The car will be dispatched at 10:00 AM on Monday. Don't worry." Output: The generated schedule answer.

[1889] Step 6:

[1890] The server sends the optimization schedule to the terminal.

[1891] Input: Generated schedule answers.

[1892] Operation: The server sends this schedule to the terminal as an HTTP response. Output: The HTTP response received by the terminal.

[1893] Step 7:

[1894] The user checks the schedule on the device.

[1895] Input: HTTP response.

[1896] Operation: The terminal displays the received schedule and the user confirms it. Output: The user feels reassured.

[1897] (Application example 2)

[1898] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1899] In food delivery services, responding to customer inquiries, optimizing delivery schedules, providing delivery personnel with location information, troubleshooting, and analyzing past delivery data are all important factors. However, conventional systems struggle to respond appropriately while taking customer emotions into account, limiting the improvement of customer satisfaction. Furthermore, it is difficult to centrally manage these factors and achieve efficient delivery operations. To address these challenges, this invention provides an advanced system that uses an emotion engine and a generative AI model.

[1900] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving inquiries from customers, analyzing them using a natural language processing model and an emotion engine, and generating an appropriate response; means for inputting truck availability, departure time, and route information, and creating an optimal dispatch schedule using a generative AI model; means for acquiring truck location information from a GPS device, providing the location information in real time, and providing information in a manner that takes user peace of mind into account; means for analyzing dispatch-related problems using a natural language processing model and an emotion engine and generating solutions; and means for collecting past dispatch data, analyzing it using the generative AI model and an emotion engine, and extracting trends and patterns. This enables quick and appropriate responses that take customer emotions into account, thereby improving the efficiency of food delivery operations and customer satisfaction.

[1901] "Customer inquiries" refers to questions or requests made by customers through the food delivery service's application, such as checking delivery status or reporting problems.

[1902] "Natural language processing models" refer to the algorithms and techniques that computers use to understand and analyze human language.

[1903] "Emotion engine" refers to software or algorithms that analyze and recognize user emotions and are used to determine a user's emotional state through text or voice data.

[1904] An "appropriate response" means a response that contains the most appropriate and useful information based on the customer's inquiry and their feelings at the time.

[1905] "Truck availability" refers to information indicating whether a truck to be used for delivery is currently available.

[1906] "Departure time" refers to data indicating the scheduled time for delivery to begin.

[1907] "Route information" refers to information including the optimal route to the delivery destination and data on intermediate points.

[1908] A "generative AI model" refers to an algorithm or framework for generating new data or information using AI technology.

[1909] "Optimal vehicle dispatch schedule" refers to the most efficient and economical vehicle dispatch plan, taking into account the availability of each truck, departure time, route information, etc.

[1910] "GPS device" refers to equipment and technology used to obtain global location information.

[1911] "Providing location information in real time" means instantly obtaining current location information and providing it to customers on the spot.

[1912] "Providing information in a manner that takes into consideration the user's sense of security" refers to a method of providing information that aims to alleviate the user's emotions and anxiety, and includes messages that are intended to give the user a sense of security.

[1913] "Dispatch issues" refer to various troubles and problems related to delivery operations and truck operations.

[1914] "Solution generation" refers to the process of providing the most appropriate response or fix to an issue that has arisen.

[1915] "Historical Trip Data" refers to historical data relating to all trips ever made.

[1916] "Extracting trends and patterns" refers to the analytical process of finding patterns and commonalities from large amounts of data.

[1917] This invention is a system that aims to improve the efficiency and customer satisfaction of food delivery services. This system optimizes the management of vehicle dispatch operations by combining an emotion engine and a generative AI model.

[1918] Responding to customer inquiries

[1919] The user inputs a query using a terminal and sends it to the server. For example, a query such as "I would like to know the delivery status of the pizza I just ordered." The server receives this query and analyzes it using a natural language processing model (e.g., BERT) and an emotion engine (e.g., IBM Watson Tone Analyzer). The server generates an appropriate answer based on the query and replies to the user after taking their emotions into consideration. This allows the user to feel that their emotions are understood and gives them a sense of security.

[1920] Optimizing delivery schedules

[1921] A user sends a delivery request using a terminal. For example, they request, "I would like delivery tomorrow morning." The server receives this request and combines the generative AI model with the emotion engine to create an optimal delivery schedule, taking into account truck availability, departure time, and route information. For example, it provides a response that takes into account the user's sense of security, such as, "We will deliver tomorrow at 10 a.m. Don't worry." In this way, by using the emotion engine, it is possible to provide a delivery schedule that takes into account the user's emotions.

[1922] Real-time delivery location information

[1923] The user sends a request from their device saying, "I want to know the current location of the delivery person." The server receives the request and analyzes the real-time location information obtained from the GPS device in combination with the emotion engine. For example, it provides the user with reassuring information such as, "The delivery person is currently traveling on a major road. Don't worry." This not only allows the user to check the delivery status in real time, but also gives them a sense of security.

[1924] Troubleshooting and Support

[1925] A user reports a delivery problem from their device. For example, they send a report such as "The delivery truck has stalled." The server receives the report and analyzes the problem using a natural language processing model and emotion engine. They then provide the user with a solution that takes their emotions into account, such as "Would you like to contact your nearest repair shop? We will take care of it right away." In this way, using the emotion engine can ease the user's anxiety and enable a prompt response.

[1926] Analysis of past delivery data

[1927] The server periodically collects past delivery data from a database. The collected data is analyzed using a generative AI model and emotion engine to extract delivery trends and patterns. For example, the system provides advice to users such as, "According to data from the past year, weekend delivery requests are on the rise, so please plan your deliveries well in advance." This enables efficient planning of delivery operations.

[1928] Examples of prompt statements

[1929] Customer inquiry prompt:

[1930] input:

[1931] "I'd like to know the status of the delivery of the pizza I just ordered."

[1932] Prompt for delivery schedule optimization:

[1933] input:

[1934] "I would like delivery tomorrow morning."

[1935] In this way, by combining an emotion engine and a generative AI model, the system of the present invention effectively realizes customer service and delivery schedule optimization, real-time location information provision, troubleshooting, and historical data analysis in food delivery services, thereby improving customer satisfaction and streamlining operations.

[1936] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1937] Step 1:

[1938] The terminal receives an inquiry from a customer. The customer uses the terminal to input and send an inquiry such as, "I'd like to know the delivery status of the pizza I just ordered." The input text data is then sent from the terminal to the server.

[1939] Step 2:

[1940] The server receives the customer's inquiry. The server uses a natural language processing model (e.g., BERT) to analyze the received inquiry. The BERT model is used to extract the intent of the inquiry and determine the appropriate action accordingly. In this process, the input text data is analyzed to identify the type and content of the inquiry.

[1941] Step 3:

[1942] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the content of the customer's inquiry. The analysis results provide information to determine the customer's emotional state. Specifically, it analyzes text data and outputs the customer's emotional state, such as whether they are feeling stressed or relieved.

[1943] Step 4:

[1944] The server generates an appropriate response based on the content of the inquiry and the results of sentiment analysis. A generative AI model is used to create a response that takes into account the customer's emotions. For example, a response that provides reassuring information such as, "The delivery person is currently driving on a major road. Don't worry," is generated. Here, a response text is generated based on the analysis results and sent back from the server to the device.

[1945] Step 5:

[1946] The server collects truck availability, departure times, and route information, and uses a generative AI model to create an optimal delivery schedule. Specifically, this information is passed as input to the system, and the generative AI model calculates the optimal schedule by taking various factors into account. The output includes the delivery schedule and the reasons for it.

[1947] Step 6:

[1948] The server obtains the truck's real-time location information from the GPS device. The obtained location information is quickly transmitted to the server. The emotion engine then processes the information in a way that increases the user's sense of security. The output is a description of the delivery situation, such as "The delivery person is currently driving on a major road. Don't worry."

[1949] Step 7:

[1950] When a user reports a delivery problem to the server, the server analyzes the problem using a natural language processing model and an emotion engine. For example, if a user reports that "the delivery truck stalled," the server analyzes the report and generates a proposal that takes into account specific solutions, such as contacting the nearest repair shop. The output is a proposal such as "Would you like to contact the nearest repair shop? We will respond immediately."

[1951] Step 8:

[1952] The server periodically collects past dispatch data from a database and analyzes it using a generative AI model and emotion engine. This analysis extracts delivery trends and patterns. For example, it can input data from the past year and output trends such as "weekend delivery requests are on the rise." Advice based on the analysis results is provided to the user.

[1953] Through the above processing steps, the system of the present invention realizes improved efficiency in food delivery operations and increased customer satisfaction.

[1954] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1955] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1956] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1957] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1958] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1959] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1960] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1961] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1962] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1963] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1964] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1965] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1966] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1967] 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.

[1968] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1969] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1970] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1971] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1972] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1973] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1974] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1975] The following is further disclosed regarding the above embodiment.

[1976] (Claim 1)

[1977] a means for receiving customer inquiries, analyzing them using a natural language processing model, and generating appropriate responses;

[1978] A means to input truck availability, departure time, and route information and use a generative AI model to create an optimal vehicle dispatch schedule;

[1979] a means for obtaining truck location information from a GPS device and providing real-time location information;

[1980] A means for analyzing vehicle dispatch problems using natural language processing models and generating solutions;

[1981] A means of collecting and analyzing past dispatch data to extract trends and patterns;

[1982] A system including:

[1983] (Claim 2)

[1984] 10. The system of claim 1, further comprising means for receiving a text-based inquiry from a customer, analyzing the inquiry using a natural language processing model, and returning a text-based response.

[1985] (Claim 3)

[1986] 10. The system of claim 1, further comprising means for automatically generating an optimal vehicle dispatch schedule using a generative AI model, taking into account truck availability, departure times, and route information.

[1987] "Example 1"

[1988] (Claim 1)

[1989] a means for receiving customer inquiries, analyzing them using a natural language processing model, and generating appropriate responses;

[1990] A means to input vehicle availability, departure times, and route information and use a generative AI model to generate an optimal vehicle dispatch schedule;

[1991] a means for acquiring vehicle location information from a positioning device and providing the location information in real time;

[1992] A means for analyzing vehicle dispatch problems using natural language processing models and generating solutions;

[1993] A means of collecting and analyzing past dispatch data to extract trends and patterns;

[1994] A system including:

[1995] (Claim 2)

[1996] 10. The system of claim 1, further comprising means for receiving a text-based inquiry from a customer, analyzing the inquiry using a natural language processing model, and returning a text-based response.

[1997] (Claim 3)

[1998] 10. The system of claim 1, further comprising means for automatically generating an optimal vehicle dispatch schedule using a generative AI model, taking into account vehicle availability, departure times, and route information.

[1999] "Application Example 1"

[2000] (Claim 1)

[2001] a means for receiving customer inquiries, analyzing them using a natural language processing model, and generating appropriate responses;

[2002] A means to input delivery...

Claims

1. a means for receiving customer inquiries, analyzing them using a natural language processing model, and generating appropriate responses; A means to input truck availability, departure time, and route information and use a generative AI model to create an optimal vehicle dispatch schedule; a means for obtaining truck location information from a GPS device and providing real-time location information; A means for analyzing vehicle dispatch problems using natural language processing models and generating solutions; A means of collecting and analyzing past dispatch data to extract trends and patterns; A system including:

2. The system of claim 1 , further comprising means for receiving a text-based inquiry from a customer, analyzing the inquiry using a natural language processing model, and returning a text-based response.

3. The system of claim 1 further comprising means for automatically generating an optimal vehicle dispatch schedule using a generative AI model, taking into account truck availability, departure times, and route information.

Images