System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting item information of an ordering source and skill information of an ordering destination; means for storing each piece of information in a database; artificial intelligence means for learning needs and seeds of a market based on the stored information; means for calculating a matching degree between the ordering source and the ordering destination using a result learned by the artificial intelligence means; means for making a recommendation to the ordering source and the ordering destination when the matching degree is high; and means for establishing matching when there is approval from both.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] This invention aims to resolve the problem of the multi-tiered subcontracting structure in the IT industry, allowing clients to directly provide optimal projects to engineers (clients). In conventional systems, multiple intermediaries are involved, resulting in insufficient compensation for engineers and in many cases in which the content of the projects is not properly matched. This makes it difficult for companies to find engineers with the necessary skills, and for engineers to find projects that match their skills. [Means for solving the problem]

[0005] The present invention provides a means for collecting project information from clients and skill information from clients and storing this information in a database. It also provides a means for calculating the degree of match between clients and clients by providing an artificial intelligence means for learning market needs and seeds based on the stored information. If the degree of match is high, the system makes a recommendation to the client and client, and if both parties approve, the system completes the match. Furthermore, the artificial intelligence means learns past matching history based on the client's project information and the client's skill information, generating an optimal matching algorithm, enabling more accurate recommendations to clients and clients. Furthermore, the system includes a means for making suggestions based on past matching history if there are deficiencies or corrections in the client's project information and the client's skill information, enabling the information to be quickly and automatically supplemented and corrected. This improves the efficiency of matching between clients and clients and effectively resolves the problem of multiple subcontracting structures in the IT industry.

[0006] A "client" is a company or organization that provides project information and is looking for engineers to carry out the project.

[0007] A "client" is an engineer or freelancer who accepts projects based on their own skills and experience and then carries out those projects.

[0008] "Artificial intelligence means" refers to a mechanism that automatically learns from information and executes algorithms or machine learning models to achieve optimal matching.

[0009] "Match degree" is a score or index that indicates how well the client's project information and the client's skill information match.

[0010] A "database" is an information management system that organizes and stores information so that it can be retrieved as needed.

[0011] "Market needs" refers to data that shows the skills and project trends that are in demand in the current market.

[0012] "Seeds" refers to data that shows trends in the skills and experience of engineers currently available in the market.

[0013] "Recommendation" refers to the act of recommending the optimal combination to the client and the recipient.

[0014] A "matching algorithm" is a calculation procedure for optimal matching based on information from the ordering party and the ordering party.

[0015] "Matching history" refers to a record of past matching between ordering parties and ordering recipients.

[0016] "Suggestion" refers to the act of pointing out information deficiencies or corrections based on the results of data analysis, and providing advice to fill in the gaps.

[0017] The "negotiation process" is the stage after a match is made in which both parties negotiate specific terms and contract contents. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The system of the present invention collects information on the ordering party and the ordering recipient, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[0040] System Overview

[0041] 1. User (Orderer, Supplier) Registration:

[0042] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[0043] The terminal sends the entered information to the server and stores it in a database.

[0044] 2. Information storage and learning:

[0045] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[0046] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[0047] 3. Match proposal and establishment:

[0048] The server compares the registered information and, if it determines that there is a high degree of match, sends a recommendation to the ordering party and the supplier.

[0049] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[0050] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[0051] 4. Feedback and Suggestions:

[0052] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[0053] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[0054] Specific examples

[0055] Specific examples of registration

[0056] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[0057] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[0058] The terminal formats this information and sends it to the server.

[0059] The server stores the received information in a database and also uses it as learning data.

[0060] Specific examples of recommendations

[0061] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[0062] The server sends recommendations and notifications to both companies and engineers.

[0063] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[0064] Specific examples of proposals

[0065] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[0066] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[0067] As described above, this invention is a system that efficiently collects information on clients and suppliers and achieves optimal matching, with the aim of eliminating the problem of multiple subcontracting structures in the IT industry. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Users (orderer, supplier) log in to the platform.

[0071] The terminal sends the user's authentication information to an input form.

[0072] The server checks the authentication information and verifies that the user has valid access.

[0073] Step 2:

[0074] The user inputs the job information or skill sheet information.

[0075] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[0076] The terminal sends the input data to the server.

[0077] Step 3:

[0078] The server stores the received data in a database.

[0079] The server validates the data format and performs any necessary conversions.

[0080] The server stores the job information or skill sheet information in a database.

[0081] Step 4:

[0082] The server provides the newly registered information to the AI ​​engine.

[0083] The server extracts new information from the database and passes it to the AI ​​engine.

[0084] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[0085] Step 5:

[0086] The server updates the matching algorithm based on market data and seed information.

[0087] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[0088] Step 6:

[0089] The server compares the registration data with market information and calculates the degree of match.

[0090] The server compares the engineer's skill sheet with the project information and generates a score.

[0091] The server refers to past matching history and adjusts the weight of each condition.

[0092] Step 7:

[0093] The server recommends candidates with high matching potential.

[0094] The server selects the best candidate for each engineer and job and sends a notification.

[0095] The device displays the recommendation content to the user.

[0096] Step 8:

[0097] The user reviews the recommendation and clicks "Like."

[0098] The device accepts the user's input and clicks the "Like" button.

[0099] The device sends the "like" information to the server.

[0100] Step 9:

[0101] The server detects both "likes" and makes a match.

[0102] The server checks both "likes" and notifies the match.

[0103] The server will contact you to proceed with the negotiation process.

[0104] Step 10:

[0105] The server will suggest any deficiencies or corrections.

[0106] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[0107] The server notifies the user of the proposal.

[0108] Step 11:

[0109] The user accepts the suggestions and makes the necessary corrections.

[0110] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[0111] The device sends the modifications to the server.

[0112] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[0113] Example 1

[0114] 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."

[0115] In the current market, there is an issue of inefficient matching between the projects desired by clients and the skills that contractors can provide. As a result, clients spend a great deal of time and effort finding suitable candidates, and contractors miss out on opportunities to find projects that will allow them to make the most of their skills. Furthermore, the current matching system lacks the functionality to provide appropriate feedback to clients and contractors regarding insufficient information or corrections, which also creates the issue of not making optimal proposals.

[0116] 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.

[0117] In this invention, the server includes: means for collecting project information from client computers and skill information from contractors; means for saving the collected information in a database; artificial intelligence means for learning market needs and seeds based on the saved information; means for calculating the degree of match between client computers and contractors using the results learned by the artificial intelligence means; means for making recommendations to client computers and contractors when the degree of match is high; means for establishing a match when the client computer and contractor computer that have received the recommendation approve the match; and means for displaying a generative AI model and proposal text for generating proposals based on the client computer and contractor computer information. This significantly improves the efficiency of matching between client computers and contractors, and by providing appropriate feedback on insufficient information and corrections, it becomes possible to match under optimal conditions.

[0118] "Client" is the party providing project information and seeking specific skills or services.

[0119] A "contractor" is a person who provides skill information and is willing to accept a specific project.

[0120] "Project information" refers to detailed information provided by the client, such as the job content, conditions, and required skills.

[0121] "Skill information" refers to detailed information such as skills, experience, and qualifications provided by the contractor.

[0122] A "database" is a system for systematically storing and managing collected information.

[0123] "Artificial intelligence means" refers to means that use technologies such as machine learning and deep learning to learn market needs and seeds and generate and improve matching algorithms.

[0124] The "match degree" is an index showing the degree of match between the project information of the client and the skill information of the contractor.

[0125] A "recommendation" is a notification or proposal made to the client and the contractor when the match is high.

[0126] "Approval" refers to the client and contractor who receive the recommendation expressing their intention to each other by using a "Like" button or similar.

[0127] A "generative AI model" is an artificial intelligence model that generates proposals based on information from the client and the contractor.

[0128] A "suggestion" is a document of improvements or suggestions that is automatically generated by a generative AI model and displayed to the user.

[0129] The system of the present invention collects information on purchasers and sellers, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[0130] User registration and information collection

[0131] Users enter information about jobs and skills through a dedicated web screen, which is built using web technologies such as HTML and JavaScript.

[0132] The terminal formats the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, with SSL / TLS encryption used for security during the transmission process.

[0133] The server parses the received JSON data and stores it in a database, using an RDBMS such as MySQL or PostgreSQL.

[0134] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[0135] Information storage and learning

[0136] The server periodically queries the information stored in the database, a process that can be automated using a scheduling tool such as a Cron job.

[0137] Example: SELECT FROM user_data

[0138] The server inputs the acquired data into a machine learning model for learning, using machine learning frameworks such as TensorFlow and PyTorch.

[0139] Example: model.fit(training_data, labels)

[0140] The server updates the matching algorithm based on the new learning results, thereby reflecting the latest matching conditions adapted to market needs and seeds.

[0141] Matching proposal and establishment

[0142] The server compares the company's project information stored in the database with the engineer's skill information and calculates the degree of match, using parameters such as skill match, years of experience, and match rate.

[0143] If the match rate is above a certain value (e.g., 80% or higher), the server sends a recommendation notification to the client and the recipient. The device displays this notification to the user. Notifications are sent via email, in-app notifications, etc.

[0144] The user checks the recommendation notification and clicks the "Like" button if they are interested. The server checks the user's "Like" and if both parties send "Likes", a match is made. After this, contact is made to proceed with the business negotiation process.

[0145] Feedback and Suggestions

[0146] The server analyzes the information of the client or contractor and identifies shortcomings and areas for correction based on past matching history and market trends.

[0147] Example: In response to an engineer's skill sheet, the analysis result may be "little experience in security-related fields."

[0148] The server uses a generative AI model to generate suggested sentences based on the analysis results and notifies the user.

[0149] For example: "Adding security-related experience may improve your match."

[0150] The user accepts the suggestion and corrects and updates the information on the skill sheet, etc. The terminal then transmits the user's updated information to the server again, updating the database.

[0151] Examples of prompt statements

[0152] 1. "Show me whether adding security-related experience to an engineer's skill sheet would improve their match."

[0153] 2. "Calculate the match between the company's job information and the engineer's skill sheet, and send a recommendation if the match is 80% or higher."

[0154] Through the above specific implementation, the system can efficiently collect information on clients and contractors and achieve optimal matching, thereby eliminating the problem of multiple subcontracting structures in the IT industry and bringing benefits to both companies and engineers.

[0155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0156] Processing Steps

[0157] Step 1: Enter your information

[0158] Users access a dedicated web screen and enter project information and skill information.

[0159] Input: Project information (e.g., project name, required skills, budget, etc.) and skill information (e.g., skill name, years of experience, desired conditions, etc.) entered by the user.

[0160] Output: Temporary data of the information entered by the user.

[0161] Specific operation: The user enters the required information into a dedicated web screen, confirms it, and then clicks the submit button.

[0162] Step 2: Submit your information

[0163] The terminal formats the input information into JSON format and sends it to the server using the HTTPS protocol.

[0164] Input: JSON format job and skill information held as temporary data.

[0165] Output: The JSON data sent to the server.

[0166] Specific operation: When the user clicks the send button, the terminal converts the entered information into JSON format and sends it to the server via the network.

[0167] Step 3: Receiving and storing information

[0168] The server parses the received JSON data and stores it in a database.

[0169] Input: The JSON data sent to the server.

[0170] Output: Opportunity and skill information stored in a database.

[0171] Specific operation: The server parses the received JSON data, extracts the necessary fields, and generates and executes SQL queries to save them to the database.

[0172] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[0173] Step 4: Gather information

[0174] The server periodically retrieves information stored in the database using queries, using a scheduling tool.

[0175] Input: Opportunity and skill information in the database.

[0176] Output: A dataset to input into a machine learning model.

[0177] Specific operation: The server retrieves the latest information from the database based on a regular schedule, for example once a day.

[0178] Example: SELECT FROM user_data

[0179] Step 5: Run machine learning

[0180] The server inputs the acquired data into a machine learning model (such as TensorFlow or PyTorch) and performs learning.

[0181] Input: A dataset retrieved from a database.

[0182] Output: An updated machine learning model.

[0183] Specific operation: Performs data preprocessing (e.g., imputing missing values ​​and normalizing data) and trains a model using the preprocessed data.

[0184] Example: model.fit(training_data, labels)

[0185] Step 6: Update the algorithm

[0186] The server updates the matching algorithm based on the new learning results.

[0187] Input: Updated machine learning model parameters.

[0188] Output: The updated matching algorithm.

[0189] Specific operation: Based on the learning results, the parameters of the current matching algorithm are updated so that matching can be performed under the new conditions.

[0190] Step 7: Matching Proposals

[0191] The server compares the company's project information with the engineer's skill information and calculates the degree of match.

[0192] Input: Updated matching algorithm, and job and skill information from the database.

[0193] Output: A list of recommendations with high match scores.

[0194] Specific operation: Generates recommendations based on the calculated match using skill match, years of experience, match rate, etc.

[0195] Step 8: Sending recommendations

[0196] If the degree of match is high, the server transmits a recommendation notification to the orderer and the order recipient.

[0197] Input: A list of recommendations with high match scores.

[0198] Output: Recommendation notification.

[0199] Specific behavior: Notifications will be sent via email, in-app notifications, etc., and will include detailed job and skill information.

[0200] Step 9: Confirm the "Like" and make a match

[0201] The user checks the recommendation notification and clicks the "Like" button if they are interested.

[0202] Input: Recommendation notification.

[0203] Output: Like button click information.

[0204] Specific operation: When a user receives a recommendation notification, they check the details and click the "Like" button if they are interested. The server receives and records the click information.

[0205] Step 10: Notification of successful match

[0206] The server will establish a match if both parties send a "like."

[0207] Input: "Like" information from both parties.

[0208] Output: Matching notification.

[0209] Specific operation: When both parties' "likes" are confirmed, the server automatically executes a process to establish a match (e.g., notifying the start of a sales process).

[0210] (Application example 1)

[0211] 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."

[0212] With conventional technology, the process of matching robots with work tasks in a factory was time-consuming and laborious, making it difficult to achieve optimal efficiency. Furthermore, managing robot skill information and the required skill information for work tasks was cumbersome, and there was a lack of effective tools for appropriate matching. This often led to a decline in overall factory work efficiency and productivity, resulting in increased costs.

[0213] 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.

[0214] In this invention, the server includes a means for collecting project information from the ordering party and skill information from the ordering party, a means for storing each piece of information in a database, and an artificial intelligence means for learning market needs and seeds based on the stored information. This makes it possible to collect information on robots and work tasks within a factory and store it in a database. In addition, the artificial intelligence means can be used to calculate optimal matches between robots and work tasks, and the results can be notified to the factory management system, making it possible to significantly improve work efficiency and productivity within the factory.

[0215] A "client" is a company or individual that requests work or a project for a product or service.

[0216] "Client" refers to a company or individual that carries out work or projects ordered by the client.

[0217] "Project information" refers to information such as the specific work content, conditions, and schedule requested by the client.

[0218] "Skill information" is information about the technology, experience, and abilities of the client.

[0219] A "database" is a system that organizes and stores collected information and allows it to be retrieved as needed.

[0220] "Artificial intelligence" is a technology that learns patterns based on data and performs optimal matching and recommendations.

[0221] "Matching" is the process of comparing the client's project information with the client's skill information and proposing the optimal combination.

[0222] "Market needs" refers to information about market demand and customer expectations.

[0223] "Seeds" refers to information about market supply and available services and products.

[0224] A "robot" is a mechanical device that automatically performs specific tasks in a factory.

[0225] A "work task" is the specific work that a robot performs in a factory.

[0226] A "management system" is a system for centrally managing and monitoring work within a factory and the operation of robots.

[0227] "Recommendation" refers to a proposal made to the client and the supplier when the degree of match is high.

[0228] This invention describes a system for achieving optimal matching between robots and work tasks in a factory. This system collects information on the ordering party and the ordering recipient, and provides effective matching using artificial intelligence that learns market needs and seeds based on the information stored in a database.

[0229] System Overview

[0230] Program Generation

[0231] The system includes a program that performs the following processes: The program retrieves information about the robot and the work task from a database, and uses a machine learning algorithm to determine the optimal pair.

[0232] Hardware and software used

[0233] Hardware: RFID-tagged robots, sensors installed at the work site, and servers

[0234] Software: SQLite (database), Scikit-learn (machine learning library), Python (integrated environment)

[0235] Natural language explanation of the process

[0236] The server collects information about robots and work tasks within the factory via RFID tags and sensors and stores it in an SQLite database. It then extracts robot skill information and the required skill information for each work task from the database and formats it into a matrix. It then uses Scikit-learn's KMeans clustering to perform clustering to match the robot best suited to the task. The final matching results are stored in the database and notified to the factory's management system.

[0237] Specific examples

[0238] For example, suppose there are five robots (A, B, C, D, E) and five tasks in a factory. Robot A is good at welding and robot B is good at painting. Task 1 requires welding and task 2 requires painting. The system will optimize by assigning task 1 to robot A and task 2 to robot B.

[0239] Prompt Sentence Examples

[0240] To implement the invention, generate a prompt like this:

[0241] "Please develop a system that optimally matches factory robots with tasks. This will be achieved using a machine learning algorithm based on the robot's skill information and the required skill information for the task. The software used will be Python and Scikit-learn, and the database will be SQLite. Please also provide specific code examples."

[0242] The above is a detailed description of an embodiment of the present invention. By using this system, it is possible to significantly improve work efficiency and productivity within a factory.

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] The user (factory manager) uses a dedicated interface to input information about the robots deployed in the factory and the work tasks to be performed. This information includes robot skill information (e.g., welding, painting, etc.) and required skill information for the work task (e.g., whether the task requires welding or painting). The input information is sent from the terminal to the server.

[0246] Step 2:

[0247] The server receives the robot's skill information and the required skill information for the work task from the terminal and stores it in an SQLite database. The database stores each robot's capabilities and task requirements in an organized format and manages them centrally.

[0248] Step 3:

[0249] The server periodically retrieves information about the robot and the work task from the database, executes database queries to extract the robot's skill information and the required skill information for the work task, and converts it into a matrix-formatted dataset for subsequent machine learning processing.

[0250] Step 4:

[0251] The server uses Scikit-learn's KMeans clustering algorithm to perform clustering based on robot skill information and the required skill information for the work task. This clustering process selects the robot best suited to each work task. Specifically, robot skill information is provided as input to the clustering algorithm, which derives the robot group that best meets the task requirements.

[0252] Step 5:

[0253] Based on the clustering results, the server generates matching results for the optimal robot for each work task. These matching results are saved back in the database and notified to the factory management system. This automatically updates the work plan within the factory, enabling efficient work execution.

[0254] Step 6:

[0255] Based on the matching results, the server sends specific work instructions to the robots, allowing them to start the appropriate work in the appropriate location. For example, robot A, which is good at welding, performs welding task 1, and robot B, which is good at painting, performs painting task 2.

[0256] Step 7:

[0257] The server receives feedback from each robot to monitor and evaluate the progress of the work in real time. The feedback includes data on the progress of the work and any unforeseen issues. This allows the system to keep up to date with the situation and adjust work schedules and instructions as needed.

[0258] Step 8:

[0259] The user (factory manager) can grasp the overall progress of work through reports provided by the server and make strategic decisions regarding factory operations as needed. The reports include evaluation of matching results, analysis of work efficiency, and proposals for future task allocation.

[0260] 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.

[0261] The system of the present invention collects information on ordering parties and customers, and uses artificial intelligence to learn market needs and seeds, thereby achieving optimal matching. Furthermore, the present invention combines an emotion engine that recognizes user emotions, enabling more appropriate recommendations. A specific embodiment of the system is shown below.

[0262] System Overview

[0263] 1. User (Orderer, Supplier) Registration:

[0264] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[0265] The terminal sends the entered information to the server and stores it in a database.

[0266] 2. Information storage and learning:

[0267] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[0268] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[0269] 3. Emotion Engine Analysis:

[0270] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user.

[0271] The emotion engine analyzes the user's facial expressions and text input to identify positive and negative emotional trends.

[0272] 4. Match proposal and establishment:

[0273] The server takes into account the analysis results of the emotion engine, compares the registered information, and if it determines that there is a high degree of match, it sends a recommendation to the ordering party and the supplier.

[0274] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[0275] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[0276] 5. Feedback and Suggestions:

[0277] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[0278] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[0279] Specific examples

[0280] Specific examples of registration

[0281] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[0282] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[0283] The terminal formats this information and sends it to the server.

[0284] The server stores the received information in a database and also uses it as learning data.

[0285] Specific examples of recommendations

[0286] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[0287] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[0288] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[0289] The server sends recommendations and notifications to both companies and engineers.

[0290] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[0291] Specific examples of proposals

[0292] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[0293] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[0294] As described above, the present invention is a system that efficiently collects information on clients and customers, and utilizes an emotion engine to achieve optimal matching while taking user emotions into consideration. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[0295] The processing flow will be explained below.

[0296] Step 1:

[0297] Users (orderer, supplier) log in to the platform.

[0298] The terminal sends the user's authentication information to an input form.

[0299] The server checks the authentication information and verifies that the user has valid access.

[0300] Step 2:

[0301] The user inputs the job information or skill sheet information.

[0302] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[0303] The terminal sends the input data to the server.

[0304] Step 3:

[0305] The server stores the received data in a database.

[0306] The server validates the data format and performs any necessary conversions.

[0307] The server stores the job information or skill sheet information in a database.

[0308] Step 4:

[0309] The server provides the newly registered information to the AI ​​engine.

[0310] The server extracts new information from the database and passes it to the AI ​​engine.

[0311] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[0312] Step 5:

[0313] The server updates the matching algorithm based on market data and seed information.

[0314] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[0315] Step 6:

[0316] The server compares the registration data with market information and calculates the degree of match.

[0317] The server compares the engineer's skill sheet with the project information and generates a score.

[0318] The server refers to past matching history and adjusts the weight of each condition.

[0319] Step 7:

[0320] The server recommends candidates with high matching potential.

[0321] The server selects the best candidate for each engineer and job and sends a notification.

[0322] The device displays the recommendation content to the user.

[0323] Step 8:

[0324] The user reviews the recommendation and clicks "Like."

[0325] The device accepts the user's input and clicks the "Like" button.

[0326] The device sends the "like" information to the server.

[0327] Step 9:

[0328] The server detects both "likes" and makes a match.

[0329] The server checks both "likes" and notifies the match.

[0330] The server will contact you to proceed with the negotiation process.

[0331] Step 10:

[0332] The server will suggest any deficiencies or corrections.

[0333] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[0334] The server notifies the user of the proposal.

[0335] Step 11:

[0336] The user accepts the suggestions and makes the necessary corrections.

[0337] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[0338] The device sends the modifications to the server.

[0339] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[0340] Step 12:

[0341] Sentiment analysis is performed based on user input and reaction data.

[0342] The terminal collects the user's input information and sends it to the server.

[0343] The server uses an emotion engine to analyze the user's emotion (e.g., positive, negative, neutral).

[0344] The server stores the results of the emotion analysis and reflects them in future matching algorithms.

[0345] Step 13:

[0346] Recommendations are adjusted based on the results of sentiment analysis.

[0347] The server takes into account the results of the user's emotion analysis obtained by the emotion engine and fine-tunes the recommendations.

[0348] Increase recommendation frequency or priority for projects or skill sheets that have strong positive sentiment.

[0349] If negative sentiment is found, the system will adjust the recommendations to include other candidates.

[0350] The above processing steps create a system that achieves optimal matching that takes user emotions into consideration and provides highly satisfying results for both companies and engineers.

[0351] Example 2

[0352] 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."

[0353] Current matching systems only match clients based on the skills and project information of the client and client, which limits the accuracy of matching. As a result, project success rates decline and users often do not receive satisfactory results. Furthermore, because matching does not take into account the user's emotions and reactions, it is difficult to increase user satisfaction. Therefore, there is a need for a more accurate matching system that takes into account the user's input information and emotions.

[0354] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0355] In this invention, the server includes means for collecting project information of ordering parties and skill information of ordering parties, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the ordering party using the results learned by the artificial intelligence means, means for making a recommendation to the ordering party and the ordering party if the degree of match is high, means for achieving a match if approval is obtained from both parties, means for analyzing input information and reactions of users using an emotion engine and analyzing emotional trends, and means for reflecting the analysis results of the emotion engine in a matching algorithm. This enables highly accurate matching that takes user emotions into consideration.

[0356] "Client's project information" refers to detailed information about a particular project or task provided by a client.

[0357] "Skill information of the client" is information about the skills, experience, and abilities provided by the party undertaking the work.

[0358] A "database" is a system for storing collected information in a structured manner and making it accessible efficiently.

[0359] "Artificial intelligence tools" are techniques that learn patterns from data to solve specific tasks or problems.

[0360] The "means for calculating the degree of match" is a function that calculates the degree of match between the orderer's project information and the order recipient's skill information based on the two.

[0361] The "means for making recommendations" is a function that suggests suitable partners to the ordering party and the ordering recipient when the degree of match is high.

[0362] "Means for achieving matching" is a function that formally links the ordering party and the customer when both parties approve.

[0363] An "emotion engine" is a technology that analyzes a user's input information and reactions and determines their emotions.

[0364] "Means for analyzing emotional trends" is a function that analyzes positive and negative emotions based on user input and reactions.

[0365] A "matching algorithm" is a calculation method for effectively matching the ordering party and the customer based on their information.

[0366] MODE FOR CARRYING OUT THE INVENTION

[0367] The present invention is a system that efficiently collects information on suppliers and recipients and utilizes an emotion engine to achieve optimal matching that takes user emotions into consideration. Below, we will explain how this system is implemented in concrete terms.

[0368] Registering Users

[0369] Users (clients and recipients) enter project information and skill information through a dedicated web screen. For example, an engineer might enter detailed information such as "five years of Python experience, ability to use the Django framework, desired monthly rate of 500,000 yen." The terminal formats the information entered and sends it to the server. This transmission is done in JSON format and sent to the server's REST API.

[0370] Information storage and learning

[0371] The server stores the received information in a database. The server then triggers scheduled jobs to retrieve new job and skill information from the database. This data is analyzed by machine learning algorithms, which use artificial intelligence technologies such as TensorFlow and Scikit-learn to learn market needs and seeds.

[0372] Emotion Engine Analysis

[0373] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user. For example, it analyzes text comments and survey responses in real time and calculates an emotion score using natural language processing (NLP) technology. It also analyzes the user's facial expression images using OpenCV and deep learning models.

[0374] Matching proposal and establishment

[0375] The server updates the matching algorithm based on the analysis results of the emotion engine. If the match is strong, a recommendation is sent to the client and the client. For example, if an engineer has a positive reaction to a "Python" project, that project will be recommended as a priority. The user is notified, checks the recommended partner, and sends a "Like." The server then confirms both "Likes" and establishes a match.

[0376] Feedback and Suggestions

[0377] If there are any deficiencies or corrections in the client or supplier information, the server will make suggestions based on past matching history and market trends. For example, it may suggest that adding security-related experience would improve the match. The user can accept the suggestions and revise their skill sheet and project information to improve the accuracy of future matches.

[0378] Specific examples

[0379] Specific examples of registration

[0380] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[0381] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[0382] The terminal formats this information and sends it to the server.

[0383] The server stores the received information in a database and also uses it as learning data.

[0384] Specific examples of recommendations

[0385] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[0386] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[0387] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[0388] The server sends recommendations and notifications to both companies and engineers.

[0389] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[0390] Specific examples of proposals

[0391] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[0392] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[0393] This provides a system that efficiently collects information on the ordering party and the ordering party, utilizes an emotion engine to take into account the user's emotions, and achieves optimal matching.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] Processing step flow

[0396] Step 1:

[0397] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[0398] Input example: An engineer enters detailed information such as "5 years of Python experience, can handle the Django framework, desired monthly rate is 500,000 yen."

[0399] The terminal formats the input information, converts it into JSON format, and sends it to the server.

[0400] Step 2:

[0401] The server parses the received JSON data and stores it in a database using SQL queries.

[0402] The server verifies and stores the data stored in the database.

[0403] Input: JSON data sent from the terminal

[0404] Output: Case information and skill information stored in the database

[0405] Step 3:

[0406] The server triggers a scheduled job to retrieve new job information and skill information from the database.

[0407] The server runs machine learning models using TensorFlow and Scikit-learn to learn market needs and seeds.

[0408] Input: Project information and skill information obtained from the database

[0409] Output: Market needs and seeds as learning results

[0410] Step 4:

[0411] The server analyzes the information and reactions entered by the user using an emotion engine.

[0412] The server analyzes text comments and survey responses in real time, calculates emotion scores using natural language processing (NLP) techniques, and analyzes user facial expression images using OpenCV and deep learning models.

[0413] Input: User's text comments and facial expression images

[0414] Output: Sentiment score from the sentiment engine

[0415] Step 5:

[0416] The server updates the matching algorithm based on the analysis results of the emotion engine.

[0417] The server calculates a score for each combination of engineer and project, and prioritizes combinations with high emotional scores by adding them to the recommendation list.

[0418] Input: Sentiment score and case information / skill information

[0419] Output: Recommendation list

[0420] Step 6:

[0421] If the server determines that the match is high, it sends a recommendation to the ordering party and the supplier.

[0422] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[0423] The server checks both "likes" and makes the match.

[0424] Input: Recommendation list and user "likes"

[0425] Output: Matching successful notification

[0426] Step 7:

[0427] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[0428] Users can accept the suggestions and revise their skill sheets and job information to improve matching accuracy in future matches.

[0429] Inputs: Past matching history and market trends

[0430] Output: Proposal to correct information

[0431] (Application example 2)

[0432] 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."

[0433] Existing ordering systems struggle to efficiently collect information on the ordering source and the ordering recipient, and perform appropriate matching. Furthermore, they lack recommendation functions that take user sentiment into account, making it difficult to improve the user experience. Furthermore, they lack navigation and real-time information provision to optimize the in-store shopping experience.

[0434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0435] In this invention, the server includes means for collecting project information of ordering parties and skill information of suppliers, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the supplier using the results learned by the artificial intelligence means, means for making recommendations to the ordering party and the supplier if the degree of match is high, means for establishing a match if approval is obtained from both parties, emotion analysis means for analyzing user emotions in real time, means for optimizing product recommendations based on the emotion analysis results, means for providing navigation within a physical store, and means for notifying limited-time sales and campaign information in real time. This enables efficient collection of information, optimal matching, and an improved user experience.

[0436] The "ordering party" is an entity that provides project information to outsource work or services.

[0437] The "client" is an entity that receives project information from the client and provides the business or service.

[0438] "Project information" is detailed information about projects and work provided by the client.

[0439] "Skill information" is information relating to the skills and experience possessed by the client.

[0440] The "database" is a data storage system for storing collected project information of the ordering party and skill information of the ordering party.

[0441] "Artificial intelligence means" refers to machine learning algorithms that learn market needs and seeds based on collected information and perform optimal matching.

[0442] The "match degree" is an index showing the degree of agreement between the order source's job information and the order recipient's skill information.

[0443] The "recommendation means" is a device or system that makes a recommendation to the ordering party and the ordering party when the degree of match is high.

[0444] The "matching means" is a device or system that establishes a match when both parties approve it.

[0445] The "emotion analysis means" is software or hardware for analyzing the user's emotions in real time.

[0446] The "product recommendation optimization means" is software or a system for recommending appropriate products to users based on the results of emotion analysis.

[0447] A "navigation means" is a device or system that guides a user to a specific product within a physical store.

[0448] "Real-time notification means" refers to software or a system that notifies users of limited-time sales and campaign information in real time.

[0449] The system for realizing this application example has the following functions.

[0450] Collecting and storing user information

[0451] Users install a smartphone application and, when they first launch it, enter their profile information, favorite product categories, past purchase history, etc. The entered information is sent from the user's device to a server and stored in a database. The database used may be, for example, MySQL or Firebase.

[0452] AI learning and matching

[0453] The server periodically passes the information stored in the database to an artificial intelligence engine (such as TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The artificial intelligence engine generates an algorithm based on the learning results to perform matching under optimal conditions. This algorithm then recommends the best products and services to users.

[0454] Emotion analysis

[0455] The server passes text data, such as when a user browses products or writes a review, to an emotion engine (such as IBM Watson or Microsoft Azure Emotion Recognition). The emotion engine analyzes the input text data and grasps the user's emotions in real time.

[0456] Product recommendation optimization

[0457] If the sentiment analysis engine determines that the user's sentiment is positive, the server will optimize the prioritization of product recommendations based on the results. Products and services that the user is particularly interested in will be displayed at the top of the recommendation list.

[0458] In-store navigation and real-time notifications

[0459] When a user uses the application in a physical store, the server provides in-store navigation functions. For example, if a user searches for a specific product in the app, the server displays a route to the location of that product. The server also provides a means to notify users of limited sales and campaign information in real time, improving the user experience.

[0460] Specific examples

[0461] For example, a user might enter the following review into the app: "This product is absolutely amazing!" The server passes this input to the emotion engine for sentiment analysis. The emotion analysis engine detects positive emotions such as "joy" and "confidence." Based on these results, the server increases the frequency of recommendations for similar or related products, and prioritizes products that match the user's interests.

[0462] Furthermore, when a user visits a physical store and searches for a product they are interested in using the app, navigation to the location of that product is displayed. At the same time, limited sale and campaign information is notified in real time, encouraging purchases.

[0463] Example prompt

[0464] An example of an input prompt for a generative AI model is:

[0465] "Review written: This product is absolutely amazing!"

[0466] Sentiment analysis results: "Happiness: 0.9, Confidence: 0.8"

[0467] Make a list of products you recommend.

[0468] This prompt can be used to input sentiment analysis results into a generative AI model to build a system that recommends appropriate products.

[0469] As described above, the embodiment of the present invention efficiently collects user information and utilizes artificial intelligence and sentiment analysis to provide optimal product recommendations and improve the user experience.

[0470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0471] Step 1: Enter your user information

[0472] When a user installs a smartphone application and launches it for the first time, they enter their profile information, favorite product categories, past purchase history, etc. The input data is sent from the device to the server in JSON format. Based on that input, the user profile data is saved on the server and used for subsequent processing.

[0473] Step 2: Save your information

[0474] The device sends the information entered by the user to the server. The server stores the received information in a database (for example, MySQL or Firebase). Specifically, entries such as each user's profile information, preferences, and purchase history are registered in the database. The input is user information, and the output is data stored in the database.

[0475] Step 3: Learning with AI

[0476] The server periodically passes the information stored in the database to an artificial intelligence engine (e.g., TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The input is user data and project data, and the output is a trained matching model. Data processing includes preprocessing and feature engineering.

[0477] Step 4: Sentiment Analysis

[0478] The server passes the text data when a user browses products or writes a review to an emotion engine (e.g., IBM Watson or Microsoft Azure Emotion Recognition) and analyzes emotions in real time. The input is the user's text data, and the output is the emotion analysis result (e.g., joy: 0.9, confidence: 0.8). The data is calculated by the emotion recognition algorithm.

[0479] Step 5: Applying the recommendation algorithm

[0480] Based on the results of the sentiment analysis, the server uses a matching algorithm generated by an AI engine to recommend the most suitable products and services to the user. The input is the sentiment analysis results and the trained model, and the output is a recommendation list. Data calculations include calculating the matching score, filtering and ranking the product list, etc.

[0481] Step 6: User Notification

[0482] Once the server generates the recommendation list, it sends a notification to the user device. The notification contains information about the recommended products and services. The input is the recommendation list, and the output is a notification message sent to the user device. Specific actions include sending a push notification or displaying a pop-up in the app.

[0483] Step 7: In-store navigation

[0484] When a user uses the app in a physical store and searches for a specific product, the server provides in-store navigation functionality. The input is the user's search query, and the output is the product's location information and a guided route. Data calculation involves calculating the route based on the store's map data. Specific operations include displaying the route within the app.

[0485] Step 8: Real-time notifications

[0486] The server notifies users in real time about limited-time sales and campaigns in stores. The input is a database of campaign information, and the output is a notification message. Specific actions include push notifications and in-app banner displays.

[0487] The processing steps for realizing the application example and their specific operations have been described above.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 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.

[0494] 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).

[0495] 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.

[0496] 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.

[0497] 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).

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] 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."

[0504] The system of the present invention collects information on the ordering party and the ordering recipient, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[0505] System Overview

[0506] 1. User (Orderer, Supplier) Registration:

[0507] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[0508] The terminal sends the entered information to the server and stores it in a database.

[0509] 2. Information storage and learning:

[0510] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[0511] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[0512] 3. Match proposal and establishment:

[0513] The server compares the registered information and, if it determines that there is a high degree of match, sends a recommendation to the ordering party and the supplier.

[0514] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[0515] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[0516] 4. Feedback and Suggestions:

[0517] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[0518] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[0519] Specific examples

[0520] Specific examples of registration

[0521] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[0522] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[0523] The terminal formats this information and sends it to the server.

[0524] The server stores the received information in a database and also uses it as learning data.

[0525] Specific examples of recommendations

[0526] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[0527] The server sends recommendations and notifications to both companies and engineers.

[0528] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[0529] Specific examples of proposals

[0530] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[0531] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[0532] As described above, this invention is a system that efficiently collects information on clients and suppliers and achieves optimal matching, with the aim of eliminating the problem of multiple subcontracting structures in the IT industry. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[0533] The processing flow will be explained below.

[0534] Step 1:

[0535] Users (orderer, supplier) log in to the platform.

[0536] The terminal sends the user's authentication information to an input form.

[0537] The server checks the authentication information and verifies that the user has valid access.

[0538] Step 2:

[0539] The user inputs the job information or skill sheet information.

[0540] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[0541] The terminal sends the input data to the server.

[0542] Step 3:

[0543] The server stores the received data in a database.

[0544] The server validates the data format and performs any necessary conversions.

[0545] The server stores the job information or skill sheet information in a database.

[0546] Step 4:

[0547] The server provides the newly registered information to the AI ​​engine.

[0548] The server extracts new information from the database and passes it to the AI ​​engine.

[0549] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[0550] Step 5:

[0551] The server updates the matching algorithm based on market data and seed information.

[0552] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[0553] Step 6:

[0554] The server compares the registration data with market information and calculates the degree of match.

[0555] The server compares the engineer's skill sheet with the project information and generates a score.

[0556] The server refers to past matching history and adjusts the weight of each condition.

[0557] Step 7:

[0558] The server recommends candidates with high matching potential.

[0559] The server selects the best candidate for each engineer and job and sends a notification.

[0560] The device displays the recommendation content to the user.

[0561] Step 8:

[0562] The user reviews the recommendation and clicks "Like."

[0563] The device accepts the user's input and clicks the "Like" button.

[0564] The device sends the "like" information to the server.

[0565] Step 9:

[0566] The server detects both "likes" and makes a match.

[0567] The server checks both "likes" and notifies the match.

[0568] The server will contact you to proceed with the negotiation process.

[0569] Step 10:

[0570] The server will suggest any deficiencies or corrections.

[0571] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[0572] The server notifies the user of the proposal.

[0573] Step 11:

[0574] The user accepts the suggestions and makes the necessary corrections.

[0575] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[0576] The device sends the modifications to the server.

[0577] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[0578] Example 1

[0579] 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."

[0580] In the current market, there is an issue of inefficient matching between the projects desired by clients and the skills that contractors can provide. As a result, clients spend a great deal of time and effort finding suitable candidates, and contractors miss out on opportunities to find projects that will allow them to make the most of their skills. Furthermore, the current matching system lacks the functionality to provide appropriate feedback to clients and contractors regarding insufficient information or corrections, which also creates the issue of not making optimal proposals.

[0581] 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.

[0582] In this invention, the server includes: means for collecting project information from client computers and skill information from contractors; means for saving the collected information in a database; artificial intelligence means for learning market needs and seeds based on the saved information; means for calculating the degree of match between client computers and contractors using the results learned by the artificial intelligence means; means for making recommendations to client computers and contractors when the degree of match is high; means for establishing a match when the client computer and contractor computer that have received the recommendation approve the match; and means for displaying a generative AI model and proposal text for generating proposals based on the client computer and contractor computer information. This significantly improves the efficiency of matching between client computers and contractors, and by providing appropriate feedback on insufficient information and corrections, it becomes possible to match under optimal conditions.

[0583] "Client" is the party providing project information and seeking specific skills or services.

[0584] A "contractor" is a person who provides skill information and is willing to accept a specific project.

[0585] "Project information" refers to detailed information provided by the client, such as the job content, conditions, and required skills.

[0586] "Skill information" refers to detailed information such as skills, experience, and qualifications provided by the contractor.

[0587] A "database" is a system for systematically storing and managing collected information.

[0588] "Artificial intelligence means" refers to means that use technologies such as machine learning and deep learning to learn market needs and seeds and generate and improve matching algorithms.

[0589] The "match degree" is an index showing the degree of match between the project information of the client and the skill information of the contractor.

[0590] A "recommendation" is a notification or proposal made to the client and the contractor when the match is high.

[0591] "Approval" refers to the client and contractor who receive the recommendation expressing their intention to each other by using a "Like" button or similar.

[0592] A "generative AI model" is an artificial intelligence model that generates proposals based on information from the client and the contractor.

[0593] A "suggestion" is a document of improvements or suggestions that is automatically generated by a generative AI model and displayed to the user.

[0594] The system of the present invention collects information on purchasers and sellers, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[0595] User registration and information collection

[0596] Users enter information about jobs and skills through a dedicated web screen, which is built using web technologies such as HTML and JavaScript.

[0597] The terminal formats the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, with SSL / TLS encryption used for security during the transmission process.

[0598] The server parses the received JSON data and stores it in a database, using an RDBMS such as MySQL or PostgreSQL.

[0599] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[0600] Information storage and learning

[0601] The server periodically queries the information stored in the database, a process that can be automated using a scheduling tool such as a Cron job.

[0602] Example: SELECT FROM user_data

[0603] The server inputs the acquired data into a machine learning model for learning, using machine learning frameworks such as TensorFlow and PyTorch.

[0604] Example: model.fit(training_data, labels)

[0605] The server updates the matching algorithm based on the new learning results, thereby reflecting the latest matching conditions adapted to market needs and seeds.

[0606] Matching proposal and establishment

[0607] The server compares the company's project information stored in the database with the engineer's skill information and calculates the degree of match, using parameters such as skill match, years of experience, and match rate.

[0608] If the match rate is above a certain value (e.g., 80% or higher), the server sends a recommendation notification to the client and the recipient. The device displays this notification to the user. Notifications are sent via email, in-app notifications, etc.

[0609] The user checks the recommendation notification and clicks the "Like" button if they are interested. The server checks the user's "Like" and if both parties send "Likes", a match is made. After this, contact is made to proceed with the business negotiation process.

[0610] Feedback and Suggestions

[0611] The server analyzes the information of the client or contractor and identifies shortcomings and areas for correction based on past matching history and market trends.

[0612] Example: In response to an engineer's skill sheet, the analysis result may be "little experience in security-related fields."

[0613] The server uses a generative AI model to generate suggested sentences based on the analysis results and notifies the user.

[0614] For example: "Adding security-related experience may improve your match."

[0615] The user accepts the suggestion and corrects and updates the information on the skill sheet, etc. The terminal then transmits the user's updated information to the server again, updating the database.

[0616] Examples of prompt statements

[0617] 1. "Show me whether adding security-related experience to an engineer's skill sheet would improve their match."

[0618] 2. "Calculate the match between the company's job information and the engineer's skill sheet, and send a recommendation if the match is 80% or higher."

[0619] Through the above specific implementation, the system can efficiently collect information on clients and contractors and achieve optimal matching, thereby eliminating the problem of multiple subcontracting structures in the IT industry and bringing benefits to both companies and engineers.

[0620] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0621] Processing Steps

[0622] Step 1: Enter your information

[0623] Users access a dedicated web screen and enter project information and skill information.

[0624] Input: Project information (e.g., project name, required skills, budget, etc.) and skill information (e.g., skill name, years of experience, desired conditions, etc.) entered by the user.

[0625] Output: Temporary data of the information entered by the user.

[0626] Specific operation: The user enters the required information into a dedicated web screen, confirms it, and then clicks the submit button.

[0627] Step 2: Submit your information

[0628] The terminal formats the input information into JSON format and sends it to the server using the HTTPS protocol.

[0629] Input: JSON format job and skill information held as temporary data.

[0630] Output: The JSON data sent to the server.

[0631] Specific operation: When the user clicks the send button, the terminal converts the entered information into JSON format and sends it to the server via the network.

[0632] Step 3: Receiving and storing information

[0633] The server parses the received JSON data and stores it in a database.

[0634] Input: The JSON data sent to the server.

[0635] Output: Opportunity and skill information stored in a database.

[0636] Specific operation: The server parses the received JSON data, extracts the necessary fields, and generates and executes SQL queries to save them to the database.

[0637] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[0638] Step 4: Gather information

[0639] The server periodically retrieves information stored in the database using queries, using a scheduling tool.

[0640] Input: Opportunity and skill information in the database.

[0641] Output: A dataset to input into a machine learning model.

[0642] Specific operation: The server retrieves the latest information from the database based on a regular schedule, for example once a day.

[0643] Example: SELECT FROM user_data

[0644] Step 5: Run machine learning

[0645] The server inputs the acquired data into a machine learning model (such as TensorFlow or PyTorch) and performs learning.

[0646] Input: A dataset retrieved from a database.

[0647] Output: An updated machine learning model.

[0648] Specific operation: Performs data preprocessing (e.g., imputing missing values ​​and normalizing data) and trains a model using the preprocessed data.

[0649] Example: model.fit(training_data, labels)

[0650] Step 6: Update the algorithm

[0651] The server updates the matching algorithm based on the new learning results.

[0652] Input: Updated machine learning model parameters.

[0653] Output: The updated matching algorithm.

[0654] Specific operation: Based on the learning results, the parameters of the current matching algorithm are updated so that matching can be performed under the new conditions.

[0655] Step 7: Matching Proposals

[0656] The server compares the company's project information with the engineer's skill information and calculates the degree of match.

[0657] Input: Updated matching algorithm, and job and skill information from the database.

[0658] Output: A list of recommendations with high match scores.

[0659] Specific operation: Generates recommendations based on the calculated match using skill match, years of experience, match rate, etc.

[0660] Step 8: Sending recommendations

[0661] If the degree of match is high, the server transmits a recommendation notification to the orderer and the order recipient.

[0662] Input: A list of recommendations with high match scores.

[0663] Output: Recommendation notification.

[0664] Specific behavior: Notifications will be sent via email, in-app notifications, etc., and will include detailed job and skill information.

[0665] Step 9: Confirm the "Like" and make a match

[0666] The user checks the recommendation notification and clicks the "Like" button if they are interested.

[0667] Input: Recommendation notification.

[0668] Output: Like button click information.

[0669] Specific operation: When a user receives a recommendation notification, they check the details and click the "Like" button if they are interested. The server receives and records the click information.

[0670] Step 10: Notification of successful match

[0671] The server will establish a match if both parties send a "like."

[0672] Input: "Like" information from both parties.

[0673] Output: Matching notification.

[0674] Specific operation: When both parties' "likes" are confirmed, the server automatically executes a process to establish a match (e.g., notifying the start of a sales process).

[0675] (Application example 1)

[0676] 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."

[0677] With conventional technology, the process of matching robots with work tasks in a factory was time-consuming and laborious, making it difficult to achieve optimal efficiency. Furthermore, managing robot skill information and the required skill information for work tasks was cumbersome, and there was a lack of effective tools for appropriate matching. This often led to a decline in overall factory work efficiency and productivity, resulting in increased costs.

[0678] 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.

[0679] In this invention, the server includes a means for collecting project information from the ordering party and skill information from the ordering party, a means for storing each piece of information in a database, and an artificial intelligence means for learning market needs and seeds based on the stored information. This makes it possible to collect information on robots and work tasks within a factory and store it in a database. In addition, the artificial intelligence means can be used to calculate optimal matches between robots and work tasks, and the results can be notified to the factory management system, making it possible to significantly improve work efficiency and productivity within the factory.

[0680] A "client" is a company or individual that requests work or a project for a product or service.

[0681] "Client" refers to a company or individual that carries out work or projects ordered by the client.

[0682] "Project information" refers to information such as the specific work content, conditions, and schedule requested by the client.

[0683] "Skill information" is information about the technology, experience, and abilities of the client.

[0684] A "database" is a system that organizes and stores collected information and allows it to be retrieved as needed.

[0685] "Artificial intelligence" is a technology that learns patterns based on data and performs optimal matching and recommendations.

[0686] "Matching" is the process of comparing the client's project information with the client's skill information and proposing the optimal combination.

[0687] "Market needs" refers to information about market demand and customer expectations.

[0688] "Seeds" refers to information about market supply and available services and products.

[0689] A "robot" is a mechanical device that automatically performs specific tasks in a factory.

[0690] A "work task" is the specific work that a robot performs in a factory.

[0691] A "management system" is a system for centrally managing and monitoring work within a factory and the operation of robots.

[0692] "Recommendation" refers to a proposal made to the client and the supplier when the degree of match is high.

[0693] This invention describes a system for achieving optimal matching between robots and work tasks in a factory. This system collects information on the ordering party and the ordering recipient, and provides effective matching using artificial intelligence that learns market needs and seeds based on the information stored in a database.

[0694] System Overview

[0695] Program Generation

[0696] The system includes a program that performs the following processes: The program retrieves information about the robot and the work task from a database, and uses a machine learning algorithm to determine the optimal pair.

[0697] Hardware and software used

[0698] Hardware: RFID-tagged robots, sensors installed at the work site, and servers

[0699] Software: SQLite (database), Scikit-learn (machine learning library), Python (integrated environment)

[0700] Natural language explanation of the process

[0701] The server collects information about robots and work tasks within the factory via RFID tags and sensors and stores it in an SQLite database. It then extracts robot skill information and the required skill information for each work task from the database and formats it into a matrix. It then uses Scikit-learn's KMeans clustering to perform clustering to match the robot best suited to the task. The final matching results are stored in the database and notified to the factory's management system.

[0702] Specific examples

[0703] For example, suppose there are five robots (A, B, C, D, E) and five tasks in a factory. Robot A is good at welding and robot B is good at painting. Task 1 requires welding and task 2 requires painting. The system will optimize by assigning task 1 to robot A and task 2 to robot B.

[0704] Prompt Sentence Examples

[0705] To implement the invention, generate a prompt like this:

[0706] "Please develop a system that optimally matches factory robots with tasks. This will be achieved using a machine learning algorithm based on the robot's skill information and the required skill information for the task. The software used will be Python and Scikit-learn, and the database will be SQLite. Please also provide specific code examples."

[0707] The above is a detailed description of an embodiment of the present invention. By using this system, it is possible to significantly improve work efficiency and productivity within a factory.

[0708] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0709] Step 1:

[0710] The user (factory manager) uses a dedicated interface to input information about the robots deployed in the factory and the work tasks to be performed. This information includes robot skill information (e.g., welding, painting, etc.) and required skill information for the work task (e.g., whether the task requires welding or painting). The input information is sent from the terminal to the server.

[0711] Step 2:

[0712] The server receives the robot's skill information and the required skill information for the work task from the terminal and stores it in an SQLite database. The database stores each robot's capabilities and task requirements in an organized format and manages them centrally.

[0713] Step 3:

[0714] The server periodically retrieves information about the robot and the work task from the database, executes database queries to extract the robot's skill information and the required skill information for the work task, and converts it into a matrix-formatted dataset for subsequent machine learning processing.

[0715] Step 4:

[0716] The server uses Scikit-learn's KMeans clustering algorithm to perform clustering based on robot skill information and the required skill information for the work task. This clustering process selects the robot best suited to each work task. Specifically, robot skill information is provided as input to the clustering algorithm, which derives the robot group that best meets the task requirements.

[0717] Step 5:

[0718] Based on the clustering results, the server generates matching results for the optimal robot for each work task. These matching results are saved back in the database and notified to the factory management system. This automatically updates the work plan within the factory, enabling efficient work execution.

[0719] Step 6:

[0720] Based on the matching results, the server sends specific work instructions to the robots, allowing them to start the appropriate work in the appropriate location. For example, robot A, which is good at welding, performs welding task 1, and robot B, which is good at painting, performs painting task 2.

[0721] Step 7:

[0722] The server receives feedback from each robot to monitor and evaluate the progress of the work in real time. The feedback includes data on the progress of the work and any unforeseen issues. This allows the system to keep up to date with the situation and adjust work schedules and instructions as needed.

[0723] Step 8:

[0724] The user (factory manager) can grasp the overall progress of work through reports provided by the server and make strategic decisions regarding factory operations as needed. The reports include evaluation of matching results, analysis of work efficiency, and proposals for future task allocation.

[0725] 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.

[0726] The system of the present invention collects information on ordering parties and customers, and uses artificial intelligence to learn market needs and seeds, thereby achieving optimal matching. Furthermore, the present invention combines an emotion engine that recognizes user emotions, enabling more appropriate recommendations. A specific embodiment of the system is shown below.

[0727] System Overview

[0728] 1. User (Orderer, Supplier) Registration:

[0729] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[0730] The terminal sends the entered information to the server and stores it in a database.

[0731] 2. Information storage and learning:

[0732] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[0733] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[0734] 3. Emotion Engine Analysis:

[0735] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user.

[0736] The emotion engine analyzes the user's facial expressions and text input to identify positive and negative emotional trends.

[0737] 4. Match proposal and establishment:

[0738] The server takes into account the analysis results of the emotion engine, compares the registered information, and if it determines that there is a high degree of match, it sends a recommendation to the ordering party and the supplier.

[0739] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[0740] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[0741] 5. Feedback and Suggestions:

[0742] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[0743] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[0744] Specific examples

[0745] Specific examples of registration

[0746] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[0747] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[0748] The terminal formats this information and sends it to the server.

[0749] The server stores the received information in a database and also uses it as learning data.

[0750] Specific examples of recommendations

[0751] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[0752] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[0753] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[0754] The server sends recommendations and notifications to both companies and engineers.

[0755] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[0756] Specific examples of proposals

[0757] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[0758] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[0759] As described above, the present invention is a system that efficiently collects information on clients and customers, and utilizes an emotion engine to achieve optimal matching while taking user emotions into consideration. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] Users (orderer, supplier) log in to the platform.

[0763] The terminal sends the user's authentication information to an input form.

[0764] The server checks the authentication information and verifies that the user has valid access.

[0765] Step 2:

[0766] The user inputs the job information or skill sheet information.

[0767] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[0768] The terminal sends the input data to the server.

[0769] Step 3:

[0770] The server stores the received data in a database.

[0771] The server validates the data format and performs any necessary conversions.

[0772] The server stores the job information or skill sheet information in a database.

[0773] Step 4:

[0774] The server provides the newly registered information to the AI ​​engine.

[0775] The server extracts new information from the database and passes it to the AI ​​engine.

[0776] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[0777] Step 5:

[0778] The server updates the matching algorithm based on market data and seed information.

[0779] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[0780] Step 6:

[0781] The server compares the registration data with market information and calculates the degree of match.

[0782] The server compares the engineer's skill sheet with the project information and generates a score.

[0783] The server refers to past matching history and adjusts the weight of each condition.

[0784] Step 7:

[0785] The server recommends candidates with high matching potential.

[0786] The server selects the best candidate for each engineer and job and sends a notification.

[0787] The device displays the recommendation content to the user.

[0788] Step 8:

[0789] The user reviews the recommendation and clicks "Like."

[0790] The device accepts the user's input and clicks the "Like" button.

[0791] The device sends the "like" information to the server.

[0792] Step 9:

[0793] The server detects both "likes" and makes a match.

[0794] The server checks both "likes" and notifies the match.

[0795] The server will contact you to proceed with the negotiation process.

[0796] Step 10:

[0797] The server will suggest any deficiencies or corrections.

[0798] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[0799] The server notifies the user of the proposal.

[0800] Step 11:

[0801] The user accepts the suggestions and makes the necessary corrections.

[0802] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[0803] The device sends the modifications to the server.

[0804] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[0805] Step 12:

[0806] Sentiment analysis is performed based on user input and reaction data.

[0807] The terminal collects the user's input information and sends it to the server.

[0808] The server uses an emotion engine to analyze the user's emotion (e.g., positive, negative, neutral).

[0809] The server stores the results of the emotion analysis and reflects them in future matching algorithms.

[0810] Step 13:

[0811] Recommendations are adjusted based on the results of sentiment analysis.

[0812] The server takes into account the results of the user's emotion analysis obtained by the emotion engine and fine-tunes the recommendations.

[0813] Increase recommendation frequency or priority for projects or skill sheets that have strong positive sentiment.

[0814] If negative sentiment is found, the system will adjust the recommendations to include other candidates.

[0815] The above processing steps create a system that achieves optimal matching that takes user emotions into consideration and provides highly satisfying results for both companies and engineers.

[0816] Example 2

[0817] 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."

[0818] Current matching systems only match clients based on the skills and project information of the client and client, which limits the accuracy of matching. As a result, project success rates decline and users often do not receive satisfactory results. Furthermore, because matching does not take into account the user's emotions and reactions, it is difficult to increase user satisfaction. Therefore, there is a need for a more accurate matching system that takes into account the user's input information and emotions.

[0819] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0820] In this invention, the server includes means for collecting project information of ordering parties and skill information of ordering parties, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the ordering party using the results learned by the artificial intelligence means, means for making a recommendation to the ordering party and the ordering party if the degree of match is high, means for achieving a match if approval is obtained from both parties, means for analyzing input information and reactions of users using an emotion engine and analyzing emotional trends, and means for reflecting the analysis results of the emotion engine in a matching algorithm. This enables highly accurate matching that takes user emotions into consideration.

[0821] "Client's project information" refers to detailed information about a particular project or task provided by a client.

[0822] "Skill information of the client" is information about the skills, experience, and abilities provided by the party undertaking the work.

[0823] A "database" is a system for storing collected information in a structured manner and making it accessible efficiently.

[0824] "Artificial intelligence tools" are techniques that learn patterns from data to solve specific tasks or problems.

[0825] The "means for calculating the degree of match" is a function that calculates the degree of match between the orderer's project information and the order recipient's skill information based on the two.

[0826] The "means for making recommendations" is a function that suggests suitable partners to the ordering party and the ordering recipient when the degree of match is high.

[0827] "Means for achieving matching" is a function that formally links the ordering party and the customer when both parties approve.

[0828] An "emotion engine" is a technology that analyzes a user's input information and reactions and determines their emotions.

[0829] "Means for analyzing emotional trends" is a function that analyzes positive and negative emotions based on user input and reactions.

[0830] A "matching algorithm" is a calculation method for effectively matching the ordering party and the customer based on their information.

[0831] MODE FOR CARRYING OUT THE INVENTION

[0832] The present invention is a system that efficiently collects information on suppliers and recipients and utilizes an emotion engine to achieve optimal matching that takes user emotions into consideration. Below, we will explain how this system is implemented in concrete terms.

[0833] Registering Users

[0834] Users (clients and recipients) enter project information and skill information through a dedicated web screen. For example, an engineer might enter detailed information such as "five years of Python experience, ability to use the Django framework, desired monthly rate of 500,000 yen." The terminal formats the information entered and sends it to the server. This transmission is done in JSON format and sent to the server's REST API.

[0835] Information storage and learning

[0836] The server stores the received information in a database. The server then triggers scheduled jobs to retrieve new job and skill information from the database. This data is analyzed by machine learning algorithms, which use artificial intelligence technologies such as TensorFlow and Scikit-learn to learn market needs and seeds.

[0837] Emotion Engine Analysis

[0838] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user. For example, it analyzes text comments and survey responses in real time and calculates an emotion score using natural language processing (NLP) technology. It also analyzes the user's facial expression images using OpenCV and deep learning models.

[0839] Matching proposal and establishment

[0840] The server updates the matching algorithm based on the analysis results of the emotion engine. If the match is strong, a recommendation is sent to the client and the client. For example, if an engineer has a positive reaction to a "Python" project, that project will be recommended as a priority. The user is notified, checks the recommended partner, and sends a "Like." The server then confirms both "Likes" and establishes a match.

[0841] Feedback and Suggestions

[0842] If there are any deficiencies or corrections in the client or supplier information, the server will make suggestions based on past matching history and market trends. For example, it may suggest that adding security-related experience would improve the match. The user can accept the suggestions and revise their skill sheet and project information to improve the accuracy of future matches.

[0843] Specific examples

[0844] Specific examples of registration

[0845] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[0846] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[0847] The terminal formats this information and sends it to the server.

[0848] The server stores the received information in a database and also uses it as learning data.

[0849] Specific examples of recommendations

[0850] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[0851] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[0852] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[0853] The server sends recommendations and notifications to both companies and engineers.

[0854] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[0855] Specific examples of proposals

[0856] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[0857] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[0858] This provides a system that efficiently collects information on the ordering party and the ordering party, utilizes an emotion engine to take into account the user's emotions, and achieves optimal matching.

[0859] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0860] Processing step flow

[0861] Step 1:

[0862] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[0863] Input example: An engineer enters detailed information such as "5 years of Python experience, can handle the Django framework, desired monthly rate is 500,000 yen."

[0864] The terminal formats the input information, converts it into JSON format, and sends it to the server.

[0865] Step 2:

[0866] The server parses the received JSON data and stores it in a database using SQL queries.

[0867] The server verifies and stores the data stored in the database.

[0868] Input: JSON data sent from the terminal

[0869] Output: Case information and skill information stored in the database

[0870] Step 3:

[0871] The server triggers a scheduled job to retrieve new job information and skill information from the database.

[0872] The server runs machine learning models using TensorFlow and Scikit-learn to learn market needs and seeds.

[0873] Input: Project information and skill information obtained from the database

[0874] Output: Market needs and seeds as learning results

[0875] Step 4:

[0876] The server analyzes the information and reactions entered by the user using an emotion engine.

[0877] The server analyzes text comments and survey responses in real time, calculates emotion scores using natural language processing (NLP) techniques, and analyzes user facial expression images using OpenCV and deep learning models.

[0878] Input: User's text comments and facial expression images

[0879] Output: Sentiment score from the sentiment engine

[0880] Step 5:

[0881] The server updates the matching algorithm based on the analysis results of the emotion engine.

[0882] The server calculates a score for each combination of engineer and project, and prioritizes combinations with high emotional scores by adding them to the recommendation list.

[0883] Input: Sentiment score and case information / skill information

[0884] Output: Recommendation list

[0885] Step 6:

[0886] If the server determines that the match is high, it sends a recommendation to the ordering party and the supplier.

[0887] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[0888] The server checks both "likes" and makes the match.

[0889] Input: Recommendation list and user "likes"

[0890] Output: Matching successful notification

[0891] Step 7:

[0892] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[0893] Users can accept the suggestions and revise their skill sheets and job information to improve matching accuracy in future matches.

[0894] Inputs: Past matching history and market trends

[0895] Output: Proposal to correct information

[0896] (Application example 2)

[0897] 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."

[0898] Existing ordering systems struggle to efficiently collect information on the ordering source and the ordering recipient, and perform appropriate matching. Furthermore, they lack recommendation functions that take user sentiment into account, making it difficult to improve the user experience. Furthermore, they lack navigation and real-time information provision to optimize the in-store shopping experience.

[0899] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0900] In this invention, the server includes means for collecting project information of ordering parties and skill information of suppliers, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the supplier using the results learned by the artificial intelligence means, means for making recommendations to the ordering party and the supplier if the degree of match is high, means for establishing a match if approval is obtained from both parties, emotion analysis means for analyzing user emotions in real time, means for optimizing product recommendations based on the emotion analysis results, means for providing navigation within a physical store, and means for notifying limited-time sales and campaign information in real time. This enables efficient collection of information, optimal matching, and an improved user experience.

[0901] The "ordering party" is an entity that provides project information to outsource work or services.

[0902] The "client" is an entity that receives project information from the client and provides the business or service.

[0903] "Project information" is detailed information about projects and work provided by the client.

[0904] "Skill information" is information relating to the skills and experience possessed by the client.

[0905] The "database" is a data storage system for storing collected project information of the ordering party and skill information of the ordering party.

[0906] "Artificial intelligence means" refers to machine learning algorithms that learn market needs and seeds based on collected information and perform optimal matching.

[0907] The "match degree" is an index showing the degree of agreement between the order source's job information and the order recipient's skill information.

[0908] The "recommendation means" is a device or system that makes a recommendation to the ordering party and the ordering party when the degree of match is high.

[0909] The "matching means" is a device or system that establishes a match when both parties approve it.

[0910] The "emotion analysis means" is software or hardware for analyzing the user's emotions in real time.

[0911] The "product recommendation optimization means" is software or a system for recommending appropriate products to users based on the results of emotion analysis.

[0912] A "navigation means" is a device or system that guides a user to a specific product within a physical store.

[0913] "Real-time notification means" refers to software or a system that notifies users of limited-time sales and campaign information in real time.

[0914] The system for realizing this application example has the following functions.

[0915] Collecting and storing user information

[0916] Users install a smartphone application and, when they first launch it, enter their profile information, favorite product categories, past purchase history, etc. The entered information is sent from the user's device to a server and stored in a database. The database used may be, for example, MySQL or Firebase.

[0917] AI learning and matching

[0918] The server periodically passes the information stored in the database to an artificial intelligence engine (such as TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The artificial intelligence engine generates an algorithm based on the learning results to perform matching under optimal conditions. This algorithm then recommends the best products and services to users.

[0919] Emotion analysis

[0920] The server passes text data, such as when a user browses products or writes a review, to an emotion engine (such as IBM Watson or Microsoft Azure Emotion Recognition). The emotion engine analyzes the input text data and grasps the user's emotions in real time.

[0921] Product recommendation optimization

[0922] If the sentiment analysis engine determines that the user's sentiment is positive, the server will optimize the prioritization of product recommendations based on the results. Products and services that the user is particularly interested in will be displayed at the top of the recommendation list.

[0923] In-store navigation and real-time notifications

[0924] When a user uses the application in a physical store, the server provides in-store navigation functions. For example, if a user searches for a specific product in the app, the server displays a route to the location of that product. The server also provides a means to notify users of limited sales and campaign information in real time, improving the user experience.

[0925] Specific examples

[0926] For example, a user might enter the following review into the app: "This product is absolutely amazing!" The server passes this input to the emotion engine for sentiment analysis. The emotion analysis engine detects positive emotions such as "joy" and "confidence." Based on these results, the server increases the frequency of recommendations for similar or related products, and prioritizes products that match the user's interests.

[0927] Furthermore, when a user visits a physical store and searches for a product they are interested in using the app, navigation to the location of that product is displayed. At the same time, limited sale and campaign information is notified in real time, encouraging purchases.

[0928] Example prompt

[0929] An example of an input prompt for a generative AI model is:

[0930] "Review written: This product is absolutely amazing!"

[0931] Sentiment analysis results: "Happiness: 0.9, Confidence: 0.8"

[0932] Make a list of products you recommend.

[0933] This prompt can be used to input sentiment analysis results into a generative AI model to build a system that recommends appropriate products.

[0934] As described above, the embodiment of the present invention efficiently collects user information and utilizes artificial intelligence and sentiment analysis to provide optimal product recommendations and improve the user experience.

[0935] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0936] Step 1: Enter your user information

[0937] When a user installs a smartphone application and launches it for the first time, they enter their profile information, favorite product categories, past purchase history, etc. The input data is sent from the device to the server in JSON format. Based on that input, the user profile data is saved on the server and used for subsequent processing.

[0938] Step 2: Save your information

[0939] The device sends the information entered by the user to the server. The server stores the received information in a database (for example, MySQL or Firebase). Specifically, entries such as each user's profile information, preferences, and purchase history are registered in the database. The input is user information, and the output is data stored in the database.

[0940] Step 3: Learning with AI

[0941] The server periodically passes the information stored in the database to an artificial intelligence engine (e.g., TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The input is user data and project data, and the output is a trained matching model. Data processing includes preprocessing and feature engineering.

[0942] Step 4: Sentiment Analysis

[0943] The server passes the text data when a user browses products or writes a review to an emotion engine (e.g., IBM Watson or Microsoft Azure Emotion Recognition) and analyzes emotions in real time. The input is the user's text data, and the output is the emotion analysis result (e.g., joy: 0.9, confidence: 0.8). The data is calculated by the emotion recognition algorithm.

[0944] Step 5: Applying the recommendation algorithm

[0945] Based on the results of the sentiment analysis, the server uses a matching algorithm generated by an AI engine to recommend the most suitable products and services to the user. The input is the sentiment analysis results and the trained model, and the output is a recommendation list. Data calculations include calculating the matching score, filtering and ranking the product list, etc.

[0946] Step 6: User Notification

[0947] Once the server generates the recommendation list, it sends a notification to the user device. The notification contains information about the recommended products and services. The input is the recommendation list, and the output is a notification message sent to the user device. Specific actions include sending a push notification or displaying a pop-up in the app.

[0948] Step 7: In-store navigation

[0949] When a user uses the app in a physical store and searches for a specific product, the server provides in-store navigation functionality. The input is the user's search query, and the output is the product's location information and a guided route. Data calculation involves calculating the route based on the store's map data. Specific operations include displaying the route within the app.

[0950] Step 8: Real-time notifications

[0951] The server notifies users in real time about limited-time sales and campaigns in stores. The input is a database of campaign information, and the output is a notification message. Specific actions include push notifications and in-app banner displays.

[0952] The processing steps for realizing the application example and their specific operations have been described above.

[0953] 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.

[0954] 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.

[0955] 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.

[0956] [Third embodiment]

[0957] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0958] 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.

[0959] 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).

[0960] 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.

[0961] 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.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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."

[0969] The system of the present invention collects information on the ordering party and the ordering recipient, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[0970] System Overview

[0971] 1. User (Orderer, Supplier) Registration:

[0972] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[0973] The terminal sends the entered information to the server and stores it in a database.

[0974] 2. Information storage and learning:

[0975] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[0976] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[0977] 3. Match proposal and establishment:

[0978] The server compares the registered information and, if it determines that there is a high degree of match, sends a recommendation to the ordering party and the supplier.

[0979] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[0980] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[0981] 4. Feedback and Suggestions:

[0982] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[0983] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[0984] Specific examples

[0985] Specific examples of registration

[0986] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[0987] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[0988] The terminal formats this information and sends it to the server.

[0989] The server stores the received information in a database and also uses it as learning data.

[0990] Specific examples of recommendations

[0991] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[0992] The server sends recommendations and notifications to both companies and engineers.

[0993] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[0994] Specific examples of proposals

[0995] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[0996] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[0997] As described above, this invention is a system that efficiently collects information on clients and suppliers and achieves optimal matching, with the aim of eliminating the problem of multiple subcontracting structures in the IT industry. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[0998] The processing flow will be explained below.

[0999] Step 1:

[1000] Users (orderer, supplier) log in to the platform.

[1001] The terminal sends the user's authentication information to an input form.

[1002] The server checks the authentication information and verifies that the user has valid access.

[1003] Step 2:

[1004] The user inputs the job information or skill sheet information.

[1005] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[1006] The terminal sends the input data to the server.

[1007] Step 3:

[1008] The server stores the received data in a database.

[1009] The server validates the data format and performs any necessary conversions.

[1010] The server stores the job information or skill sheet information in a database.

[1011] Step 4:

[1012] The server provides the newly registered information to the AI ​​engine.

[1013] The server extracts new information from the database and passes it to the AI ​​engine.

[1014] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[1015] Step 5:

[1016] The server updates the matching algorithm based on market data and seed information.

[1017] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[1018] Step 6:

[1019] The server compares the registration data with market information and calculates the degree of match.

[1020] The server compares the engineer's skill sheet with the project information and generates a score.

[1021] The server refers to past matching history and adjusts the weight of each condition.

[1022] Step 7:

[1023] The server recommends candidates with high matching potential.

[1024] The server selects the best candidate for each engineer and job and sends a notification.

[1025] The device displays the recommendation content to the user.

[1026] Step 8:

[1027] The user reviews the recommendation and clicks "Like."

[1028] The device accepts the user's input and clicks the "Like" button.

[1029] The device sends the "like" information to the server.

[1030] Step 9:

[1031] The server detects both "likes" and makes a match.

[1032] The server checks both "likes" and notifies the match.

[1033] The server will contact you to proceed with the negotiation process.

[1034] Step 10:

[1035] The server will suggest any deficiencies or corrections.

[1036] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[1037] The server notifies the user of the proposal.

[1038] Step 11:

[1039] The user accepts the suggestions and makes the necessary corrections.

[1040] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[1041] The device sends the modifications to the server.

[1042] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[1043] Example 1

[1044] 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."

[1045] In the current market, there is an issue of inefficient matching between the projects desired by clients and the skills that contractors can provide. As a result, clients spend a great deal of time and effort finding suitable candidates, and contractors miss out on opportunities to find projects that will allow them to make the most of their skills. Furthermore, the current matching system lacks the functionality to provide appropriate feedback to clients and contractors regarding insufficient information or corrections, which also creates the issue of not making optimal proposals.

[1046] 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.

[1047] In this invention, the server includes: means for collecting project information from client computers and skill information from contractors; means for saving the collected information in a database; artificial intelligence means for learning market needs and seeds based on the saved information; means for calculating the degree of match between client computers and contractors using the results learned by the artificial intelligence means; means for making recommendations to client computers and contractors when the degree of match is high; means for establishing a match when the client computer and contractor computer that have received the recommendation approve the match; and means for displaying a generative AI model and proposal text for generating proposals based on the client computer and contractor computer information. This significantly improves the efficiency of matching between client computers and contractors, and by providing appropriate feedback on insufficient information and corrections, it becomes possible to match under optimal conditions.

[1048] "Client" is the party providing project information and seeking specific skills or services.

[1049] A "contractor" is a person who provides skill information and is willing to accept a specific project.

[1050] "Project information" refers to detailed information provided by the client, such as the job content, conditions, and required skills.

[1051] "Skill information" refers to detailed information such as skills, experience, and qualifications provided by the contractor.

[1052] A "database" is a system for systematically storing and managing collected information.

[1053] "Artificial intelligence means" refers to means that use technologies such as machine learning and deep learning to learn market needs and seeds and generate and improve matching algorithms.

[1054] The "match degree" is an index showing the degree of match between the project information of the client and the skill information of the contractor.

[1055] A "recommendation" is a notification or proposal made to the client and the contractor when the match is high.

[1056] "Approval" refers to the client and contractor who receive the recommendation expressing their intention to each other by using a "Like" button or similar.

[1057] A "generative AI model" is an artificial intelligence model that generates proposals based on information from the client and the contractor.

[1058] A "suggestion" is a document of improvements or suggestions that is automatically generated by a generative AI model and displayed to the user.

[1059] The system of the present invention collects information on purchasers and sellers, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[1060] User registration and information collection

[1061] Users enter information about jobs and skills through a dedicated web screen, which is built using web technologies such as HTML and JavaScript.

[1062] The terminal formats the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, with SSL / TLS encryption used for security during the transmission process.

[1063] The server parses the received JSON data and stores it in a database, using an RDBMS such as MySQL or PostgreSQL.

[1064] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[1065] Information storage and learning

[1066] The server periodically queries the information stored in the database, a process that can be automated using a scheduling tool such as a Cron job.

[1067] Example: SELECT FROM user_data

[1068] The server inputs the acquired data into a machine learning model for learning, using machine learning frameworks such as TensorFlow and PyTorch.

[1069] Example: model.fit(training_data, labels)

[1070] The server updates the matching algorithm based on the new learning results, thereby reflecting the latest matching conditions adapted to market needs and seeds.

[1071] Matching proposal and establishment

[1072] The server compares the company's project information stored in the database with the engineer's skill information and calculates the degree of match, using parameters such as skill match, years of experience, and match rate.

[1073] If the match rate is above a certain value (e.g., 80% or higher), the server sends a recommendation notification to the client and the recipient. The device displays this notification to the user. Notifications are sent via email, in-app notifications, etc.

[1074] The user checks the recommendation notification and clicks the "Like" button if they are interested. The server checks the user's "Like" and if both parties send "Likes", a match is made. After this, contact is made to proceed with the business negotiation process.

[1075] Feedback and Suggestions

[1076] The server analyzes the information of the client or contractor and identifies shortcomings and areas for correction based on past matching history and market trends.

[1077] Example: In response to an engineer's skill sheet, the analysis result may be "little experience in security-related fields."

[1078] The server uses a generative AI model to generate suggested sentences based on the analysis results and notifies the user.

[1079] For example: "Adding security-related experience may improve your match."

[1080] The user accepts the suggestion and corrects and updates the information on the skill sheet, etc. The terminal then transmits the user's updated information to the server again, updating the database.

[1081] Examples of prompt statements

[1082] 1. "Show me whether adding security-related experience to an engineer's skill sheet would improve their match."

[1083] 2. "Calculate the match between the company's job information and the engineer's skill sheet, and send a recommendation if the match is 80% or higher."

[1084] Through the above specific implementation, the system can efficiently collect information on clients and contractors and achieve optimal matching, thereby eliminating the problem of multiple subcontracting structures in the IT industry and bringing benefits to both companies and engineers.

[1085] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1086] Processing Steps

[1087] Step 1: Enter your information

[1088] Users access a dedicated web screen and enter project information and skill information.

[1089] Input: Project information (e.g., project name, required skills, budget, etc.) and skill information (e.g., skill name, years of experience, desired conditions, etc.) entered by the user.

[1090] Output: Temporary data of the information entered by the user.

[1091] Specific operation: The user enters the required information into a dedicated web screen, confirms it, and then clicks the submit button.

[1092] Step 2: Submit your information

[1093] The terminal formats the input information into JSON format and sends it to the server using the HTTPS protocol.

[1094] Input: JSON format job and skill information held as temporary data.

[1095] Output: The JSON data sent to the server.

[1096] Specific operation: When the user clicks the send button, the terminal converts the entered information into JSON format and sends it to the server via the network.

[1097] Step 3: Receiving and storing information

[1098] The server parses the received JSON data and stores it in a database.

[1099] Input: The JSON data sent to the server.

[1100] Output: Opportunity and skill information stored in a database.

[1101] Specific operation: The server parses the received JSON data, extracts the necessary fields, and generates and executes SQL queries to save them to the database.

[1102] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[1103] Step 4: Gather information

[1104] The server periodically retrieves information stored in the database using queries, using a scheduling tool.

[1105] Input: Opportunity and skill information in the database.

[1106] Output: A dataset to input into a machine learning model.

[1107] Specific operation: The server retrieves the latest information from the database based on a regular schedule, for example once a day.

[1108] Example: SELECT FROM user_data

[1109] Step 5: Run machine learning

[1110] The server inputs the acquired data into a machine learning model (such as TensorFlow or PyTorch) and performs learning.

[1111] Input: A dataset retrieved from a database.

[1112] Output: An updated machine learning model.

[1113] Specific operation: Performs data preprocessing (e.g., imputing missing values ​​and normalizing data) and trains a model using the preprocessed data.

[1114] Example: model.fit(training_data, labels)

[1115] Step 6: Update the algorithm

[1116] The server updates the matching algorithm based on the new learning results.

[1117] Input: Updated machine learning model parameters.

[1118] Output: The updated matching algorithm.

[1119] Specific operation: Based on the learning results, the parameters of the current matching algorithm are updated so that matching can be performed under the new conditions.

[1120] Step 7: Matching Proposals

[1121] The server compares the company's project information with the engineer's skill information and calculates the degree of match.

[1122] Input: Updated matching algorithm, and job and skill information from the database.

[1123] Output: A list of recommendations with high match scores.

[1124] Specific operation: Generates recommendations based on the calculated match using skill match, years of experience, match rate, etc.

[1125] Step 8: Sending recommendations

[1126] If the degree of match is high, the server transmits a recommendation notification to the orderer and the order recipient.

[1127] Input: A list of recommendations with high match scores.

[1128] Output: Recommendation notification.

[1129] Specific behavior: Notifications will be sent via email, in-app notifications, etc., and will include detailed job and skill information.

[1130] Step 9: Confirm the "Like" and make a match

[1131] The user checks the recommendation notification and clicks the "Like" button if they are interested.

[1132] Input: Recommendation notification.

[1133] Output: Like button click information.

[1134] Specific operation: When a user receives a recommendation notification, they check the details and click the "Like" button if they are interested. The server receives and records the click information.

[1135] Step 10: Notification of successful match

[1136] The server will establish a match if both parties send a "like."

[1137] Input: "Like" information from both parties.

[1138] Output: Matching notification.

[1139] Specific operation: When both parties' "likes" are confirmed, the server automatically executes a process to establish a match (e.g., notifying the start of a sales process).

[1140] (Application example 1)

[1141] 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."

[1142] With conventional technology, the process of matching robots with work tasks in a factory was time-consuming and laborious, making it difficult to achieve optimal efficiency. Furthermore, managing robot skill information and the required skill information for work tasks was cumbersome, and there was a lack of effective tools for appropriate matching. This often led to a decline in overall factory work efficiency and productivity, resulting in increased costs.

[1143] 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.

[1144] In this invention, the server includes a means for collecting project information from the ordering party and skill information from the ordering party, a means for storing each piece of information in a database, and an artificial intelligence means for learning market needs and seeds based on the stored information. This makes it possible to collect information on robots and work tasks within a factory and store it in a database. In addition, the artificial intelligence means can be used to calculate optimal matches between robots and work tasks, and the results can be notified to the factory management system, making it possible to significantly improve work efficiency and productivity within the factory.

[1145] A "client" is a company or individual that requests work or a project for a product or service.

[1146] "Client" refers to a company or individual that carries out work or projects ordered by the client.

[1147] "Project information" refers to information such as the specific work content, conditions, and schedule requested by the client.

[1148] "Skill information" is information about the technology, experience, and abilities of the client.

[1149] A "database" is a system that organizes and stores collected information and allows it to be retrieved as needed.

[1150] "Artificial intelligence" is a technology that learns patterns based on data and performs optimal matching and recommendations.

[1151] "Matching" is the process of comparing the client's project information with the client's skill information and proposing the optimal combination.

[1152] "Market needs" refers to information about market demand and customer expectations.

[1153] "Seeds" refers to information about market supply and available services and products.

[1154] A "robot" is a mechanical device that automatically performs specific tasks in a factory.

[1155] A "work task" is the specific work that a robot performs in a factory.

[1156] A "management system" is a system for centrally managing and monitoring work within a factory and the operation of robots.

[1157] "Recommendation" refers to a proposal made to the client and the supplier when the degree of match is high.

[1158] This invention describes a system for achieving optimal matching between robots and work tasks in a factory. This system collects information on the ordering party and the ordering recipient, and provides effective matching using artificial intelligence that learns market needs and seeds based on the information stored in a database.

[1159] System Overview

[1160] Program Generation

[1161] The system includes a program that performs the following processes: The program retrieves information about the robot and the work task from a database, and uses a machine learning algorithm to determine the optimal pair.

[1162] Hardware and software used

[1163] Hardware: RFID-tagged robots, sensors installed at the work site, and servers

[1164] Software: SQLite (database), Scikit-learn (machine learning library), Python (integrated environment)

[1165] Natural language explanation of the process

[1166] The server collects information about robots and work tasks within the factory via RFID tags and sensors and stores it in an SQLite database. It then extracts robot skill information and the required skill information for each work task from the database and formats it into a matrix. It then uses Scikit-learn's KMeans clustering to perform clustering to match the robot best suited to the task. The final matching results are stored in the database and notified to the factory's management system.

[1167] Specific examples

[1168] For example, suppose there are five robots (A, B, C, D, E) and five tasks in a factory. Robot A is good at welding and robot B is good at painting. Task 1 requires welding and task 2 requires painting. The system will optimize by assigning task 1 to robot A and task 2 to robot B.

[1169] Prompt Sentence Examples

[1170] To implement the invention, generate a prompt like this:

[1171] "Please develop a system that optimally matches factory robots with tasks. This will be achieved using a machine learning algorithm based on the robot's skill information and the required skill information for the task. The software used will be Python and Scikit-learn, and the database will be SQLite. Please also provide specific code examples."

[1172] The above is a detailed description of an embodiment of the present invention. By using this system, it is possible to significantly improve work efficiency and productivity within a factory.

[1173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1174] Step 1:

[1175] The user (factory manager) uses a dedicated interface to input information about the robots deployed in the factory and the work tasks to be performed. This information includes robot skill information (e.g., welding, painting, etc.) and required skill information for the work task (e.g., whether the task requires welding or painting). The input information is sent from the terminal to the server.

[1176] Step 2:

[1177] The server receives the robot's skill information and the required skill information for the work task from the terminal and stores it in an SQLite database. The database stores each robot's capabilities and task requirements in an organized format and manages them centrally.

[1178] Step 3:

[1179] The server periodically retrieves information about the robot and the work task from the database, executes database queries to extract the robot's skill information and the required skill information for the work task, and converts it into a matrix-formatted dataset for subsequent machine learning processing.

[1180] Step 4:

[1181] The server uses Scikit-learn's KMeans clustering algorithm to perform clustering based on robot skill information and the required skill information for the work task. This clustering process selects the robot best suited to each work task. Specifically, robot skill information is provided as input to the clustering algorithm, which derives the robot group that best meets the task requirements.

[1182] Step 5:

[1183] Based on the clustering results, the server generates matching results for the optimal robot for each work task. These matching results are saved back in the database and notified to the factory management system. This automatically updates the work plan within the factory, enabling efficient work execution.

[1184] Step 6:

[1185] Based on the matching results, the server sends specific work instructions to the robots, allowing them to start the appropriate work in the appropriate location. For example, robot A, which is good at welding, performs welding task 1, and robot B, which is good at painting, performs painting task 2.

[1186] Step 7:

[1187] The server receives feedback from each robot to monitor and evaluate the progress of the work in real time. The feedback includes data on the progress of the work and any unforeseen issues. This allows the system to keep up to date with the situation and adjust work schedules and instructions as needed.

[1188] Step 8:

[1189] The user (factory manager) can grasp the overall progress of work through reports provided by the server and make strategic decisions regarding factory operations as needed. The reports include evaluation of matching results, analysis of work efficiency, and proposals for future task allocation.

[1190] 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.

[1191] The system of the present invention collects information on ordering parties and customers, and uses artificial intelligence to learn market needs and seeds, thereby achieving optimal matching. Furthermore, the present invention combines an emotion engine that recognizes user emotions, enabling more appropriate recommendations. A specific embodiment of the system is shown below.

[1192] System Overview

[1193] 1. User (Orderer, Supplier) Registration:

[1194] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[1195] The terminal sends the entered information to the server and stores it in a database.

[1196] 2. Information storage and learning:

[1197] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[1198] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[1199] 3. Emotion Engine Analysis:

[1200] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user.

[1201] The emotion engine analyzes the user's facial expressions and text input to identify positive and negative emotional trends.

[1202] 4. Match proposal and establishment:

[1203] The server takes into account the analysis results of the emotion engine, compares the registered information, and if it determines that there is a high degree of match, it sends a recommendation to the ordering party and the supplier.

[1204] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[1205] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[1206] 5. Feedback and Suggestions:

[1207] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[1208] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[1209] Specific examples

[1210] Specific examples of registration

[1211] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[1212] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[1213] The terminal formats this information and sends it to the server.

[1214] The server stores the received information in a database and also uses it as learning data.

[1215] Specific examples of recommendations

[1216] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[1217] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[1218] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[1219] The server sends recommendations and notifications to both companies and engineers.

[1220] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[1221] Specific examples of proposals

[1222] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[1223] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[1224] As described above, the present invention is a system that efficiently collects information on clients and customers, and utilizes an emotion engine to achieve optimal matching while taking user emotions into consideration. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[1225] The processing flow will be explained below.

[1226] Step 1:

[1227] Users (orderer, supplier) log in to the platform.

[1228] The terminal sends the user's authentication information to an input form.

[1229] The server checks the authentication information and verifies that the user has valid access.

[1230] Step 2:

[1231] The user inputs the job information or skill sheet information.

[1232] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[1233] The terminal sends the input data to the server.

[1234] Step 3:

[1235] The server stores the received data in a database.

[1236] The server validates the data format and performs any necessary conversions.

[1237] The server stores the job information or skill sheet information in a database.

[1238] Step 4:

[1239] The server provides the newly registered information to the AI ​​engine.

[1240] The server extracts new information from the database and passes it to the AI ​​engine.

[1241] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[1242] Step 5:

[1243] The server updates the matching algorithm based on market data and seed information.

[1244] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[1245] Step 6:

[1246] The server compares the registration data with market information and calculates the degree of match.

[1247] The server compares the engineer's skill sheet with the project information and generates a score.

[1248] The server refers to past matching history and adjusts the weight of each condition.

[1249] Step 7:

[1250] The server recommends candidates with high matching potential.

[1251] The server selects the best candidate for each engineer and job and sends a notification.

[1252] The device displays the recommendation content to the user.

[1253] Step 8:

[1254] The user reviews the recommendation and clicks "Like."

[1255] The device accepts the user's input and clicks the "Like" button.

[1256] The device sends the "like" information to the server.

[1257] Step 9:

[1258] The server detects both "likes" and makes a match.

[1259] The server checks both "likes" and notifies the match.

[1260] The server will contact you to proceed with the negotiation process.

[1261] Step 10:

[1262] The server will suggest any deficiencies or corrections.

[1263] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[1264] The server notifies the user of the proposal.

[1265] Step 11:

[1266] The user accepts the suggestions and makes the necessary corrections.

[1267] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[1268] The device sends the modifications to the server.

[1269] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[1270] Step 12:

[1271] Sentiment analysis is performed based on user input and reaction data.

[1272] The terminal collects the user's input information and sends it to the server.

[1273] The server uses an emotion engine to analyze the user's emotion (e.g., positive, negative, neutral).

[1274] The server stores the results of the emotion analysis and reflects them in future matching algorithms.

[1275] Step 13:

[1276] Recommendations are adjusted based on the results of sentiment analysis.

[1277] The server takes into account the results of the user's emotion analysis obtained by the emotion engine and fine-tunes the recommendations.

[1278] Increase recommendation frequency or priority for projects or skill sheets that have strong positive sentiment.

[1279] If negative sentiment is found, the system will adjust the recommendations to include other candidates.

[1280] The above processing steps create a system that achieves optimal matching that takes user emotions into consideration and provides highly satisfying results for both companies and engineers.

[1281] Example 2

[1282] 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."

[1283] Current matching systems only match clients based on the skills and project information of the client and client, which limits the accuracy of matching. As a result, project success rates decline and users often do not receive satisfactory results. Furthermore, because matching does not take into account the user's emotions and reactions, it is difficult to increase user satisfaction. Therefore, there is a need for a more accurate matching system that takes into account the user's input information and emotions.

[1284] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1285] In this invention, the server includes means for collecting project information of ordering parties and skill information of ordering parties, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the ordering party using the results learned by the artificial intelligence means, means for making a recommendation to the ordering party and the ordering party if the degree of match is high, means for achieving a match if approval is obtained from both parties, means for analyzing input information and reactions of users using an emotion engine and analyzing emotional trends, and means for reflecting the analysis results of the emotion engine in a matching algorithm. This enables highly accurate matching that takes user emotions into consideration.

[1286] "Client's project information" refers to detailed information about a particular project or task provided by a client.

[1287] "Skill information of the client" is information about the skills, experience, and abilities provided by the party undertaking the work.

[1288] A "database" is a system for storing collected information in a structured manner and making it accessible efficiently.

[1289] "Artificial intelligence tools" are techniques that learn patterns from data to solve specific tasks or problems.

[1290] The "means for calculating the degree of match" is a function that calculates the degree of match between the orderer's project information and the order recipient's skill information based on the two.

[1291] The "means for making recommendations" is a function that suggests suitable partners to the ordering party and the ordering recipient when the degree of match is high.

[1292] "Means for achieving matching" is a function that formally links the ordering party and the customer when both parties approve.

[1293] An "emotion engine" is a technology that analyzes a user's input information and reactions and determines their emotions.

[1294] "Means for analyzing emotional trends" is a function that analyzes positive and negative emotions based on user input and reactions.

[1295] A "matching algorithm" is a calculation method for effectively matching the ordering party and the customer based on their information.

[1296] MODE FOR CARRYING OUT THE INVENTION

[1297] The present invention is a system that efficiently collects information on suppliers and recipients and utilizes an emotion engine to achieve optimal matching that takes user emotions into consideration. Below, we will explain how this system is implemented in concrete terms.

[1298] Registering Users

[1299] Users (clients and recipients) enter project information and skill information through a dedicated web screen. For example, an engineer might enter detailed information such as "five years of Python experience, ability to use the Django framework, desired monthly rate of 500,000 yen." The terminal formats the information entered and sends it to the server. This transmission is done in JSON format and sent to the server's REST API.

[1300] Information storage and learning

[1301] The server stores the received information in a database. The server then triggers scheduled jobs to retrieve new job and skill information from the database. This data is analyzed by machine learning algorithms, which use artificial intelligence technologies such as TensorFlow and Scikit-learn to learn market needs and seeds.

[1302] Emotion Engine Analysis

[1303] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user. For example, it analyzes text comments and survey responses in real time and calculates an emotion score using natural language processing (NLP) technology. It also analyzes the user's facial expression images using OpenCV and deep learning models.

[1304] Matching proposal and establishment

[1305] The server updates the matching algorithm based on the analysis results of the emotion engine. If the match is strong, a recommendation is sent to the client and the client. For example, if an engineer has a positive reaction to a "Python" project, that project will be recommended as a priority. The user is notified, checks the recommended partner, and sends a "Like." The server then confirms both "Likes" and establishes a match.

[1306] Feedback and Suggestions

[1307] If there are any deficiencies or corrections in the client or supplier information, the server will make suggestions based on past matching history and market trends. For example, it may suggest that adding security-related experience would improve the match. The user can accept the suggestions and revise their skill sheet and project information to improve the accuracy of future matches.

[1308] Specific examples

[1309] Specific examples of registration

[1310] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[1311] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[1312] The terminal formats this information and sends it to the server.

[1313] The server stores the received information in a database and also uses it as learning data.

[1314] Specific examples of recommendations

[1315] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[1316] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[1317] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[1318] The server sends recommendations and notifications to both companies and engineers.

[1319] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[1320] Specific examples of proposals

[1321] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[1322] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[1323] This provides a system that efficiently collects information on the ordering party and the ordering party, utilizes an emotion engine to take into account the user's emotions, and achieves optimal matching.

[1324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1325] Processing step flow

[1326] Step 1:

[1327] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[1328] Input example: An engineer enters detailed information such as "5 years of Python experience, can handle the Django framework, desired monthly rate is 500,000 yen."

[1329] The terminal formats the input information, converts it into JSON format, and sends it to the server.

[1330] Step 2:

[1331] The server parses the received JSON data and stores it in a database using SQL queries.

[1332] The server verifies and stores the data stored in the database.

[1333] Input: JSON data sent from the terminal

[1334] Output: Case information and skill information stored in the database

[1335] Step 3:

[1336] The server triggers a scheduled job to retrieve new job information and skill information from the database.

[1337] The server runs machine learning models using TensorFlow and Scikit-learn to learn market needs and seeds.

[1338] Input: Project information and skill information obtained from the database

[1339] Output: Market needs and seeds as learning results

[1340] Step 4:

[1341] The server analyzes the information and reactions entered by the user using an emotion engine.

[1342] The server analyzes text comments and survey responses in real time, calculates emotion scores using natural language processing (NLP) techniques, and analyzes user facial expression images using OpenCV and deep learning models.

[1343] Input: User's text comments and facial expression images

[1344] Output: Sentiment score from the sentiment engine

[1345] Step 5:

[1346] The server updates the matching algorithm based on the analysis results of the emotion engine.

[1347] The server calculates a score for each combination of engineer and project, and prioritizes combinations with high emotional scores by adding them to the recommendation list.

[1348] Input: Sentiment score and case information / skill information

[1349] Output: Recommendation list

[1350] Step 6:

[1351] If the server determines that the match is high, it sends a recommendation to the ordering party and the supplier.

[1352] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[1353] The server checks both "likes" and makes the match.

[1354] Input: Recommendation list and user "likes"

[1355] Output: Matching successful notification

[1356] Step 7:

[1357] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[1358] Users can accept the suggestions and revise their skill sheets and job information to improve matching accuracy in future matches.

[1359] Inputs: Past matching history and market trends

[1360] Output: Proposal to correct information

[1361] (Application example 2)

[1362] 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."

[1363] Existing ordering systems struggle to efficiently collect information on the ordering source and the ordering recipient, and perform appropriate matching. Furthermore, they lack recommendation functions that take user sentiment into account, making it difficult to improve the user experience. Furthermore, they lack navigation and real-time information provision to optimize the in-store shopping experience.

[1364] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1365] In this invention, the server includes means for collecting project information of ordering parties and skill information of suppliers, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the supplier using the results learned by the artificial intelligence means, means for making recommendations to the ordering party and the supplier if the degree of match is high, means for establishing a match if approval is obtained from both parties, emotion analysis means for analyzing user emotions in real time, means for optimizing product recommendations based on the emotion analysis results, means for providing navigation within a physical store, and means for notifying limited-time sales and campaign information in real time. This enables efficient collection of information, optimal matching, and an improved user experience.

[1366] The "ordering party" is an entity that provides project information to outsource work or services.

[1367] The "client" is an entity that receives project information from the client and provides the business or service.

[1368] "Project information" is detailed information about projects and work provided by the client.

[1369] "Skill information" is information relating to the skills and experience possessed by the client.

[1370] The "database" is a data storage system for storing collected project information of the ordering party and skill information of the ordering party.

[1371] "Artificial intelligence means" refers to machine learning algorithms that learn market needs and seeds based on collected information and perform optimal matching.

[1372] The "match degree" is an index showing the degree of agreement between the order source's job information and the order recipient's skill information.

[1373] The "recommendation means" is a device or system that makes a recommendation to the ordering party and the ordering party when the degree of match is high.

[1374] The "matching means" is a device or system that establishes a match when both parties approve it.

[1375] The "emotion analysis means" is software or hardware for analyzing the user's emotions in real time.

[1376] The "product recommendation optimization means" is software or a system for recommending appropriate products to users based on the results of emotion analysis.

[1377] A "navigation means" is a device or system that guides a user to a specific product within a physical store.

[1378] "Real-time notification means" refers to software or a system that notifies users of limited-time sales and campaign information in real time.

[1379] The system for realizing this application example has the following functions.

[1380] Collecting and storing user information

[1381] Users install a smartphone application and, when they first launch it, enter their profile information, favorite product categories, past purchase history, etc. The entered information is sent from the user's device to a server and stored in a database. The database used may be, for example, MySQL or Firebase.

[1382] AI learning and matching

[1383] The server periodically passes the information stored in the database to an artificial intelligence engine (such as TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The artificial intelligence engine generates an algorithm based on the learning results to perform matching under optimal conditions. This algorithm then recommends the best products and services to users.

[1384] Emotion analysis

[1385] The server passes text data, such as when a user browses products or writes a review, to an emotion engine (such as IBM Watson or Microsoft Azure Emotion Recognition). The emotion engine analyzes the input text data and grasps the user's emotions in real time.

[1386] Product recommendation optimization

[1387] If the sentiment analysis engine determines that the user's sentiment is positive, the server will optimize the prioritization of product recommendations based on the results. Products and services that the user is particularly interested in will be displayed at the top of the recommendation list.

[1388] In-store navigation and real-time notifications

[1389] When a user uses the application in a physical store, the server provides in-store navigation functions. For example, if a user searches for a specific product in the app, the server displays a route to the location of that product. The server also provides a means to notify users of limited sales and campaign information in real time, improving the user experience.

[1390] Specific examples

[1391] For example, a user might enter the following review into the app: "This product is absolutely amazing!" The server passes this input to the emotion engine for sentiment analysis. The emotion analysis engine detects positive emotions such as "joy" and "confidence." Based on these results, the server increases the frequency of recommendations for similar or related products, and prioritizes products that match the user's interests.

[1392] Furthermore, when a user visits a physical store and searches for a product they are interested in using the app, navigation to the location of that product is displayed. At the same time, limited sale and campaign information is notified in real time, encouraging purchases.

[1393] Example prompt

[1394] An example of an input prompt for a generative AI model is:

[1395] "Review written: This product is absolutely amazing!"

[1396] Sentiment analysis results: "Happiness: 0.9, Confidence: 0.8"

[1397] Make a list of products you recommend.

[1398] This prompt can be used to input sentiment analysis results into a generative AI model to build a system that recommends appropriate products.

[1399] As described above, the embodiment of the present invention efficiently collects user information and utilizes artificial intelligence and sentiment analysis to provide optimal product recommendations and improve the user experience.

[1400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1401] Step 1: Enter your user information

[1402] When a user installs a smartphone application and launches it for the first time, they enter their profile information, favorite product categories, past purchase history, etc. The input data is sent from the device to the server in JSON format. Based on that input, the user profile data is saved on the server and used for subsequent processing.

[1403] Step 2: Save your information

[1404] The device sends the information entered by the user to the server. The server stores the received information in a database (for example, MySQL or Firebase). Specifically, entries such as each user's profile information, preferences, and purchase history are registered in the database. The input is user information, and the output is data stored in the database.

[1405] Step 3: Learning with AI

[1406] The server periodically passes the information stored in the database to an artificial intelligence engine (e.g., TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The input is user data and project data, and the output is a trained matching model. Data processing includes preprocessing and feature engineering.

[1407] Step 4: Sentiment Analysis

[1408] The server passes the text data when a user browses products or writes a review to an emotion engine (e.g., IBM Watson or Microsoft Azure Emotion Recognition) and analyzes emotions in real time. The input is the user's text data, and the output is the emotion analysis result (e.g., joy: 0.9, confidence: 0.8). The data is calculated by the emotion recognition algorithm.

[1409] Step 5: Applying the recommendation algorithm

[1410] Based on the results of the sentiment analysis, the server uses a matching algorithm generated by an AI engine to recommend the most suitable products and services to the user. The input is the sentiment analysis results and the trained model, and the output is a recommendation list. Data calculations include calculating the matching score, filtering and ranking the product list, etc.

[1411] Step 6: User Notification

[1412] Once the server generates the recommendation list, it sends a notification to the user device. The notification contains information about the recommended products and services. The input is the recommendation list, and the output is a notification message sent to the user device. Specific actions include sending a push notification or displaying a pop-up in the app.

[1413] Step 7: In-store navigation

[1414] When a user uses the app in a physical store and searches for a specific product, the server provides in-store navigation functionality. The input is the user's search query, and the output is the product's location information and a guided route. Data calculation involves calculating the route based on the store's map data. Specific operations include displaying the route within the app.

[1415] Step 8: Real-time notifications

[1416] The server notifies users in real time about limited-time sales and campaigns in stores. The input is a database of campaign information, and the output is a notification message. Specific actions include push notifications and in-app banner displays.

[1417] The processing steps for realizing the application example and their specific operations have been described above.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] [Fourth embodiment]

[1422] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1423] 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.

[1424] 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).

[1425] 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.

[1426] 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.

[1427] 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).

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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."

[1435] The system of the present invention collects information on the ordering party and the ordering recipient, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[1436] System Overview

[1437] 1. User (Orderer, Supplier) Registration:

[1438] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[1439] The terminal sends the entered information to the server and stores it in a database.

[1440] 2. Information storage and learning:

[1441] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[1442] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[1443] 3. Match proposal and establishment:

[1444] The server compares the registered information and, if it determines that there is a high degree of match, sends a recommendation to the ordering party and the supplier.

[1445] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[1446] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[1447] 4. Feedback and Suggestions:

[1448] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[1449] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[1450] Specific examples

[1451] Specific examples of registration

[1452] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[1453] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[1454] The terminal formats this information and sends it to the server.

[1455] The server stores the received information in a database and also uses it as learning data.

[1456] Specific examples of recommendations

[1457] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[1458] The server sends recommendations and notifications to both companies and engineers.

[1459] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[1460] Specific examples of proposals

[1461] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[1462] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[1463] As described above, this invention is a system that efficiently collects information on clients and suppliers and achieves optimal matching, with the aim of eliminating the problem of multiple subcontracting structures in the IT industry. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[1464] The processing flow will be explained below.

[1465] Step 1:

[1466] Users (orderer, supplier) log in to the platform.

[1467] The terminal sends the user's authentication information to an input form.

[1468] The server checks the authentication information and verifies that the user has valid access.

[1469] Step 2:

[1470] The user inputs the job information or skill sheet information.

[1471] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[1472] The terminal sends the input data to the server.

[1473] Step 3:

[1474] The server stores the received data in a database.

[1475] The server validates the data format and performs any necessary conversions.

[1476] The server stores the job information or skill sheet information in a database.

[1477] Step 4:

[1478] The server provides the newly registered information to the AI ​​engine.

[1479] The server extracts new information from the database and passes it to the AI ​​engine.

[1480] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[1481] Step 5:

[1482] The server updates the matching algorithm based on market data and seed information.

[1483] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[1484] Step 6:

[1485] The server compares the registration data with market information and calculates the degree of match.

[1486] The server compares the engineer's skill sheet with the project information and generates a score.

[1487] The server refers to past matching history and adjusts the weight of each condition.

[1488] Step 7:

[1489] The server recommends candidates with high matching potential.

[1490] The server selects the best candidate for each engineer and job and sends a notification.

[1491] The device displays the recommendation content to the user.

[1492] Step 8:

[1493] The user reviews the recommendation and clicks "Like."

[1494] The device accepts the user's input and clicks the "Like" button.

[1495] The device sends the "like" information to the server.

[1496] Step 9:

[1497] The server detects both "likes" and makes a match.

[1498] The server checks both "likes" and notifies the match.

[1499] The server will contact you to proceed with the negotiation process.

[1500] Step 10:

[1501] The server will suggest any deficiencies or corrections.

[1502] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[1503] The server notifies the user of the proposal.

[1504] Step 11:

[1505] The user accepts the suggestions and makes the necessary corrections.

[1506] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[1507] The device sends the modifications to the server.

[1508] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[1509] Example 1

[1510] 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."

[1511] In the current market, there is an issue of inefficient matching between the projects desired by clients and the skills that contractors can provide. As a result, clients spend a great deal of time and effort finding suitable candidates, and contractors miss out on opportunities to find projects that will allow them to make the most of their skills. Furthermore, the current matching system lacks the functionality to provide appropriate feedback to clients and contractors regarding insufficient information or corrections, which also creates the issue of not making optimal proposals.

[1512] 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.

[1513] In this invention, the server includes: means for collecting project information from client computers and skill information from contractors; means for saving the collected information in a database; artificial intelligence means for learning market needs and seeds based on the saved information; means for calculating the degree of match between client computers and contractors using the results learned by the artificial intelligence means; means for making recommendations to client computers and contractors when the degree of match is high; means for establishing a match when the client computer and contractor computer that have received the recommendation approve the match; and means for displaying a generative AI model and proposal text for generating proposals based on the client computer and contractor computer information. This significantly improves the efficiency of matching between client computers and contractors, and by providing appropriate feedback on insufficient information and corrections, it becomes possible to match under optimal conditions.

[1514] "Client" is the party providing project information and seeking specific skills or services.

[1515] A "contractor" is a person who provides skill information and is willing to accept a specific project.

[1516] "Project information" refers to detailed information provided by the client, such as the job content, conditions, and required skills.

[1517] "Skill information" refers to detailed information such as skills, experience, and qualifications provided by the contractor.

[1518] A "database" is a system for systematically storing and managing collected information.

[1519] "Artificial intelligence means" refers to means that use technologies such as machine learning and deep learning to learn market needs and seeds and generate and improve matching algorithms.

[1520] The "match degree" is an index showing the degree of match between the project information of the client and the skill information of the contractor.

[1521] A "recommendation" is a notification or proposal made to the client and the contractor when the match is high.

[1522] "Approval" refers to the client and contractor who receive the recommendation expressing their intention to each other by using a "Like" button or similar.

[1523] A "generative AI model" is an artificial intelligence model that generates proposals based on information from the client and the contractor.

[1524] A "suggestion" is a document of improvements or suggestions that is automatically generated by a generative AI model and displayed to the user.

[1525] The system of the present invention collects information on purchasers and sellers, and uses artificial intelligence to learn market needs and seeds based on the information stored in a database, achieving appropriate matching. A specific embodiment of the system is shown below.

[1526] User registration and information collection

[1527] Users enter information about jobs and skills through a dedicated web screen, which is built using web technologies such as HTML and JavaScript.

[1528] The terminal formats the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, with SSL / TLS encryption used for security during the transmission process.

[1529] The server parses the received JSON data and stores it in a database, using an RDBMS such as MySQL or PostgreSQL.

[1530] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[1531] Information storage and learning

[1532] The server periodically queries the information stored in the database, a process that can be automated using a scheduling tool such as a Cron job.

[1533] Example: SELECT FROM user_data

[1534] The server inputs the acquired data into a machine learning model for learning, using machine learning frameworks such as TensorFlow and PyTorch.

[1535] Example: model.fit(training_data, labels)

[1536] The server updates the matching algorithm based on the new learning results, thereby reflecting the latest matching conditions adapted to market needs and seeds.

[1537] Matching proposal and establishment

[1538] The server compares the company's project information stored in the database with the engineer's skill information and calculates the degree of match, using parameters such as skill match, years of experience, and match rate.

[1539] If the match rate is above a certain value (e.g., 80% or higher), the server sends a recommendation notification to the client and the recipient. The device displays this notification to the user. Notifications are sent via email, in-app notifications, etc.

[1540] The user checks the recommendation notification and clicks the "Like" button if they are interested. The server checks the user's "Like" and if both parties send "Likes", a match is made. After this, contact is made to proceed with the business negotiation process.

[1541] Feedback and Suggestions

[1542] The server analyzes the information of the client or contractor and identifies shortcomings and areas for correction based on past matching history and market trends.

[1543] Example: In response to an engineer's skill sheet, the analysis result may be "little experience in security-related fields."

[1544] The server uses a generative AI model to generate suggested sentences based on the analysis results and notifies the user.

[1545] For example: "Adding security-related experience may improve your match."

[1546] The user accepts the suggestion and corrects and updates the information on the skill sheet, etc. The terminal then transmits the user's updated information to the server again, updating the database.

[1547] Examples of prompt statements

[1548] 1. "Show me whether adding security-related experience to an engineer's skill sheet would improve their match."

[1549] 2. "Calculate the match between the company's job information and the engineer's skill sheet, and send a recommendation if the match is 80% or higher."

[1550] Through the above specific implementation, the system can efficiently collect information on clients and contractors and achieve optimal matching, thereby eliminating the problem of multiple subcontracting structures in the IT industry and bringing benefits to both companies and engineers.

[1551] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1552] Processing Steps

[1553] Step 1: Enter your information

[1554] Users access a dedicated web screen and enter project information and skill information.

[1555] Input: Project information (e.g., project name, required skills, budget, etc.) and skill information (e.g., skill name, years of experience, desired conditions, etc.) entered by the user.

[1556] Output: Temporary data of the information entered by the user.

[1557] Specific operation: The user enters the required information into a dedicated web screen, confirms it, and then clicks the submit button.

[1558] Step 2: Submit your information

[1559] The terminal formats the input information into JSON format and sends it to the server using the HTTPS protocol.

[1560] Input: JSON format job and skill information held as temporary data.

[1561] Output: The JSON data sent to the server.

[1562] Specific operation: When the user clicks the send button, the terminal converts the entered information into JSON format and sends it to the server via the network.

[1563] Step 3: Receiving and storing information

[1564] The server parses the received JSON data and stores it in a database.

[1565] Input: The JSON data sent to the server.

[1566] Output: Opportunity and skill information stored in a database.

[1567] Specific operation: The server parses the received JSON data, extracts the necessary fields, and generates and executes SQL queries to save them to the database.

[1568] Example: INSERT INTO user_data (name, skills, experience) VALUES ("Yamada Taro", "Python, Django", 5)

[1569] Step 4: Gather information

[1570] The server periodically retrieves information stored in the database using queries, using a scheduling tool.

[1571] Input: Opportunity and skill information in the database.

[1572] Output: A dataset to input into a machine learning model.

[1573] Specific operation: The server retrieves the latest information from the database based on a regular schedule, for example once a day.

[1574] Example: SELECT FROM user_data

[1575] Step 5: Run machine learning

[1576] The server inputs the acquired data into a machine learning model (such as TensorFlow or PyTorch) and performs learning.

[1577] Input: A dataset retrieved from a database.

[1578] Output: An updated machine learning model.

[1579] Specific operation: Performs data preprocessing (e.g., imputing missing values ​​and normalizing data) and trains a model using the preprocessed data.

[1580] Example: model.fit(training_data, labels)

[1581] Step 6: Update the algorithm

[1582] The server updates the matching algorithm based on the new learning results.

[1583] Input: Updated machine learning model parameters.

[1584] Output: The updated matching algorithm.

[1585] Specific operation: Based on the learning results, the parameters of the current matching algorithm are updated so that matching can be performed under the new conditions.

[1586] Step 7: Matching Proposals

[1587] The server compares the company's project information with the engineer's skill information and calculates the degree of match.

[1588] Input: Updated matching algorithm, and job and skill information from the database.

[1589] Output: A list of recommendations with high match scores.

[1590] Specific operation: Generates recommendations based on the calculated match using skill match, years of experience, match rate, etc.

[1591] Step 8: Sending recommendations

[1592] If the degree of match is high, the server transmits a recommendation notification to the orderer and the order recipient.

[1593] Input: A list of recommendations with high match scores.

[1594] Output: Recommendation notification.

[1595] Specific behavior: Notifications will be sent via email, in-app notifications, etc., and will include detailed job and skill information.

[1596] Step 9: Confirm the "Like" and make a match

[1597] The user checks the recommendation notification and clicks the "Like" button if they are interested.

[1598] Input: Recommendation notification.

[1599] Output: Like button click information.

[1600] Specific operation: When a user receives a recommendation notification, they check the details and click the "Like" button if they are interested. The server receives and records the click information.

[1601] Step 10: Notification of successful match

[1602] The server will establish a match if both parties send a "like."

[1603] Input: "Like" information from both parties.

[1604] Output: Matching notification.

[1605] Specific operation: When both parties' "likes" are confirmed, the server automatically executes a process to establish a match (e.g., notifying the start of a sales process).

[1606] (Application example 1)

[1607] 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."

[1608] With conventional technology, the process of matching robots with work tasks in a factory was time-consuming and laborious, making it difficult to achieve optimal efficiency. Furthermore, managing robot skill information and the required skill information for work tasks was cumbersome, and there was a lack of effective tools for appropriate matching. This often led to a decline in overall factory work efficiency and productivity, resulting in increased costs.

[1609] 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.

[1610] In this invention, the server includes a means for collecting project information from the ordering party and skill information from the ordering party, a means for storing each piece of information in a database, and an artificial intelligence means for learning market needs and seeds based on the stored information. This makes it possible to collect information on robots and work tasks within a factory and store it in a database. In addition, the artificial intelligence means can be used to calculate optimal matches between robots and work tasks, and the results can be notified to the factory management system, making it possible to significantly improve work efficiency and productivity within the factory.

[1611] A "client" is a company or individual that requests work or a project for a product or service.

[1612] "Client" refers to a company or individual that carries out work or projects ordered by the client.

[1613] "Project information" refers to information such as the specific work content, conditions, and schedule requested by the client.

[1614] "Skill information" is information about the technology, experience, and abilities of the client.

[1615] A "database" is a system that organizes and stores collected information and allows it to be retrieved as needed.

[1616] "Artificial intelligence" is a technology that learns patterns based on data and performs optimal matching and recommendations.

[1617] "Matching" is the process of comparing the client's project information with the client's skill information and proposing the optimal combination.

[1618] "Market needs" refers to information about market demand and customer expectations.

[1619] "Seeds" refers to information about market supply and available services and products.

[1620] A "robot" is a mechanical device that automatically performs specific tasks in a factory.

[1621] A "work task" is the specific work that a robot performs in a factory.

[1622] A "management system" is a system for centrally managing and monitoring work within a factory and the operation of robots.

[1623] "Recommendation" refers to a proposal made to the client and the supplier when the degree of match is high.

[1624] This invention describes a system for achieving optimal matching between robots and work tasks in a factory. This system collects information on the ordering party and the ordering recipient, and provides effective matching using artificial intelligence that learns market needs and seeds based on the information stored in a database.

[1625] System Overview

[1626] Program Generation

[1627] The system includes a program that performs the following processes: The program retrieves information about the robot and the work task from a database, and uses a machine learning algorithm to determine the optimal pair.

[1628] Hardware and software used

[1629] Hardware: RFID-tagged robots, sensors installed at the work site, and servers

[1630] Software: SQLite (database), Scikit-learn (machine learning library), Python (integrated environment)

[1631] Natural language explanation of the process

[1632] The server collects information about robots and work tasks within the factory via RFID tags and sensors and stores it in an SQLite database. It then extracts robot skill information and the required skill information for each work task from the database and formats it into a matrix. It then uses Scikit-learn's KMeans clustering to perform clustering to match the robot best suited to the task. The final matching results are stored in the database and notified to the factory's management system.

[1633] Specific examples

[1634] For example, suppose there are five robots (A, B, C, D, E) and five tasks in a factory. Robot A is good at welding and robot B is good at painting. Task 1 requires welding and task 2 requires painting. The system will optimize by assigning task 1 to robot A and task 2 to robot B.

[1635] Prompt Sentence Examples

[1636] To implement the invention, generate a prompt like this:

[1637] "Please develop a system that optimally matches factory robots with tasks. This will be achieved using a machine learning algorithm based on the robot's skill information and the required skill information for the task. The software used will be Python and Scikit-learn, and the database will be SQLite. Please also provide specific code examples."

[1638] The above is a detailed description of an embodiment of the present invention. By using this system, it is possible to significantly improve work efficiency and productivity within a factory.

[1639] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1640] Step 1:

[1641] The user (factory manager) uses a dedicated interface to input information about the robots deployed in the factory and the work tasks to be performed. This information includes robot skill information (e.g., welding, painting, etc.) and required skill information for the work task (e.g., whether the task requires welding or painting). The input information is sent from the terminal to the server.

[1642] Step 2:

[1643] The server receives the robot's skill information and the required skill information for the work task from the terminal and stores it in an SQLite database. The database stores each robot's capabilities and task requirements in an organized format and manages them centrally.

[1644] Step 3:

[1645] The server periodically retrieves information about the robot and the work task from the database, executes database queries to extract the robot's skill information and the required skill information for the work task, and converts it into a matrix-formatted dataset for subsequent machine learning processing.

[1646] Step 4:

[1647] The server uses Scikit-learn's KMeans clustering algorithm to perform clustering based on robot skill information and the required skill information for the work task. This clustering process selects the robot best suited to each work task. Specifically, robot skill information is provided as input to the clustering algorithm, which derives the robot group that best meets the task requirements.

[1648] Step 5:

[1649] Based on the clustering results, the server generates matching results for the optimal robot for each work task. These matching results are saved back in the database and notified to the factory management system. This automatically updates the work plan within the factory, enabling efficient work execution.

[1650] Step 6:

[1651] Based on the matching results, the server sends specific work instructions to the robots, allowing them to start the appropriate work in the appropriate location. For example, robot A, which is good at welding, performs welding task 1, and robot B, which is good at painting, performs painting task 2.

[1652] Step 7:

[1653] The server receives feedback from each robot to monitor and evaluate the progress of the work in real time. The feedback includes data on the progress of the work and any unforeseen issues. This allows the system to keep up to date with the situation and adjust work schedules and instructions as needed.

[1654] Step 8:

[1655] The user (factory manager) can grasp the overall progress of work through reports provided by the server and make strategic decisions regarding factory operations as needed. The reports include evaluation of matching results, analysis of work efficiency, and proposals for future task allocation.

[1656] 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.

[1657] The system of the present invention collects information on ordering parties and customers, and uses artificial intelligence to learn market needs and seeds, thereby achieving optimal matching. Furthermore, the present invention combines an emotion engine that recognizes user emotions, enabling more appropriate recommendations. A specific embodiment of the system is shown below.

[1658] System Overview

[1659] 1. User (Orderer, Supplier) Registration:

[1660] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[1661] The terminal sends the entered information to the server and stores it in a database.

[1662] 2. Information storage and learning:

[1663] The server periodically passes the information stored in the database to an artificial intelligence engine, which uses machine learning algorithms to learn about market needs and seeds.

[1664] The server updates the matching algorithm based on the learning results to achieve matching under optimal conditions.

[1665] 3. Emotion Engine Analysis:

[1666] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user.

[1667] The emotion engine analyzes the user's facial expressions and text input to identify positive and negative emotional trends.

[1668] 4. Match proposal and establishment:

[1669] The server takes into account the analysis results of the emotion engine, compares the registered information, and if it determines that there is a high degree of match, it sends a recommendation to the ordering party and the supplier.

[1670] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[1671] The server checks both "likes", completes the match, and moves on to the business negotiation process.

[1672] 5. Feedback and Suggestions:

[1673] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[1674] The user can accept the suggestions and correct the information to improve the accuracy of the match from next time onwards.

[1675] Specific examples

[1676] Specific examples of registration

[1677] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[1678] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[1679] The terminal formats this information and sends it to the server.

[1680] The server stores the received information in a database and also uses it as learning data.

[1681] Specific examples of recommendations

[1682] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[1683] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[1684] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[1685] The server sends recommendations and notifications to both companies and engineers.

[1686] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[1687] Specific examples of proposals

[1688] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[1689] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[1690] As described above, the present invention is a system that efficiently collects information on clients and customers, and utilizes an emotion engine to achieve optimal matching while taking user emotions into consideration. This makes it easier for companies to find reliable engineers with the skills they need, and allows engineers to find projects that allow them to make the most of their skills.

[1691] The processing flow will be explained below.

[1692] Step 1:

[1693] Users (orderer, supplier) log in to the platform.

[1694] The terminal sends the user's authentication information to an input form.

[1695] The server checks the authentication information and verifies that the user has valid access.

[1696] Step 2:

[1697] The user inputs the job information or skill sheet information.

[1698] The terminal displays an input form, and the user enters each item (e.g., technical skills, years of experience, desired rate, etc.).

[1699] The terminal sends the input data to the server.

[1700] Step 3:

[1701] The server stores the received data in a database.

[1702] The server validates the data format and performs any necessary conversions.

[1703] The server stores the job information or skill sheet information in a database.

[1704] Step 4:

[1705] The server provides the newly registered information to the AI ​​engine.

[1706] The server extracts new information from the database and passes it to the AI ​​engine.

[1707] The AI ​​engine learns market data (e.g., recent increase in Python projects) and new information.

[1708] Step 5:

[1709] The server updates the matching algorithm based on market data and seed information.

[1710] The server learns from the new data obtained from the AI ​​engine and builds the optimal matching model.

[1711] Step 6:

[1712] The server compares the registration data with market information and calculates the degree of match.

[1713] The server compares the engineer's skill sheet with the project information and generates a score.

[1714] The server refers to past matching history and adjusts the weight of each condition.

[1715] Step 7:

[1716] The server recommends candidates with high matching potential.

[1717] The server selects the best candidate for each engineer and job and sends a notification.

[1718] The device displays the recommendation content to the user.

[1719] Step 8:

[1720] The user reviews the recommendation and clicks "Like."

[1721] The device accepts the user's input and clicks the "Like" button.

[1722] The device sends the "like" information to the server.

[1723] Step 9:

[1724] The server detects both "likes" and makes a match.

[1725] The server checks both "likes" and notifies the match.

[1726] The server will contact you to proceed with the negotiation process.

[1727] Step 10:

[1728] The server will suggest any deficiencies or corrections.

[1729] The server analyzes past matching history and identifies areas for improvement (e.g., relaxing requirements, adding additional information, etc.).

[1730] The server notifies the user of the proposal.

[1731] Step 11:

[1732] The user accepts the suggestions and makes the necessary corrections.

[1733] The terminal displays an edit form to the user and allows the user to enter corrections based on the suggestions.

[1734] The device sends the modifications to the server.

[1735] The server saves the correction information in a database and provides it to the AI ​​engine again as learning data.

[1736] Step 12:

[1737] Sentiment analysis is performed based on user input and reaction data.

[1738] The terminal collects the user's input information and sends it to the server.

[1739] The server uses an emotion engine to analyze the user's emotion (e.g., positive, negative, neutral).

[1740] The server stores the results of the emotion analysis and reflects them in future matching algorithms.

[1741] Step 13:

[1742] Recommendations are adjusted based on the results of sentiment analysis.

[1743] The server takes into account the results of the user's emotion analysis obtained by the emotion engine and fine-tunes the recommendations.

[1744] Increase recommendation frequency or priority for projects or skill sheets that have strong positive sentiment.

[1745] If negative sentiment is found, the system will adjust the recommendations to include other candidates.

[1746] The above processing steps create a system that achieves optimal matching that takes user emotions into consideration and provides highly satisfying results for both companies and engineers.

[1747] Example 2

[1748] 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."

[1749] Current matching systems only match clients based on the skills and project information of the client and client, which limits the accuracy of matching. As a result, project success rates decline and users often do not receive satisfactory results. Furthermore, because matching does not take into account the user's emotions and reactions, it is difficult to increase user satisfaction. Therefore, there is a need for a more accurate matching system that takes into account the user's input information and emotions.

[1750] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1751] In this invention, the server includes means for collecting project information of ordering parties and skill information of ordering parties, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the ordering party using the results learned by the artificial intelligence means, means for making a recommendation to the ordering party and the ordering party if the degree of match is high, means for achieving a match if approval is obtained from both parties, means for analyzing input information and reactions of users using an emotion engine and analyzing emotional trends, and means for reflecting the analysis results of the emotion engine in a matching algorithm. This enables highly accurate matching that takes user emotions into consideration.

[1752] "Client's project information" refers to detailed information about a particular project or task provided by a client.

[1753] "Skill information of the client" is information about the skills, experience, and abilities provided by the party undertaking the work.

[1754] A "database" is a system for storing collected information in a structured manner and making it accessible efficiently.

[1755] "Artificial intelligence tools" are techniques that learn patterns from data to solve specific tasks or problems.

[1756] The "means for calculating the degree of match" is a function that calculates the degree of match between the orderer's project information and the order recipient's skill information based on the two.

[1757] The "means for making recommendations" is a function that suggests suitable partners to the ordering party and the ordering recipient when the degree of match is high.

[1758] "Means for achieving matching" is a function that formally links the ordering party and the customer when both parties approve.

[1759] An "emotion engine" is a technology that analyzes a user's input information and reactions and determines their emotions.

[1760] "Means for analyzing emotional trends" is a function that analyzes positive and negative emotions based on user input and reactions.

[1761] A "matching algorithm" is a calculation method for effectively matching the ordering party and the customer based on their information.

[1762] MODE FOR CARRYING OUT THE INVENTION

[1763] The present invention is a system that efficiently collects information on suppliers and recipients and utilizes an emotion engine to achieve optimal matching that takes user emotions into consideration. Below, we will explain how this system is implemented in concrete terms.

[1764] Registering Users

[1765] Users (clients and recipients) enter project information and skill information through a dedicated web screen. For example, an engineer might enter detailed information such as "five years of Python experience, ability to use the Django framework, desired monthly rate of 500,000 yen." The terminal formats the information entered and sends it to the server. This transmission is done in JSON format and sent to the server's REST API.

[1766] Information storage and learning

[1767] The server stores the received information in a database. The server then triggers scheduled jobs to retrieve new job and skill information from the database. This data is analyzed by machine learning algorithms, which use artificial intelligence technologies such as TensorFlow and Scikit-learn to learn market needs and seeds.

[1768] Emotion Engine Analysis

[1769] The server uses an emotion engine to analyze the user's emotions based on the information and reactions entered by the user. For example, it analyzes text comments and survey responses in real time and calculates an emotion score using natural language processing (NLP) technology. It also analyzes the user's facial expression images using OpenCV and deep learning models.

[1770] Matching proposal and establishment

[1771] The server updates the matching algorithm based on the analysis results of the emotion engine. If the match is strong, a recommendation is sent to the client and the client. For example, if an engineer has a positive reaction to a "Python" project, that project will be recommended as a priority. The user is notified, checks the recommended partner, and sends a "Like." The server then confirms both "Likes" and establishes a match.

[1772] Feedback and Suggestions

[1773] If there are any deficiencies or corrections in the client or supplier information, the server will make suggestions based on past matching history and market trends. For example, it may suggest that adding security-related experience would improve the match. The user can accept the suggestions and revise their skill sheet and project information to improve the accuracy of future matches.

[1774] Specific examples

[1775] Specific examples of registration

[1776] When registering their own skill sheet, users (engineers) enter detailed information such as the languages ​​they use and years of experience.

[1777] Example: "5 years of Python experience, can use the Django framework, desired monthly rate is 500,000 yen."

[1778] The terminal formats this information and sends it to the server.

[1779] The server stores the received information in a database and also uses it as learning data.

[1780] Specific examples of recommendations

[1781] The server compares the engineer's skill sheet with the company's project information and calculates a high match rate (e.g., 80%).

[1782] The server analyzes the user's emotions using an emotion engine, and if a positive reaction is confirmed, it makes recommendations preferentially.

[1783] Example: If an engineer responds positively to a "Python" job, recommend that job more frequently.

[1784] The server sends recommendations and notifications to both companies and engineers.

[1785] If both the company and the engineer send a "like," the server will establish a match and contact them to move forward with the negotiation process.

[1786] Specific examples of proposals

[1787] The server analyzes an engineer's skill sheet and suggests that adding security-related experience would improve the match.

[1788] The engineer (user) accepts the proposal and updates his / her skill sheet to increase the matching rate in future.

[1789] This provides a system that efficiently collects information on the ordering party and the ordering party, utilizes an emotion engine to take into account the user's emotions, and achieves optimal matching.

[1790] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1791] Processing step flow

[1792] Step 1:

[1793] Users (clients and recipients) enter project information and skill information through a dedicated web screen.

[1794] Input example: An engineer enters detailed information such as "5 years of Python experience, can handle the Django framework, desired monthly rate is 500,000 yen."

[1795] The terminal formats the input information, converts it into JSON format, and sends it to the server.

[1796] Step 2:

[1797] The server parses the received JSON data and stores it in a database using SQL queries.

[1798] The server verifies and stores the data stored in the database.

[1799] Input: JSON data sent from the terminal

[1800] Output: Case information and skill information stored in the database

[1801] Step 3:

[1802] The server triggers a scheduled job to retrieve new job information and skill information from the database.

[1803] The server runs machine learning models using TensorFlow and Scikit-learn to learn market needs and seeds.

[1804] Input: Project information and skill information obtained from the database

[1805] Output: Market needs and seeds as learning results

[1806] Step 4:

[1807] The server analyzes the information and reactions entered by the user using an emotion engine.

[1808] The server analyzes text comments and survey responses in real time, calculates emotion scores using natural language processing (NLP) techniques, and analyzes user facial expression images using OpenCV and deep learning models.

[1809] Input: User's text comments and facial expression images

[1810] Output: Sentiment score from the sentiment engine

[1811] Step 5:

[1812] The server updates the matching algorithm based on the analysis results of the emotion engine.

[1813] The server calculates a score for each combination of engineer and project, and prioritizes combinations with high emotional scores by adding them to the recommendation list.

[1814] Input: Sentiment score and case information / skill information

[1815] Output: Recommendation list

[1816] Step 6:

[1817] If the server determines that the match is high, it sends a recommendation to the ordering party and the supplier.

[1818] The user (orderer, supplier) receives a notification, checks the recommended partner, and sends a "Like" to them.

[1819] The server checks both "likes" and makes the match.

[1820] Input: Recommendation list and user "likes"

[1821] Output: Matching successful notification

[1822] Step 7:

[1823] If there are any deficiencies or corrections in the information of the ordering source or the ordering recipient, the server will make a proposal based on past matching history and market trends.

[1824] Users can accept the suggestions and revise their skill sheets and job information to improve matching accuracy in future matches.

[1825] Inputs: Past matching history and market trends

[1826] Output: Proposal to correct information

[1827] (Application example 2)

[1828] 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."

[1829] Existing ordering systems struggle to efficiently collect information on the ordering source and the ordering recipient, and perform appropriate matching. Furthermore, they lack recommendation functions that take user sentiment into account, making it difficult to improve the user experience. Furthermore, they lack navigation and real-time information provision to optimize the in-store shopping experience.

[1830] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1831] In this invention, the server includes means for collecting project information of ordering parties and skill information of suppliers, means for saving each piece of information in a database, artificial intelligence means for learning market needs and seeds based on the saved information, means for calculating the degree of match between the ordering party and the supplier using the results learned by the artificial intelligence means, means for making recommendations to the ordering party and the supplier if the degree of match is high, means for establishing a match if approval is obtained from both parties, emotion analysis means for analyzing user emotions in real time, means for optimizing product recommendations based on the emotion analysis results, means for providing navigation within a physical store, and means for notifying limited-time sales and campaign information in real time. This enables efficient collection of information, optimal matching, and an improved user experience.

[1832] The "ordering party" is an entity that provides project information to outsource work or services.

[1833] The "client" is an entity that receives project information from the client and provides the business or service.

[1834] "Project information" is detailed information about projects and work provided by the client.

[1835] "Skill information" is information relating to the skills and experience possessed by the client.

[1836] The "database" is a data storage system for storing collected project information of the ordering party and skill information of the ordering party.

[1837] "Artificial intelligence means" refers to machine learning algorithms that learn market needs and seeds based on collected information and perform optimal matching.

[1838] The "match degree" is an index showing the degree of agreement between the order source's job information and the order recipient's skill information.

[1839] The "recommendation means" is a device or system that makes a recommendation to the ordering party and the ordering party when the degree of match is high.

[1840] The "matching means" is a device or system that establishes a match when both parties approve it.

[1841] The "emotion analysis means" is software or hardware for analyzing the user's emotions in real time.

[1842] The "product recommendation optimization means" is software or a system for recommending appropriate products to users based on the results of emotion analysis.

[1843] A "navigation means" is a device or system that guides a user to a specific product within a physical store.

[1844] "Real-time notification means" refers to software or a system that notifies users of limited-time sales and campaign information in real time.

[1845] The system for realizing this application example has the following functions.

[1846] Collecting and storing user information

[1847] Users install a smartphone application and, when they first launch it, enter their profile information, favorite product categories, past purchase history, etc. The entered information is sent from the user's device to a server and stored in a database. The database used may be, for example, MySQL or Firebase.

[1848] AI learning and matching

[1849] The server periodically passes the information stored in the database to an artificial intelligence engine (such as TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The artificial intelligence engine generates an algorithm based on the learning results to perform matching under optimal conditions. This algorithm then recommends the best products and services to users.

[1850] Emotion analysis

[1851] The server passes text data, such as when a user browses products or writes a review, to an emotion engine (such as IBM Watson or Microsoft Azure Emotion Recognition). The emotion engine analyzes the input text data and grasps the user's emotions in real time.

[1852] Product recommendation optimization

[1853] If the sentiment analysis engine determines that the user's sentiment is positive, the server will optimize the prioritization of product recommendations based on the results. Products and services that the user is particularly interested in will be displayed at the top of the recommendation list.

[1854] In-store navigation and real-time notifications

[1855] When a user uses the application in a physical store, the server provides in-store navigation functions. For example, if a user searches for a specific product in the app, the server displays a route to the location of that product. The server also provides a means to notify users of limited sales and campaign information in real time, improving the user experience.

[1856] Specific examples

[1857] For example, a user might enter the following review into the app: "This product is absolutely amazing!" The server passes this input to the emotion engine for sentiment analysis. The emotion analysis engine detects positive emotions such as "joy" and "confidence." Based on these results, the server increases the frequency of recommendations for similar or related products, and prioritizes products that match the user's interests.

[1858] Furthermore, when a user visits a physical store and searches for a product they are interested in using the app, navigation to the location of that product is displayed. At the same time, limited sale and campaign information is notified in real time, encouraging purchases.

[1859] Example prompt

[1860] An example of an input prompt for a generative AI model is:

[1861] "Review written: This product is absolutely amazing!"

[1862] Sentiment analysis results: "Happiness: 0.9, Confidence: 0.8"

[1863] Make a list of products you recommend.

[1864] This prompt can be used to input sentiment analysis results into a generative AI model to build a system that recommends appropriate products.

[1865] As described above, the embodiment of the present invention efficiently collects user information and utilizes artificial intelligence and sentiment analysis to provide optimal product recommendations and improve the user experience.

[1866] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1867] Step 1: Enter your user information

[1868] When a user installs a smartphone application and launches it for the first time, they enter their profile information, favorite product categories, past purchase history, etc. The input data is sent from the device to the server in JSON format. Based on that input, the user profile data is saved on the server and used for subsequent processing.

[1869] Step 2: Save your information

[1870] The device sends the information entered by the user to the server. The server stores the received information in a database (for example, MySQL or Firebase). Specifically, entries such as each user's profile information, preferences, and purchase history are registered in the database. The input is user information, and the output is data stored in the database.

[1871] Step 3: Learning with AI

[1872] The server periodically passes the information stored in the database to an artificial intelligence engine (e.g., TensorFlow or PyTorch), which uses machine learning algorithms to learn about market needs and seeds. The input is user data and project data, and the output is a trained matching model. Data processing includes preprocessing and feature engineering.

[1873] Step 4: Sentiment Analysis

[1874] The server passes the text data when a user browses products or writes a review to an emotion engine (e.g., IBM Watson or Microsoft Azure Emotion Recognition) and analyzes emotions in real time. The input is the user's text data, and the output is the emotion analysis result (e.g., joy: 0.9, confidence: 0.8). The data is calculated by the emotion recognition algorithm.

[1875] Step 5: Applying the recommendation algorithm

[1876] Based on the results of the sentiment analysis, the server uses a matching algorithm generated by an AI engine to recommend the most suitable products and services to the user. The input is the sentiment analysis results and the trained model, and the output is a recommendation list. Data calculations include calculating the matching score, filtering and ranking the product list, etc.

[1877] Step 6: User Notification

[1878] Once the server generates the recommendation list, it sends a notification to the user device. The notification contains information about the recommended products and services. The input is the recommendation list, and the output is a notification message sent to the user device. Specific actions include sending a push notification or displaying a pop-up in the app.

[1879] Step 7: In-store navigation

[1880] When a user uses the app in a physical store and searches for a specific product, the server provides in-store navigation functionality. The input is the user's search query, and the output is the product's location information and a guided route. Data calculation involves calculating the route based on the store's map data. Specific operations include displaying the route within the app.

[1881] Step 8: Real-time notifications

[1882] The server notifies users in real time about limited-time sales and campaigns in stores. The input is a database of campaign information, and the output is a notification message. Specific actions include push notifications and in-app banner displays.

[1883] The processing steps for realizing the application example and their specific operations have been described above.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] 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.

[1888] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1889] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1890] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1891] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1892] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1893] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1894] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1895] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1896] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1897] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1898] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1899] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1900] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1901] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1902] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1903] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1904] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1905] The following is further disclosed regarding the above embodiment.

[1906] (Claim 1)

[1907] A means for collecting project information of an ordering source and skill information of an ordering party;

[1908] a means for storing each piece of information in a database;

[1909] an artificial intelligence means for learning market needs and seeds based on the stored information;

[1910] A means for calculating a match degree between an order source and an order recipient using the results learned by the artificial intelligence means;

[1911] A means for making a recommendation to the client and the customer when the degree of match is high;

[1912] A means for matching to occur if there is mutual approval;

[1913] A system including:

[1914] (Claim 2)

[1915] The system according to claim 1, wherein the artificial intelligence means learns past matching history based on the project information of the client and the skill information of the client, and generates an optimal matching algorithm.

[1916] (Claim 3)

[1917] The system according to claim 1, further comprising means for making suggestions based on past matching history when there are deficiencies or corrections in the project information of the client and the skill information of the client.

[1918] "Example 1"

[1919] (Claim 1)

[1920] A means for collecting project information of the client and skill information of the contractor;

[1921] a means for storing the collected information in a database;

[1922] artificial intelligence means for learning market needs and seeds based on the stored information;

[1923] A means for calculating a match degree between a purchaser and a contractor using the results learned by the artificial intelligence means;

[1924] A means for making a recommendation to the client and the contractor when the degree of match is high;

[1925] A means for matching to be established when the recommended client and contractor approve the match;

[1926] A generative AI model for generating a proposal based on information of the client and the contractor, and a means for displaying a proposal;

[1927] A system including:

[1928] (Claim 2)

[1929] The system according to claim 1, wherein the artificial intelligence means learns past matching history based on the client's project information and the contractor's skill information, and generates an optimal matching algorithm.

[1930] (Claim 3)

[1931] The system according to claim 1, further comprising means for making suggestions based on past matching history when there are deficiencies or corrections in the project information of the client and the skill information of the contractor.

[1932] "Application Example 1"

[1933] (Claim 1)

[1934] A means for collecting project information of an ordering source and skill information of an ordering party;

[1935] a means for storing each piece of information in a database;

[1936] an artificial intelligence means for learning market needs and seeds based on the stored information;

[1937] A means for calculating a match degree between an order source and an order recipient using the results learned by the artificial intelligence means;

[1938] A means for making a recommendation to the client and the customer when the degree of match is high;

[1939] A means for matching to occur if there is mutual approval;

[1940] A means for collecting information about robots and work tasks in the factory;

[1941] A means for storing the skill information of the robot and the required skill information of the work task in a database;

[1942] means for calculating an optimal match between a robot and a work task using artificial intelligence means;

[1943] A means for notifying the results to the factory management system;

[1944] A system including:

[1945] (Claim 2)

[1946] The system according to claim 1, wherein the artificial intelligence means learns past matching history based on the project information of the client and the skill information of the client, and generates an optimal matching algorithm.

[1947] (Claim 3)

[1948] The system according to claim 1, further comprising means for making suggestions based on past matching history when there are deficiencies or corrections in the project information of the client and the skill information of the client.

[1949] "Example 2: Combining Emotion Engines"

[1950] (Claim 1)

[1951] A means for collecting project information of an ordering source and skill information of an ordering party;

[1952] a means for storing each piece of information in a database;

[1953] an artificial intelligence means for learning market needs and seeds based on the stored information;

[1954] A means for calculating a match degree between an order source and an order recipient using the results learned by the artificial intelligence means;

[1955] A means for making a recommendation to the client and the customer when the degree of match is high;

[1956] A means for matching to occur if there is mutual approval;

[1957] A means for analyzing user input information and reactions using an emotion engine to analyze emotional trends;

[1958] A means for reflecting the analysis results of the emotion engine in the matching algorithm;

[1959] A system including:

[1960] (Claim 2)

[1961] The system according to claim 1, wherein the artificial intelligence means learns past matching history based on the project information of the client and the skill information of the client, and generates an optimal matching algorithm.

[1962] (Claim 3)

[1963] The system according to claim 1, further comprising means for making suggestions based on past matching history when there are deficiencies or corrections in the project information of the client and the skill information of the client.

[1964] "Application example 2 when combining emotion engines"

[1965] (Claim 1)

[1966] A means for collecting project information of an ordering source and skill information of an ordering party;

[1967] a means for storing each piece of information in a database;

[1968] an artificial intelligence means for learning market needs and seeds based on the stored information;

[1969] A means for calculating a match degree between an order source and an order recipient using the results learned by the artificial intelligence means;

[1970] A means for making a recommendation to the client and the customer when the degree of match is high;

[1971] A means for matching to occur if there is mutual approval;

[1972] emotion analysis means for analyzing user emotions in real time;

[1973] A means for optimizing product recommendations based on the sentiment analysis results;

[1974] A means of providing navigation within a physical store;

[1975] A means to notify limited sales and campaign information in real time,

[1976] A system including:

[1977] (Claim 2)

[1978] The system according to claim 1, wherein the artificial intelligence means learns past matching history based on the project information of the client and the skill information of the client, and generates an optimal matching algorithm.

[1979] (Claim 3)

[1980] The system according to claim 1, further comprising means for making suggestions based on past matching history when there are deficiencies or corrections in the project information of the client and the skill information of the client. [Explanation of symbols]

[1981] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting project information of an ordering source and skill information of an ordering party; a means for storing each piece of information in a database; an artificial intelligence means for learning market needs and seeds based on the stored information; A means for calculating a match degree between an order source and an order recipient using the results learned by the artificial intelligence means; A means for making a recommendation to the client and the customer when the degree of match is high; A means for matching to occur if there is mutual approval; A system including:

2. 2. The system according to claim 1, wherein the artificial intelligence means learns past matching history based on the project information of the client and the skill information of the client, and generates an optimal matching algorithm.

3. 2. The system according to claim 1, further comprising means for making a proposal based on past matching history when there are deficiencies or corrections in the project information of the ordering party and the skill information of the ordering party.

Images