System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving deal information sent by a trader; generative AI model means for analyzing the deal information and extracting a required skill set; means for searching a database for a freelance having the required skill set; means for selecting an optimal freelance from a result of the searching and notifying the optimal freelance as a matching candidate; and means for receiving an intention of the freelance to approve the matching candidate.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the IT industry, a multi-tiered subcontracting structure has become commonplace, making it difficult for clients to find qualified personnel with the desired skill sets. Furthermore, the large number of intermediaries makes it difficult for IT freelancers to receive compensation commensurate with the skills they provide. As a result, clients are unable to secure the right talent at a fair price, and IT freelancers are unable to receive adequate compensation. Furthermore, this opaque structure increases the risk of talented IT talent leaving the industry for overseas jobs. There is a need for a platform that can solve these issues and achieve fair and efficient matching. [Means for solving the problem]

[0005] To solve the above problems, this invention provides a system that utilizes a generative AI model to directly match clients with IT freelancers. Specifically, the generative AI model analyzes project information received from the client and extracts the required skill set. It then searches a database for freelancers with the corresponding skill set, selects the most suitable candidate, and notifies them. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer after the transaction is completed. This eliminates the multi-tiered subcontracting structure and provides an environment in which clients and freelancers can transact directly.

[0006] "Project information" refers to information about the details of a project provided by the client, including the skill set, duration, budget, objectives, etc.

[0007] A "generative AI model" is an artificial intelligence model used to analyze input data and extract required skill sets and other specific characteristics.

[0008] A "skill set" is the set of technical or professional abilities required to accomplish a particular project or task.

[0009] A "database" is a system that systematically stores various data, including information on freelancers and projects, and enables searching and management.

[0010] "Matching candidates" are the most suitable individuals or groups selected from among freelancers with skill sets that match the project information.

[0011] "Notification" is an act or system for informing a target person (in this case, a freelancer) of certain information.

[0012] "Transaction progress" means the progress of ongoing transactions or projects between the client and the freelancer.

[0013] "Remuneration" means money or other consideration paid to a freelancer for services or labor provided. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention relates to a system that uses generative AI models to directly match clients with IT freelancers. This invention eliminates the multi-tiered subcontracting structure and provides a fair and efficient ordering process.

[0036] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches the database for freelancers with matching skill sets, selects the best candidate, and notifies both parties. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[0037] Program processing

[0038] 1. User (orderer) registration

[0039] The server receives a new registration request from the client.

[0040] The terminal allows the client to enter basic information and project information.

[0041] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[0042] The server stores the company's data in a database.

[0043] 2. User (freelance) registration

[0044] The server receives a new registration request from a freelancer.

[0045] The terminal allows freelancers to input their skill set and past performance.

[0046] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[0047] The server stores the freelance data in a database.

[0048] 3. Entering project information and matching

[0049] The purchaser enters new project information.

[0050] The server analyzes the case information and extracts the required skill set through a generative AI model.

[0051] The server searches the database for freelancers with the relevant skill set.

[0052] The server selects the best candidates and notifies the freelancer of the matching candidates.

[0053] 4. Match Approval and Notification

[0054] The freelancer confirms their intention to participate in the project.

[0055] The terminal sends the authorization information to the server.

[0056] The server provides the client and the freelancer with the final matching information and arranges for direct contact.

[0057] 5. Transaction progress monitoring and reward payment

[0058] It provides the interface necessary for the server to monitor the progress of the transaction.

[0059] The purchaser updates the transaction progress to the server.

[0060] The server confirms the completion of the project and receives payment from the client.

[0061] The server pays the freelancer the amount minus the commission.

[0062] Specific examples

[0063] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[0064] 1. Registering Client A and entering project information

[0065] The server receives basic information and project information from client A.

[0066] The terminal allows A to input Python and React skill sets.

[0067] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[0068] The server saves A's information in the database.

[0069] 2. Registration of Freelance B

[0070] The server receives a new registration request from Freelance B.

[0071] The terminal prompts B to input his skill set and past achievements.

[0072] The server analyzes using the generated AI model and extracts B's skill keywords.

[0073] The server saves B's information in the database.

[0074] 3. Notification of potential matches

[0075] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[0076] The server sends a notification of a potential match to Freelance B.

[0077] 4. Approval and Transaction Progress

[0078] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[0079] The server notifies A of the authorization information and arranges for direct contact.

[0080] The server monitors the transaction progress and pays the reward to B after completion.

[0081] In this way, the system of the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[0082] The processing flow will be explained below.

[0083] Step 1:

[0084] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[0085] Step 2:

[0086] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[0087] Step 3:

[0088] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[0089] Step 4:

[0090] The server stores the extracted skill sets and company information in a database.

[0091] Step 5:

[0092] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[0093] Step 6:

[0094] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[0095] Step 7:

[0096] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[0097] Step 8:

[0098] The server stores the extracted keywords and freelance information in a database.

[0099] Step 9:

[0100] The user (client) enters new project information. The terminal displays the project information input form.

[0101] Step 10:

[0102] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[0103] Step 11:

[0104] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[0105] Step 12:

[0106] The server searches the database for freelancers with the relevant skill set.

[0107] Step 13:

[0108] The server creates a list of applicable freelancers and selects the most suitable freelancer.

[0109] Step 14:

[0110] The server sends matching candidate information to the most suitable freelancer.

[0111] Step 15:

[0112] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[0113] Step 16:

[0114] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[0115] Step 17:

[0116] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[0117] Step 18:

[0118] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[0119] Step 19:

[0120] The user (client) notifies the server of project completion.

[0121] Step 20:

[0122] The server confirms the completion of the transaction and receives payment from the customer.

[0123] Step 21:

[0124] The server pays the freelancer the fee minus the commission.

[0125] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers.

[0126] Example 1

[0127] 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."

[0128] In conventional ordering systems, multiple subcontracting structures and opaque processes made it difficult to ensure fair and efficient matching between clients and freelancers. This often led to inefficiencies and unfair transactions. It also required a great deal of effort for clients to quickly find freelancers with the right skill sets.

[0129] 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.

[0130] In this invention, the server includes: means for receiving project information sent by a client; a generative AI model means for analyzing the project information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; means for saving basic information and transaction information from both the client and the freelancer in the database; and means for providing an interface for the generative AI model to analyze the project information and skill data. This makes it possible to quickly achieve direct and fair matching between client and freelancer, providing an efficient and highly transparent ordering process.

[0131] "Client" refers to an individual or company that requests work.

[0132] "Project information" refers to information provided by the client, such as project details, required skills, time frame, budget, etc.

[0133] A "generative AI model" is a type of artificial intelligence that analyzes given data with high precision and generates the desired results.

[0134] A "skill set" refers to the collection of skills and experience required to perform a particular job or role.

[0135] "Freelance" refers to a sole proprietor or contract employee who independently undertakes work.

[0136] A "database" refers to a system for efficiently managing and searching large amounts of data.

[0137] "Matching candidates" refer to freelancers who match the project information and are selected by the generative AI model.

[0138] "Transaction progress" refers to the progress of the ordered work.

[0139] "Remuneration" refers to the compensation paid to a freelancer upon completion of work.

[0140] An "interface" refers to the window or means through which a user operates or inputs data into a system.

[0141] This invention relates to a system that uses a generative AI model to directly match clients with freelancers. The purpose of this invention is to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. Specific embodiments are described below.

[0142] The system includes a server, terminals, and a generative AI model. The server centrally manages data on clients and freelancers and performs the necessary processing. The terminals provide an interface for clients and freelancers to input and display information. The generative AI model uses natural language processing technology to analyze project information and skill data and perform appropriate matching.

[0143] First, the client accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the client and displays a form on the terminal for entering basic information and project information. Once the client enters this information and submits it, the server uses a generative AI model to analyze the project information and extract the required skill sets. The extracted information is stored in a database.

[0144] Next, the freelancer also accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the freelancer and displays a form on the terminal for entering their skill set and past achievements. Once the freelancer enters and submits this information, the server uses a generative AI model to analyze the skill set and extract related skill keywords. The extracted information is also stored in a database.

[0145] When a client inputs new project information, the server again analyzes the project information using the generative AI model and extracts the required skill set. The server then searches the database for freelancers with the corresponding skill set, selects the most suitable candidate, and notifies them. The freelancer sends their intention to participate in the project to the server via their device, and the server notifies the client of that information. This allows the client and freelancer to communicate directly.

[0146] Furthermore, the server monitors the progress of the transaction and provides an interface for the client to update the progress information. When the transaction is completed, the server receives payment from the client and pays the remaining amount minus a commission to the freelancer.

[0147] As a concrete example, if Client A is looking for a freelancer with Python and React skills for a web development project, they can input the following prompt into the generative AI model:

[0148] "Please select a freelancer with the best Python and React skills for Client A's web development project."

[0149] In this way, the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1: New customer registration

[0152] The server receives a new registration request from the user (orderer).

[0153] Input: New registration request from purchaser

[0154] Output: Basic information and case information input form

[0155] When the server receives the request, it displays a form on the terminal where the user can enter basic information (such as name, email address, and company information) and project information (such as project title, description, and required skills).

[0156] Step 2: Enter the job information

[0157] The terminal prompts the user (client) to enter basic information and project information, which is then sent to the server.

[0158] Input: Basic information of the client and project information

[0159] Output: Sending information to the server

[0160] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends the entered information to the server.

[0161] Step 3: Parse and save case information

[0162] The server analyzes the case information using a generative AI model and extracts the required skill sets.

[0163] Input: Purchaser's project information

[0164] Output: Extracted skill sets and client information stored in a database

[0165] The server inputs the case information into the generative AI model, which uses natural language processing technology to extract the skill sets required for the project, and stores the extracted information in a database.

[0166] Step 4: Register as a freelancer

[0167] The server receives a new registration request from a user (freelancer).

[0168] Input: New freelance registration request

[0169] Output: A form for inputting skillsets and achievements

[0170] When the server receives the request, it displays a form on the terminal for entering the skill set (programming languages, tools, etc.) and past achievements.

[0171] Step 5: Enter your freelance information

[0172] The terminal prompts the user (freelancer) to enter their skill set and past achievements, which are then sent to the server.

[0173] Input: Freelance skillset and past performance

[0174] Output: Sending information to the server

[0175] The user (freelancer) enters their skill set and past achievements and clicks the send button. The terminal sends the entered information to the server.

[0176] Step 6: Freelance information analysis and storage

[0177] The server uses a generative AI model to analyze the freelancer's input information and extract relevant skill keywords.

[0178] Input: Freelance skillset and track record information

[0179] Output: Extracted skill keywords and freelance information stored in a database

[0180] The server inputs freelancer information into the generative AI model and extracts relevant skill keywords, which are then stored in a database.

[0181] Step 7: Enter new job information

[0182] The user (client) enters new project information into the terminal and sends it to the server.

[0183] Input: Purchaser's new project information

[0184] Output: Sending information to the server

[0185] The user (client) enters new project information and clicks the send button. The terminal sends the information to the server.

[0186] Step 8: Reanalyze case information and extract skill sets

[0187] The server uses a generative AI model to analyze new case information and extract the required skill sets.

[0188] Input: Purchaser's new project information

[0189] Output: Extracted skillset

[0190] The server inputs new case information into the generative AI model and extracts the required skill sets.

[0191] Step 9: Search for freelancers

[0192] The server searches the database for freelancers with the relevant skill set.

[0193] Input: Extracted skillset

[0194] Output: A list of matching freelancers

[0195] Based on the skill set extracted by the server, the server searches for freelancers in the database and generates a list of relevant freelancers.

[0196] Step 10: Match selection and notification

[0197] The server selects the most suitable freelancer and notifies them as a matching candidate.

[0198] Input: List of applicable freelancers

[0199] Output: Optimal freelance notifications

[0200] The server will select the best freelancer from the list and send a notification.

[0201] Step 11: Freelance Approval

[0202] A user (freelancer) transmits his / her intention to participate in a project to the server via his / her terminal.

[0203] Input: Freelance participation intention

[0204] Output: Notification to the server

[0205] The freelancer enters their intention to participate in the project into their device and clicks the send button. The server receives the information.

[0206] Step 12: Final notification and adjustments

[0207] The server notifies the client of the approval information and arranges for the client and the freelancer to directly contact each other.

[0208] Input: Freelance approval information

[0209] Output: Notification to client and communication coordination

[0210] The server notifies the client of the approval information, and the client and the freelancer are set up to be able to contact each other directly.

[0211] Step 13: Monitor the progress of your transaction

[0212] The server provides an interface for users (orderers) to update them on the progress of the transaction.

[0213] Input: Transaction progress information

[0214] Output: Transaction progress update

[0215] The server provides an interface to the client to request progress information and receives updated information.

[0216] Step 14: Completing the transaction and paying out

[0217] The server confirms the completion of the project, receives payment from the user (client), and pays the freelancer.

[0218] Input: Transaction Completion Information and Payment

[0219] Output: Freelance payment

[0220] The server confirms the completion of the project, receives payment from the client, and pays the remaining amount minus the commission to the freelancer.

[0221] (Application example 1)

[0222] 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."

[0223] In factories, quickly and efficiently matching workers and robots with the skills required for specific tasks is a challenge. Currently, managers must manually coordinate workers and robots, which inevitably leads to work delays and human error. This has led to problems such as reduced work efficiency and increased costs.

[0224] 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.

[0225] In this invention, the server includes means for receiving job information sent by a client, a generating AI model means for analyzing the job information and extracting the required skill set, a means for searching a database for workers with the required skill set, a means for selecting the most suitable worker from the search results and notifying them as a matching candidate, a means for receiving the worker's approval of the matching candidate, a means for monitoring work progress and paying the worker a remuneration after the work is completed, a means for receiving and analyzing work task information within the factory and identifying the required skill set, and a means for searching for and matching workers or robots suitable for the work tasks. This enables efficient and fair matching of work tasks within the factory, improving work efficiency and reducing costs.

[0226] The "client" is the party that provides work tasks and case information to execute a business or project and manages its progress.

[0227] "Project information" is information provided by the client regarding the skills and conditions required for a work task or project.

[0228] A "generative AI model" is an artificial intelligence model that analyzes input information and extracts the necessary skill sets and conditions from it.

[0229] A "skill set" refers to the collection of skills and knowledge required to perform a particular job or task.

[0230] A "database" is a digital collection of information that can be centrally managed and searched for, including information on clients, workers, project information, and skill sets.

[0231] A "worker" is a person or automated robot with a specific skill set that performs work tasks based on case information.

[0232] A "matching candidate" is someone selected as the most suitable worker based on the skill set extracted by the generative AI model.

[0233] "Notification" refers to the act of informing matching candidates of selection information and project details via electronic means.

[0234] "Work progress" refers to the progress of work or projects being carried out based on case information.

[0235] "Remuneration" is the consideration paid by the client for the work that the worker has performed based on the project information.

[0236] The system for implementing this invention aims to improve work efficiency in factories. Specifically, it is a system that analyzes work task information provided by the client using an AI model and automatically matches the most suitable worker (or robot). This system consists of a server, terminals, and various software.

[0237] Hardware and Software Configuration

[0238] server

[0239] The server uses a web framework such as Flask to execute a web API to receive project information and skill sets sent by clients and workers.

[0240] The server uses a generative AI model (e.g., OpenAI API) to analyze the submitted job information and extract the required skill sets.

[0241] Terminal

[0242] The terminal provides an interface for the orderer and the worker to input information.

[0243] The information entered on the terminal is sent to the server and stored in a database.

[0244] Explained processing flow

[0245] 1. User (orderer) registration

[0246] The server receives a new registration request from the client and stores it in a database. The client enters basic information and project information on their device, which then sends it to the server. The server uses a generative AI model to analyze the project information and extract the required skill set.

[0247] 2. User (operator) registration

[0248] The server receives a new registration request from a worker and stores it in a database. The worker enters their skill set and past performance data on their device, which then sends it to the server. The server then uses a generative AI model to analyze the input information and extract skill keywords.

[0249] 3. Entering project information and matching

[0250] The client inputs new work task information. The server analyzes the task information and extracts the required skill set through a generative AI model. The server then searches the database for workers with the required skill set.

[0251] 4. Notification of potential matches

[0252] The server selects the most suitable worker and notifies the worker of that information. When the worker approves their intention to participate in the project, that information is sent to the server via their terminal. The server then provides the approval information to the client and arranges for the two parties to contact each other.

[0253] 5. Monitoring trading progress and reward payment

[0254] The server checks the progress of the work and updates the progress to the server. When the work is completed, the server receives payment from the client and pays the worker a reward.

[0255] Specific examples

[0256] The following example illustrates the operation of the system:

[0257] Prompt Sentence Examples

[0258] "What skill set is required for the following work task: Wiring and debugging a PLC?"

[0259] By inputting this prompt into a generative AI model, the model extracts the required skill set. For example, "PLC wiring," "debugging," and "electrical engineering" are extracted. Based on these skill sets, the server searches the database for the relevant worker and notifies the most suitable candidate.

[0260] In this way, this system can be used to efficiently match workers and robots with the necessary skills within a factory, dramatically improving work efficiency.

[0261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0262] Step 1:

[0263] The server receives a new registration request sent by the client. The client uses a terminal to enter basic information and project information. The terminal sends this information to the server, which then analyzes the project information using a generative AI model. This analysis extracts the required skill set and stores it in a database.

[0264] Input: Basic information of the client and project information

[0265] Output: Client information and required skill sets stored in a database

[0266] Step 2:

[0267] The server receives a new registration request sent by a worker. The worker uses a terminal to input their own skill set and past performance. The terminal sends this information to the server, which then analyzes the input data using a generative AI model. The skill keywords extracted through the analysis are stored in a database.

[0268] Inputs: Worker skill set and past performance

[0269] Output: Worker information and skill keywords stored in the database

[0270] Step 3:

[0271] The client inputs new work task information into the terminal, which then sends the information to the server, which analyzes the task information using a generative AI model to extract the required skill set, then searches the database for workers who match that skill set.

[0272] Input: Work task information

[0273] Output: A list of workers that match the required skill set

[0274] Step 4:

[0275] The server selects the most suitable worker from the search results and notifies the worker as a matching candidate. The worker receives the notification and sends their intention to participate in the project to the server from their terminal. The server provides this approval information to the client and arranges for the two parties to contact each other.

[0276] Input: List of workers who match the required skill set, worker approval

[0277] Output: Information for both the client and the worker to contact each other

[0278] Step 5:

[0279] The server checks the progress of the work and provides the necessary interface. The client updates the progress to the server, and the information is saved in a database. When the work is completed, the server receives payment from the client and pays the worker a reward.

[0280] Input: Work progress, payment information from the client

[0281] Output: Reward payment and database update after transaction completion

[0282] In this way, a system that efficiently matches work tasks within a factory and manages progress is created through a series of steps. This system is expected to facilitate smooth cooperation between clients and workers and improve work efficiency.

[0283] 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.

[0284] This invention relates to a system that directly matches clients with IT freelancers using a generative AI model and an emotion engine. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, better matching is achieved by taking into account the user's emotional state.

[0285] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches a database for freelancers with matching skill sets, selects the most suitable candidate, and notifies both parties. It also uses an emotion engine to recognize the emotional state of the client and freelancer, and takes this into account when matching. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[0286] Program processing

[0287] 1. User (orderer) registration

[0288] The server receives a new registration request from the client.

[0289] The terminal allows the client to enter basic information and project information.

[0290] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[0291] The emotional engine analyzes the client's emotional state and adjusts the skill set to take this data into account.

[0292] The server stores the company's data in a database.

[0293] 2. User (freelance) registration

[0294] The server receives a new registration request from a freelancer.

[0295] The terminal allows freelancers to input their skill set and past performance.

[0296] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[0297] The emotion engine analyzes the freelancer's emotional state and adjusts the skill information taking this data into account.

[0298] The server stores the freelance data in a database.

[0299] 3. Entering project information and matching

[0300] The purchaser enters new project information.

[0301] The server analyzes the case information and extracts the required skill set through a generative AI model.

[0302] The server searches the database for freelancers with the relevant skill set.

[0303] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[0304] The server sends a notification of the best candidate to the freelancer.

[0305] 4. Match Approval and Notification

[0306] The freelancer confirms their intention to participate in the project.

[0307] The terminal sends the authorization information to the server.

[0308] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[0309] 5. Transaction progress monitoring and reward payment

[0310] It provides the interface necessary for the server to monitor the progress of the transaction.

[0311] The purchaser updates the transaction progress to the server.

[0312] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, automatically providing alerts and support based on their emotional state.

[0313] The client notifies the server of project completion.

[0314] The server confirms the completion of the transaction and receives payment from the customer.

[0315] The server pays the freelancer the amount minus the commission.

[0316] Specific examples

[0317] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[0318] 1. Registering Client A and entering project information

[0319] The server receives basic information and project information from client A.

[0320] The terminal allows A to input Python and React skill sets.

[0321] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[0322] The emotion engine analyzes A's emotional state and adjusts the skill set taking this data into account.

[0323] The server saves A's information in the database.

[0324] 2. Registration of Freelance B

[0325] The server receives a new registration request from Freelance B.

[0326] The terminal prompts B to input his skill set and past achievements.

[0327] The server analyzes using the generated AI model and extracts B's skill keywords.

[0328] The emotion engine analyzes B's emotional state and corrects the skill information taking this data into account.

[0329] The server saves B's information in the database.

[0330] 3. Notification of potential matches

[0331] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[0332] The emotion engine analyzes the emotional state of the client and the freelancer and selects B as the most suitable candidate.

[0333] The server sends a notification of a potential match to Freelance B.

[0334] 4. Approval and Transaction Progress

[0335] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[0336] The server notifies A of the authorization information and arranges for direct contact.

[0337] The server monitors the transaction progress and pays the reward to B after completion.

[0338] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[0339] The processing flow will be explained below.

[0340] Step 1:

[0341] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[0342] Step 2:

[0343] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[0344] Step 3:

[0345] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[0346] Step 4:

[0347] The emotion engine analyzes the client's emotional state and feeds this data into the generative AI model to correct the skill set.

[0348] Step 5:

[0349] The server stores the corrected skill set and company information in a database.

[0350] Step 6:

[0351] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[0352] Step 7:

[0353] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[0354] Step 8:

[0355] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[0356] Step 9:

[0357] The emotion engine analyzes the freelancer's emotional state and reflects this data in the generative AI model to correct skill keywords.

[0358] Step 10:

[0359] The server stores the corrected keywords and freelance information in a database.

[0360] Step 11:

[0361] The user (client) enters new project information. The terminal displays the project information input form.

[0362] Step 12:

[0363] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[0364] Step 13:

[0365] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[0366] Step 14:

[0367] The server searches the database for freelancers with the relevant skill set.

[0368] Step 15:

[0369] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[0370] Step 16:

[0371] The server sends a notification of a potential match to the most suitable freelancer.

[0372] Step 17:

[0373] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[0374] Step 18:

[0375] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[0376] Step 19:

[0377] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[0378] Step 20:

[0379] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[0380] Step 21:

[0381] The emotion engine monitors the progress of the deal in real time and automatically provides alerts and support based on the emotional state of the client and freelancer.

[0382] Step 22:

[0383] The user (client) notifies the server of project completion.

[0384] Step 23:

[0385] The server confirms the completion of the transaction and receives payment from the customer.

[0386] Step 24:

[0387] The server pays the freelancer the amount minus the commission.

[0388] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers at an even higher level by incorporating an emotion engine.

[0389] Example 2

[0390] 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."

[0391] Conventional matching systems between clients and IT freelancers focus on matching skill sets, but do not take into account the user's emotional state, which often leads to problems in actual transactions. Specifically, if the client is under high stress or the freelancer is dissatisfied, this can have a negative impact on the progress of the transaction and the quality of the deliverables. The challenge is to solve these problems and provide an efficient and fair ordering process.

[0392] 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 job information sent by the client; a generation AI model means for analyzing the job information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; and means including an emotion engine for analyzing the emotional states of the client and freelancer and taking this into consideration when matching. This enables matching and transactions that take the emotional states of the client and freelancer into consideration, making it possible to realize an efficient and fair ordering and purchase process.

[0393] "Project information" refers to detailed project information provided by the client, including required skill sets and work content.

[0394] A "generative AI model" is a system that uses machine learning algorithms to analyze data and extract necessary information.

[0395] "Freelance" refers to a worker who has the ability to independently accept and carry out work.

[0396] A "database" is a system that stores information in an organized manner and makes it easy to search and update.

[0397] An "emotion engine" is a system that has the ability to analyze the user's emotional state and respond appropriately based on that.

[0398] "Matching" is the process of comparing the client's project information with the freelancer's skill set and selecting the appropriate candidate.

[0399] "Transaction progress" is information indicating the progress of a project, and is used to evaluate the progress and achievement of work.

[0400] "Compensation" means the monetary compensation a Freelancer receives for completing a Project.

[0401] "Notification" is the act of the system conveying information to the user.

[0402] "Intention" refers to the freelancer's decision whether or not to participate in a project.

[0403] This invention relates to a system that directly matches clients with IT freelancers. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, it achieves better matching by taking into account the user's emotional state.

[0404] System configuration

[0405] This system mainly consists of a server, terminal, generative AI model, emotion engine, and database. The server is the core of the entire system and processes and manages various data. The terminal provides an interface for users to input data. The generative AI model is used to analyze project information and freelance skill sets. The emotion engine analyzes the user's emotional state and takes it into consideration when matching. The database is used to store information about clients and freelancers.

[0406] Program processing overview

[0407] 1. User (orderer) registration

[0408] The server receives a new registration request from the client and prompts them to enter basic information and project information via their terminal. The generative AI model analyzes this data and extracts the required skill set. The emotion engine analyzes the client's emotional state and adjusts the skill set. Finally, the server stores the client's data in a database.

[0409] 2. User (freelance) registration

[0410] The server receives a new registration request from a freelancer and prompts them to enter their skill set and past performance via their device. A generative AI model analyzes this data and extracts the freelancer's skill keywords. An emotion engine analyzes the freelancer's emotional state and corrects the skill information. The server saves the freelancer's data in a database.

[0411] 3. Entering project information and matching

[0412] When a client inputs new project information, the server uses the generative AI model to analyze the project information and extract the required skill set. The server then searches for freelancers in its database who have the relevant skill set, and an emotion engine analyzes the emotional states of the client and freelancer to select the most suitable match candidate. The server then notifies the freelancer of the most suitable candidate.

[0413] 4. Match Approval and Notification

[0414] When a freelancer approves their intention to participate in a project, the device sends the information to the server. The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[0415] 5. Transaction progress monitoring and reward payment

[0416] The server provides an interface for monitoring the progress of the transaction, and the client updates the transaction progress. The emotion engine monitors the emotional state of the client and freelancer in real time and provides alerts and support as needed. The client notifies the server of project completion, and the server confirms the completion of the transaction and then pays the freelancer the fee minus a commission.

[0417] Specific examples

[0418] For example, if Client A is looking for a freelancer with Python and React skills for a web development project, the process would be as follows:

[0419] Client A enters basic information and project information, and the generative AI model extracts Python and React skill sets.

[0420] The emotion engine analyzes the emotional state of client A and adjusts the skill set accordingly.

[0421] Freelance B registers and inputs his / her skill set and past achievements. The generative AI model analyzes the data and extracts skill keywords.

[0422] The server searches the database for freelancers with Python and React skills, and the emotion engine selects Freelance B as the best candidate.

[0423] Freelance B is notified of the potential match and approves the project.

[0424] The server notifies the client A of the approval information, monitors the progress of the transaction, and even makes the payment of the reward.

[0425] Prompt Sentence Examples

[0426] "Client A is looking for a freelancer with Python and React skills. Please select the best freelancer taking into consideration Client A's emotional state."

[0427] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[0428] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0429] Step 1:

[0430] Receiving a new registration request from a user (orderer)

[0431] The server receives a new registration request from the client. This is done by receiving data as an HTTP request using the POST method. The input is the client's basic information and job information, and the output is a response confirming receipt.

[0432] Step 2:

[0433] Enter basic information and project information

[0434] The terminal prompts the client to enter basic information (name, contact details, company information, etc.) and project information (project overview, required skills, etc.). Specifically, a web form is used, and the user enters data into the input fields. The input is the information entered by the client, and the output is the input data.

[0435] Step 3:

[0436] Analysis of project information and extraction of skill sets

[0437] The server uses the generated AI model to analyze project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​processes the data to extract keywords such as "Python" and "React." The output is the extracted skill set.

[0438] Step 4:

[0439] Emotional state analysis and skill set adjustment

[0440] The emotion engine analyzes the client's emotional state and adjusts the skill set. The input is the client's emotional information, and the emotion engine processes the data to evaluate the state of stress, relief, etc. For example, in a high-stress state, the skill set requirements are relaxed. The output is the adjusted skill set.

[0441] Step 5:

[0442] Data storage

[0443] The server saves the client's data in the database. The input is the corrected skill set and the client's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[0444] Step 6:

[0445] Receiving new freelance registration requests

[0446] The server receives a new registration request from a freelancer. This is done by receiving data as an HTTP request using the POST method. The input is the freelancer's basic information and skill information, and the output is a response confirming the registration.

[0447] Step 7:

[0448] Enter your skill set and past achievements

[0449] The terminal allows the freelancer to input their skill set and past performance. Specifically, a web form is used, and the user enters data into input fields. The input is the information entered by the freelancer, and the output is the input data.

[0450] Step 8:

[0451] Analyzing input data and extracting skill keywords

[0452] The server uses the generated AI model to analyze the freelancer's input data and extract skill keywords. The input is the skill information entered by the freelancer, and the AI ​​processes the data to extract keywords such as "JavaScript" and "database management." The output is the extracted skill keywords.

[0453] Step 9:

[0454] Emotional state analysis and skill information correction

[0455] The emotion engine analyzes the freelancer's emotional state and corrects the skill information. The input is the freelancer's emotional information, and the emotion engine processes the data to evaluate their state, such as their motivation and sense of security. For example, if they feel secure, detailed achievement information is emphasized. The output is corrected skill information.

[0456] Step 10:

[0457] Data storage

[0458] The server saves the freelancer's data in a database. The input is the corrected skill information and the freelancer's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[0459] Step 11:

[0460] Entering project information

[0461] The client inputs new job information. The input is the new job information from the client, and the client enters data into the input fields using a web form. The output is the entered job information.

[0462] Step 12:

[0463] Analysis of project information

[0464] The server uses the generated AI model to analyze the project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​extracts the skill sets as data processing. The output is the extracted skill sets.

[0465] Step 13:

[0466] Freelance Search

[0467] The server searches for freelancers in the database who have the corresponding skill set. The input is the extracted skill set, and a SQL query is used to process the data and filter the matching freelancers. The output is the search result.

[0468] Step 14:

[0469] Emotional state analysis and optimal candidate selection

[0470] The emotion engine analyzes the emotional state of the freelancer and client and selects the optimal match candidate. The input is the emotional information of the client and freelancer, and the emotion engine processes the data by evaluating their emotional state and calculating the matching success rate. The output is the optimal match candidate.

[0471] Step 15:

[0472] Notification of potential matches

[0473] The server notifies the freelancer of the best candidate. The input is the best match candidate, and the output is a notification message to the freelancer. The specific operation is to send a notification to the freelancer via email or SMS.

[0474] Step 16:

[0475] Approval of intention to participate in the project

[0476] The freelancer approves their intention to participate in the project. The input is the freelancer's intention to participate, and the output is the approval information. Specifically, the freelancer clicks the "Participate" button on the dashboard.

[0477] Step 17:

[0478] Sending approval information

[0479] The terminal sends the approval information to the server. The input is the freelancer's approval information, and the data is sent to the server as an HTTP request using the POST method. The output is a notification to the server.

[0480] Step 18:

[0481] Receiving and adjusting approval information

[0482] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact. The input is the freelancer's approval information, and the output is a notification to the client and the freelancer. Specific operations include sending email notifications to both parties and providing contact details.

[0483] Step 19:

[0484] Providing a progress monitoring interface

[0485] The server provides an interface for monitoring the progress of transactions. The input is an access request to the progress monitoring system, and the output is a display of the progress. Specific operation is to provide a UI that allows the progress to be viewed on a web portal or dashboard.

[0486] Step 20:

[0487] Progress Updates

[0488] The purchaser updates the transaction progress to the server. The input is the purchaser's updated progress information, and the output is the updated result in the database. In concrete terms, the purchaser enters the task completion status on the dashboard.

[0489] Step 21:

[0490] Real-time emotional state monitoring and support

[0491] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, providing alerts and support as needed. The input is real-time emotional information, and the emotion engine evaluates the emotional state as data processing. The output is alerts and support messages as needed. For example, if stress increases, a warning message is automatically sent.

[0492] Step 22:

[0493] Project Completion Notification

[0494] The client notifies the server that the project is complete. The input is the client's notification of project completion, and the output is an update of the completion status to the database. The specific action is that the client clicks the "Complete" button on the dashboard.

[0495] Step 23:

[0496] Confirmation of transaction completion and payment

[0497] The server confirms the completion of the transaction and receives payment from the client. The input is a notification of project completion, and the output is payment processing to the freelancer. Specifically, the server processes the payment through a payment gateway.

[0498] The server pays the freelancer the amount minus the fee. The input is a confirmation of the transaction completion, and the output is an automatic transfer to the freelancer's bank account.

[0499] (Application example 2)

[0500] 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."

[0501] In food delivery, efficient and appropriate delivery partner matching is necessary to ensure customers receive their food quickly and reliably. However, conventional systems often fail to fully consider the customer's emotional state or the suitability of the delivery partner, resulting in inefficiency and dissatisfaction. Furthermore, extracting job information and skill sets is a time-consuming and labor-intensive process. To solve these issues, an advanced matching system using generative AI models and emotion engines is needed.

[0502] The identification process 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 order information sent by the orderer; a generative AI model means for analyzing the order information and extracting necessary conditions; means for searching a database for delivery partners who meet the necessary conditions; means for selecting the most suitable delivery partner from the search results and notifying them as a matching candidate; means for receiving the delivery partner's approval of the matching candidate; means for monitoring the progress of the transaction and paying a reward to the delivery partner after the transaction is completed; and an emotion engine means for analyzing the emotional states of the orderer and delivery partner and adjusting the matching conditions. This enables efficient and appropriate matching that takes into account the emotional state of the customer and the suitability of the delivery partner.

[0503] An "orderer" is a user who places an order for a service or product.

[0504] "Order information" refers to detailed information provided by a purchaser when ordering a service or product.

[0505] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and extract and process specific information.

[0506] "Conditions" means specific requirements or requirements parsed from the Order Information.

[0507] A database is a digital storage system that systematically organizes information so that it can be searched and used efficiently.

[0508] "Delivery Partner" means an individual or company responsible for delivering ordered products to customers.

[0509] "Matching candidates" refer to delivery partners who are likely to meet the optimal conditions based on order information.

[0510] The "emotion engine" is a system that analyzes the user's emotional state and performs appropriate processing and corrections based on the data.

[0511] "Deal Progress" refers to the status of the current stage of a deal.

[0512] "Remuneration" means money or other items of value paid in exchange for services rendered.

[0513] This invention relates to a food delivery system that efficiently matches customers (orderers) with delivery partners. The system consists of a server, a generative AI model, an emotion engine, a database, and a terminal used by the user.

[0514] Program Generation

[0515] The system works as follows: When the server receives the order information entered by the customer, it analyzes the order information using a generative AI model and extracts the necessary conditions. Based on the extracted conditions, the server searches the delivery partner information in its database and selects candidates who meet the conditions.

[0516] Furthermore, the server uses an emotion engine to analyze the emotional state of the orderer and delivery partner, and adjusts the matching conditions based on the analysis results, enabling efficient matching that takes into account the emotional state of the orderer and the suitability of the delivery partner.

[0517] For example, if a customer in a hurry orders a pizza, the system will prioritize delivery partners who can respond quickly. This is achieved by the emotion engine analyzing the customer's emotional state of "being in a hurry" and reflecting this in the conditions.

[0518] Hardware and Software Use

[0519] The system utilizes the following hardware and software:

[0520] Hardware: Smartphones, cloud servers

[0521] Software: Python (generative AI model), TensorFlow or PyTorch (emotion engine), React Native (smartphone application development)

[0522] The generative AI model is built in Python and deployed on a server. The emotion engine is built using TensorFlow or PyTorch and operates in real time to analyze the user's emotional state. The smartphone application is developed using React Native, providing an intuitive interface for users.

[0523] Specific examples

[0524] For example, when Customer A orders a pizza using a smartphone app, the server performs the following steps:

[0525] 1. Receive order information from the application.

[0526] 2. The order information is analyzed using a generative AI model to extract the necessary delivery conditions (type of food, delivery time, etc.).

[0527] 3. Search for the relevant delivery partner in the database and use the emotion engine to analyze that Customer A is in a hurry.

[0528] 4. Delivery partner B, who can deliver quickly, is selected and notified as a matching candidate.

[0529] Example prompt: "Customer A has ordered a pizza delivery and is in a rush. Please find the delivery partner who is available with the highest priority."

[0530] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0531] Step 1:

[0532] The user (orderer) uses a terminal to input order information. The terminal sends the basic information and order information (e.g., type of food, desired delivery time) provided by the orderer to the server. The input includes the type of food and desired delivery time, and the output includes the order information sent to the server.

[0533] Step 2:

[0534] The server analyzes the received order information. It uses a generative AI model to extract the necessary conditions from the order information. Specifically, it receives the order information as input, and the generative AI model extracts the conditions (e.g., delivery speed, type of food). The output is the analyzed conditions.

[0535] Step 3:

[0536] The server searches the delivery partner information in the database and finds delivery partners that match the criteria. The input is the criteria extracted in step 2, and the output is a list of matching delivery partners. The server selects the most suitable delivery partner candidates based on this list.

[0537] Step 4:

[0538] The server uses an emotion engine to analyze the emotional states of the orderer and delivery partner. The inputs are the orderer's emotional data and the delivery partner's emotional data, and the output is a correction condition based on the emotional state. The emotion engine operates in real time and reflects specific conditions, such as when the orderer is in a hurry.

[0539] Step 5:

[0540] The server combines the results of steps 3 and 4 to select the best match candidate. The input is the list of delivery partners and the adjusted conditions, and the output is the best match candidate. This selection includes prioritizing delivery partners that take into account the customer's urgent situation.

[0541] Step 6:

[0542] The server notifies the best match candidates. The selected delivery partner is notified of the match candidates and the delivery partner is asked whether to accept them. The input is the match candidates, and the output is the notification sent to the delivery partner.

[0543] Step 7:

[0544] The server receives the delivery partner's intention and determines the final match. If the delivery partner approves the match candidate, the server notifies both the orderer and the delivery partner of the final matching information and begins the transaction. The input is the delivery partner's approval information, and the output is the final matching information.

[0545] Step 8:

[0546] The server monitors the progress of the transaction. The purchaser acknowledges receipt of the order and provides real-time updates on the progress of the transaction. The input is the transaction progress data, and the output is the updated progress.

[0547] Step 9:

[0548] The server pays the reward to the delivery partner after the transaction is completed. It confirms that the transaction is completed, receives payment from the customer, and transfers the amount minus the commission to the delivery partner. The inputs are transaction completion confirmation information and payment information, and the output is the transfer of the reward.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] [Second embodiment]

[0553] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0554] 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.

[0555] 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).

[0556] 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.

[0557] 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.

[0558] 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).

[0559] 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.

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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.

[0564] 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."

[0565] This invention relates to a system that uses generative AI models to directly match clients with IT freelancers. This invention eliminates the multi-tiered subcontracting structure and provides a fair and efficient ordering process.

[0566] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches the database for freelancers with matching skill sets, selects the best candidate, and notifies both parties. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[0567] Program processing

[0568] 1. User (orderer) registration

[0569] The server receives a new registration request from the client.

[0570] The terminal allows the client to enter basic information and project information.

[0571] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[0572] The server stores the company's data in a database.

[0573] 2. User (freelance) registration

[0574] The server receives a new registration request from a freelancer.

[0575] The terminal allows freelancers to input their skill set and past performance.

[0576] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[0577] The server stores the freelance data in a database.

[0578] 3. Entering project information and matching

[0579] The purchaser enters new project information.

[0580] The server analyzes the case information and extracts the required skill set through a generative AI model.

[0581] The server searches the database for freelancers with the relevant skill set.

[0582] The server selects the best candidates and notifies the freelancer of the matching candidates.

[0583] 4. Match Approval and Notification

[0584] The freelancer confirms their intention to participate in the project.

[0585] The terminal sends the authorization information to the server.

[0586] The server provides the client and the freelancer with the final matching information and arranges for direct contact.

[0587] 5. Transaction progress monitoring and reward payment

[0588] It provides the interface necessary for the server to monitor the progress of the transaction.

[0589] The purchaser updates the transaction progress to the server.

[0590] The server confirms the completion of the project and receives payment from the client.

[0591] The server pays the freelancer the amount minus the commission.

[0592] Specific examples

[0593] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[0594] 1. Registering Client A and entering project information

[0595] The server receives basic information and project information from client A.

[0596] The terminal allows A to input Python and React skill sets.

[0597] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[0598] The server saves A's information in the database.

[0599] 2. Registration of Freelance B

[0600] The server receives a new registration request from Freelance B.

[0601] The terminal prompts B to input his skill set and past achievements.

[0602] The server analyzes using the generated AI model and extracts B's skill keywords.

[0603] The server saves B's information in the database.

[0604] 3. Notification of potential matches

[0605] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[0606] The server sends a notification of a potential match to Freelance B.

[0607] 4. Approval and Transaction Progress

[0608] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[0609] The server notifies A of the authorization information and arranges for direct contact.

[0610] The server monitors the transaction progress and pays the reward to B after completion.

[0611] In this way, the system of the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[0612] The processing flow will be explained below.

[0613] Step 1:

[0614] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[0615] Step 2:

[0616] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[0617] Step 3:

[0618] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[0619] Step 4:

[0620] The server stores the extracted skill sets and company information in a database.

[0621] Step 5:

[0622] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[0623] Step 6:

[0624] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[0625] Step 7:

[0626] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[0627] Step 8:

[0628] The server stores the extracted keywords and freelance information in a database.

[0629] Step 9:

[0630] The user (client) enters new project information. The terminal displays the project information input form.

[0631] Step 10:

[0632] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[0633] Step 11:

[0634] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[0635] Step 12:

[0636] The server searches the database for freelancers with the relevant skill set.

[0637] Step 13:

[0638] The server creates a list of applicable freelancers and selects the most suitable freelancer.

[0639] Step 14:

[0640] The server sends matching candidate information to the most suitable freelancer.

[0641] Step 15:

[0642] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[0643] Step 16:

[0644] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[0645] Step 17:

[0646] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[0647] Step 18:

[0648] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[0649] Step 19:

[0650] The user (client) notifies the server of project completion.

[0651] Step 20:

[0652] The server confirms the completion of the transaction and receives payment from the customer.

[0653] Step 21:

[0654] The server pays the freelancer the fee minus the commission.

[0655] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers.

[0656] Example 1

[0657] 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."

[0658] In conventional ordering systems, multiple subcontracting structures and opaque processes made it difficult to ensure fair and efficient matching between clients and freelancers. This often led to inefficiencies and unfair transactions. It also required a great deal of effort for clients to quickly find freelancers with the right skill sets.

[0659] 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.

[0660] In this invention, the server includes: means for receiving project information sent by a client; a generative AI model means for analyzing the project information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; means for saving basic information and transaction information from both the client and the freelancer in the database; and means for providing an interface for the generative AI model to analyze the project information and skill data. This makes it possible to quickly achieve direct and fair matching between client and freelancer, providing an efficient and highly transparent ordering process.

[0661] "Client" refers to an individual or company that requests work.

[0662] "Project information" refers to information provided by the client, such as project details, required skills, time frame, budget, etc.

[0663] A "generative AI model" is a type of artificial intelligence that analyzes given data with high precision and generates the desired results.

[0664] A "skill set" refers to the collection of skills and experience required to perform a particular job or role.

[0665] "Freelance" refers to a sole proprietor or contract employee who independently undertakes work.

[0666] A "database" refers to a system for efficiently managing and searching large amounts of data.

[0667] "Matching candidates" refer to freelancers who match the project information and are selected by the generative AI model.

[0668] "Transaction progress" refers to the progress of the ordered work.

[0669] "Remuneration" refers to the compensation paid to a freelancer upon completion of work.

[0670] An "interface" refers to the window or means through which a user operates or inputs data into a system.

[0671] This invention relates to a system that uses a generative AI model to directly match clients with freelancers. The purpose of this invention is to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. Specific embodiments are described below.

[0672] The system includes a server, terminals, and a generative AI model. The server centrally manages data on clients and freelancers and performs the necessary processing. The terminals provide an interface for clients and freelancers to input and display information. The generative AI model uses natural language processing technology to analyze project information and skill data and perform appropriate matching.

[0673] First, the client accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the client and displays a form on the terminal for entering basic information and project information. Once the client enters this information and submits it, the server uses a generative AI model to analyze the project information and extract the required skill sets. The extracted information is stored in a database.

[0674] Next, the freelancer also accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the freelancer and displays a form on the terminal for entering their skill set and past achievements. Once the freelancer enters and submits this information, the server uses a generative AI model to analyze the skill set and extract related skill keywords. The extracted information is also stored in a database.

[0675] When a client inputs new project information, the server again analyzes the project information using the generative AI model and extracts the required skill set. The server then searches the database for freelancers with the corresponding skill set, selects the most suitable candidate, and notifies them. The freelancer sends their intention to participate in the project to the server via their device, and the server notifies the client of that information. This allows the client and freelancer to communicate directly.

[0676] Furthermore, the server monitors the progress of the transaction and provides an interface for the client to update the progress information. When the transaction is completed, the server receives payment from the client and pays the remaining amount minus a commission to the freelancer.

[0677] As a concrete example, if Client A is looking for a freelancer with Python and React skills for a web development project, they can input the following prompt into the generative AI model:

[0678] "Please select a freelancer with the best Python and React skills for Client A's web development project."

[0679] In this way, the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[0680] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0681] Step 1: New customer registration

[0682] The server receives a new registration request from the user (orderer).

[0683] Input: New registration request from purchaser

[0684] Output: Basic information and case information input form

[0685] When the server receives the request, it displays a form on the terminal where the user can enter basic information (such as name, email address, and company information) and project information (such as project title, description, and required skills).

[0686] Step 2: Enter the job information

[0687] The terminal prompts the user (client) to enter basic information and project information, which is then sent to the server.

[0688] Input: Basic information of the client and project information

[0689] Output: Sending information to the server

[0690] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends the entered information to the server.

[0691] Step 3: Parse and save case information

[0692] The server analyzes the case information using a generative AI model and extracts the required skill sets.

[0693] Input: Purchaser's project information

[0694] Output: Extracted skill sets and client information stored in a database

[0695] The server inputs the case information into the generative AI model, which uses natural language processing technology to extract the skill sets required for the project, and stores the extracted information in a database.

[0696] Step 4: Register as a freelancer

[0697] The server receives a new registration request from a user (freelancer).

[0698] Input: New freelance registration request

[0699] Output: A form for inputting skillsets and achievements

[0700] When the server receives the request, it displays a form on the terminal for entering the skill set (programming languages, tools, etc.) and past achievements.

[0701] Step 5: Enter your freelance information

[0702] The terminal prompts the user (freelancer) to enter their skill set and past achievements, which are then sent to the server.

[0703] Input: Freelance skillset and past performance

[0704] Output: Sending information to the server

[0705] The user (freelancer) enters their skill set and past achievements and clicks the send button. The terminal sends the entered information to the server.

[0706] Step 6: Freelance information analysis and storage

[0707] The server uses a generative AI model to analyze the freelancer's input information and extract relevant skill keywords.

[0708] Input: Freelance skillset and track record information

[0709] Output: Extracted skill keywords and freelance information stored in a database

[0710] The server inputs freelancer information into the generative AI model and extracts relevant skill keywords, which are then stored in a database.

[0711] Step 7: Enter new job information

[0712] The user (client) enters new project information into the terminal and sends it to the server.

[0713] Input: Purchaser's new project information

[0714] Output: Sending information to the server

[0715] The user (client) enters new project information and clicks the send button. The terminal sends the information to the server.

[0716] Step 8: Reanalyze case information and extract skill sets

[0717] The server uses a generative AI model to analyze new case information and extract the required skill sets.

[0718] Input: Purchaser's new project information

[0719] Output: Extracted skillset

[0720] The server inputs new case information into the generative AI model and extracts the required skill sets.

[0721] Step 9: Search for freelancers

[0722] The server searches the database for freelancers with the relevant skill set.

[0723] Input: Extracted skillset

[0724] Output: A list of matching freelancers

[0725] Based on the skill set extracted by the server, the server searches for freelancers in the database and generates a list of relevant freelancers.

[0726] Step 10: Match selection and notification

[0727] The server selects the most suitable freelancer and notifies them as a matching candidate.

[0728] Input: List of applicable freelancers

[0729] Output: Optimal freelance notifications

[0730] The server will select the best freelancer from the list and send a notification.

[0731] Step 11: Freelance Approval

[0732] A user (freelancer) transmits his / her intention to participate in a project to the server via his / her terminal.

[0733] Input: Freelance participation intention

[0734] Output: Notification to the server

[0735] The freelancer enters their intention to participate in the project into their device and clicks the send button. The server receives the information.

[0736] Step 12: Final notification and adjustments

[0737] The server notifies the client of the approval information and arranges for the client and the freelancer to directly contact each other.

[0738] Input: Freelance approval information

[0739] Output: Notification to client and communication coordination

[0740] The server notifies the client of the approval information, and the client and the freelancer are set up to be able to contact each other directly.

[0741] Step 13: Monitor the progress of your transaction

[0742] The server provides an interface for users (orderers) to update them on the progress of the transaction.

[0743] Input: Transaction progress information

[0744] Output: Transaction progress update

[0745] The server provides an interface to the client to request progress information and receives updated information.

[0746] Step 14: Completing the transaction and paying out

[0747] The server confirms the completion of the project, receives payment from the user (client), and pays the freelancer.

[0748] Input: Transaction Completion Information and Payment

[0749] Output: Freelance payment

[0750] The server confirms the completion of the project, receives payment from the client, and pays the remaining amount minus the commission to the freelancer.

[0751] (Application example 1)

[0752] 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."

[0753] In factories, quickly and efficiently matching workers and robots with the skills required for specific tasks is a challenge. Currently, managers must manually coordinate workers and robots, which inevitably leads to work delays and human error. This has led to problems such as reduced work efficiency and increased costs.

[0754] 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.

[0755] In this invention, the server includes means for receiving job information sent by a client, a generating AI model means for analyzing the job information and extracting the required skill set, a means for searching a database for workers with the required skill set, a means for selecting the most suitable worker from the search results and notifying them as a matching candidate, a means for receiving the worker's approval of the matching candidate, a means for monitoring work progress and paying the worker a remuneration after the work is completed, a means for receiving and analyzing work task information within the factory and identifying the required skill set, and a means for searching for and matching workers or robots suitable for the work tasks. This enables efficient and fair matching of work tasks within the factory, improving work efficiency and reducing costs.

[0756] The "client" is the party that provides work tasks and case information to execute a business or project and manages its progress.

[0757] "Project information" is information provided by the client regarding the skills and conditions required for a work task or project.

[0758] A "generative AI model" is an artificial intelligence model that analyzes input information and extracts the necessary skill sets and conditions from it.

[0759] A "skill set" refers to the collection of skills and knowledge required to perform a particular job or task.

[0760] A "database" is a digital collection of information that can be centrally managed and searched for, including information on clients, workers, project information, and skill sets.

[0761] A "worker" is a person or automated robot with a specific skill set that performs work tasks based on case information.

[0762] A "matching candidate" is someone selected as the most suitable worker based on the skill set extracted by the generative AI model.

[0763] "Notification" refers to the act of informing matching candidates of selection information and project details via electronic means.

[0764] "Work progress" refers to the progress of work or projects being carried out based on case information.

[0765] "Remuneration" is the consideration paid by the client for the work that the worker has performed based on the project information.

[0766] The system for implementing this invention aims to improve work efficiency in factories. Specifically, it is a system that analyzes work task information provided by the client using an AI model and automatically matches the most suitable worker (or robot). This system consists of a server, terminals, and various software.

[0767] Hardware and Software Configuration

[0768] server

[0769] The server uses a web framework such as Flask to execute a web API to receive project information and skill sets sent by clients and workers.

[0770] The server uses a generative AI model (e.g., OpenAI API) to analyze the submitted job information and extract the required skill sets.

[0771] Terminal

[0772] The terminal provides an interface for the orderer and the worker to input information.

[0773] The information entered on the terminal is sent to the server and stored in a database.

[0774] Explained processing flow

[0775] 1. User (orderer) registration

[0776] The server receives a new registration request from the client and stores it in a database. The client enters basic information and project information on their device, which then sends it to the server. The server uses a generative AI model to analyze the project information and extract the required skill set.

[0777] 2. User (operator) registration

[0778] The server receives a new registration request from a worker and stores it in a database. The worker enters their skill set and past performance data on their device, which then sends it to the server. The server then uses a generative AI model to analyze the input information and extract skill keywords.

[0779] 3. Entering project information and matching

[0780] The client inputs new work task information. The server analyzes the task information and extracts the required skill set through a generative AI model. The server then searches the database for workers with the required skill set.

[0781] 4. Notification of potential matches

[0782] The server selects the most suitable worker and notifies the worker of that information. When the worker approves their intention to participate in the project, that information is sent to the server via their terminal. The server then provides the approval information to the client and arranges for the two parties to contact each other.

[0783] 5. Monitoring trading progress and reward payment

[0784] The server checks the progress of the work and updates the progress to the server. When the work is completed, the server receives payment from the client and pays the worker a reward.

[0785] Specific examples

[0786] The following example illustrates the operation of the system:

[0787] Prompt Sentence Examples

[0788] "What skill set is required for the following work task: Wiring and debugging a PLC?"

[0789] By inputting this prompt into a generative AI model, the model extracts the required skill set. For example, "PLC wiring," "debugging," and "electrical engineering" are extracted. Based on these skill sets, the server searches the database for the relevant worker and notifies the most suitable candidate.

[0790] In this way, this system can be used to efficiently match workers and robots with the necessary skills within a factory, dramatically improving work efficiency.

[0791] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0792] Step 1:

[0793] The server receives a new registration request sent by the client. The client uses a terminal to enter basic information and project information. The terminal sends this information to the server, which then analyzes the project information using a generative AI model. This analysis extracts the required skill set and stores it in a database.

[0794] Input: Basic information of the client and project information

[0795] Output: Client information and required skill sets stored in a database

[0796] Step 2:

[0797] The server receives a new registration request sent by a worker. The worker uses a terminal to input their own skill set and past performance. The terminal sends this information to the server, which then analyzes the input data using a generative AI model. The skill keywords extracted through the analysis are stored in a database.

[0798] Inputs: Worker skill set and past performance

[0799] Output: Worker information and skill keywords stored in the database

[0800] Step 3:

[0801] The client inputs new work task information into the terminal, which then sends the information to the server, which analyzes the task information using a generative AI model to extract the required skill set, then searches the database for workers who match that skill set.

[0802] Input: Work task information

[0803] Output: A list of workers that match the required skill set

[0804] Step 4:

[0805] The server selects the most suitable worker from the search results and notifies the worker as a matching candidate. The worker receives the notification and sends their intention to participate in the project to the server from their terminal. The server provides this approval information to the client and arranges for the two parties to contact each other.

[0806] Input: List of workers who match the required skill set, worker approval

[0807] Output: Information for both the client and the worker to contact each other

[0808] Step 5:

[0809] The server checks the progress of the work and provides the necessary interface. The client updates the progress to the server, and the information is saved in a database. When the work is completed, the server receives payment from the client and pays the worker a reward.

[0810] Input: Work progress, payment information from the client

[0811] Output: Reward payment and database update after transaction completion

[0812] In this way, a system that efficiently matches work tasks within a factory and manages progress is created through a series of steps. This system is expected to facilitate smooth cooperation between clients and workers and improve work efficiency.

[0813] 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.

[0814] This invention relates to a system that directly matches clients with IT freelancers using a generative AI model and an emotion engine. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, better matching is achieved by taking into account the user's emotional state.

[0815] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches a database for freelancers with matching skill sets, selects the most suitable candidate, and notifies both parties. It also uses an emotion engine to recognize the emotional state of the client and freelancer, and takes this into account when matching. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[0816] Program processing

[0817] 1. User (orderer) registration

[0818] The server receives a new registration request from the client.

[0819] The terminal allows the client to enter basic information and project information.

[0820] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[0821] The emotional engine analyzes the client's emotional state and adjusts the skill set to take this data into account.

[0822] The server stores the company's data in a database.

[0823] 2. User (freelance) registration

[0824] The server receives a new registration request from a freelancer.

[0825] The terminal allows freelancers to input their skill set and past performance.

[0826] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[0827] The emotion engine analyzes the freelancer's emotional state and adjusts the skill information taking this data into account.

[0828] The server stores the freelance data in a database.

[0829] 3. Entering project information and matching

[0830] The purchaser enters new project information.

[0831] The server analyzes the case information and extracts the required skill set through a generative AI model.

[0832] The server searches the database for freelancers with the relevant skill set.

[0833] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[0834] The server sends a notification of the best candidate to the freelancer.

[0835] 4. Match Approval and Notification

[0836] The freelancer confirms their intention to participate in the project.

[0837] The terminal sends the authorization information to the server.

[0838] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[0839] 5. Transaction progress monitoring and reward payment

[0840] It provides the interface necessary for the server to monitor the progress of the transaction.

[0841] The purchaser updates the transaction progress to the server.

[0842] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, automatically providing alerts and support based on their emotional state.

[0843] The client notifies the server of project completion.

[0844] The server confirms the completion of the transaction and receives payment from the customer.

[0845] The server pays the freelancer the amount minus the commission.

[0846] Specific examples

[0847] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[0848] 1. Registering Client A and entering project information

[0849] The server receives basic information and project information from client A.

[0850] The terminal allows A to input Python and React skill sets.

[0851] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[0852] The emotion engine analyzes A's emotional state and adjusts the skill set taking this data into account.

[0853] The server saves A's information in the database.

[0854] 2. Registration of Freelance B

[0855] The server receives a new registration request from Freelance B.

[0856] The terminal prompts B to input his skill set and past achievements.

[0857] The server analyzes using the generated AI model and extracts B's skill keywords.

[0858] The emotion engine analyzes B's emotional state and corrects the skill information taking this data into account.

[0859] The server saves B's information in the database.

[0860] 3. Notification of potential matches

[0861] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[0862] The emotion engine analyzes the emotional state of the client and the freelancer and selects B as the most suitable candidate.

[0863] The server sends a notification of a potential match to Freelance B.

[0864] 4. Approval and Transaction Progress

[0865] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[0866] The server notifies A of the authorization information and arranges for direct contact.

[0867] The server monitors the transaction progress and pays the reward to B after completion.

[0868] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[0869] The processing flow will be explained below.

[0870] Step 1:

[0871] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[0872] Step 2:

[0873] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[0874] Step 3:

[0875] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[0876] Step 4:

[0877] The emotion engine analyzes the client's emotional state and feeds this data into the generative AI model to correct the skill set.

[0878] Step 5:

[0879] The server stores the corrected skill set and company information in a database.

[0880] Step 6:

[0881] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[0882] Step 7:

[0883] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[0884] Step 8:

[0885] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[0886] Step 9:

[0887] The emotion engine analyzes the freelancer's emotional state and reflects this data in the generative AI model to correct skill keywords.

[0888] Step 10:

[0889] The server stores the corrected keywords and freelance information in a database.

[0890] Step 11:

[0891] The user (client) enters new project information. The terminal displays the project information input form.

[0892] Step 12:

[0893] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[0894] Step 13:

[0895] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[0896] Step 14:

[0897] The server searches the database for freelancers with the relevant skill set.

[0898] Step 15:

[0899] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[0900] Step 16:

[0901] The server sends a notification of a potential match to the most suitable freelancer.

[0902] Step 17:

[0903] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[0904] Step 18:

[0905] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[0906] Step 19:

[0907] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[0908] Step 20:

[0909] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[0910] Step 21:

[0911] The emotion engine monitors the progress of the deal in real time and automatically provides alerts and support based on the emotional state of the client and freelancer.

[0912] Step 22:

[0913] The user (client) notifies the server of project completion.

[0914] Step 23:

[0915] The server confirms the completion of the transaction and receives payment from the customer.

[0916] Step 24:

[0917] The server pays the freelancer the amount minus the commission.

[0918] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers at an even higher level by incorporating an emotion engine.

[0919] Example 2

[0920] 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."

[0921] Conventional matching systems between clients and IT freelancers focus on matching skill sets, but do not take into account the user's emotional state, which often leads to problems in actual transactions. Specifically, if the client is under high stress or the freelancer is dissatisfied, this can have a negative impact on the progress of the transaction and the quality of the deliverables. The challenge is to solve these problems and provide an efficient and fair ordering process.

[0922] 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 job information sent by the client; a generation AI model means for analyzing the job information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; and means including an emotion engine for analyzing the emotional states of the client and freelancer and taking this into consideration when matching. This enables matching and transactions that take the emotional states of the client and freelancer into consideration, making it possible to realize an efficient and fair ordering and purchase process.

[0923] "Project information" refers to detailed project information provided by the client, including required skill sets and work content.

[0924] A "generative AI model" is a system that uses machine learning algorithms to analyze data and extract necessary information.

[0925] "Freelance" refers to a worker who has the ability to independently accept and carry out work.

[0926] A "database" is a system that stores information in an organized manner and makes it easy to search and update.

[0927] An "emotion engine" is a system that has the ability to analyze the user's emotional state and respond appropriately based on that.

[0928] "Matching" is the process of comparing the client's project information with the freelancer's skill set and selecting the appropriate candidate.

[0929] "Transaction progress" is information indicating the progress of a project, and is used to evaluate the progress and achievement of work.

[0930] "Compensation" means the monetary compensation a Freelancer receives for completing a Project.

[0931] "Notification" is the act of the system conveying information to the user.

[0932] "Intention" refers to the freelancer's decision whether or not to participate in a project.

[0933] This invention relates to a system that directly matches clients with IT freelancers. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, it achieves better matching by taking into account the user's emotional state.

[0934] System configuration

[0935] This system mainly consists of a server, terminal, generative AI model, emotion engine, and database. The server is the core of the entire system and processes and manages various data. The terminal provides an interface for users to input data. The generative AI model is used to analyze project information and freelance skill sets. The emotion engine analyzes the user's emotional state and takes it into consideration when matching. The database is used to store information about clients and freelancers.

[0936] Program processing overview

[0937] 1. User (orderer) registration

[0938] The server receives a new registration request from the client and prompts them to enter basic information and project information via their terminal. The generative AI model analyzes this data and extracts the required skill set. The emotion engine analyzes the client's emotional state and adjusts the skill set. Finally, the server stores the client's data in a database.

[0939] 2. User (freelance) registration

[0940] The server receives a new registration request from a freelancer and prompts them to enter their skill set and past performance via their device. A generative AI model analyzes this data and extracts the freelancer's skill keywords. An emotion engine analyzes the freelancer's emotional state and corrects the skill information. The server saves the freelancer's data in a database.

[0941] 3. Entering project information and matching

[0942] When a client inputs new project information, the server uses the generative AI model to analyze the project information and extract the required skill set. The server then searches for freelancers in its database who have the relevant skill set, and an emotion engine analyzes the emotional states of the client and freelancer to select the most suitable match candidate. The server then notifies the freelancer of the most suitable candidate.

[0943] 4. Match Approval and Notification

[0944] When a freelancer approves their intention to participate in a project, the device sends the information to the server. The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[0945] 5. Transaction progress monitoring and reward payment

[0946] The server provides an interface for monitoring the progress of the transaction, and the client updates the transaction progress. The emotion engine monitors the emotional state of the client and freelancer in real time and provides alerts and support as needed. The client notifies the server of project completion, and the server confirms the completion of the transaction and then pays the freelancer the fee minus a commission.

[0947] Specific examples

[0948] For example, if Client A is looking for a freelancer with Python and React skills for a web development project, the process would be as follows:

[0949] Client A enters basic information and project information, and the generative AI model extracts Python and React skill sets.

[0950] The emotion engine analyzes the emotional state of client A and adjusts the skill set accordingly.

[0951] Freelance B registers and inputs his / her skill set and past achievements. The generative AI model analyzes the data and extracts skill keywords.

[0952] The server searches the database for freelancers with Python and React skills, and the emotion engine selects Freelance B as the best candidate.

[0953] Freelance B is notified of the potential match and approves the project.

[0954] The server notifies the client A of the approval information, monitors the progress of the transaction, and even makes the payment of the reward.

[0955] Prompt Sentence Examples

[0956] "Client A is looking for a freelancer with Python and React skills. Please select the best freelancer taking into consideration Client A's emotional state."

[0957] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[0958] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] Receiving a new registration request from a user (orderer)

[0961] The server receives a new registration request from the client. This is done by receiving data as an HTTP request using the POST method. The input is the client's basic information and job information, and the output is a response confirming receipt.

[0962] Step 2:

[0963] Enter basic information and project information

[0964] The terminal prompts the client to enter basic information (name, contact details, company information, etc.) and project information (project overview, required skills, etc.). Specifically, a web form is used, and the user enters data into the input fields. The input is the information entered by the client, and the output is the input data.

[0965] Step 3:

[0966] Analysis of project information and extraction of skill sets

[0967] The server uses the generated AI model to analyze project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​processes the data to extract keywords such as "Python" and "React." The output is the extracted skill set.

[0968] Step 4:

[0969] Emotional state analysis and skill set adjustment

[0970] The emotion engine analyzes the client's emotional state and adjusts the skill set. The input is the client's emotional information, and the emotion engine processes the data to evaluate the state of stress, relief, etc. For example, in a high-stress state, the skill set requirements are relaxed. The output is the adjusted skill set.

[0971] Step 5:

[0972] Data storage

[0973] The server saves the client's data in the database. The input is the corrected skill set and the client's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[0974] Step 6:

[0975] Receiving new freelance registration requests

[0976] The server receives a new registration request from a freelancer. This is done by receiving data as an HTTP request using the POST method. The input is the freelancer's basic information and skill information, and the output is a response confirming the registration.

[0977] Step 7:

[0978] Enter your skill set and past achievements

[0979] The terminal allows the freelancer to input their skill set and past performance. Specifically, a web form is used, and the user enters data into input fields. The input is the information entered by the freelancer, and the output is the input data.

[0980] Step 8:

[0981] Analyzing input data and extracting skill keywords

[0982] The server uses the generated AI model to analyze the freelancer's input data and extract skill keywords. The input is the skill information entered by the freelancer, and the AI ​​processes the data to extract keywords such as "JavaScript" and "database management." The output is the extracted skill keywords.

[0983] Step 9:

[0984] Emotional state analysis and skill information correction

[0985] The emotion engine analyzes the freelancer's emotional state and corrects the skill information. The input is the freelancer's emotional information, and the emotion engine processes the data to evaluate their state, such as their motivation and sense of security. For example, if they feel secure, detailed achievement information is emphasized. The output is corrected skill information.

[0986] Step 10:

[0987] Data storage

[0988] The server saves the freelancer's data in a database. The input is the corrected skill information and the freelancer's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[0989] Step 11:

[0990] Entering project information

[0991] The client inputs new job information. The input is the new job information from the client, and the client enters data into the input fields using a web form. The output is the entered job information.

[0992] Step 12:

[0993] Analysis of project information

[0994] The server uses the generated AI model to analyze the project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​extracts the skill sets as data processing. The output is the extracted skill sets.

[0995] Step 13:

[0996] Freelance Search

[0997] The server searches for freelancers in the database who have the corresponding skill set. The input is the extracted skill set, and a SQL query is used to process the data and filter the matching freelancers. The output is the search result.

[0998] Step 14:

[0999] Emotional state analysis and optimal candidate selection

[1000] The emotion engine analyzes the emotional state of the freelancer and client and selects the optimal match candidate. The input is the emotional information of the client and freelancer, and the emotion engine processes the data by evaluating their emotional state and calculating the matching success rate. The output is the optimal match candidate.

[1001] Step 15:

[1002] Notification of potential matches

[1003] The server notifies the freelancer of the best candidate. The input is the best match candidate, and the output is a notification message to the freelancer. The specific operation is to send a notification to the freelancer via email or SMS.

[1004] Step 16:

[1005] Approval of intention to participate in the project

[1006] The freelancer approves their intention to participate in the project. The input is the freelancer's intention to participate, and the output is the approval information. Specifically, the freelancer clicks the "Participate" button on the dashboard.

[1007] Step 17:

[1008] Sending approval information

[1009] The terminal sends the approval information to the server. The input is the freelancer's approval information, and the data is sent to the server as an HTTP request using the POST method. The output is a notification to the server.

[1010] Step 18:

[1011] Receiving and adjusting approval information

[1012] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact. The input is the freelancer's approval information, and the output is a notification to the client and the freelancer. Specific operations include sending email notifications to both parties and providing contact details.

[1013] Step 19:

[1014] Providing a progress monitoring interface

[1015] The server provides an interface for monitoring the progress of transactions. The input is an access request to the progress monitoring system, and the output is a display of the progress. Specific operation is to provide a UI that allows the progress to be viewed on a web portal or dashboard.

[1016] Step 20:

[1017] Progress Updates

[1018] The purchaser updates the transaction progress to the server. The input is the purchaser's updated progress information, and the output is the updated result in the database. In concrete terms, the purchaser enters the task completion status on the dashboard.

[1019] Step 21:

[1020] Real-time emotional state monitoring and support

[1021] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, providing alerts and support as needed. The input is real-time emotional information, and the emotion engine evaluates the emotional state as data processing. The output is alerts and support messages as needed. For example, if stress increases, a warning message is automatically sent.

[1022] Step 22:

[1023] Project Completion Notification

[1024] The client notifies the server that the project is complete. The input is the client's notification of project completion, and the output is an update of the completion status to the database. The specific action is that the client clicks the "Complete" button on the dashboard.

[1025] Step 23:

[1026] Confirmation of transaction completion and payment

[1027] The server confirms the completion of the transaction and receives payment from the client. The input is a notification of project completion, and the output is payment processing to the freelancer. Specifically, the server processes the payment through a payment gateway.

[1028] The server pays the freelancer the amount minus the fee. The input is a confirmation of the transaction completion, and the output is an automatic transfer to the freelancer's bank account.

[1029] (Application example 2)

[1030] 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."

[1031] In food delivery, efficient and appropriate delivery partner matching is necessary to ensure customers receive their food quickly and reliably. However, conventional systems often fail to fully consider the customer's emotional state or the suitability of the delivery partner, resulting in inefficiency and dissatisfaction. Furthermore, extracting job information and skill sets is a time-consuming and labor-intensive process. To solve these issues, an advanced matching system using generative AI models and emotion engines is needed.

[1032] The identification process 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 order information sent by the orderer; a generative AI model means for analyzing the order information and extracting necessary conditions; means for searching a database for delivery partners who meet the necessary conditions; means for selecting the most suitable delivery partner from the search results and notifying them as a matching candidate; means for receiving the delivery partner's approval of the matching candidate; means for monitoring the progress of the transaction and paying a reward to the delivery partner after the transaction is completed; and an emotion engine means for analyzing the emotional states of the orderer and delivery partner and adjusting the matching conditions. This enables efficient and appropriate matching that takes into account the emotional state of the customer and the suitability of the delivery partner.

[1033] An "orderer" is a user who places an order for a service or product.

[1034] "Order information" refers to detailed information provided by a purchaser when ordering a service or product.

[1035] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and extract and process specific information.

[1036] "Conditions" means specific requirements or requirements parsed from the Order Information.

[1037] A database is a digital storage system that systematically organizes information so that it can be searched and used efficiently.

[1038] "Delivery Partner" means an individual or company responsible for delivering ordered products to customers.

[1039] "Matching candidates" refer to delivery partners who are likely to meet the optimal conditions based on order information.

[1040] The "emotion engine" is a system that analyzes the user's emotional state and performs appropriate processing and corrections based on the data.

[1041] "Deal Progress" refers to the status of the current stage of a deal.

[1042] "Remuneration" means money or other items of value paid in exchange for services rendered.

[1043] This invention relates to a food delivery system that efficiently matches customers (orderers) with delivery partners. The system consists of a server, a generative AI model, an emotion engine, a database, and a terminal used by the user.

[1044] Program Generation

[1045] The system works as follows: When the server receives the order information entered by the customer, it analyzes the order information using a generative AI model and extracts the necessary conditions. Based on the extracted conditions, the server searches the delivery partner information in its database and selects candidates who meet the conditions.

[1046] Furthermore, the server uses an emotion engine to analyze the emotional state of the orderer and delivery partner, and adjusts the matching conditions based on the analysis results, enabling efficient matching that takes into account the emotional state of the orderer and the suitability of the delivery partner.

[1047] For example, if a customer in a hurry orders a pizza, the system will prioritize delivery partners who can respond quickly. This is achieved by the emotion engine analyzing the customer's emotional state of "being in a hurry" and reflecting this in the conditions.

[1048] Hardware and Software Use

[1049] The system utilizes the following hardware and software:

[1050] Hardware: Smartphones, cloud servers

[1051] Software: Python (generative AI model), TensorFlow or PyTorch (emotion engine), React Native (smartphone application development)

[1052] The generative AI model is built in Python and deployed on a server. The emotion engine is built using TensorFlow or PyTorch and operates in real time to analyze the user's emotional state. The smartphone application is developed using React Native, providing an intuitive interface for users.

[1053] Specific examples

[1054] For example, when Customer A orders a pizza using a smartphone app, the server performs the following steps:

[1055] 1. Receive order information from the application.

[1056] 2. The order information is analyzed using a generative AI model to extract the necessary delivery conditions (type of food, delivery time, etc.).

[1057] 3. Search for the relevant delivery partner in the database and use the emotion engine to analyze that Customer A is in a hurry.

[1058] 4. Delivery partner B, who can deliver quickly, is selected and notified as a matching candidate.

[1059] Example prompt: "Customer A has ordered a pizza delivery and is in a rush. Please find the delivery partner who is available with the highest priority."

[1060] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1061] Step 1:

[1062] The user (orderer) uses a terminal to input order information. The terminal sends the basic information and order information (e.g., type of food, desired delivery time) provided by the orderer to the server. The input includes the type of food and desired delivery time, and the output includes the order information sent to the server.

[1063] Step 2:

[1064] The server analyzes the received order information. It uses a generative AI model to extract the necessary conditions from the order information. Specifically, it receives the order information as input, and the generative AI model extracts the conditions (e.g., delivery speed, type of food). The output is the analyzed conditions.

[1065] Step 3:

[1066] The server searches the delivery partner information in the database and finds delivery partners that match the criteria. The input is the criteria extracted in step 2, and the output is a list of matching delivery partners. The server selects the most suitable delivery partner candidates based on this list.

[1067] Step 4:

[1068] The server uses an emotion engine to analyze the emotional states of the orderer and delivery partner. The inputs are the orderer's emotional data and the delivery partner's emotional data, and the output is a correction condition based on the emotional state. The emotion engine operates in real time and reflects specific conditions, such as when the orderer is in a hurry.

[1069] Step 5:

[1070] The server combines the results of steps 3 and 4 to select the best match candidate. The input is the list of delivery partners and the adjusted conditions, and the output is the best match candidate. This selection includes prioritizing delivery partners that take into account the customer's urgent situation.

[1071] Step 6:

[1072] The server notifies the best match candidates. The selected delivery partner is notified of the match candidates and the delivery partner is asked whether to accept them. The input is the match candidates, and the output is the notification sent to the delivery partner.

[1073] Step 7:

[1074] The server receives the delivery partner's intention and determines the final match. If the delivery partner approves the match candidate, the server notifies both the orderer and the delivery partner of the final matching information and begins the transaction. The input is the delivery partner's approval information, and the output is the final matching information.

[1075] Step 8:

[1076] The server monitors the progress of the transaction. The purchaser acknowledges receipt of the order and provides real-time updates on the progress of the transaction. The input is the transaction progress data, and the output is the updated progress.

[1077] Step 9:

[1078] The server pays the reward to the delivery partner after the transaction is completed. It confirms that the transaction is completed, receives payment from the customer, and transfers the amount minus the commission to the delivery partner. The inputs are transaction completion confirmation information and payment information, and the output is the transfer of the reward.

[1079] 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.

[1080] 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.

[1081] 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.

[1082] [Third embodiment]

[1083] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1084] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1085] 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).

[1086] 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.

[1087] 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.

[1088] 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).

[1089] 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.

[1090] 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.

[1091] 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.

[1092] 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.

[1093] 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.

[1094] 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."

[1095] This invention relates to a system that uses generative AI models to directly match clients with IT freelancers. This invention eliminates the multi-tiered subcontracting structure and provides a fair and efficient ordering process.

[1096] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches the database for freelancers with matching skill sets, selects the best candidate, and notifies both parties. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[1097] Program processing

[1098] 1. User (orderer) registration

[1099] The server receives a new registration request from the client.

[1100] The terminal allows the client to enter basic information and project information.

[1101] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[1102] The server stores the company's data in a database.

[1103] 2. User (freelance) registration

[1104] The server receives a new registration request from a freelancer.

[1105] The terminal allows freelancers to input their skill set and past performance.

[1106] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[1107] The server stores the freelance data in a database.

[1108] 3. Entering project information and matching

[1109] The purchaser enters new project information.

[1110] The server analyzes the case information and extracts the required skill set through a generative AI model.

[1111] The server searches the database for freelancers with the relevant skill set.

[1112] The server selects the best candidates and notifies the freelancer of the matching candidates.

[1113] 4. Match Approval and Notification

[1114] The freelancer confirms their intention to participate in the project.

[1115] The terminal sends the authorization information to the server.

[1116] The server provides the client and the freelancer with the final matching information and arranges for direct contact.

[1117] 5. Transaction progress monitoring and reward payment

[1118] It provides the interface necessary for the server to monitor the progress of the transaction.

[1119] The purchaser updates the transaction progress to the server.

[1120] The server confirms the completion of the project and receives payment from the client.

[1121] The server pays the freelancer the amount minus the commission.

[1122] Specific examples

[1123] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[1124] 1. Registering Client A and entering project information

[1125] The server receives basic information and project information from client A.

[1126] The terminal allows A to input Python and React skill sets.

[1127] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[1128] The server saves A's information in the database.

[1129] 2. Registration of Freelance B

[1130] The server receives a new registration request from Freelance B.

[1131] The terminal prompts B to input his skill set and past achievements.

[1132] The server analyzes using the generated AI model and extracts B's skill keywords.

[1133] The server saves B's information in the database.

[1134] 3. Notification of potential matches

[1135] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[1136] The server sends a notification of a potential match to Freelance B.

[1137] 4. Approval and Transaction Progress

[1138] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[1139] The server notifies A of the authorization information and arranges for direct contact.

[1140] The server monitors the transaction progress and pays the reward to B after completion.

[1141] In this way, the system of the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[1142] The processing flow will be explained below.

[1143] Step 1:

[1144] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[1145] Step 2:

[1146] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[1147] Step 3:

[1148] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[1149] Step 4:

[1150] The server stores the extracted skill sets and company information in a database.

[1151] Step 5:

[1152] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[1153] Step 6:

[1154] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[1155] Step 7:

[1156] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[1157] Step 8:

[1158] The server stores the extracted keywords and freelance information in a database.

[1159] Step 9:

[1160] The user (client) enters new project information. The terminal displays the project information input form.

[1161] Step 10:

[1162] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[1163] Step 11:

[1164] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[1165] Step 12:

[1166] The server searches the database for freelancers with the relevant skill set.

[1167] Step 13:

[1168] The server creates a list of applicable freelancers and selects the most suitable freelancer.

[1169] Step 14:

[1170] The server sends matching candidate information to the most suitable freelancer.

[1171] Step 15:

[1172] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[1173] Step 16:

[1174] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[1175] Step 17:

[1176] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[1177] Step 18:

[1178] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[1179] Step 19:

[1180] The user (client) notifies the server of project completion.

[1181] Step 20:

[1182] The server confirms the completion of the transaction and receives payment from the customer.

[1183] Step 21:

[1184] The server pays the freelancer the fee minus the commission.

[1185] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers.

[1186] Example 1

[1187] 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."

[1188] In conventional ordering systems, multiple subcontracting structures and opaque processes made it difficult to ensure fair and efficient matching between clients and freelancers. This often led to inefficiencies and unfair transactions. It also required a great deal of effort for clients to quickly find freelancers with the right skill sets.

[1189] 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.

[1190] In this invention, the server includes: means for receiving project information sent by a client; a generative AI model means for analyzing the project information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; means for saving basic information and transaction information from both the client and the freelancer in the database; and means for providing an interface for the generative AI model to analyze the project information and skill data. This makes it possible to quickly achieve direct and fair matching between client and freelancer, providing an efficient and highly transparent ordering process.

[1191] "Client" refers to an individual or company that requests work.

[1192] "Project information" refers to information provided by the client, such as project details, required skills, time frame, budget, etc.

[1193] A "generative AI model" is a type of artificial intelligence that analyzes given data with high precision and generates the desired results.

[1194] A "skill set" refers to the collection of skills and experience required to perform a particular job or role.

[1195] "Freelance" refers to a sole proprietor or contract employee who independently undertakes work.

[1196] A "database" refers to a system for efficiently managing and searching large amounts of data.

[1197] "Matching candidates" refer to freelancers who match the project information and are selected by the generative AI model.

[1198] "Transaction progress" refers to the progress of the ordered work.

[1199] "Remuneration" refers to the compensation paid to a freelancer upon completion of work.

[1200] An "interface" refers to the window or means through which a user operates or inputs data into a system.

[1201] This invention relates to a system that uses a generative AI model to directly match clients with freelancers. The purpose of this invention is to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. Specific embodiments are described below.

[1202] The system includes a server, terminals, and a generative AI model. The server centrally manages data on clients and freelancers and performs the necessary processing. The terminals provide an interface for clients and freelancers to input and display information. The generative AI model uses natural language processing technology to analyze project information and skill data and perform appropriate matching.

[1203] First, the client accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the client and displays a form on the terminal for entering basic information and project information. Once the client enters this information and submits it, the server uses a generative AI model to analyze the project information and extract the required skill sets. The extracted information is stored in a database.

[1204] Next, the freelancer also accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the freelancer and displays a form on the terminal for entering their skill set and past achievements. Once the freelancer enters and submits this information, the server uses a generative AI model to analyze the skill set and extract related skill keywords. The extracted information is also stored in a database.

[1205] When a client inputs new project information, the server again analyzes the project information using the generative AI model and extracts the required skill set. The server then searches the database for freelancers with the corresponding skill set, selects the most suitable candidate, and notifies them. The freelancer sends their intention to participate in the project to the server via their device, and the server notifies the client of that information. This allows the client and freelancer to communicate directly.

[1206] Furthermore, the server monitors the progress of the transaction and provides an interface for the client to update the progress information. When the transaction is completed, the server receives payment from the client and pays the remaining amount minus a commission to the freelancer.

[1207] As a concrete example, if Client A is looking for a freelancer with Python and React skills for a web development project, they can input the following prompt into the generative AI model:

[1208] "Please select a freelancer with the best Python and React skills for Client A's web development project."

[1209] In this way, the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[1210] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1211] Step 1: New customer registration

[1212] The server receives a new registration request from the user (orderer).

[1213] Input: New registration request from purchaser

[1214] Output: Basic information and case information input form

[1215] When the server receives the request, it displays a form on the terminal where the user can enter basic information (such as name, email address, and company information) and project information (such as project title, description, and required skills).

[1216] Step 2: Enter the job information

[1217] The terminal prompts the user (client) to enter basic information and project information, which is then sent to the server.

[1218] Input: Basic information of the client and project information

[1219] Output: Sending information to the server

[1220] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends the entered information to the server.

[1221] Step 3: Parse and save case information

[1222] The server analyzes the case information using a generative AI model and extracts the required skill sets.

[1223] Input: Purchaser's project information

[1224] Output: Extracted skill sets and client information stored in a database

[1225] The server inputs the case information into the generative AI model, which uses natural language processing technology to extract the skill sets required for the project, and stores the extracted information in a database.

[1226] Step 4: Register as a freelancer

[1227] The server receives a new registration request from a user (freelancer).

[1228] Input: New freelance registration request

[1229] Output: A form for inputting skillsets and achievements

[1230] When the server receives the request, it displays a form on the terminal for entering the skill set (programming languages, tools, etc.) and past achievements.

[1231] Step 5: Enter your freelance information

[1232] The terminal prompts the user (freelancer) to enter their skill set and past achievements, which are then sent to the server.

[1233] Input: Freelance skillset and past performance

[1234] Output: Sending information to the server

[1235] The user (freelancer) enters their skill set and past achievements and clicks the send button. The terminal sends the entered information to the server.

[1236] Step 6: Freelance information analysis and storage

[1237] The server uses a generative AI model to analyze the freelancer's input information and extract relevant skill keywords.

[1238] Input: Freelance skillset and track record information

[1239] Output: Extracted skill keywords and freelance information stored in a database

[1240] The server inputs freelancer information into the generative AI model and extracts relevant skill keywords, which are then stored in a database.

[1241] Step 7: Enter new job information

[1242] The user (client) enters new project information into the terminal and sends it to the server.

[1243] Input: Purchaser's new project information

[1244] Output: Sending information to the server

[1245] The user (client) enters new project information and clicks the send button. The terminal sends the information to the server.

[1246] Step 8: Reanalyze case information and extract skill sets

[1247] The server uses a generative AI model to analyze new case information and extract the required skill sets.

[1248] Input: Purchaser's new project information

[1249] Output: Extracted skillset

[1250] The server inputs new case information into the generative AI model and extracts the required skill sets.

[1251] Step 9: Search for freelancers

[1252] The server searches the database for freelancers with the relevant skill set.

[1253] Input: Extracted skillset

[1254] Output: A list of matching freelancers

[1255] Based on the skill set extracted by the server, the server searches for freelancers in the database and generates a list of relevant freelancers.

[1256] Step 10: Match selection and notification

[1257] The server selects the most suitable freelancer and notifies them as a matching candidate.

[1258] Input: List of applicable freelancers

[1259] Output: Optimal freelance notifications

[1260] The server will select the best freelancer from the list and send a notification.

[1261] Step 11: Freelance Approval

[1262] A user (freelancer) transmits his / her intention to participate in a project to the server via his / her terminal.

[1263] Input: Freelance participation intention

[1264] Output: Notification to the server

[1265] The freelancer enters their intention to participate in the project into their device and clicks the send button. The server receives the information.

[1266] Step 12: Final notification and adjustments

[1267] The server notifies the client of the approval information and arranges for the client and the freelancer to directly contact each other.

[1268] Input: Freelance approval information

[1269] Output: Notification to client and communication coordination

[1270] The server notifies the client of the approval information, and the client and the freelancer are set up to be able to contact each other directly.

[1271] Step 13: Monitor the progress of your transaction

[1272] The server provides an interface for users (orderers) to update them on the progress of the transaction.

[1273] Input: Transaction progress information

[1274] Output: Transaction progress update

[1275] The server provides an interface to the client to request progress information and receives updated information.

[1276] Step 14: Completing the transaction and paying out

[1277] The server confirms the completion of the project, receives payment from the user (client), and pays the freelancer.

[1278] Input: Transaction Completion Information and Payment

[1279] Output: Freelance payment

[1280] The server confirms the completion of the project, receives payment from the client, and pays the remaining amount minus the commission to the freelancer.

[1281] (Application example 1)

[1282] 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."

[1283] In factories, quickly and efficiently matching workers and robots with the skills required for specific tasks is a challenge. Currently, managers must manually coordinate workers and robots, which inevitably leads to work delays and human error. This has led to problems such as reduced work efficiency and increased costs.

[1284] 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.

[1285] In this invention, the server includes means for receiving job information sent by a client, a generating AI model means for analyzing the job information and extracting the required skill set, a means for searching a database for workers with the required skill set, a means for selecting the most suitable worker from the search results and notifying them as a matching candidate, a means for receiving the worker's approval of the matching candidate, a means for monitoring work progress and paying the worker a remuneration after the work is completed, a means for receiving and analyzing work task information within the factory and identifying the required skill set, and a means for searching for and matching workers or robots suitable for the work tasks. This enables efficient and fair matching of work tasks within the factory, improving work efficiency and reducing costs.

[1286] The "client" is the party that provides work tasks and case information to execute a business or project and manages its progress.

[1287] "Project information" is information provided by the client regarding the skills and conditions required for a work task or project.

[1288] A "generative AI model" is an artificial intelligence model that analyzes input information and extracts the necessary skill sets and conditions from it.

[1289] A "skill set" refers to the collection of skills and knowledge required to perform a particular job or task.

[1290] A "database" is a digital collection of information that can be centrally managed and searched for, including information on clients, workers, project information, and skill sets.

[1291] A "worker" is a person or automated robot with a specific skill set that performs work tasks based on case information.

[1292] A "matching candidate" is someone selected as the most suitable worker based on the skill set extracted by the generative AI model.

[1293] "Notification" refers to the act of informing matching candidates of selection information and project details via electronic means.

[1294] "Work progress" refers to the progress of work or projects being carried out based on case information.

[1295] "Remuneration" is the consideration paid by the client for the work that the worker has performed based on the project information.

[1296] The system for implementing this invention aims to improve work efficiency in factories. Specifically, it is a system that analyzes work task information provided by the client using an AI model and automatically matches the most suitable worker (or robot). This system consists of a server, terminals, and various software.

[1297] Hardware and Software Configuration

[1298] server

[1299] The server uses a web framework such as Flask to execute a web API to receive project information and skill sets sent by clients and workers.

[1300] The server uses a generative AI model (e.g., OpenAI API) to analyze the submitted job information and extract the required skill sets.

[1301] Terminal

[1302] The terminal provides an interface for the orderer and the worker to input information.

[1303] The information entered on the terminal is sent to the server and stored in a database.

[1304] Explained processing flow

[1305] 1. User (orderer) registration

[1306] The server receives a new registration request from the client and stores it in a database. The client enters basic information and project information on their device, which then sends it to the server. The server uses a generative AI model to analyze the project information and extract the required skill set.

[1307] 2. User (operator) registration

[1308] The server receives a new registration request from a worker and stores it in a database. The worker enters their skill set and past performance data on their device, which then sends it to the server. The server then uses a generative AI model to analyze the input information and extract skill keywords.

[1309] 3. Entering project information and matching

[1310] The client inputs new work task information. The server analyzes the task information and extracts the required skill set through a generative AI model. The server then searches the database for workers with the required skill set.

[1311] 4. Notification of potential matches

[1312] The server selects the most suitable worker and notifies the worker of that information. When the worker approves their intention to participate in the project, that information is sent to the server via their terminal. The server then provides the approval information to the client and arranges for the two parties to contact each other.

[1313] 5. Monitoring trading progress and reward payment

[1314] The server checks the progress of the work and updates the progress to the server. When the work is completed, the server receives payment from the client and pays the worker a reward.

[1315] Specific examples

[1316] The following example illustrates the operation of the system:

[1317] Prompt Sentence Examples

[1318] "What skill set is required for the following work task: Wiring and debugging a PLC?"

[1319] By inputting this prompt into a generative AI model, the model extracts the required skill set. For example, "PLC wiring," "debugging," and "electrical engineering" are extracted. Based on these skill sets, the server searches the database for the relevant worker and notifies the most suitable candidate.

[1320] In this way, this system can be used to efficiently match workers and robots with the necessary skills within a factory, dramatically improving work efficiency.

[1321] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1322] Step 1:

[1323] The server receives a new registration request sent by the client. The client uses a terminal to enter basic information and project information. The terminal sends this information to the server, which then analyzes the project information using a generative AI model. This analysis extracts the required skill set and stores it in a database.

[1324] Input: Basic information of the client and project information

[1325] Output: Client information and required skill sets stored in a database

[1326] Step 2:

[1327] The server receives a new registration request sent by a worker. The worker uses a terminal to input their own skill set and past performance. The terminal sends this information to the server, which then analyzes the input data using a generative AI model. The skill keywords extracted through the analysis are stored in a database.

[1328] Inputs: Worker skill set and past performance

[1329] Output: Worker information and skill keywords stored in the database

[1330] Step 3:

[1331] The client inputs new work task information into the terminal, which then sends the information to the server, which analyzes the task information using a generative AI model to extract the required skill set, then searches the database for workers who match that skill set.

[1332] Input: Work task information

[1333] Output: A list of workers that match the required skill set

[1334] Step 4:

[1335] The server selects the most suitable worker from the search results and notifies the worker as a matching candidate. The worker receives the notification and sends their intention to participate in the project to the server from their terminal. The server provides this approval information to the client and arranges for the two parties to contact each other.

[1336] Input: List of workers who match the required skill set, worker approval

[1337] Output: Information for both the client and the worker to contact each other

[1338] Step 5:

[1339] The server checks the progress of the work and provides the necessary interface. The client updates the progress to the server, and the information is saved in a database. When the work is completed, the server receives payment from the client and pays the worker a reward.

[1340] Input: Work progress, payment information from the client

[1341] Output: Reward payment and database update after transaction completion

[1342] In this way, a system that efficiently matches work tasks within a factory and manages progress is created through a series of steps. This system is expected to facilitate smooth cooperation between clients and workers and improve work efficiency.

[1343] 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.

[1344] This invention relates to a system that directly matches clients with IT freelancers using a generative AI model and an emotion engine. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, better matching is achieved by taking into account the user's emotional state.

[1345] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches a database for freelancers with matching skill sets, selects the most suitable candidate, and notifies both parties. It also uses an emotion engine to recognize the emotional state of the client and freelancer, and takes this into account when matching. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[1346] Program processing

[1347] 1. User (orderer) registration

[1348] The server receives a new registration request from the client.

[1349] The terminal allows the client to enter basic information and project information.

[1350] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[1351] The emotional engine analyzes the client's emotional state and adjusts the skill set to take this data into account.

[1352] The server stores the company's data in a database.

[1353] 2. User (freelance) registration

[1354] The server receives a new registration request from a freelancer.

[1355] The terminal allows freelancers to input their skill set and past performance.

[1356] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[1357] The emotion engine analyzes the freelancer's emotional state and adjusts the skill information taking this data into account.

[1358] The server stores the freelance data in a database.

[1359] 3. Entering project information and matching

[1360] The purchaser enters new project information.

[1361] The server analyzes the case information and extracts the required skill set through a generative AI model.

[1362] The server searches the database for freelancers with the relevant skill set.

[1363] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[1364] The server sends a notification of the best candidate to the freelancer.

[1365] 4. Match Approval and Notification

[1366] The freelancer confirms their intention to participate in the project.

[1367] The terminal sends the authorization information to the server.

[1368] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[1369] 5. Transaction progress monitoring and reward payment

[1370] It provides the interface necessary for the server to monitor the progress of the transaction.

[1371] The purchaser updates the transaction progress to the server.

[1372] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, automatically providing alerts and support based on their emotional state.

[1373] The client notifies the server of project completion.

[1374] The server confirms the completion of the transaction and receives payment from the customer.

[1375] The server pays the freelancer the amount minus the commission.

[1376] Specific examples

[1377] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[1378] 1. Registering Client A and entering project information

[1379] The server receives basic information and project information from client A.

[1380] The terminal allows A to input Python and React skill sets.

[1381] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[1382] The emotion engine analyzes A's emotional state and adjusts the skill set taking this data into account.

[1383] The server saves A's information in the database.

[1384] 2. Registration of Freelance B

[1385] The server receives a new registration request from Freelance B.

[1386] The terminal prompts B to input his skill set and past achievements.

[1387] The server analyzes using the generated AI model and extracts B's skill keywords.

[1388] The emotion engine analyzes B's emotional state and corrects the skill information taking this data into account.

[1389] The server saves B's information in the database.

[1390] 3. Notification of potential matches

[1391] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[1392] The emotion engine analyzes the emotional state of the client and the freelancer and selects B as the most suitable candidate.

[1393] The server sends a notification of a potential match to Freelance B.

[1394] 4. Approval and Transaction Progress

[1395] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[1396] The server notifies A of the authorization information and arranges for direct contact.

[1397] The server monitors the transaction progress and pays the reward to B after completion.

[1398] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[1399] The processing flow will be explained below.

[1400] Step 1:

[1401] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[1402] Step 2:

[1403] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[1404] Step 3:

[1405] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[1406] Step 4:

[1407] The emotion engine analyzes the client's emotional state and feeds this data into the generative AI model to correct the skill set.

[1408] Step 5:

[1409] The server stores the corrected skill set and company information in a database.

[1410] Step 6:

[1411] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[1412] Step 7:

[1413] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[1414] Step 8:

[1415] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[1416] Step 9:

[1417] The emotion engine analyzes the freelancer's emotional state and reflects this data in the generative AI model to correct skill keywords.

[1418] Step 10:

[1419] The server stores the corrected keywords and freelance information in a database.

[1420] Step 11:

[1421] The user (client) enters new project information. The terminal displays the project information input form.

[1422] Step 12:

[1423] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[1424] Step 13:

[1425] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[1426] Step 14:

[1427] The server searches the database for freelancers with the relevant skill set.

[1428] Step 15:

[1429] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[1430] Step 16:

[1431] The server sends a notification of a potential match to the most suitable freelancer.

[1432] Step 17:

[1433] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[1434] Step 18:

[1435] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[1436] Step 19:

[1437] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[1438] Step 20:

[1439] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[1440] Step 21:

[1441] The emotion engine monitors the progress of the deal in real time and automatically provides alerts and support based on the emotional state of the client and freelancer.

[1442] Step 22:

[1443] The user (client) notifies the server of project completion.

[1444] Step 23:

[1445] The server confirms the completion of the transaction and receives payment from the customer.

[1446] Step 24:

[1447] The server pays the freelancer the amount minus the commission.

[1448] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers at an even higher level by incorporating an emotion engine.

[1449] Example 2

[1450] 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."

[1451] Conventional matching systems between clients and IT freelancers focus on matching skill sets, but do not take into account the user's emotional state, which often leads to problems in actual transactions. Specifically, if the client is under high stress or the freelancer is dissatisfied, this can have a negative impact on the progress of the transaction and the quality of the deliverables. The challenge is to solve these problems and provide an efficient and fair ordering process.

[1452] 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 job information sent by the client; a generation AI model means for analyzing the job information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; and means including an emotion engine for analyzing the emotional states of the client and freelancer and taking this into consideration when matching. This enables matching and transactions that take the emotional states of the client and freelancer into consideration, making it possible to realize an efficient and fair ordering and purchase process.

[1453] "Project information" refers to detailed project information provided by the client, including required skill sets and work content.

[1454] A "generative AI model" is a system that uses machine learning algorithms to analyze data and extract necessary information.

[1455] "Freelance" refers to a worker who has the ability to independently accept and carry out work.

[1456] A "database" is a system that stores information in an organized manner and makes it easy to search and update.

[1457] An "emotion engine" is a system that has the ability to analyze the user's emotional state and respond appropriately based on that.

[1458] "Matching" is the process of comparing the client's project information with the freelancer's skill set and selecting the appropriate candidate.

[1459] "Transaction progress" is information indicating the progress of a project, and is used to evaluate the progress and achievement of work.

[1460] "Compensation" means the monetary compensation a Freelancer receives for completing a Project.

[1461] "Notification" is the act of the system conveying information to the user.

[1462] "Intention" refers to the freelancer's decision whether or not to participate in a project.

[1463] This invention relates to a system that directly matches clients with IT freelancers. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, it achieves better matching by taking into account the user's emotional state.

[1464] System configuration

[1465] This system mainly consists of a server, terminal, generative AI model, emotion engine, and database. The server is the core of the entire system and processes and manages various data. The terminal provides an interface for users to input data. The generative AI model is used to analyze project information and freelance skill sets. The emotion engine analyzes the user's emotional state and takes it into consideration when matching. The database is used to store information about clients and freelancers.

[1466] Program processing overview

[1467] 1. User (orderer) registration

[1468] The server receives a new registration request from the client and prompts them to enter basic information and project information via their terminal. The generative AI model analyzes this data and extracts the required skill set. The emotion engine analyzes the client's emotional state and adjusts the skill set. Finally, the server stores the client's data in a database.

[1469] 2. User (freelance) registration

[1470] The server receives a new registration request from a freelancer and prompts them to enter their skill set and past performance via their device. A generative AI model analyzes this data and extracts the freelancer's skill keywords. An emotion engine analyzes the freelancer's emotional state and corrects the skill information. The server saves the freelancer's data in a database.

[1471] 3. Entering project information and matching

[1472] When a client inputs new project information, the server uses the generative AI model to analyze the project information and extract the required skill set. The server then searches for freelancers in its database who have the relevant skill set, and an emotion engine analyzes the emotional states of the client and freelancer to select the most suitable match candidate. The server then notifies the freelancer of the most suitable candidate.

[1473] 4. Match Approval and Notification

[1474] When a freelancer approves their intention to participate in a project, the device sends the information to the server. The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[1475] 5. Transaction progress monitoring and reward payment

[1476] The server provides an interface for monitoring the progress of the transaction, and the client updates the transaction progress. The emotion engine monitors the emotional state of the client and freelancer in real time and provides alerts and support as needed. The client notifies the server of project completion, and the server confirms the completion of the transaction and then pays the freelancer the fee minus a commission.

[1477] Specific examples

[1478] For example, if Client A is looking for a freelancer with Python and React skills for a web development project, the process would be as follows:

[1479] Client A enters basic information and project information, and the generative AI model extracts Python and React skill sets.

[1480] The emotion engine analyzes the emotional state of client A and adjusts the skill set accordingly.

[1481] Freelance B registers and inputs his / her skill set and past achievements. The generative AI model analyzes the data and extracts skill keywords.

[1482] The server searches the database for freelancers with Python and React skills, and the emotion engine selects Freelance B as the best candidate.

[1483] Freelance B is notified of the potential match and approves the project.

[1484] The server notifies the client A of the approval information, monitors the progress of the transaction, and even makes the payment of the reward.

[1485] Prompt Sentence Examples

[1486] "Client A is looking for a freelancer with Python and React skills. Please select the best freelancer taking into consideration Client A's emotional state."

[1487] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[1488] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1489] Step 1:

[1490] Receiving a new registration request from a user (orderer)

[1491] The server receives a new registration request from the client. This is done by receiving data as an HTTP request using the POST method. The input is the client's basic information and job information, and the output is a response confirming receipt.

[1492] Step 2:

[1493] Enter basic information and project information

[1494] The terminal prompts the client to enter basic information (name, contact details, company information, etc.) and project information (project overview, required skills, etc.). Specifically, a web form is used, and the user enters data into the input fields. The input is the information entered by the client, and the output is the input data.

[1495] Step 3:

[1496] Analysis of project information and extraction of skill sets

[1497] The server uses the generated AI model to analyze project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​processes the data to extract keywords such as "Python" and "React." The output is the extracted skill set.

[1498] Step 4:

[1499] Emotional state analysis and skill set adjustment

[1500] The emotion engine analyzes the client's emotional state and adjusts the skill set. The input is the client's emotional information, and the emotion engine processes the data to evaluate the state of stress, relief, etc. For example, in a high-stress state, the skill set requirements are relaxed. The output is the adjusted skill set.

[1501] Step 5:

[1502] Data storage

[1503] The server saves the client's data in the database. The input is the corrected skill set and the client's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[1504] Step 6:

[1505] Receiving new freelance registration requests

[1506] The server receives a new registration request from a freelancer. This is done by receiving data as an HTTP request using the POST method. The input is the freelancer's basic information and skill information, and the output is a response confirming the registration.

[1507] Step 7:

[1508] Enter your skill set and past achievements

[1509] The terminal allows the freelancer to input their skill set and past performance. Specifically, a web form is used, and the user enters data into input fields. The input is the information entered by the freelancer, and the output is the input data.

[1510] Step 8:

[1511] Analyzing input data and extracting skill keywords

[1512] The server uses the generated AI model to analyze the freelancer's input data and extract skill keywords. The input is the skill information entered by the freelancer, and the AI ​​processes the data to extract keywords such as "JavaScript" and "database management." The output is the extracted skill keywords.

[1513] Step 9:

[1514] Emotional state analysis and skill information correction

[1515] The emotion engine analyzes the freelancer's emotional state and corrects the skill information. The input is the freelancer's emotional information, and the emotion engine processes the data to evaluate their state, such as their motivation and sense of security. For example, if they feel secure, detailed achievement information is emphasized. The output is corrected skill information.

[1516] Step 10:

[1517] Data storage

[1518] The server saves the freelancer's data in a database. The input is the corrected skill information and the freelancer's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[1519] Step 11:

[1520] Entering project information

[1521] The client inputs new job information. The input is the new job information from the client, and the client enters data into the input fields using a web form. The output is the entered job information.

[1522] Step 12:

[1523] Analysis of project information

[1524] The server uses the generated AI model to analyze the project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​extracts the skill sets as data processing. The output is the extracted skill sets.

[1525] Step 13:

[1526] Freelance Search

[1527] The server searches for freelancers in the database who have the corresponding skill set. The input is the extracted skill set, and a SQL query is used to process the data and filter the matching freelancers. The output is the search result.

[1528] Step 14:

[1529] Emotional state analysis and optimal candidate selection

[1530] The emotion engine analyzes the emotional state of the freelancer and client and selects the optimal match candidate. The input is the emotional information of the client and freelancer, and the emotion engine processes the data by evaluating their emotional state and calculating the matching success rate. The output is the optimal match candidate.

[1531] Step 15:

[1532] Notification of potential matches

[1533] The server notifies the freelancer of the best candidate. The input is the best match candidate, and the output is a notification message to the freelancer. The specific operation is to send a notification to the freelancer via email or SMS.

[1534] Step 16:

[1535] Approval of intention to participate in the project

[1536] The freelancer approves their intention to participate in the project. The input is the freelancer's intention to participate, and the output is the approval information. Specifically, the freelancer clicks the "Participate" button on the dashboard.

[1537] Step 17:

[1538] Sending approval information

[1539] The terminal sends the approval information to the server. The input is the freelancer's approval information, and the data is sent to the server as an HTTP request using the POST method. The output is a notification to the server.

[1540] Step 18:

[1541] Receiving and adjusting approval information

[1542] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact. The input is the freelancer's approval information, and the output is a notification to the client and the freelancer. Specific operations include sending email notifications to both parties and providing contact details.

[1543] Step 19:

[1544] Providing a progress monitoring interface

[1545] The server provides an interface for monitoring the progress of transactions. The input is an access request to the progress monitoring system, and the output is a display of the progress. Specific operation is to provide a UI that allows the progress to be viewed on a web portal or dashboard.

[1546] Step 20:

[1547] Progress Updates

[1548] The purchaser updates the transaction progress to the server. The input is the purchaser's updated progress information, and the output is the updated result in the database. In concrete terms, the purchaser enters the task completion status on the dashboard.

[1549] Step 21:

[1550] Real-time emotional state monitoring and support

[1551] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, providing alerts and support as needed. The input is real-time emotional information, and the emotion engine evaluates the emotional state as data processing. The output is alerts and support messages as needed. For example, if stress increases, a warning message is automatically sent.

[1552] Step 22:

[1553] Project Completion Notification

[1554] The client notifies the server that the project is complete. The input is the client's notification of project completion, and the output is an update of the completion status to the database. The specific action is that the client clicks the "Complete" button on the dashboard.

[1555] Step 23:

[1556] Confirmation of transaction completion and payment

[1557] The server confirms the completion of the transaction and receives payment from the client. The input is a notification of project completion, and the output is payment processing to the freelancer. Specifically, the server processes the payment through a payment gateway.

[1558] The server pays the freelancer the amount minus the fee. The input is a confirmation of the transaction completion, and the output is an automatic transfer to the freelancer's bank account.

[1559] (Application example 2)

[1560] 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."

[1561] In food delivery, efficient and appropriate delivery partner matching is necessary to ensure customers receive their food quickly and reliably. However, conventional systems often fail to fully consider the customer's emotional state or the suitability of the delivery partner, resulting in inefficiency and dissatisfaction. Furthermore, extracting job information and skill sets is a time-consuming and labor-intensive process. To solve these issues, an advanced matching system using generative AI models and emotion engines is needed.

[1562] The identification process 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 order information sent by the orderer; a generative AI model means for analyzing the order information and extracting necessary conditions; means for searching a database for delivery partners who meet the necessary conditions; means for selecting the most suitable delivery partner from the search results and notifying them as a matching candidate; means for receiving the delivery partner's approval of the matching candidate; means for monitoring the progress of the transaction and paying a reward to the delivery partner after the transaction is completed; and an emotion engine means for analyzing the emotional states of the orderer and delivery partner and adjusting the matching conditions. This enables efficient and appropriate matching that takes into account the emotional state of the customer and the suitability of the delivery partner.

[1563] An "orderer" is a user who places an order for a service or product.

[1564] "Order information" refers to detailed information provided by a purchaser when ordering a service or product.

[1565] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and extract and process specific information.

[1566] "Conditions" means specific requirements or requirements parsed from the Order Information.

[1567] A database is a digital storage system that systematically organizes information so that it can be searched and used efficiently.

[1568] "Delivery Partner" means an individual or company responsible for delivering ordered products to customers.

[1569] "Matching candidates" refer to delivery partners who are likely to meet the optimal conditions based on order information.

[1570] The "emotion engine" is a system that analyzes the user's emotional state and performs appropriate processing and corrections based on the data.

[1571] "Deal Progress" refers to the status of the current stage of a deal.

[1572] "Remuneration" means money or other items of value paid in exchange for services rendered.

[1573] This invention relates to a food delivery system that efficiently matches customers (orderers) with delivery partners. The system consists of a server, a generative AI model, an emotion engine, a database, and a terminal used by the user.

[1574] Program Generation

[1575] The system works as follows: When the server receives the order information entered by the customer, it analyzes the order information using a generative AI model and extracts the necessary conditions. Based on the extracted conditions, the server searches the delivery partner information in its database and selects candidates who meet the conditions.

[1576] Furthermore, the server uses an emotion engine to analyze the emotional state of the orderer and delivery partner, and adjusts the matching conditions based on the analysis results, enabling efficient matching that takes into account the emotional state of the orderer and the suitability of the delivery partner.

[1577] For example, if a customer in a hurry orders a pizza, the system will prioritize delivery partners who can respond quickly. This is achieved by the emotion engine analyzing the customer's emotional state of "being in a hurry" and reflecting this in the conditions.

[1578] Hardware and Software Use

[1579] The system utilizes the following hardware and software:

[1580] Hardware: Smartphones, cloud servers

[1581] Software: Python (generative AI model), TensorFlow or PyTorch (emotion engine), React Native (smartphone application development)

[1582] The generative AI model is built in Python and deployed on a server. The emotion engine is built using TensorFlow or PyTorch and operates in real time to analyze the user's emotional state. The smartphone application is developed using React Native, providing an intuitive interface for users.

[1583] Specific examples

[1584] For example, when Customer A orders a pizza using a smartphone app, the server performs the following steps:

[1585] 1. Receive order information from the application.

[1586] 2. The order information is analyzed using a generative AI model to extract the necessary delivery conditions (type of food, delivery time, etc.).

[1587] 3. Search for the relevant delivery partner in the database and use the emotion engine to analyze that Customer A is in a hurry.

[1588] 4. Delivery partner B, who can deliver quickly, is selected and notified as a matching candidate.

[1589] Example prompt: "Customer A has ordered a pizza delivery and is in a rush. Please find the delivery partner who is available with the highest priority."

[1590] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1591] Step 1:

[1592] The user (orderer) uses a terminal to input order information. The terminal sends the basic information and order information (e.g., type of food, desired delivery time) provided by the orderer to the server. The input includes the type of food and desired delivery time, and the output includes the order information sent to the server.

[1593] Step 2:

[1594] The server analyzes the received order information. It uses a generative AI model to extract the necessary conditions from the order information. Specifically, it receives the order information as input, and the generative AI model extracts the conditions (e.g., delivery speed, type of food). The output is the analyzed conditions.

[1595] Step 3:

[1596] The server searches the delivery partner information in the database and finds delivery partners that match the criteria. The input is the criteria extracted in step 2, and the output is a list of matching delivery partners. The server selects the most suitable delivery partner candidates based on this list.

[1597] Step 4:

[1598] The server uses an emotion engine to analyze the emotional states of the orderer and delivery partner. The inputs are the orderer's emotional data and the delivery partner's emotional data, and the output is a correction condition based on the emotional state. The emotion engine operates in real time and reflects specific conditions, such as when the orderer is in a hurry.

[1599] Step 5:

[1600] The server combines the results of steps 3 and 4 to select the best match candidate. The input is the list of delivery partners and the adjusted conditions, and the output is the best match candidate. This selection includes prioritizing delivery partners that take into account the customer's urgent situation.

[1601] Step 6:

[1602] The server notifies the best match candidates. The selected delivery partner is notified of the match candidates and the delivery partner is asked whether to accept them. The input is the match candidates, and the output is the notification sent to the delivery partner.

[1603] Step 7:

[1604] The server receives the delivery partner's intention and determines the final match. If the delivery partner approves the match candidate, the server notifies both the orderer and the delivery partner of the final matching information and begins the transaction. The input is the delivery partner's approval information, and the output is the final matching information.

[1605] Step 8:

[1606] The server monitors the progress of the transaction. The purchaser acknowledges receipt of the order and provides real-time updates on the progress of the transaction. The input is the transaction progress data, and the output is the updated progress.

[1607] Step 9:

[1608] The server pays the reward to the delivery partner after the transaction is completed. It confirms that the transaction is completed, receives payment from the customer, and transfers the amount minus the commission to the delivery partner. The inputs are transaction completion confirmation information and payment information, and the output is the transfer of the reward.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] [Fourth embodiment]

[1613] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1614] 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.

[1615] 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).

[1616] 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.

[1617] 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.

[1618] 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).

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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."

[1626] This invention relates to a system that uses generative AI models to directly match clients with IT freelancers. This invention eliminates the multi-tiered subcontracting structure and provides a fair and efficient ordering process.

[1627] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches the database for freelancers with matching skill sets, selects the best candidate, and notifies both parties. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[1628] Program processing

[1629] 1. User (orderer) registration

[1630] The server receives a new registration request from the client.

[1631] The terminal allows the client to enter basic information and project information.

[1632] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[1633] The server stores the company's data in a database.

[1634] 2. User (freelance) registration

[1635] The server receives a new registration request from a freelancer.

[1636] The terminal allows freelancers to input their skill set and past performance.

[1637] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[1638] The server stores the freelance data in a database.

[1639] 3. Entering project information and matching

[1640] The purchaser enters new project information.

[1641] The server analyzes the case information and extracts the required skill set through a generative AI model.

[1642] The server searches the database for freelancers with the relevant skill set.

[1643] The server selects the best candidates and notifies the freelancer of the matching candidates.

[1644] 4. Match Approval and Notification

[1645] The freelancer confirms their intention to participate in the project.

[1646] The terminal sends the authorization information to the server.

[1647] The server provides the client and the freelancer with the final matching information and arranges for direct contact.

[1648] 5. Transaction progress monitoring and reward payment

[1649] It provides the interface necessary for the server to monitor the progress of the transaction.

[1650] The purchaser updates the transaction progress to the server.

[1651] The server confirms the completion of the project and receives payment from the client.

[1652] The server pays the freelancer the amount minus the commission.

[1653] Specific examples

[1654] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[1655] 1. Registering Client A and entering project information

[1656] The server receives basic information and project information from client A.

[1657] The terminal allows A to input Python and React skill sets.

[1658] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[1659] The server saves A's information in the database.

[1660] 2. Registration of Freelance B

[1661] The server receives a new registration request from Freelance B.

[1662] The terminal prompts B to input his skill set and past achievements.

[1663] The server analyzes using the generated AI model and extracts B's skill keywords.

[1664] The server saves B's information in the database.

[1665] 3. Notification of potential matches

[1666] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[1667] The server sends a notification of a potential match to Freelance B.

[1668] 4. Approval and Transaction Progress

[1669] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[1670] The server notifies A of the authorization information and arranges for direct contact.

[1671] The server monitors the transaction progress and pays the reward to B after completion.

[1672] In this way, the system of the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[1673] The processing flow will be explained below.

[1674] Step 1:

[1675] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[1676] Step 2:

[1677] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[1678] Step 3:

[1679] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[1680] Step 4:

[1681] The server stores the extracted skill sets and company information in a database.

[1682] Step 5:

[1683] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[1684] Step 6:

[1685] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[1686] Step 7:

[1687] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[1688] Step 8:

[1689] The server stores the extracted keywords and freelance information in a database.

[1690] Step 9:

[1691] The user (client) enters new project information. The terminal displays the project information input form.

[1692] Step 10:

[1693] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[1694] Step 11:

[1695] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[1696] Step 12:

[1697] The server searches the database for freelancers with the relevant skill set.

[1698] Step 13:

[1699] The server creates a list of applicable freelancers and selects the most suitable freelancer.

[1700] Step 14:

[1701] The server sends matching candidate information to the most suitable freelancer.

[1702] Step 15:

[1703] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[1704] Step 16:

[1705] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[1706] Step 17:

[1707] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[1708] Step 18:

[1709] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[1710] Step 19:

[1711] The user (client) notifies the server of project completion.

[1712] Step 20:

[1713] The server confirms the completion of the transaction and receives payment from the customer.

[1714] Step 21:

[1715] The server pays the freelancer the fee minus the commission.

[1716] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers.

[1717] Example 1

[1718] 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."

[1719] In conventional ordering systems, multiple subcontracting structures and opaque processes made it difficult to ensure fair and efficient matching between clients and freelancers. This often led to inefficiencies and unfair transactions. It also required a great deal of effort for clients to quickly find freelancers with the right skill sets.

[1720] 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.

[1721] In this invention, the server includes: means for receiving project information sent by a client; a generative AI model means for analyzing the project information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; means for saving basic information and transaction information from both the client and the freelancer in the database; and means for providing an interface for the generative AI model to analyze the project information and skill data. This makes it possible to quickly achieve direct and fair matching between client and freelancer, providing an efficient and highly transparent ordering process.

[1722] "Client" refers to an individual or company that requests work.

[1723] "Project information" refers to information provided by the client, such as project details, required skills, time frame, budget, etc.

[1724] A "generative AI model" is a type of artificial intelligence that analyzes given data with high precision and generates the desired results.

[1725] A "skill set" refers to the collection of skills and experience required to perform a particular job or role.

[1726] "Freelance" refers to a sole proprietor or contract employee who independently undertakes work.

[1727] A "database" refers to a system for efficiently managing and searching large amounts of data.

[1728] "Matching candidates" refer to freelancers who match the project information and are selected by the generative AI model.

[1729] "Transaction progress" refers to the progress of the ordered work.

[1730] "Remuneration" refers to the compensation paid to a freelancer upon completion of work.

[1731] An "interface" refers to the window or means through which a user operates or inputs data into a system.

[1732] This invention relates to a system that uses a generative AI model to directly match clients with freelancers. The purpose of this invention is to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. Specific embodiments are described below.

[1733] The system includes a server, terminals, and a generative AI model. The server centrally manages data on clients and freelancers and performs the necessary processing. The terminals provide an interface for clients and freelancers to input and display information. The generative AI model uses natural language processing technology to analyze project information and skill data and perform appropriate matching.

[1734] First, the client accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the client and displays a form on the terminal for entering basic information and project information. Once the client enters this information and submits it, the server uses a generative AI model to analyze the project information and extract the required skill sets. The extracted information is stored in a database.

[1735] Next, the freelancer also accesses the system using a terminal and sends a new registration request to the server. The server receives the request from the freelancer and displays a form on the terminal for entering their skill set and past achievements. Once the freelancer enters and submits this information, the server uses a generative AI model to analyze the skill set and extract related skill keywords. The extracted information is also stored in a database.

[1736] When a client inputs new project information, the server again analyzes the project information using the generative AI model and extracts the required skill set. The server then searches the database for freelancers with the corresponding skill set, selects the most suitable candidate, and notifies them. The freelancer sends their intention to participate in the project to the server via their device, and the server notifies the client of that information. This allows the client and freelancer to communicate directly.

[1737] Furthermore, the server monitors the progress of the transaction and provides an interface for the client to update the progress information. When the transaction is completed, the server receives payment from the client and pays the remaining amount minus a commission to the freelancer.

[1738] As a concrete example, if Client A is looking for a freelancer with Python and React skills for a web development project, they can input the following prompt into the generative AI model:

[1739] "Please select a freelancer with the best Python and React skills for Client A's web development project."

[1740] In this way, the present invention uses a generative AI model and database to achieve efficient and fair matching and transactions between clients and freelancers.

[1741] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1742] Step 1: New customer registration

[1743] The server receives a new registration request from the user (orderer).

[1744] Input: New registration request from purchaser

[1745] Output: Basic information and case information input form

[1746] When the server receives the request, it displays a form on the terminal where the user can enter basic information (such as name, email address, and company information) and project information (such as project title, description, and required skills).

[1747] Step 2: Enter the job information

[1748] The terminal prompts the user (client) to enter basic information and project information, which is then sent to the server.

[1749] Input: Basic information of the client and project information

[1750] Output: Sending information to the server

[1751] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends the entered information to the server.

[1752] Step 3: Parse and save case information

[1753] The server analyzes the case information using a generative AI model and extracts the required skill sets.

[1754] Input: Purchaser's project information

[1755] Output: Extracted skill sets and client information stored in a database

[1756] The server inputs the case information into the generative AI model, which uses natural language processing technology to extract the skill sets required for the project, and stores the extracted information in a database.

[1757] Step 4: Register as a freelancer

[1758] The server receives a new registration request from a user (freelancer).

[1759] Input: New freelance registration request

[1760] Output: A form for inputting skillsets and achievements

[1761] When the server receives the request, it displays a form on the terminal for entering the skill set (programming languages, tools, etc.) and past achievements.

[1762] Step 5: Enter your freelance information

[1763] The terminal prompts the user (freelancer) to enter their skill set and past achievements, which are then sent to the server.

[1764] Input: Freelance skillset and past performance

[1765] Output: Sending information to the server

[1766] The user (freelancer) enters their skill set and past achievements and clicks the send button. The terminal sends the entered information to the server.

[1767] Step 6: Freelance information analysis and storage

[1768] The server uses a generative AI model to analyze the freelancer's input information and extract relevant skill keywords.

[1769] Input: Freelance skillset and track record information

[1770] Output: Extracted skill keywords and freelance information stored in a database

[1771] The server inputs freelancer information into the generative AI model and extracts relevant skill keywords, which are then stored in a database.

[1772] Step 7: Enter new job information

[1773] The user (client) enters new project information into the terminal and sends it to the server.

[1774] Input: Purchaser's new project information

[1775] Output: Sending information to the server

[1776] The user (client) enters new project information and clicks the send button. The terminal sends the information to the server.

[1777] Step 8: Reanalyze case information and extract skill sets

[1778] The server uses a generative AI model to analyze new case information and extract the required skill sets.

[1779] Input: Purchaser's new project information

[1780] Output: Extracted skillset

[1781] The server inputs new case information into the generative AI model and extracts the required skill sets.

[1782] Step 9: Search for freelancers

[1783] The server searches the database for freelancers with the relevant skill set.

[1784] Input: Extracted skillset

[1785] Output: A list of matching freelancers

[1786] Based on the skill set extracted by the server, the server searches for freelancers in the database and generates a list of relevant freelancers.

[1787] Step 10: Match selection and notification

[1788] The server selects the most suitable freelancer and notifies them as a matching candidate.

[1789] Input: List of applicable freelancers

[1790] Output: Optimal freelance notifications

[1791] The server will select the best freelancer from the list and send a notification.

[1792] Step 11: Freelance Approval

[1793] A user (freelancer) transmits his / her intention to participate in a project to the server via his / her terminal.

[1794] Input: Freelance participation intention

[1795] Output: Notification to the server

[1796] The freelancer enters their intention to participate in the project into their device and clicks the send button. The server receives the information.

[1797] Step 12: Final notification and adjustments

[1798] The server notifies the client of the approval information and arranges for the client and the freelancer to directly contact each other.

[1799] Input: Freelance approval information

[1800] Output: Notification to client and communication coordination

[1801] The server notifies the client of the approval information, and the client and the freelancer are set up to be able to contact each other directly.

[1802] Step 13: Monitor the progress of your transaction

[1803] The server provides an interface for users (orderers) to update them on the progress of the transaction.

[1804] Input: Transaction progress information

[1805] Output: Transaction progress update

[1806] The server provides an interface to the client to request progress information and receives updated information.

[1807] Step 14: Completing the transaction and paying out

[1808] The server confirms the completion of the project, receives payment from the user (client), and pays the freelancer.

[1809] Input: Transaction Completion Information and Payment

[1810] Output: Freelance payment

[1811] The server confirms the completion of the project, receives payment from the client, and pays the remaining amount minus the commission to the freelancer.

[1812] (Application example 1)

[1813] 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."

[1814] In factories, quickly and efficiently matching workers and robots with the skills required for specific tasks is a challenge. Currently, managers must manually coordinate workers and robots, which inevitably leads to work delays and human error. This has led to problems such as reduced work efficiency and increased costs.

[1815] 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.

[1816] In this invention, the server includes means for receiving job information sent by a client, a generating AI model means for analyzing the job information and extracting the required skill set, a means for searching a database for workers with the required skill set, a means for selecting the most suitable worker from the search results and notifying them as a matching candidate, a means for receiving the worker's approval of the matching candidate, a means for monitoring work progress and paying the worker a remuneration after the work is completed, a means for receiving and analyzing work task information within the factory and identifying the required skill set, and a means for searching for and matching workers or robots suitable for the work tasks. This enables efficient and fair matching of work tasks within the factory, improving work efficiency and reducing costs.

[1817] The "client" is the party that provides work tasks and case information to execute a business or project and manages its progress.

[1818] "Project information" is information provided by the client regarding the skills and conditions required for a work task or project.

[1819] A "generative AI model" is an artificial intelligence model that analyzes input information and extracts the necessary skill sets and conditions from it.

[1820] A "skill set" refers to the collection of skills and knowledge required to perform a particular job or task.

[1821] A "database" is a digital collection of information that can be centrally managed and searched for, including information on clients, workers, project information, and skill sets.

[1822] A "worker" is a person or automated robot with a specific skill set that performs work tasks based on case information.

[1823] A "matching candidate" is someone selected as the most suitable worker based on the skill set extracted by the generative AI model.

[1824] "Notification" refers to the act of informing matching candidates of selection information and project details via electronic means.

[1825] "Work progress" refers to the progress of work or projects being carried out based on case information.

[1826] "Remuneration" is the consideration paid by the client for the work that the worker has performed based on the project information.

[1827] The system for implementing this invention aims to improve work efficiency in factories. Specifically, it is a system that analyzes work task information provided by the client using an AI model and automatically matches the most suitable worker (or robot). This system consists of a server, terminals, and various software.

[1828] Hardware and Software Configuration

[1829] server

[1830] The server uses a web framework such as Flask to execute a web API to receive project information and skill sets sent by clients and workers.

[1831] The server uses a generative AI model (e.g., OpenAI API) to analyze the submitted job information and extract the required skill sets.

[1832] Terminal

[1833] The terminal provides an interface for the orderer and the worker to input information.

[1834] The information entered on the terminal is sent to the server and stored in a database.

[1835] Explained processing flow

[1836] 1. User (orderer) registration

[1837] The server receives a new registration request from the client and stores it in a database. The client enters basic information and project information on their device, which then sends it to the server. The server uses a generative AI model to analyze the project information and extract the required skill set.

[1838] 2. User (operator) registration

[1839] The server receives a new registration request from a worker and stores it in a database. The worker enters their skill set and past performance data on their device, which then sends it to the server. The server then uses a generative AI model to analyze the input information and extract skill keywords.

[1840] 3. Entering project information and matching

[1841] The client inputs new work task information. The server analyzes the task information and extracts the required skill set through a generative AI model. The server then searches the database for workers with the required skill set.

[1842] 4. Notification of potential matches

[1843] The server selects the most suitable worker and notifies the worker of that information. When the worker approves their intention to participate in the project, that information is sent to the server via their terminal. The server then provides the approval information to the client and arranges for the two parties to contact each other.

[1844] 5. Monitoring trading progress and reward payment

[1845] The server checks the progress of the work and updates the progress to the server. When the work is completed, the server receives payment from the client and pays the worker a reward.

[1846] Specific examples

[1847] The following example illustrates the operation of the system:

[1848] Prompt Sentence Examples

[1849] "What skill set is required for the following work task: Wiring and debugging a PLC?"

[1850] By inputting this prompt into a generative AI model, the model extracts the required skill set. For example, "PLC wiring," "debugging," and "electrical engineering" are extracted. Based on these skill sets, the server searches the database for the relevant worker and notifies the most suitable candidate.

[1851] In this way, this system can be used to efficiently match workers and robots with the necessary skills within a factory, dramatically improving work efficiency.

[1852] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1853] Step 1:

[1854] The server receives a new registration request sent by the client. The client uses a terminal to enter basic information and project information. The terminal sends this information to the server, which then analyzes the project information using a generative AI model. This analysis extracts the required skill set and stores it in a database.

[1855] Input: Basic information of the client and project information

[1856] Output: Client information and required skill sets stored in a database

[1857] Step 2:

[1858] The server receives a new registration request sent by a worker. The worker uses a terminal to input their own skill set and past performance. The terminal sends this information to the server, which then analyzes the input data using a generative AI model. The skill keywords extracted through the analysis are stored in a database.

[1859] Inputs: Worker skill set and past performance

[1860] Output: Worker information and skill keywords stored in the database

[1861] Step 3:

[1862] The client inputs new work task information into the terminal, which then sends the information to the server, which analyzes the task information using a generative AI model to extract the required skill set, then searches the database for workers who match that skill set.

[1863] Input: Work task information

[1864] Output: A list of workers that match the required skill set

[1865] Step 4:

[1866] The server selects the most suitable worker from the search results and notifies the worker as a matching candidate. The worker receives the notification and sends their intention to participate in the project to the server from their terminal. The server provides this approval information to the client and arranges for the two parties to contact each other.

[1867] Input: List of workers who match the required skill set, worker approval

[1868] Output: Information for both the client and the worker to contact each other

[1869] Step 5:

[1870] The server checks the progress of the work and provides the necessary interface. The client updates the progress to the server, and the information is saved in a database. When the work is completed, the server receives payment from the client and pays the worker a reward.

[1871] Input: Work progress, payment information from the client

[1872] Output: Reward payment and database update after transaction completion

[1873] In this way, a system that efficiently matches work tasks within a factory and manages progress is created through a series of steps. This system is expected to facilitate smooth cooperation between clients and workers and improve work efficiency.

[1874] 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.

[1875] This invention relates to a system that directly matches clients with IT freelancers using a generative AI model and an emotion engine. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, better matching is achieved by taking into account the user's emotional state.

[1876] Specifically, the system receives project information sent by the client, analyzes it using a generative AI model, and extracts the required skill set. It then searches a database for freelancers with matching skill sets, selects the most suitable candidate, and notifies both parties. It also uses an emotion engine to recognize the emotional state of the client and freelancer, and takes this into account when matching. If the freelancer approves the project, it monitors the progress of the transaction and pays the freelancer once the transaction is completed.

[1877] Program processing

[1878] 1. User (orderer) registration

[1879] The server receives a new registration request from the client.

[1880] The terminal allows the client to enter basic information and project information.

[1881] The server uses the generated AI model to analyze the case information and extract the required skill sets.

[1882] The emotional engine analyzes the client's emotional state and adjusts the skill set to take this data into account.

[1883] The server stores the company's data in a database.

[1884] 2. User (freelance) registration

[1885] The server receives a new registration request from a freelancer.

[1886] The terminal allows freelancers to input their skill set and past performance.

[1887] The server analyzes the input data using a generative AI model and extracts freelance skill keywords.

[1888] The emotion engine analyzes the freelancer's emotional state and adjusts the skill information taking this data into account.

[1889] The server stores the freelance data in a database.

[1890] 3. Entering project information and matching

[1891] The purchaser enters new project information.

[1892] The server analyzes the case information and extracts the required skill set through a generative AI model.

[1893] The server searches the database for freelancers with the relevant skill set.

[1894] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[1895] The server sends a notification of the best candidate to the freelancer.

[1896] 4. Match Approval and Notification

[1897] The freelancer confirms their intention to participate in the project.

[1898] The terminal sends the authorization information to the server.

[1899] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[1900] 5. Transaction progress monitoring and reward payment

[1901] It provides the interface necessary for the server to monitor the progress of the transaction.

[1902] The purchaser updates the transaction progress to the server.

[1903] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, automatically providing alerts and support based on their emotional state.

[1904] The client notifies the server of project completion.

[1905] The server confirms the completion of the transaction and receives payment from the customer.

[1906] The server pays the freelancer the amount minus the commission.

[1907] Specific examples

[1908] For example, let's say Client A is looking for a freelancer with Python and React skills for a web development project.

[1909] 1. Registering Client A and entering project information

[1910] The server receives basic information and project information from client A.

[1911] The terminal allows A to input Python and React skill sets.

[1912] The server analyzes the case information using the generated AI model and extracts the required skill sets.

[1913] The emotion engine analyzes A's emotional state and adjusts the skill set taking this data into account.

[1914] The server saves A's information in the database.

[1915] 2. Registration of Freelance B

[1916] The server receives a new registration request from Freelance B.

[1917] The terminal prompts B to input his skill set and past achievements.

[1918] The server analyzes using the generated AI model and extracts B's skill keywords.

[1919] The emotion engine analyzes B's emotional state and corrects the skill information taking this data into account.

[1920] The server saves B's information in the database.

[1921] 3. Notification of potential matches

[1922] The server searches the database for freelancers with Python and React skills and selects B as a candidate.

[1923] The emotion engine analyzes the emotional state of the client and the freelancer and selects B as the most suitable candidate.

[1924] The server sends a notification of a potential match to Freelance B.

[1925] 4. Approval and Transaction Progress

[1926] The terminal receives the intention to participate in the project from Freelance B and transmits it to the server.

[1927] The server notifies A of the authorization information and arranges for direct contact.

[1928] The server monitors the transaction progress and pays the reward to B after completion.

[1929] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[1930] The processing flow will be explained below.

[1931] Step 1:

[1932] The terminal displays a new registration form to the client, who then enters basic company information and project information (required skill set, project duration, budget, etc.).

[1933] Step 2:

[1934] The user (orderer) enters basic information and project information and clicks the send button. The terminal sends this input data to the server.

[1935] Step 3:

[1936] The server passes the received data to the generative AI model, which analyzes the case information and extracts the required skill set.

[1937] Step 4:

[1938] The emotion engine analyzes the client's emotional state and feeds this data into the generative AI model to correct the skill set.

[1939] Step 5:

[1940] The server stores the corrected skill set and company information in a database.

[1941] Step 6:

[1942] The terminal displays a new registration form to the freelancer, who then enters basic information, skill set, past performance, etc.

[1943] Step 7:

[1944] The user (freelancer) enters basic information and skill set and clicks the send button. The terminal sends this input data to the server.

[1945] Step 8:

[1946] The server passes the received freelance data to the generative AI model, which analyzes the skill information and track record. The generative AI model extracts the freelancer's skill keywords.

[1947] Step 9:

[1948] The emotion engine analyzes the freelancer's emotional state and reflects this data in the generative AI model to correct skill keywords.

[1949] Step 10:

[1950] The server stores the corrected keywords and freelance information in a database.

[1951] Step 11:

[1952] The user (client) enters new project information. The terminal displays the project information input form.

[1953] Step 12:

[1954] The user (client) enters the project information and clicks the send button. The terminal sends the data to the server.

[1955] Step 13:

[1956] The server passes the received job information to the generative AI model, which analyzes and extracts the required skill sets.

[1957] Step 14:

[1958] The server searches the database for freelancers with the relevant skill set.

[1959] Step 15:

[1960] The emotion engine analyzes the emotional state of the freelancer and client and selects the most suitable match candidate.

[1961] Step 16:

[1962] The server sends a notification of a potential match to the most suitable freelancer.

[1963] Step 17:

[1964] The user (freelancer) checks the details of the project and clicks the approval button to indicate their intention to participate. The device sends the approval information to the server.

[1965] Step 18:

[1966] The server receives the approval information, sends a notification to both the client and the freelancer that the matching is complete, and arranges for the two parties to contact each other directly.

[1967] Step 19:

[1968] The server provides an interface for the client and the freelancer to monitor the progress of the transaction.

[1969] Step 20:

[1970] The user (client) periodically updates the project progress, and the device sends the updated data to the server.

[1971] Step 21:

[1972] The emotion engine monitors the progress of the deal in real time and automatically provides alerts and support based on the emotional state of the client and freelancer.

[1973] Step 22:

[1974] The user (client) notifies the server of project completion.

[1975] Step 23:

[1976] The server confirms the completion of the transaction and receives payment from the customer.

[1977] Step 24:

[1978] The server pays the freelancer the amount minus the commission.

[1979] In this way, the system of the present invention realizes fair and efficient matching and transactions between clients and freelancers at an even higher level by incorporating an emotion engine.

[1980] Example 2

[1981] 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."

[1982] Conventional matching systems between clients and IT freelancers focus on matching skill sets, but do not take into account the user's emotional state, which often leads to problems in actual transactions. Specifically, if the client is under high stress or the freelancer is dissatisfied, this can have a negative impact on the progress of the transaction and the quality of the deliverables. The challenge is to solve these problems and provide an efficient and fair ordering process.

[1983] 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 job information sent by the client; a generation AI model means for analyzing the job information and extracting the required skill set; means for searching a database for freelancers with the required skill set; means for selecting the most suitable freelancer from the search results and notifying them as a matching candidate; means for receiving the freelancer's approval of the matching candidate; means for monitoring the transaction progress and paying the freelancer a fee after the transaction is completed; and means including an emotion engine for analyzing the emotional states of the client and freelancer and taking this into consideration when matching. This enables matching and transactions that take the emotional states of the client and freelancer into consideration, making it possible to realize an efficient and fair ordering and purchase process.

[1984] "Project information" refers to detailed project information provided by the client, including required skill sets and work content.

[1985] A "generative AI model" is a system that uses machine learning algorithms to analyze data and extract necessary information.

[1986] "Freelance" refers to a worker who has the ability to independently accept and carry out work.

[1987] A "database" is a system that stores information in an organized manner and makes it easy to search and update.

[1988] An "emotion engine" is a system that has the ability to analyze the user's emotional state and respond appropriately based on that.

[1989] "Matching" is the process of comparing the client's project information with the freelancer's skill set and selecting the appropriate candidate.

[1990] "Transaction progress" is information indicating the progress of a project, and is used to evaluate the progress and achievement of work.

[1991] "Compensation" means the monetary compensation a Freelancer receives for completing a Project.

[1992] "Notification" is the act of the system conveying information to the user.

[1993] "Intention" refers to the freelancer's decision whether or not to participate in a project.

[1994] This invention relates to a system that directly matches clients with IT freelancers. The system aims to eliminate the multi-tiered subcontracting structure and provide a fair and efficient ordering process. By adding an emotion engine, it achieves better matching by taking into account the user's emotional state.

[1995] System configuration

[1996] This system mainly consists of a server, terminal, generative AI model, emotion engine, and database. The server is the core of the entire system and processes and manages various data. The terminal provides an interface for users to input data. The generative AI model is used to analyze project information and freelance skill sets. The emotion engine analyzes the user's emotional state and takes it into consideration when matching. The database is used to store information about clients and freelancers.

[1997] Program processing overview

[1998] 1. User (orderer) registration

[1999] The server receives a new registration request from the client and prompts them to enter basic information and project information via their terminal. The generative AI model analyzes this data and extracts the required skill set. The emotion engine analyzes the client's emotional state and adjusts the skill set. Finally, the server stores the client's data in a database.

[2000] 2. User (freelance) registration

[2001] The server receives a new registration request from a freelancer and prompts them to enter their skill set and past performance via their device. A generative AI model analyzes this data and extracts the freelancer's skill keywords. An emotion engine analyzes the freelancer's emotional state and corrects the skill information. The server saves the freelancer's data in a database.

[2002] 3. Entering project information and matching

[2003] When a client inputs new project information, the server uses the generative AI model to analyze the project information and extract the required skill set. The server then searches for freelancers in its database who have the relevant skill set, and an emotion engine analyzes the emotional states of the client and freelancer to select the most suitable match candidate. The server then notifies the freelancer of the most suitable candidate.

[2004] 4. Match Approval and Notification

[2005] When a freelancer approves their intention to participate in a project, the device sends the information to the server. The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact.

[2006] 5. Transaction progress monitoring and reward payment

[2007] The server provides an interface for monitoring the progress of the transaction, and the client updates the transaction progress. The emotion engine monitors the emotional state of the client and freelancer in real time and provides alerts and support as needed. The client notifies the server of project completion, and the server confirms the completion of the transaction and then pays the freelancer the fee minus a commission.

[2008] Specific examples

[2009] For example, if Client A is looking for a freelancer with Python and React skills for a web development project, the process would be as follows:

[2010] Client A enters basic information and project information, and the generative AI model extracts Python and React skill sets.

[2011] The emotion engine analyzes the emotional state of client A and adjusts the skill set accordingly.

[2012] Freelance B registers and inputs his / her skill set and past achievements. The generative AI model analyzes the data and extracts skill keywords.

[2013] The server searches the database for freelancers with Python and React skills, and the emotion engine selects Freelance B as the best candidate.

[2014] Freelance B is notified of the potential match and approves the project.

[2015] The server notifies the client A of the approval information, monitors the progress of the transaction, and even makes the payment of the reward.

[2016] Prompt Sentence Examples

[2017] "Client A is looking for a freelancer with Python and React skills. Please select the best freelancer taking into consideration Client A's emotional state."

[2018] In this way, the system of the present invention uses a generative AI model and an emotion engine to achieve efficient and fair matching and transactions between clients and freelancers.

[2019] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2020] Step 1:

[2021] Receiving a new registration request from a user (orderer)

[2022] The server receives a new registration request from the client. This is done by receiving data as an HTTP request using the POST method. The input is the client's basic information and job information, and the output is a response confirming receipt.

[2023] Step 2:

[2024] Enter basic information and project information

[2025] The terminal prompts the client to enter basic information (name, contact details, company information, etc.) and project information (project overview, required skills, etc.). Specifically, a web form is used, and the user enters data into the input fields. The input is the information entered by the client, and the output is the input data.

[2026] Step 3:

[2027] Analysis of project information and extraction of skill sets

[2028] The server uses the generated AI model to analyze project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​processes the data to extract keywords such as "Python" and "React." The output is the extracted skill set.

[2029] Step 4:

[2030] Emotional state analysis and skill set adjustment

[2031] The emotion engine analyzes the client's emotional state and adjusts the skill set. The input is the client's emotional information, and the emotion engine processes the data to evaluate the state of stress, relief, etc. For example, in a high-stress state, the skill set requirements are relaxed. The output is the adjusted skill set.

[2032] Step 5:

[2033] Data storage

[2034] The server saves the client's data in the database. The input is the corrected skill set and the client's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[2035] Step 6:

[2036] Receiving new freelance registration requests

[2037] The server receives a new registration request from a freelancer. This is done by receiving data as an HTTP request using the POST method. The input is the freelancer's basic information and skill information, and the output is a response confirming the registration.

[2038] Step 7:

[2039] Enter your skill set and past achievements

[2040] The terminal allows the freelancer to input their skill set and past performance. Specifically, a web form is used, and the user enters data into input fields. The input is the information entered by the freelancer, and the output is the input data.

[2041] Step 8:

[2042] Analyzing input data and extracting skill keywords

[2043] The server uses the generated AI model to analyze the freelancer's input data and extract skill keywords. The input is the skill information entered by the freelancer, and the AI ​​processes the data to extract keywords such as "JavaScript" and "database management." The output is the extracted skill keywords.

[2044] Step 9:

[2045] Emotional state analysis and skill information correction

[2046] The emotion engine analyzes the freelancer's emotional state and corrects the skill information. The input is the freelancer's emotional information, and the emotion engine processes the data to evaluate their state, such as their motivation and sense of security. For example, if they feel secure, detailed achievement information is emphasized. The output is corrected skill information.

[2047] Step 10:

[2048] Data storage

[2049] The server saves the freelancer's data in a database. The input is the corrected skill information and the freelancer's basic information, and the output is the result saved in the database. Specifically, an INSERT operation is performed on the SQL database.

[2050] Step 11:

[2051] Entering project information

[2052] The client inputs new job information. The input is the new job information from the client, and the client enters data into the input fields using a web form. The output is the entered job information.

[2053] Step 12:

[2054] Analysis of project information

[2055] The server uses the generated AI model to analyze the project information and extract the required skill sets. The input is the project information entered by the client, and the AI ​​extracts the skill sets as data processing. The output is the extracted skill sets.

[2056] Step 13:

[2057] Freelance Search

[2058] The server searches for freelancers in the database who have the corresponding skill set. The input is the extracted skill set, and a SQL query is used to process the data and filter the matching freelancers. The output is the search result.

[2059] Step 14:

[2060] Emotional state analysis and optimal candidate selection

[2061] The emotion engine analyzes the emotional state of the freelancer and client and selects the optimal match candidate. The input is the emotional information of the client and freelancer, and the emotion engine processes the data by evaluating their emotional state and calculating the matching success rate. The output is the optimal match candidate.

[2062] Step 15:

[2063] Notification of potential matches

[2064] The server notifies the freelancer of the best candidate. The input is the best match candidate, and the output is a notification message to the freelancer. The specific operation is to send a notification to the freelancer via email or SMS.

[2065] Step 16:

[2066] Approval of intention to participate in the project

[2067] The freelancer approves their intention to participate in the project. The input is the freelancer's intention to participate, and the output is the approval information. Specifically, the freelancer clicks the "Participate" button on the dashboard.

[2068] Step 17:

[2069] Sending approval information

[2070] The terminal sends the approval information to the server. The input is the freelancer's approval information, and the data is sent to the server as an HTTP request using the POST method. The output is a notification to the server.

[2071] Step 18:

[2072] Receiving and adjusting approval information

[2073] The server receives the approval information, provides the final matching information to both the client and the freelancer, and arranges for direct contact. The input is the freelancer's approval information, and the output is a notification to the client and the freelancer. Specific operations include sending email notifications to both parties and providing contact details.

[2074] Step 19:

[2075] Providing a progress monitoring interface

[2076] The server provides an interface for monitoring the progress of transactions. The input is an access request to the progress monitoring system, and the output is a display of the progress. Specific operation is to provide a UI that allows the progress to be viewed on a web portal or dashboard.

[2077] Step 20:

[2078] Progress Updates

[2079] The purchaser updates the transaction progress to the server. The input is the purchaser's updated progress information, and the output is the updated result in the database. In concrete terms, the purchaser enters the task completion status on the dashboard.

[2080] Step 21:

[2081] Real-time emotional state monitoring and support

[2082] The emotion engine monitors the emotional state of clients and freelancers in real time as the transaction progresses, providing alerts and support as needed. The input is real-time emotional information, and the emotion engine evaluates the emotional state as data processing. The output is alerts and support messages as needed. For example, if stress increases, a warning message is automatically sent.

[2083] Step 22:

[2084] Project Completion Notification

[2085] The client notifies the server that the project is complete. The input is the client's notification of project completion, and the output is an update of the completion status to the database. The specific action is that the client clicks the "Complete" button on the dashboard.

[2086] Step 23:

[2087] Confirmation of transaction completion and payment

[2088] The server confirms the completion of the transaction and receives payment from the client. The input is a notification of project completion, and the output is payment processing to the freelancer. Specifically, the server processes the payment through a payment gateway.

[2089] The server pays the freelancer the amount minus the fee. The input is a confirmation of the transaction completion, and the output is an automatic transfer to the freelancer's bank account.

[2090] (Application example 2)

[2091] 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."

[2092] In food delivery, efficient and appropriate delivery partner matching is necessary to ensure customers receive their food quickly and reliably. However, conventional systems often fail to fully consider the customer's emotional state or the suitability of the delivery partner, resulting in inefficiency and dissatisfaction. Furthermore, extracting job information and skill sets is a time-consuming and labor-intensive process. To solve these issues, an advanced matching system using generative AI models and emotion engines is needed.

[2093] The identification process 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 order information sent by the orderer; a generative AI model means for analyzing the order information and extracting necessary conditions; means for searching a database for delivery partners who meet the necessary conditions; means for selecting the most suitable delivery partner from the search results and notifying them as a matching candidate; means for receiving the delivery partner's approval of the matching candidate; means for monitoring the progress of the transaction and paying a reward to the delivery partner after the transaction is completed; and an emotion engine means for analyzing the emotional states of the orderer and delivery partner and adjusting the matching conditions. This enables efficient and appropriate matching that takes into account the emotional state of the customer and the suitability of the delivery partner.

[2094] An "orderer" is a user who places an order for a service or product.

[2095] "Order information" refers to detailed information provided by a purchaser when ordering a service or product.

[2096] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze data and extract and process specific information.

[2097] "Conditions" means specific requirements or requirements parsed from the Order Information.

[2098] A database is a digital storage system that systematically organizes information so that it can be searched and used efficiently.

[2099] "Delivery Partner" means an individual or company responsible for delivering ordered products to customers.

[2100] "Matching candidates" refer to delivery partners who are likely to meet the optimal conditions based on order information.

[2101] The "emotion engine" is a system that analyzes the user's emotional state and performs appropriate processing and corrections based on the data.

[2102] "Deal Progress" refers to the status of the current stage of a deal.

[2103] "Remuneration" means money or other items of value paid in exchange for services rendered.

[2104] This invention relates to a food delivery system that efficiently matches customers (orderers) with delivery partners. The system consists of a server, a generative AI model, an emotion engine, a database, and a terminal used by the user.

[2105] Program Generation

[2106] The system works as follows: When the server receives the order information entered by the customer, it analyzes the order information using a generative AI model and extracts the necessary conditions. Based on the extracted conditions, the server searches the delivery partner information in its database and selects candidates who meet the conditions.

[2107] Furthermore, the server uses an emotion engine to analyze the emotional state of the orderer and delivery partner, and adjusts the matching conditions based on the analysis results, enabling efficient matching that takes into account the emotional state of the orderer and the suitability of the delivery partner.

[2108] For example, if a customer in a hurry orders a pizza, the system will prioritize delivery partners who can respond quickly. This is achieved by the emotion engine analyzing the customer's emotional state of "being in a hurry" and reflecting this in the conditions.

[2109] Hardware and Software Use

[2110] The system utilizes the following hardware and software:

[2111] Hardware: Smartphones, cloud servers

[2112] Software: Python (generative AI model), TensorFlow or PyTorch (emotion engine), React Native (smartphone application development)

[2113] The generative AI model is built in Python and deployed on a server. The emotion engine is built using TensorFlow or PyTorch and operates in real time to analyze the user's emotional state. The smartphone application is developed using React Native, providing an intuitive interface for users.

[2114] Specific examples

[2115] For example, when Customer A orders a pizza using a smartphone app, the server performs the following steps:

[2116] 1. Receive order information from the application.

[2117] 2. The order information is analyzed using a generative AI model to extract the necessary delivery conditions (type of food, delivery time, etc.).

[2118] 3. Search for the relevant delivery partner in the database and use the emotion engine to analyze that Customer A is in a hurry.

[2119] 4. Delivery partner B, who can deliver quickly, is selected and notified as a matching candidate.

[2120] Example prompt: "Customer A has ordered a pizza delivery and is in a rush. Please find the delivery partner who is available with the highest priority."

[2121] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2122] Step 1:

[2123] The user (orderer) uses a terminal to input order information. The terminal sends the basic information and order information (e.g., type of food, desired delivery time) provided by the orderer to the server. The input includes the type of food and desired delivery time, and the output includes the order information sent to the server.

[2124] Step 2:

[2125] The server analyzes the received order information. It uses a generative AI model to extract the necessary conditions from the order information. Specifically, it receives the order information as input, and the generative AI model extracts the conditions (e.g., delivery speed, type of food). The output is the analyzed conditions.

[2126] Step 3:

[2127] The server searches the delivery partner information in the database and finds delivery partners that match the criteria. The input is the criteria extracted in step 2, and the output is a list of matching delivery partners. The server selects the most suitable delivery partner candidates based on this list.

[2128] Step 4:

[2129] The server uses an emotion engine to analyze the emotional states of the orderer and delivery partner. The inputs are the orderer's emotional data and the delivery partner's emotional data, and the output is a correction condition based on the emotional state. The emotion engine operates in real time and reflects specific conditions, such as when the orderer is in a hurry.

[2130] Step 5:

[2131] The server combines the results of steps 3 and 4 to select the best match candidate. The input is the list of delivery partners and the adjusted conditions, and the output is the best match candidate. This selection includes prioritizing delivery partners that take into account the customer's urgent situation.

[2132] Step 6:

[2133] The server notifies the best match candidates. The selected delivery partner is notified of the match candidates and the delivery partner is asked whether to accept them. The input is the match candidates, and the output is the notification sent to the delivery partner.

[2134] Step 7:

[2135] The server receives the delivery partner's intention and determines the final match. If the delivery partner approves the match candidate, the server notifies both the orderer and the delivery partner of the final matching information and begins the transaction. The input is the delivery partner's approval information, and the output is the final matching information.

[2136] Step 8:

[2137] The server monitors the progress of the transaction. The purchaser acknowledges receipt of the order and provides real-time updates on the progress of the transaction. The input is the transaction progress data, and the output is the updated progress.

[2138] Step 9:

[2139] The server pays the reward to the delivery partner after the transaction is completed. It confirms that the transaction is completed, receives payment from the customer, and transfers the amount minus the commission to the delivery partner. The inputs are transaction completion confirmation information and payment information, and the output is the transfer of the reward.

[2140] 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.

[2141] 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.

[2142] 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.

[2143] 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.

[2144] 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 cl...

Claims

1. A means for receiving project information sent by an orderer; A generating AI model means for analyzing the case information and extracting a required skill set; A way to search the database for freelancers with the required skill set, A method to select the most suitable freelancer from the search results and notify them as a matching candidate, A means for receiving the freelancer's intention to approve the matching candidate; A way to monitor the progress of the transaction and pay the freelancer after the transaction is completed, A system including:

2. The system according to claim 1, which analyzes data from both clients and freelancers using a generative AI model to provide optimal matching.

3. The system according to claim 1, wherein the skill sets of freelancers in the database are compared based on the client's project information.

Images