system

Abstract

Provide a system. 【Solution means】 A platform for promoting collaboration among users with different specialized fields, Means for receiving information regarding project proposals from users, Means for selecting experts with relevant specialized fields from a database based on the project proposals, Means for using artificial intelligence to match the selected experts, Means for presenting the matching results to users, Means for providing a multilingual collaborative work environment where multiple users can cooperate in real time, Means for enabling efficient matching of experts in urban function improvement projects, Means for users to track the progress of urban development and easily manage shared items, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, when experts with different specialized fields work together, there are problems such as communication gaps caused by differences in specialized terms and knowledge, difficulties in communication in a multilingual environment, and a lack of a mechanism for quickly matching appropriate experts. Furthermore, these problems are particularly prominent in global projects and interdisciplinary research, hindering efficient knowledge integration and project progress. To address such problems, it is required to enable smooth collaboration among experts in different fields and promote the creation of new knowledge towards the realization of a sustainable society.

Means for Solving the Problems

[0005] This invention provides a platform to facilitate collaboration among users with different areas of expertise. It receives project proposals from users and selects experts with relevant expertise from a database based on those proposals. Furthermore, artificial intelligence is used to match the selected experts, analyzing each expert's profile using natural language processing and machine learning algorithms. This allows the platform to present users with the most suitable matching results and provides a multilingual collaborative work environment where multiple users can work together in real time. This eliminates communication gaps between different fields and enables effective project management.

[0006] "Different fields of expertise" refers to multiple areas or disciplines that possess different academic or practical knowledge.

[0007] "Collaboration" refers to the joint efforts of multiple experts or organizations to achieve a common goal.

[0008] A "platform" refers to a foundational system or environment provided to carry out a particular service or activity.

[0009] "User" refers to anyone who uses the system, especially professionals who propose projects or participate in collaborative work.

[0010] A "project proposal" refers to the act of presenting a plan or idea for achieving a specific objective in written or digital format.

[0011] The term "expert" refers to an individual who possesses advanced knowledge and experience in a particular field or area.

[0012] A "database" refers to a system for efficiently storing, searching, and managing structured information and data.

[0013] "Artificial intelligence" refers to technology in which machines and computer systems imitate human intellectual behavior.

[0014] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[0015] A "machine learning algorithm" refers to a computer program that learns patterns from large amounts of data and performs predictions and classifications.

[0016] "Matching results" refer to the output after pairing or linking related elements or individuals based on specific criteria.

[0017] "Multilingual support" refers to a feature that facilitates communication between users who speak different languages.

[0018] A "collaborative work environment" refers to a system or application that enables multiple users to collaborate in real time. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the 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.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0033] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] This invention provides a platform for users with diverse areas of expertise to collaborate and advance projects. The system includes functions for selecting appropriate experts based on user proposals and effectively matching them. It also provides a multilingual collaborative work environment to facilitate real-time communication.

[0041] Server operation

[0042] The server receives information from the user regarding project proposals. This information includes the project's objectives, required expertise, and expected outcomes. Based on the received information, the server extracts experts with relevant expertise from its database. Next, the server uses artificial intelligence to match the candidate experts with the project's needs in the most appropriate way. In this process, natural language processing and machine learning algorithms are used to analyze each expert's profile in detail. The resulting matching information is then presented to the user.

[0043] Terminal operation

[0044] The terminal receives matching results from the server and provides an interface that visually presents them to the user. Users can review detailed profiles of the presented experts and select project members they wish to participate in. The terminal also includes features such as chat, video conferencing, and document sharing to enable real-time collaboration. In particular, the multilingual real-time translation function facilitates smooth communication between users speaking different languages.

[0045] User actions

[0046] Users input information via their device to plan projects and find the necessary experts. This includes detailed project requirements and schedules. After reviewing the experts and their profiles displayed for each proposal, users select the required members and join the collaborative environment. This allows users to track project progress in real time and make adjustments as needed.

[0047] Specific example

[0048] For example, suppose a user working in the research and development department of a pharmaceutical company starts a new drug development project. The user uses the platform to find experts in chemistry, bioinformatics, and drug regulatory affairs necessary for this project. The server analyzes the project requirements and matches the user with the most suitable experts via AI. The user can then leverage the real-time translation function to communicate smoothly with international experts and proceed with development.

[0049] Thus, this invention presents a concrete model for enabling experts from different fields to collaborate efficiently and smoothly advance projects.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The user creates a project proposal using a terminal, entering detailed information about the project's objectives, required expertise, and expected outcomes. This information is then transmitted from the terminal to the server.

[0053] Step 2:

[0054] The server analyzes project proposal information received from users. Natural language processing is used for the analysis to extract relevant keywords and technical terms from the text and identify the specialized fields required for the project.

[0055] Step 3:

[0056] The server searches the database for relevant expert profiles based on the extracted expertise information. A dedicated search algorithm is then used to generate a list of appropriate experts.

[0057] Step 4:

[0058] The server optimizes the list of experts obtained using artificial intelligence. It uses machine learning algorithms to calculate the degree of match between project proposals and each expert's profile, selecting the expert with the highest score.

[0059] Step 5:

[0060] The terminal visualizes the matching results received from the server for the user. The user can review the profile information of the presented experts and select which experts to include in the project.

[0061] Step 6:

[0062] The server determines the project team based on user selection and creates a dedicated real-time collaborative environment for the project. This environment includes chat, video conferencing, and multilingual translation capabilities.

[0063] Step 7:

[0064] Users can communicate within the project team via their devices and utilize real-time translation features to smoothly communicate with team members who speak different languages, enabling them to advance the project.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] In modern technology projects, the selection and rapid matching of appropriate experts are crucial for efficient collaboration among specialists with diverse technical backgrounds. However, traditional systems often lack sufficient expert profile analysis and struggle with real-time communication between experts who speak different languages. This situation can lead to project delays and the risk of inappropriate expert selection.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes means for receiving information regarding a plan proposal from a user, means for selecting experts with relevant technical fields from an information storage device based on the plan proposal, and means for utilizing intelligent functions to match the selected experts. This enables the rapid and accurate selection and matching of experts in different technical fields, and further enables immediate communication in a multilingual environment.

[0070] A "platform" is a system that serves as a foundation for users with different technical skills to collaborate.

[0071] "Users" refers to individual participants who submit project proposals through the platform and input information for selecting experts.

[0072] A "project proposal" is a document that includes the project's objectives, requirements, and necessary expertise, and serves as the criteria for selecting experts on the platform.

[0073] An "information storage device" is a digital storage system used to retain expert profile information and past achievements.

[0074] "Intelligent function" refers to the technology that applies computational techniques to analyze the profiles of experts and make appropriate selections.

[0075] A "collaborative work environment" is a form of workspace that provides a space where multiple users can work on a project in real time.

[0076] "Multilingual translation functionality" is a language conversion technology that enables smooth communication between users who speak different languages.

[0077] This invention provides a system that offers a platform for users with different technical skills to collaborate and advance projects. This system utilizes the following hardware and software to provide expert selection and a collaborative work environment.

[0078] First, the server receives information about the project proposal from the user. This information is typically sent via an API in a data format such as JSON and parsed using a web framework such as Flask or Django. This information includes the project's objectives, required technical fields, and expected outcomes.

[0079] Next, the server uses an information storage device (e.g., PostgreSQL, MongoDB) to extract experts with relevant technical skills based on selection criteria. This process involves quickly searching existing information in the database to identify experts.

[0080] Furthermore, intelligent functions are used to optimally match selected experts. These functions leverage language processing technologies (e.g., spaCy, NLTK) and learning algorithms (e.g., TENSORFLOW®, PyTorch) to analyze each expert's profile in detail. This analysis ensures optimal matching, and the results are presented to the user.

[0081] The terminal utilizes front-end technologies such as React and Vue.js to visually present the matching results received from the server to the user. Furthermore, the terminal provides a collaborative work environment combining WebRTC and other communication technologies to enable immediate user cooperation, and also integrates multilingual translation functionality.

[0082] Users can review the profiles of presented experts through their devices and select members to participate in the project. During this process, they can directly communicate with the selected members to adjust the project schedule and division of roles. Furthermore, the ability to communicate immediately allows for continuous monitoring of the project's progress and course corrections as needed.

[0083] As a concrete example, consider a case where a researcher launches a new drug development project. This researcher uses the platform to find experts in chemistry, bioinformatics, and pharmaceutical regulatory affairs necessary for the project. The server analyzes the researcher's proposed plan and matches them with the most suitable experts. The researcher can utilize the instant translation function to communicate smoothly with multinational experts.

[0084] An example of a prompt statement is: "We need experts in chemistry, bioinformatics, and pharmaceutical regulations for a new drug development project. The project objectives and timeframe are as follows..." In this way, users can use prompt statements to appropriately find the necessary experts and maximize the efficiency of the project.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server receives information about project proposals from users. This input includes the project objectives, required technical fields, and expected outcomes. The received data is sent via the API in JSON format and parsed using frameworks such as Flask or Django. The parsing results identify the project requirements, which are then output as foundational data for selecting experts in the next step.

[0088] Step 2:

[0089] The server selects relevant experts from its information storage system based on the proposed plan. This step uses a database management system (e.g., PostgreSQL, MongoDB) to search for experts matching the received project requirements. Queries are written based on technical areas and expertise, and an initial list of selected experts is output as a response.

[0090] Step 3:

[0091] The server utilizes intelligent functions to analyze the profiles of selected experts. The list of experts obtained in step 2 is used as input data. This analysis employs natural language processing tools (e.g., spaCy, NLTK) and machine learning algorithms (e.g., TensorFlow, PyTorch). These are used to evaluate each expert's expertise and past achievements, select the most suitable members for the project, and output the matching results.

[0092] Step 4:

[0093] The terminal receives the matching results from the server and presents them visually to the user. The terminal has an interface developed using React and Vue.js, displaying the profile information of the selected experts to the user. Based on the presented profiles, the user can review detailed information and proceed with selecting project members. The user's selection results are output as input data for the next step.

[0094] Step 5:

[0095] Users review the profiles of selected experts on their devices and choose the members to participate in the project. Through the device's GUI, users compare each expert's experience and skill set to determine the most suitable members. As a result, a list of members capable of real-time communication within the platform is output.

[0096] Step 6:

[0097] The terminal provides a collaborative environment that enables selected members and users to work together in real time. Key features include video conferencing using WebRTC and other communication technologies, chat, and document sharing. Furthermore, it integrates multilingual translation capabilities, enabling smooth communication between users who speak different languages. Users can leverage this environment to make immediate adjustments and provide feedback on ongoing projects.

[0098] (Application Example 1)

[0099] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0100] When experts from different fields collaborate, there is a lack of an environment that effectively matches experts and facilitates smooth communication through multilingual support. Furthermore, in projects such as urban function improvement projects, efficient matching of experts and management and sharing of project progress are difficult.

[0101] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0102] In this invention, the server includes means for receiving information on project proposals from users, means for selecting experts with relevant expertise from a database, and means for using artificial intelligence to match the selected experts. This enables real-time collaboration and efficient project management among experts from different fields.

[0103] "Different fields of expertise" refers to a variety of technical and academic fields, such as information technology, urban planning, and environmental science.

[0104] A "user" refers to an individual or group that proposes a project and seeks experts from different fields.

[0105] A "project proposal" is information that outlines the activities and processes planned to achieve a specific objective.

[0106] An "expert" is an individual who possesses advanced knowledge and experience in a specific field.

[0107] A "database" refers to a collection of information that systematically stores profiles and related information about experts.

[0108] "Artificial intelligence" is a technology in which machines imitate human intelligence, and in particular, it is used to select experts through natural language processing and machine learning.

[0109] "Matching" is the process of selecting and appropriately connecting experts who are suitable for the project's requirements.

[0110] "Multilingual support" refers to a function that enables smooth communication between individuals who use different languages.

[0111] A "collaborative work environment" is a system that provides a virtual workspace where multiple users can work together efficiently.

[0112] A "city function improvement project" refers to a project related to smart cities that aims to improve the urban environment.

[0113] "Progress tracking" refers to the activity of monitoring the progress of a project and making necessary adjustments.

[0114] "Shared resources" refer to data, documents, deliverables, etc., related to a project, and are made accessible to all stakeholders.

[0115] The system for implementing this invention effectively matches experts with different fields of expertise and provides a multilingual collaborative work environment.

[0116] The server receives information about project proposals from users. The Flask framework, written in Python, functions as the server's API, collecting data on project objectives and required skills. The database also stores information on multiple experts, and artificial intelligence is used to analyze these profiles and select the most suitable expert for the project. Natural language processing and machine learning algorithms utilizing TensorFlow are used to evaluate the experts' skills and experience.

[0117] On the device, an application developed using React Native runs, visually presenting matching results to the user. This application includes features such as chat, video conferencing, and document sharing, and utilizes real-time multilingual translation capabilities provided by the Google® Translate API to facilitate smooth communication between users.

[0118] Through this interface, users can plan urban function improvement projects, track their progress, and manage shared resources. This system facilitates the efficient execution of urban development projects.

[0119] As a concrete example, consider a city planning a project to implement a smart transportation system. The user would use this system to efficiently match and select the necessary experts in transportation engineering, environmental science, and IT infrastructure, thereby supporting the progress of the project.

[0120] Example prompts for generative AI models:

[0121] "You are planning a smart city traffic management project. This project requires experts in traffic engineering, environmental science, and IT infrastructure. We would like to utilize a platform that can efficiently match these experts."

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The server receives project proposal information from the user. The user inputs the project objectives, required areas of expertise, expected outcomes, etc. The server receives this input data and prepares to access the database. At this stage, the proposal is saved and the initial data is organized.

[0125] Step 2:

[0126] The server selects experts with relevant expertise from its database based on the received project proposal information. It extracts a list of experts by executing database queries. The input is the skill set required for the project, and the output is a list of candidate experts who match that skill set.

[0127] Step 3:

[0128] The server uses artificial intelligence to analyze the profiles of selected experts. Specifically, it leverages natural language processing and machine learning algorithms using TensorFlow. It receives profile data as input and analyzes and evaluates their expertise and skill levels. The output is a priority list of experts best suited to the project.

[0129] Step 4:

[0130] The server generates matching results and sends them to the terminal. Data processing involves assigning rankings and suitability scores to experts from a list of experts and converting them into a format that can be presented to the user.

[0131] Step 5:

[0132] The terminal visually displays the matching results received from the server to the user. Based on this information, the user proceeds with the process of selecting appropriate experts as project members. The input is data from the server, and the output is a list of experts that the user can select.

[0133] Step 6:

[0134] The device provides multilingual chat and video conferencing capabilities to enable real-time communication with experts selected by the user. Using the Google Translate API, input messages are automatically translated into the required language. The output consists of translated messages and conversation transcripts.

[0135] Step 7:

[0136] Users track project progress via their devices and adjust project parameters as needed. This phase supports decision-making based on the display and analysis of progress data. The input is project progress data, and the output is the adjusted project plan.

[0137] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0138] This invention is a system that combines a platform for users with different areas of expertise to collaborate efficiently with an emotion engine that recognizes users' emotions. In addition to providing a collaborative work environment, this system aims to improve the quality of communication by recognizing users' emotional states in real time, as well as providing project proposals, expert matching, and collaborative work environments.

[0139] Server operation

[0140] The server first receives project proposal information from the user and analyzes its content using natural language processing and machine learning. Based on this analysis, it searches for appropriate experts in the database and uses artificial intelligence to select the expert best suited to the project. Simultaneously, the server analyzes voice and text data acquired during communication with the user using an emotion engine to determine the user's emotional state. The data obtained from emotion recognition is used to adjust the interface of the collaborative work environment.

[0141] Terminal operation

[0142] The terminal visualizes matching results and sentiment recognition information received from the server for the user. The user can review the presented experts and select the best members for the project. Furthermore, the terminal provides real-time sentiment-based feedback to facilitate smooth communication. If the user's emotions are recognized, the terminal changes the interface's color scheme and layout as needed to make adjustments that reduce stress.

[0143] User actions

[0144] Users input project proposals via their devices, and experts are matched based on these proposals. Users can then check the emotional state of each member before beginning collaboration with the matched experts. Throughout the project, users utilize feedback provided by the emotional engine to maintain engagement among all project participants. This improves communication efficiency and increases the project's success rate.

[0145] Specific example

[0146] A company plans a new product development project and will use this system. The user inputs project details as a proposal, and the server uses this information to match appropriate marketing, design, and engineering experts. During expert meetings, the emotion engine analyzes the participants' emotions and adjusts the environment in real time, such as changing the interface to calmer colors if tension is high. This allows participants to exchange ideas in a more relaxed state and fosters creative ideas.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] The user enters detailed project proposals via a terminal. This includes the project name, objectives, required expertise, and expected outcomes. This data is then transmitted from the terminal to the server.

[0150] Step 2:

[0151] The server analyzes project proposal information received from users. Using natural language processing, it extracts keywords and technical terms from the proposal and identifies the specialized fields required for the project.

[0152] Step 3:

[0153] The server searches the database for relevant expert profiles based on the analysis results. Using a dedicated algorithm that evaluates the skill information and past project history contained in each profile, it generates a list of the most suitable experts.

[0154] Step 4:

[0155] The server utilizes machine learning algorithms to calculate the degree of match and optimize the list of experts. This process selects the expert best suited to the project's needs.

[0156] Step 5:

[0157] The server analyzes voice and text data using an emotion engine to determine the user's emotional state. Simultaneously, it monitors changes in emotions within the communication in real time.

[0158] Step 6:

[0159] The terminal presents the user with matching results and sentiment recognition information obtained from the server. The user can then review the detailed profiles of the presented experts and select the members who will join the project.

[0160] Step 7:

[0161] The device will create a real-time collaborative environment with selected team members. This environment will include chat, video conferencing, multilingual translation, and real-time sentiment feedback.

[0162] Step 8:

[0163] Users communicate through their devices based on emotional feedback and advance the project by adjusting the interface as needed. This adjustment includes changing the screen's color tone and the priority of information presentation.

[0164] The above describes the processing steps of a platform that uses an emotion engine.

[0165] (Example 2)

[0166] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0167] In collaborations between engineers from different fields, inefficiencies can arise due to emotional and communication mismatches. In particular, when using different languages, misunderstandings and communication breakdowns are more likely, leading to a decrease in project success rates. Solutions are needed to address this challenge and improve the quality of collaboration.

[0168] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0169] In this invention, the server includes means for receiving information about project proposals from users, means for selecting engineers with relevant expertise from an information set, means for using an emotion engine to analyze the user's emotional state, and means for adjusting the display of the collaborative work environment based on the emotion data. This enables real-time and effective collaboration among engineers and improves communication that transcends emotional and language barriers.

[0170] A "user" refers to an individual or organization that uses the system to propose projects and collaborate with engineers.

[0171] A "project proposal" is information entered by the user through the system, describing the specific tasks and objectives of the collaborative project.

[0172] "Area of ​​expertise" refers to the field of specialized knowledge and skills possessed by an engineer, and serves as a criterion for selecting relevant engineers according to the content of the project proposal.

[0173] An "engineer" refers to an individual who possesses specialized knowledge and skills in a specific field and is selected based on their project proposal.

[0174] An "information set" refers to a database or information resource about engineers, a collection of data that holds engineers' profiles and skill information.

[0175] "Intelligent functions" refer to artificial intelligence technologies used to effectively combine selected engineers and optimize collaboration with users.

[0176] An "emotion engine" refers to a technology that analyzes a user's emotional state and provides it as data, enabling real-time emotion recognition.

[0177] A "collaborative work environment" refers to a workspace where multiple users can cooperate in real time, supporting communication and enabling the efficient execution of projects.

[0178] "Display adjustment" refers to changing the appearance and layout of the user interface based on emotional data, and is an operation performed to improve user comfort and reduce stress.

[0179] This invention is a platform for engineers from different fields to collaborate efficiently, incorporating an emotion engine that recognizes user emotions. This enables comprehensive support, from project proposals and engineer matching to the provision of a collaborative work environment.

[0180] The server receives project proposal information from users and analyzes its content using natural language processing and training algorithms. Specifically, Python's natural language processing libraries and related libraries are applied. Based on the analysis results, the server searches for and selects appropriate engineers from the information set. In this process, artificial intelligence is used to determine the most suitable engineer. Simultaneously, the server analyzes the user's voice and text data using an emotion engine and quantifies their emotional state. This data is used to optimize the display of the collaborative work environment.

[0181] The terminal visualizes the matching results and emotion recognition information of engineers received from the server for the user. The user interface is built using web technologies, particularly frameworks such as React.js. Users can review the presented engineers and select the most suitable collaborators. Furthermore, the terminal provides real-time emotion-based feedback to support smooth communication. If the emotion is negative, the UI's colors and layout are changed to reduce stress.

[0182] Users can input project proposals via their devices and view the results of engineer matching performed on the server side. Based on this information, users can check the emotional state of each member before the project starts and prepare the optimal collaborative structure. During the project, users can utilize the feedback obtained through the emotional engine to maintain and improve team member engagement.

[0183] For example, if an organization plans to develop a new product, the server matches them with engineers who possess the appropriate expertise after they input the project details. During a meeting, the emotion engine analyzes participants' facial expressions and voices, and softens the UI's color scheme if tension is detected. This promotes relaxation among participants and enables more creative discussion.

[0184] An example of a prompt to input into the generating AI model is as follows: "Please tell me how to select the best engineers for a new product development project and build a system that analyzes the emotions of meeting participants and adjusts the UI accordingly."

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The server receives project proposal information from the user. As input, it receives text data entered by the user via a terminal. This information includes a summary of the proposal and the required technical fields. The received text data is prepared for natural language processing.

[0188] Step 2:

[0189] The server analyzes the project proposal using natural language processing (NLP) techniques. Specifically, it uses Python's natural language processing library to tokenize, tag, and extract keywords from the text data. The input is the text data received in step 1, and the output is a keyword list that describes the proposal. Based on these analysis results, the server identifies the relevant technical fields.

[0190] Step 3:

[0191] The server uses the analysis results to select appropriate engineers from the information set. It applies a machine learning algorithm (e.g., using Scikit-learn) to search for experts in relevant fields from an engineer database. The input is the keyword list from step 2, and the output is a list of suitable engineer candidates. This list provides engineers who match the project requirements, scored accordingly.

[0192] Step 4:

[0193] The terminal visualizes the engineer matching results received from the server for the user. A UI is built using web technologies to display a list of candidate engineers on the screen. The input is the list of candidate engineers generated in step 3, and the output is the visual information displayed on the user's screen. Based on this list, the user can select the most suitable collaborators for their project.

[0194] Step 5:

[0195] The server transmits user communication data to the emotion engine in real time and analyzes the emotional state. It takes in voice and text data, applies an emotion recognition algorithm, and quantifies emotions such as joy, anger, sadness, and happiness. The input is user voice and text data acquired in real time, and the output is numerical data indicating the emotional state.

[0196] Step 6:

[0197] The device adjusts the display of the collaborative work environment based on emotional data. It changes the UI's color scheme and layout as needed to reduce user stress. The input is the emotional state data generated in step 5, and the output is the modified UI. This adjustment allows users to collaborate in a more comfortable environment.

[0198] (Application Example 2)

[0199] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0200] In collaborations between users with different areas of expertise, emotional disagreements and communication breakdowns are likely to occur, potentially impacting project progress. Furthermore, maintaining smooth communication is difficult in multilingual environments and across different cultural backgrounds. There is a need to improve these situations and provide an efficient and smooth collaborative environment.

[0201] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0202] In this invention, the server includes means for receiving information on work proposals from users, means for selecting experts with relevant expertise from a data storage device, means for matching experts using artificial intelligence, means for providing a common work environment in which multiple users can cooperate in real time, and means including an emotion understanding engine for analyzing the emotional state of users. This makes it possible to minimize communication obstacles and realize an effective collaborative environment by providing feedback that takes into account the emotional state of users.

[0203] "Different areas of expertise" refers to fields with distinct technical or knowledge systems, encompassing multiple areas, each possessing specific knowledge and skills.

[0204] "User" refers to an individual or group that uses the system to propose projects or engage in collaborative activities.

[0205] A "work proposal" refers to information that includes the project's goals, objectives, and progress plan and intentions, and collaboration proceeds based on this proposal.

[0206] A "specialist" refers to a person who possesses advanced knowledge and skills in a specific area of ​​expertise and who utilizes that knowledge to contribute to a project.

[0207] A "data storage device" refers to an information recording device that stores and saves information about experts and allows it to be retrieved as needed.

[0208] "Artificial intelligence" refers to the technology used to enable computer systems to think like humans and solve problems or make decisions.

[0209] A "shared work environment" refers to a workspace or interface provided for users to collaborate in real time, and includes features such as multilingual support and adjustment functions based on sentiment analysis.

[0210] An "emotion understanding engine" refers to a computer program or process that analyzes data extracted from a user's voice and facial expressions to determine the user's emotional state.

[0211] "Feedback" refers to the responses and guidelines provided by a system based on the user's behavior and emotional state, and is used to facilitate smoother collaboration.

[0212] The server cross-references the work proposal information received from the user with expert information stored in data storage, and uses artificial intelligence to select the most suitable expert. Natural language processing technology and machine learning algorithms are used to analyze the received text data. This method enables accurate expert selection based on the project content. Furthermore, it utilizes an emotion understanding engine to analyze voice and text data acquired during communication, grasping the user's emotional state in real time.

[0213] The terminal visualizes and presents to the user information regarding matching results and emotional states provided by the server. Based on the acquired information, the terminal adjusts the interface's color scheme and layout according to the emotional state, thereby reducing user stress and supporting smooth communication.

[0214] Users enter project proposals using their devices and begin collaborating with matched experts. Throughout the project, feedback provided by the sentiment understanding engine is utilized to maintain engagement among all participants. This improves project efficiency and success rates.

[0215] As a concrete example, a consumer robot installed in a home can analyze conversations between family members using an emotion-understanding engine and provide feedback, such as playing calming music if tension is present, thereby making the living environment more comfortable. In this way, it becomes possible to improve the user experience.

[0216] An example of a prompt is: "Generate prompts for developing an application for a consumer robot that analyzes the user's emotional state and adjusts the dialogue accordingly."

[0217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0218] Step 1:

[0219] The server receives work proposals from users. As input, it obtains information about the project's purpose and details, which the user enters via their terminal. This information is received as text data and temporarily stored in a database. The server then processes this data to retrieve it in the correct format.

[0220] Step 2:

[0221] The server analyzes received work proposals using natural language processing techniques. It uses the received text data as input. The text data is tokenized, keywords are extracted, and the server determines which areas of expertise the project content relates to, generating analysis results. The output is data containing the specific keywords and themes analyzed.

[0222] Step 3:

[0223] The server searches for experts with relevant expertise from its data storage based on the analysis results. The keywords and themes extracted in step 2 are provided as input. A database search algorithm is applied to generate a list of relevant experts based on this information. The output is a list of candidate experts.

[0224] Step 4:

[0225] The server uses artificial intelligence to select the most suitable expert for a specific project. The input consists of a list of candidates and each expert's profile data. A machine learning model evaluates the experts' skill sets and historical performance data to rank the most suitable candidates. The output is a final list of matched experts.

[0226] Step 5:

[0227] The terminal receives matching results from the server and presents them visually to the user. It receives matching result data from the server as input. It uses UI components to format the data in a visually easy-to-understand way. The user reviews the list of candidates and makes a selection.

[0228] Step 6:

[0229] The server uses an emotion understanding engine to analyze real-time voice and text data received from the terminal. The input is voice and text data acquired during communication. This data is processed by an emotion analysis algorithm to generate data that determines the user's current emotional state. The output is data indicating the recognized emotional state.

[0230] Step 7:

[0231] The device adjusts the interface's color scheme and layout for the user based on sentiment analysis data. It uses sentiment data obtained from an sentiment understanding engine as input. The device uses dynamic UI components to make the necessary adjustments. The output is the adjusted interface, optimized to reduce user stress.

[0232] Step 8:

[0233] Users leverage feedback provided during project progress to improve the efficiency of collaboration. They receive feedback based on emotional states provided by their devices. Based on this feedback, users adjust their communication methods and project progress. As a result, highly engaged collaboration is achieved.

[0234] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0235] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0236] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0237] [Second Embodiment]

[0238] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0239] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0240] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0241] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0242] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0243] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0244] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0245] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0246] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0247] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0248] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0249] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0250] This invention provides a platform for users with diverse areas of expertise to collaborate and advance projects. The system includes functions for selecting appropriate experts based on user proposals and effectively matching them. It also provides a multilingual collaborative work environment to facilitate real-time communication.

[0251] Server operation

[0252] The server receives information from the user regarding project proposals. This information includes the project's objectives, required expertise, and expected outcomes. Based on the received information, the server extracts experts with relevant expertise from its database. Next, the server uses artificial intelligence to match the candidate experts with the project's needs in the most appropriate way. In this process, natural language processing and machine learning algorithms are used to analyze each expert's profile in detail. The resulting matching information is then presented to the user.

[0253] Terminal operation

[0254] The terminal receives matching results from the server and provides an interface that visually presents them to the user. Users can review detailed profiles of the presented experts and select project members they wish to participate in. The terminal also includes features such as chat, video conferencing, and document sharing to enable real-time collaboration. In particular, the multilingual real-time translation function facilitates smooth communication between users speaking different languages.

[0255] User actions

[0256] Users input information via their device to plan projects and find the necessary experts. This includes detailed project requirements and schedules. After reviewing the experts and their profiles displayed for each proposal, users select the required members and join the collaborative environment. This allows users to track project progress in real time and make adjustments as needed.

[0257] Specific example

[0258] For example, suppose a user working in the research and development department of a pharmaceutical company starts a new drug development project. The user uses the platform to find experts in chemistry, bioinformatics, and drug regulatory affairs necessary for this project. The server analyzes the project requirements and matches the user with the most suitable experts via AI. The user can then leverage the real-time translation function to communicate smoothly with international experts and proceed with development.

[0259] Thus, this invention presents a concrete model for enabling experts from different fields to collaborate efficiently and smoothly advance projects.

[0260] The following describes the processing flow.

[0261] Step 1:

[0262] The user creates a project proposal using a terminal, entering detailed information about the project's objectives, required expertise, and expected outcomes. This information is then sent from the terminal to the server.

[0263] Step 2:

[0264] The server analyzes project proposal information received from users. Natural language processing is used for the analysis to extract relevant keywords and technical terms from the text and identify the specialized fields required for the project.

[0265] Step 3:

[0266] The server searches the database for relevant expert profiles based on the extracted expertise information. A dedicated search algorithm is then used to generate a list of appropriate experts.

[0267] Step 4:

[0268] The server optimizes the list of experts obtained using artificial intelligence. It uses machine learning algorithms to calculate the degree of match between project proposals and each expert's profile, selecting the expert with the highest score.

[0269] Step 5:

[0270] The terminal visualizes the matching results received from the server for the user. The user can review the profile information of the presented experts and select which experts to include in the project.

[0271] Step 6:

[0272] The server determines the project team based on user selection and creates a dedicated real-time collaborative environment for the project. This environment includes chat, video conferencing, and multilingual translation capabilities.

[0273] Step 7:

[0274] Users can communicate within the project team via their devices and utilize real-time translation features to smoothly communicate with team members who speak different languages, enabling them to advance the project.

[0275] (Example 1)

[0276] Next, we will describe Example 1. 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."

[0277] In modern technology projects, in order for experts with different technical fields to collaborate efficiently, it is important to select appropriate experts and conduct quick matching. However, in conventional systems, there are problems that the analysis of experts' profiles is not sufficiently carried out and real-time communication between experts using different languages is difficult. In such a situation, there is a risk that the progress of the project will be delayed or experts will not be appropriately selected.

[0278] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 1 is realized by the following means.

[0279] In this invention, the server includes means for receiving information regarding a plan proposal from a user, means for selecting experts having related technical fields from an information storage device based on the plan proposal, and means for using an intelligent function for matching the selected experts. Thereby, experts in different technical fields can be selected and matched quickly and accurately, and furthermore, immediate communication in a multilingual environment becomes possible.

[0280] A "platform" is a system that serves as a basis for users with different technical fields to perform collaborative work.

[0281] A "user" refers to each individual participant who makes a project proposal through a platform and inputs information for selecting experts.

[0282] A "plan proposal" is a document that includes the purpose, requirements, and necessary expertise of a project, and serves as a criterion for selecting experts on a platform.

[0283] An "information storage device" is a digital storage system for holding experts' profile information and past achievements.

[0284] An "intelligent function" refers to a technology that applies computing technology to analyze experts' profiles for appropriate selection.

[0285] A "collaborative working environment" is a form that provides a working space where multiple users can carry out a project in real time.

[0286] A "multilingual translation function" is a language conversion technology that enables smooth communication between users who use different languages.

[0287] The present invention is a system that provides a platform for users with different technical fields to cooperate and promote a project. This system utilizes the following hardware and software to select experts and provide a collaborative working environment.

[0288] First, the server receives information regarding a project proposal from a user. The information is usually transmitted in a data format such as JSON via an API and analyzed using a web framework such as Flask or Django. This information includes the purpose of the project, the required technical fields, the expected outcomes, and the like.

[0289] Next, the server uses an information storage device (e.g., PostgreSQL, MongoDB) to extract experts with relevant technical fields based on selection criteria. In this process, the existing information in the database is quickly searched to identify experts.

[0290] Furthermore, an intelligent function is used to optimally match the selected experts. This function utilizes language processing technologies (e.g., spaCy, NLTK) and learning algorithms (e.g., TensorFlow, PyTorch) to analyze the profiles of each expert in detail. Through this analysis, an optimal matching is performed and the results are presented to the user.

[0291] The terminal utilizes front-end technologies such as React and Vue.js to visually present the matching results received from the server to the user. Furthermore, the terminal provides a collaborative work environment combining WebRTC and other communication technologies to enable immediate user cooperation, and also integrates multilingual translation functionality.

[0292] Users can review the profiles of presented experts through their devices and select members to participate in the project. During this process, they can directly communicate with the selected members to adjust the project schedule and division of roles. Furthermore, the ability to communicate immediately allows for continuous monitoring of the project's progress and course corrections as needed.

[0293] As a concrete example, consider a case where a researcher launches a new drug development project. This researcher uses the platform to find experts in chemistry, bioinformatics, and pharmaceutical regulatory affairs necessary for the project. The server analyzes the researcher's proposed plan and matches them with the most suitable experts. The researcher can utilize the instant translation function to communicate smoothly with multinational experts.

[0294] An example of a prompt statement is: "We need experts in chemistry, bioinformatics, and pharmaceutical regulations for a new drug development project. The project objectives and timeframe are as follows..." In this way, users can use prompt statements to appropriately find the necessary experts and maximize the efficiency of the project.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The server receives information about project proposals from users. This input includes the project objectives, required technical fields, and expected outcomes. The received data is sent via the API in JSON format and parsed using frameworks such as Flask or Django. The parsing results identify the project requirements, which are then output as foundational data for selecting experts in the next step.

[0298] Step 2:

[0299] The server selects relevant experts from its information storage system based on the proposed plan. This step uses a database management system (e.g., PostgreSQL, MongoDB) to search for experts matching the received project requirements. Queries are written based on technical areas and expertise, and an initial list of selected experts is output as a response.

[0300] Step 3:

[0301] The server utilizes intelligent functions to analyze the profiles of selected experts. The list of experts obtained in step 2 is used as input data. This analysis employs natural language processing tools (e.g., spaCy, NLTK) and machine learning algorithms (e.g., TensorFlow, PyTorch). These are used to evaluate each expert's expertise and past achievements, select the most suitable members for the project, and output the matching results.

[0302] Step 4:

[0303] The terminal receives the matching results from the server and presents them visually to the user. The terminal has an interface developed using React and Vue.js, displaying the profile information of the selected experts to the user. Based on the presented profiles, the user can review detailed information and proceed with selecting project members. The user's selection results are output as input data for the next step.

[0304] Step 5:

[0305] The user checks the profile of the selected expert on the terminal and selects the members who will participate in the project. The user compares the experience and skill sets of each expert via the GUI of the terminal and determines the most suitable members. As a result, a member list that enables real-time communication within the platform is output.

[0306] Step 6:

[0307] The terminal provides a collaborative work environment so that the selected members and the user can cooperate in real time. The main functions include video conferencing, chatting, and document sharing using WebRTC and other communication technologies. Furthermore, a multilingual translation function is integrated to enable smooth communication between users who use different languages. The user can utilize this environment to immediately make adjustments and provide feedback on the ongoing project.

[0308] (Application Example 1)

[0309] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0310] When experts with different specialties cooperate, there is a lack of an environment for effectively matching experts and smoothly communicating in multiple languages. Also, in projects such as urban function improvement projects, it is difficult to efficiently match experts and manage and share the progress of the project.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0312] In this invention, the server includes means for receiving information on project proposals from users, means for selecting experts with relevant expertise from a database, and means for using artificial intelligence to match the selected experts. This enables real-time collaboration and efficient project management among experts from different fields.

[0313] "Different fields of expertise" refers to a variety of technical and academic fields, such as information technology, urban planning, and environmental science.

[0314] A "user" refers to an individual or group that proposes a project and seeks experts from different fields.

[0315] A "project proposal" is information that outlines the activities and processes planned to achieve a specific objective.

[0316] An "expert" is an individual who possesses advanced knowledge and experience in a specific field.

[0317] A "database" refers to a collection of information that systematically stores profiles and related information about experts.

[0318] "Artificial intelligence" is a technology in which machines imitate human intelligence, and in particular, it is used to select experts through natural language processing and machine learning.

[0319] "Matching" is the process of selecting and appropriately connecting experts who are suitable for the project's requirements.

[0320] "Multilingual support" refers to a function that enables smooth communication between individuals who use different languages.

[0321] A "collaborative work environment" is a system that provides a virtual workspace where multiple users can work together efficiently.

[0322] A "city function improvement project" refers to a project related to smart cities that aims to improve the urban environment.

[0323] "Progress tracking" refers to the activity of monitoring the progress of a project and making necessary adjustments.

[0324] "Shared resources" refer to data, documents, deliverables, etc., related to a project, and are made accessible to all stakeholders.

[0325] The system for implementing this invention effectively matches experts with different fields of expertise and provides a multilingual collaborative work environment.

[0326] The server receives information about project proposals from users. The Flask framework, written in Python, functions as the server's API, collecting data on project objectives and required skills. The database also stores information on multiple experts, and artificial intelligence is used to analyze these profiles and select the most suitable expert for the project. Natural language processing and machine learning algorithms utilizing TensorFlow are used to evaluate the experts' skills and experience.

[0327] On the device, an application developed using React Native runs, visually presenting matching results to the user. This application includes features such as chat, video conferencing, and document sharing, and utilizes real-time multilingual translation capabilities via the Google Translate API to facilitate smooth communication between users.

[0328] Through this interface, users can plan urban function improvement projects, track their progress, and manage shared resources. This system facilitates the efficient execution of urban development projects.

[0329] As a concrete example, consider a city planning a project to implement a smart transportation system. The user would use this system to efficiently match and select the necessary experts in transportation engineering, environmental science, and IT infrastructure, thereby supporting the progress of the project.

[0330] Example prompts for generative AI models:

[0331] "You are planning a smart city traffic management project. This project requires experts in traffic engineering, environmental science, and IT infrastructure. We would like to utilize a platform that can efficiently match these experts."

[0332] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0333] Step 1:

[0334] The server receives project proposal information from the user. The user inputs the project objectives, required areas of expertise, expected outcomes, etc. The server receives this input data and prepares to access the database. At this stage, the proposal is saved and the initial data is organized.

[0335] Step 2:

[0336] The server selects experts with relevant expertise from its database based on the received project proposal information. It extracts a list of experts by executing database queries. The input is the skill set required for the project, and the output is a list of candidate experts who match that skill set.

[0337] Step 3:

[0338] The server uses artificial intelligence to analyze the profiles of selected experts. Specifically, it leverages natural language processing and machine learning algorithms using TensorFlow. It receives profile data as input and analyzes and evaluates their expertise and skill levels. The output is a priority list of experts best suited to the project.

[0339] Step 4:

[0340] The server generates matching results and sends them to the terminal. Data processing involves assigning rankings and suitability scores to experts from a list of experts and converting them into a format that can be presented to the user.

[0341] Step 5:

[0342] The terminal visually displays the matching results received from the server to the user. Based on this information, the user proceeds with the process of selecting appropriate experts as project members. The input is data from the server, and the output is a list of experts that the user can select.

[0343] Step 6:

[0344] The device provides multilingual chat and video conferencing capabilities to enable real-time communication with experts selected by the user. Using the Google Translate API, input messages are automatically translated into the required language. The output consists of translated messages and conversation transcripts.

[0345] Step 7:

[0346] Users track project progress via their devices and adjust project parameters as needed. This phase supports decision-making based on the display and analysis of progress data. The input is project progress data, and the output is the adjusted project plan.

[0347] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0348] This invention is a system that combines a platform for users with different areas of expertise to collaborate efficiently with an emotion engine that recognizes users' emotions. In addition to providing a collaborative work environment, this system aims to improve the quality of communication by recognizing users' emotional states in real time, as well as providing project proposals, expert matching, and collaborative work environments.

[0349] Server operation

[0350] The server first receives project proposal information from the user and analyzes its content using natural language processing and machine learning. Based on this analysis, it searches for appropriate experts in the database and uses artificial intelligence to select the expert best suited to the project. Simultaneously, the server analyzes voice and text data acquired during communication with the user using an emotion engine to determine the user's emotional state. The data obtained from emotion recognition is used to adjust the interface of the collaborative work environment.

[0351] Terminal operation

[0352] The terminal visualizes matching results and sentiment recognition information received from the server for the user. The user can review the presented experts and select the best members for the project. Furthermore, the terminal provides real-time sentiment-based feedback to facilitate smooth communication. If the user's emotions are recognized, the terminal changes the interface's color scheme and layout as needed, making adjustments to reduce stress.

[0353] User actions

[0354] Users input project proposals via their devices, and experts are matched based on these proposals. Users can then check the emotional state of each member before beginning collaboration with the matched experts. Throughout the project, users utilize feedback provided by the emotional engine to maintain engagement among all project participants. This improves communication efficiency and increases the project's success rate.

[0355] Specific example

[0356] A company plans a new product development project and will use this system. The user inputs project details as a proposal, and the server uses this information to match appropriate marketing, design, and engineering experts. During expert meetings, the emotion engine analyzes the participants' emotions and adjusts the environment in real time, such as changing the interface to calmer colors if tension is high. This allows participants to exchange ideas in a more relaxed state and fosters creative ideas.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The user enters detailed project proposals via a terminal. This includes the project name, objectives, required expertise, and expected outcomes. This data is then transmitted from the terminal to the server.

[0360] Step 2:

[0361] The server analyzes project proposal information received from users. Using natural language processing, it extracts keywords and technical terms from the proposal and identifies the specialized fields required for the project.

[0362] Step 3:

[0363] The server searches the database for relevant expert profiles based on the analysis results. Using a dedicated algorithm that evaluates the skill information and past project history contained in each profile, it generates a list of the most suitable experts.

[0364] Step 4:

[0365] The server utilizes machine learning algorithms to calculate the degree of match and optimize the list of experts. This process selects the expert best suited to the project's needs.

[0366] Step 5:

[0367] The server analyzes voice and text data using an emotion engine to determine the user's emotional state. Simultaneously, it monitors emotional changes within the communication in real time.

[0368] Step 6:

[0369] The terminal presents the user with matching results and sentiment recognition information obtained from the server. The user can then review the detailed profiles of the presented experts and select the members who will join the project.

[0370] Step 7:

[0371] The device will create a real-time collaborative environment with selected team members. This environment will include chat, video conferencing, multilingual translation, and real-time sentiment feedback.

[0372] Step 8:

[0373] Users communicate through their devices based on emotional feedback and advance the project by adjusting the interface as needed. This adjustment includes changing the screen's color tone and the priority of information presentation.

[0374] The above describes the processing steps of a platform that uses an emotion engine.

[0375] (Example 2)

[0376] Next, we will describe Example 2. 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".

[0377] In collaborations between engineers from different fields, inefficiencies can arise due to emotional and communication mismatches. In particular, when using different languages, misunderstandings and communication breakdowns are more likely, leading to a decrease in project success rates. Solutions are needed to address this challenge and improve the quality of collaboration.

[0378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0379] In this invention, the server includes means for receiving information about project proposals from users, means for selecting engineers with relevant expertise from an information set, means for using an emotion engine to analyze the user's emotional state, and means for adjusting the display of the collaborative work environment based on the emotion data. This enables real-time and effective collaboration among engineers and improves communication that transcends emotional and language barriers.

[0380] A "user" refers to an individual or organization that uses the system to propose projects and collaborate with engineers.

[0381] A "project proposal" is information entered by the user through the system, describing the specific tasks and objectives of the collaborative project.

[0382] "Area of ​​expertise" refers to the field of specialized knowledge and skills possessed by an engineer, and serves as a criterion for selecting relevant engineers according to the content of the project proposal.

[0383] An "engineer" refers to an individual who possesses specialized knowledge and skills in a specific field and is selected based on their project proposal.

[0384] An "information set" refers to a database or information resource about engineers, a collection of data that holds engineers' profiles and skill information.

[0385] "Intelligent functions" refer to artificial intelligence technologies used to effectively combine selected engineers and optimize collaboration with users.

[0386] An "emotion engine" refers to a technology that analyzes a user's emotional state and provides it as data, enabling real-time emotion recognition.

[0387] A "collaborative work environment" refers to a workspace where multiple users can cooperate in real time, supporting communication and enabling the efficient execution of projects.

[0388] "Display adjustment" refers to changing the appearance and layout of the user interface based on emotional data, and is an operation performed to improve user comfort and reduce stress.

[0389] This invention is a platform for engineers from different fields to collaborate efficiently, incorporating an emotion engine that recognizes user emotions. This enables comprehensive support, from project proposals and engineer matching to the provision of a collaborative work environment.

[0390] The server receives project proposal information from users and analyzes its content using natural language processing and training algorithms. Specifically, Python's natural language processing libraries and related libraries are applied. Based on the analysis results, the server searches for and selects appropriate engineers from the information set. In this process, artificial intelligence is used to determine the most suitable engineer. Simultaneously, the server analyzes the user's voice and text data using an emotion engine and quantifies their emotional state. This data is used to optimize the display of the collaborative work environment.

[0391] The terminal visualizes the matching results and emotion recognition information of engineers received from the server for the user. The user interface is built using web technologies, particularly frameworks such as React.js. Users can review the presented engineers and select the most suitable collaborators. Furthermore, the terminal provides real-time emotion-based feedback to support smooth communication. If the emotion is negative, the UI's colors and layout are changed to reduce stress.

[0392] Users can input project proposals via their devices and view the results of engineer matching performed on the server side. Based on this information, users can check the emotional state of each member before the project starts and prepare the optimal collaborative structure. During the project, users can utilize the feedback obtained through the emotional engine to maintain and improve team member engagement.

[0393] For example, if an organization plans to develop a new product, the server matches them with engineers who possess the appropriate expertise after they input the project details. During a meeting, the emotion engine analyzes participants' facial expressions and voices, and softens the UI's color scheme if tension is detected. This promotes relaxation among participants and enables more creative discussion.

[0394] An example of a prompt to input into the generating AI model is as follows: "Please tell me how to select the best engineers for a new product development project and build a system that analyzes the emotions of meeting participants and adjusts the UI accordingly."

[0395] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0396] Step 1:

[0397] The server receives project proposal information from the user. As input, it receives text data entered by the user via a terminal. This information includes a summary of the proposal and the required technical fields. The received text data is prepared for natural language processing.

[0398] Step 2:

[0399] The server analyzes the project proposal using natural language processing (NLP) techniques. Specifically, it uses Python's natural language processing library to tokenize, tag, and extract keywords from the text data. The input is the text data received in step 1, and the output is a keyword list that describes the proposal. Based on these analysis results, the server identifies the relevant technical fields.

[0400] Step 3:

[0401] The server uses the analysis results to select appropriate engineers from the information set. It applies a machine learning algorithm (e.g., using Scikit-learn) to search for experts in relevant fields from an engineer database. The input is the keyword list from step 2, and the output is a list of suitable engineer candidates. This list provides engineers who match the project requirements, scored accordingly.

[0402] Step 4:

[0403] The terminal visualizes the engineer matching results received from the server for the user. A UI is built using web technologies to display a list of candidate engineers on the screen. The input is the list of candidate engineers generated in step 3, and the output is the visual information displayed on the user's screen. Based on this list, the user can select the most suitable collaborators for their project.

[0404] Step 5:

[0405] The server transmits user communication data to the emotion engine in real time and analyzes the emotional state. It takes in voice and text data, applies an emotion recognition algorithm, and quantifies emotions such as joy, anger, sadness, and happiness. The input is user voice and text data acquired in real time, and the output is numerical data indicating the emotional state.

[0406] Step 6:

[0407] The device adjusts the display of the collaborative work environment based on emotional data. It changes the UI's color scheme and layout as needed to reduce user stress. The input is the emotional state data generated in step 5, and the output is the modified UI. This adjustment allows users to collaborate in a more comfortable environment.

[0408] (Application Example 2)

[0409] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0410] In collaborations between users with different areas of expertise, emotional disagreements and communication breakdowns are likely to occur, potentially impacting project progress. Furthermore, maintaining smooth communication is difficult in multilingual environments and across different cultural backgrounds. There is a need to improve these situations and provide an efficient and smooth collaborative environment.

[0411] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0412] In this invention, the server includes means for receiving information on work proposals from users, means for selecting experts with relevant expertise from a data storage device, means for matching experts using artificial intelligence, means for providing a common work environment in which multiple users can cooperate in real time, and means including an emotion understanding engine for analyzing the emotional state of users. This makes it possible to minimize communication obstacles and realize an effective collaborative environment by providing feedback that takes into account the emotional state of users.

[0413] "Different areas of expertise" refers to fields with distinct technical or knowledge systems, encompassing multiple areas, each possessing specific knowledge and skills.

[0414] "User" refers to an individual or group that uses the system to propose projects or engage in collaborative activities.

[0415] A "work proposal" refers to information that includes the project's goals, objectives, and progress plan and intentions, and collaboration proceeds based on this proposal.

[0416] A "specialist" refers to a person who possesses advanced knowledge and skills in a specific area of ​​expertise and who utilizes that knowledge to contribute to a project.

[0417] A "data storage device" refers to an information recording device that stores and saves information about experts and allows it to be retrieved as needed.

[0418] "Artificial intelligence" refers to the technology used to enable computer systems to think like humans and solve problems or make decisions.

[0419] A "shared work environment" refers to a workspace or interface provided for users to collaborate in real time, and includes features such as multilingual support and adjustment functions based on sentiment analysis.

[0420] An "emotion understanding engine" refers to a computer program or process that analyzes data extracted from a user's voice and facial expressions to determine the user's emotional state.

[0421] "Feedback" refers to the responses and guidelines provided by a system based on the user's behavior and emotional state, and is used to facilitate smoother collaboration.

[0422] The server cross-references the work proposal information received from the user with expert information stored in data storage, and uses artificial intelligence to select the most suitable expert. Natural language processing technology and machine learning algorithms are used to analyze the received text data. This method enables accurate expert selection based on the project content. Furthermore, it utilizes an emotion understanding engine to analyze voice and text data acquired during communication, grasping the user's emotional state in real time.

[0423] The terminal visualizes and presents to the user information regarding matching results and emotional states provided by the server. Based on the acquired information, the terminal adjusts the interface's color scheme and layout according to the emotional state, thereby reducing user stress and supporting smooth communication.

[0424] Users enter project proposals using their devices and begin collaborating with matched experts. Throughout the project, feedback provided by the sentiment understanding engine is utilized to maintain engagement among all participants. This improves project efficiency and success rates.

[0425] As a concrete example, a consumer robot installed in a home can analyze conversations between family members using an emotion-understanding engine and provide feedback, such as playing calming music if tension is present, thereby making the living environment more comfortable. In this way, it becomes possible to improve the user experience.

[0426] An example of a prompt is: "Generate prompts for developing an application for a consumer robot that analyzes the user's emotional state and adjusts the dialogue accordingly."

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The server receives work proposals from users. As input, it obtains information about the project's purpose and details, which the user enters via their terminal. This information is received as text data and temporarily stored in a database. The server then processes this data to retrieve it in the correct format.

[0430] Step 2:

[0431] The server analyzes received work proposals using natural language processing techniques. It uses the received text data as input. The text data is tokenized, keywords are extracted, and the server determines which areas of expertise the project content relates to, generating analysis results. The output is data containing the specific keywords and themes analyzed.

[0432] Step 3:

[0433] The server searches for experts with relevant expertise from its data storage based on the analysis results. The keywords and themes extracted in step 2 are provided as input. A database search algorithm is applied to generate a list of relevant experts based on this information. The output is a list of candidate experts.

[0434] Step 4:

[0435] The server uses artificial intelligence to select the most suitable expert for a specific project. The input consists of a list of candidates and each expert's profile data. A machine learning model evaluates the experts' skill sets and historical performance data to rank the most suitable candidates. The output is a final list of matched experts.

[0436] Step 5:

[0437] The terminal receives matching results from the server and presents them visually to the user. It receives matching result data from the server as input. It uses UI components to format the data in a visually easy-to-understand way. The user reviews the list of candidates and makes a selection.

[0438] Step 6:

[0439] The server uses an emotion understanding engine to analyze real-time voice and text data received from the terminal. The input is voice and text data acquired during communication. This data is processed by an emotion analysis algorithm to generate data that determines the user's current emotional state. The output is data indicating the recognized emotional state.

[0440] Step 7:

[0441] The device adjusts the interface's color scheme and layout for the user based on sentiment analysis data. It uses sentiment data obtained from an sentiment understanding engine as input. The device uses dynamic UI components to make the necessary adjustments. The output is the adjusted interface, optimized to reduce user stress.

[0442] Step 8:

[0443] Users leverage feedback provided during project progress to improve the efficiency of collaboration. They receive feedback based on emotional states provided by their devices. Based on this feedback, users adjust their communication methods and project progress. As a result, highly engaged collaboration is achieved.

[0444] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0445] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0446] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0447] [Third Embodiment]

[0448] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0449] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0450] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0451] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0452] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0453] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0454] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0455] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0456] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0457] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0458] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0459] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0460] This invention provides a platform for users with diverse areas of expertise to collaborate and advance projects. The system includes functions for selecting appropriate experts based on user proposals and effectively matching them. It also provides a multilingual collaborative work environment to facilitate real-time communication.

[0461] Server operation

[0462] The server receives information from the user regarding project proposals. This information includes the project's objectives, required expertise, and expected outcomes. Based on the received information, the server extracts experts with relevant expertise from its database. Next, the server uses artificial intelligence to match the candidate experts with the project's needs in the most appropriate way. In this process, natural language processing and machine learning algorithms are used to analyze each expert's profile in detail. The resulting matching information is then presented to the user.

[0463] Terminal operation

[0464] The terminal receives matching results from the server and provides an interface that visually presents them to the user. Users can review detailed profiles of the presented experts and select project members they wish to participate in. The terminal also includes features such as chat, video conferencing, and document sharing to enable real-time collaboration. In particular, the multilingual real-time translation function facilitates smooth communication between users speaking different languages.

[0465] User actions

[0466] Users input information via their device to plan projects and find the necessary experts. This includes detailed project requirements and schedules. After reviewing the experts and their profiles displayed for each proposal, users select the required members and join the collaborative environment. This allows users to track project progress in real time and make adjustments as needed.

[0467] Specific example

[0468] For example, suppose a user working in the research and development department of a pharmaceutical company starts a new drug development project. The user uses the platform to find experts in chemistry, bioinformatics, and drug regulatory affairs necessary for this project. The server analyzes the project requirements and matches the user with the most suitable experts via AI. The user can then leverage the real-time translation function to communicate smoothly with international experts and proceed with development.

[0469] Thus, this invention presents a concrete model for enabling experts from different fields to collaborate efficiently and smoothly advance projects.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] The user creates a project proposal using a terminal, entering detailed information about the project's objectives, required expertise, and expected outcomes. This information is then sent from the terminal to the server.

[0473] Step 2:

[0474] The server analyzes project proposal information received from users. Natural language processing is used for the analysis to extract relevant keywords and technical terms from the text and identify the specialized fields required for the project.

[0475] Step 3:

[0476] The server searches the database for relevant expert profiles based on the extracted expertise information. A dedicated search algorithm is then used to generate a list of appropriate experts.

[0477] Step 4:

[0478] The server optimizes the list of experts obtained using artificial intelligence. It uses machine learning algorithms to calculate the degree of match between project proposals and each expert's profile, selecting the expert with the highest score.

[0479] Step 5:

[0480] The terminal visualizes the matching results received from the server for the user. The user can review the profile information of the presented experts and select which experts to include in the project.

[0481] Step 6:

[0482] The server determines the project team based on user selection and creates a dedicated real-time collaborative environment for the project. This environment includes chat, video conferencing, and multilingual translation capabilities.

[0483] Step 7:

[0484] Users can communicate within the project team via their devices and utilize real-time translation features to smoothly communicate with team members who speak different languages, enabling them to advance the project.

[0485] (Example 1)

[0486] Next, we will describe Example 1. 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."

[0487] In modern technology projects, the selection and rapid matching of appropriate experts are crucial for efficient collaboration among specialists with diverse technical backgrounds. However, traditional systems often lack sufficient expert profile analysis and struggle with real-time communication between experts who speak different languages. This situation can lead to project delays and the risk of inappropriate expert selection.

[0488] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0489] In this invention, the server includes means for receiving information regarding a plan proposal from a user, means for selecting experts with relevant technical fields from an information storage device based on the plan proposal, and means for utilizing intelligent functions to match the selected experts. This enables the rapid and accurate selection and matching of experts in different technical fields, and further enables immediate communication in a multilingual environment.

[0490] A "platform" is a system that serves as a foundation for users with different technical skills to collaborate.

[0491] "Users" refers to individual participants who submit project proposals through the platform and input information for selecting experts.

[0492] A "project proposal" is a document that includes the project's objectives, requirements, and necessary expertise, and serves as the criteria for selecting experts on the platform.

[0493] An "information storage device" is a digital storage system used to retain expert profile information and past achievements.

[0494] "Intelligent function" refers to the technology that applies computational techniques to analyze the profiles of experts and make appropriate selections.

[0495] A "collaborative work environment" is a form of workspace that provides a space where multiple users can work on a project in real time.

[0496] "Multilingual translation functionality" is a language conversion technology that enables smooth communication between users who speak different languages.

[0497] This invention provides a system that offers a platform for users with different technical skills to collaborate and advance projects. This system utilizes the following hardware and software to provide expert selection and a collaborative work environment.

[0498] First, the server receives information about the project proposal from the user. This information is typically sent via an API in a data format such as JSON and parsed using a web framework such as Flask or Django. This information includes the project's objectives, required technical fields, and expected outcomes.

[0499] Next, the server uses an information storage device (e.g., PostgreSQL, MongoDB) to extract experts with relevant technical skills based on selection criteria. This process involves quickly searching existing information in the database to identify experts.

[0500] Furthermore, intelligent functions are used to optimally match selected experts. These functions leverage language processing technologies (e.g., spaCy, NLTK) and learning algorithms (e.g., TensorFlow, PyTorch) to analyze each expert's profile in detail. This analysis ensures optimal matching, and the results are presented to the user.

[0501] The terminal utilizes front-end technologies such as React and Vue.js to visually present the matching results received from the server to the user. Furthermore, the terminal provides a collaborative work environment combining WebRTC and other communication technologies to enable immediate user cooperation, and also integrates multilingual translation functionality.

[0502] Users can review the profiles of presented experts through their devices and select members to participate in the project. During this process, they can directly communicate with the selected members to adjust the project schedule and division of roles. Furthermore, the ability to communicate immediately allows for continuous monitoring of the project's progress and course corrections as needed.

[0503] As a concrete example, consider a case where a researcher launches a new drug development project. This researcher uses the platform to find experts in chemistry, bioinformatics, and pharmaceutical regulatory affairs necessary for the project. The server analyzes the researcher's proposed plan and matches them with the most suitable experts. The researcher can utilize the instant translation function to communicate smoothly with multinational experts.

[0504] An example of a prompt statement is: "We need experts in chemistry, bioinformatics, and pharmaceutical regulations for a new drug development project. The project objectives and timeframe are as follows..." In this way, users can use prompt statements to appropriately find the necessary experts and maximize the efficiency of the project.

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The server receives information about project proposals from users. This input includes the project objectives, required technical fields, and expected outcomes. The received data is sent via the API in JSON format and parsed using frameworks such as Flask or Django. The parsing results identify the project requirements, which are then output as foundational data for selecting experts in the next step.

[0508] Step 2:

[0509] The server selects relevant experts from its information storage system based on the proposed plan. This step uses a database management system (e.g., PostgreSQL, MongoDB) to search for experts matching the received project requirements. Queries are written based on technical areas and expertise, and an initial list of selected experts is output as a response.

[0510] Step 3:

[0511] The server utilizes intelligent functions to analyze the profiles of selected experts. The list of experts obtained in step 2 is used as input data. This analysis employs natural language processing tools (e.g., spaCy, NLTK) and machine learning algorithms (e.g., TensorFlow, PyTorch). These are used to evaluate each expert's expertise and past achievements, select the most suitable members for the project, and output the matching results.

[0512] Step 4:

[0513] The terminal receives the matching results from the server and presents them visually to the user. The terminal has an interface developed using React and Vue.js, displaying the profile information of the selected experts to the user. Based on the presented profiles, the user can review detailed information and proceed with selecting project members. The user's selection results are output as input data for the next step.

[0514] Step 5:

[0515] Users review the profiles of selected experts on their devices and choose the members to participate in the project. Through the device's GUI, users compare each expert's experience and skill set to determine the most suitable members. As a result, a list of members capable of real-time communication within the platform is output.

[0516] Step 6:

[0517] The terminal provides a collaborative environment that enables selected members and users to work together in real time. Key features include video conferencing using WebRTC and other communication technologies, chat, and document sharing. Furthermore, it integrates multilingual translation capabilities, enabling smooth communication between users who speak different languages. Users can leverage this environment to make immediate adjustments and provide feedback on ongoing projects.

[0518] (Application Example 1)

[0519] Next, we will explain Application Example 1. In the following explanation, 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."

[0520] When experts from different fields collaborate, there is a lack of an environment that effectively matches experts and facilitates smooth communication through multilingual support. Furthermore, in projects such as urban function improvement projects, efficient matching of experts and management and sharing of project progress are difficult.

[0521] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0522] In this invention, the server includes means for receiving information on project proposals from users, means for selecting experts with relevant expertise from a database, and means for using artificial intelligence to match the selected experts. This enables real-time collaboration and efficient project management among experts from different fields.

[0523] "Different fields of expertise" refers to a variety of technical and academic fields, such as information technology, urban planning, and environmental science.

[0524] A "user" refers to an individual or group that proposes a project and seeks experts from different fields.

[0525] A "project proposal" is information that outlines the activities and processes planned to achieve a specific objective.

[0526] An "expert" is an individual who possesses advanced knowledge and experience in a specific field.

[0527] A "database" refers to a collection of information that systematically stores profiles and related information about experts.

[0528] "Artificial intelligence" is a technology in which machines imitate human intelligence, and in particular, it is used to select experts through natural language processing and machine learning.

[0529] "Matching" is the process of selecting and appropriately connecting experts who are suitable for the project's requirements.

[0530] "Multilingual support" refers to a function that enables smooth communication between individuals who use different languages.

[0531] A "collaborative work environment" is a system that provides a virtual workspace where multiple users can work together efficiently.

[0532] A "city function improvement project" refers to a project related to smart cities that aims to improve the urban environment.

[0533] "Progress tracking" refers to the activity of monitoring the progress of a project and making necessary adjustments.

[0534] "Shared resources" refer to data, documents, deliverables, etc., related to a project, and are made accessible to all stakeholders.

[0535] The system for implementing this invention effectively matches experts with different fields of expertise and provides a multilingual collaborative work environment.

[0536] The server receives information about project proposals from users. The Flask framework, written in Python, functions as the server's API, collecting data on project objectives and required skills. The database also stores information on multiple experts, and artificial intelligence is used to analyze these profiles and select the most suitable expert for the project. Natural language processing and machine learning algorithms utilizing TensorFlow are used to evaluate the experts' skills and experience.

[0537] On the device, an application developed using React Native runs, visually presenting matching results to the user. This application includes features such as chat, video conferencing, and document sharing, and utilizes real-time multilingual translation capabilities via the Google Translate API to facilitate smooth communication between users.

[0538] Through this interface, users can plan urban function improvement projects, track their progress, and manage shared resources. This system facilitates the efficient execution of urban development projects.

[0539] As a concrete example, consider a city planning a project to implement a smart transportation system. The user would use this system to efficiently match and select the necessary experts in transportation engineering, environmental science, and IT infrastructure, thereby supporting the progress of the project.

[0540] Example prompts for generative AI models:

[0541] "You are planning a smart city traffic management project. This project requires experts in traffic engineering, environmental science, and IT infrastructure. We would like to utilize a platform that can efficiently match these experts."

[0542] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0543] Step 1:

[0544] The server receives project proposal information from the user. The user inputs the project objectives, required areas of expertise, expected outcomes, etc. The server receives this input data and prepares to access the database. At this stage, the proposal is saved and the initial data is organized.

[0545] Step 2:

[0546] The server selects experts with relevant expertise from its database based on the received project proposal information. It extracts a list of experts by executing database queries. The input is the skill set required for the project, and the output is a list of candidate experts who match that skill set.

[0547] Step 3:

[0548] The server uses artificial intelligence to analyze the profiles of selected experts. Specifically, it leverages natural language processing and machine learning algorithms using TensorFlow. It receives profile data as input and analyzes and evaluates their expertise and skill levels. The output is a priority list of experts best suited to the project.

[0549] Step 4:

[0550] The server generates matching results and sends them to the terminal. Data processing involves assigning rankings and suitability scores to experts from a list of experts and converting them into a format that can be presented to the user.

[0551] Step 5:

[0552] The terminal visually displays the matching results received from the server to the user. Based on this information, the user proceeds with the process of selecting appropriate experts as project members. The input is data from the server, and the output is a list of experts that the user can select.

[0553] Step 6:

[0554] The device provides multilingual chat and video conferencing capabilities to enable real-time communication with experts selected by the user. Using the Google Translate API, input messages are automatically translated into the required language. The output consists of translated messages and conversation transcripts.

[0555] Step 7:

[0556] Users track project progress via their devices and adjust project parameters as needed. This phase supports decision-making based on the display and analysis of progress data. The input is project progress data, and the output is the adjusted project plan.

[0557] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0558] This invention is a system that combines a platform for users with different areas of expertise to collaborate efficiently with an emotion engine that recognizes users' emotions. In addition to providing a collaborative work environment, this system aims to improve the quality of communication by recognizing users' emotional states in real time, as well as providing project proposals, expert matching, and collaborative work environments.

[0559] Server operation

[0560] The server first receives project proposal information from the user and analyzes its content using natural language processing and machine learning. Based on this analysis, it searches for appropriate experts in the database and uses artificial intelligence to select the expert best suited to the project. Simultaneously, the server analyzes voice and text data acquired during communication with the user using an emotion engine to determine the user's emotional state. The data obtained from emotion recognition is used to adjust the interface of the collaborative work environment.

[0561] Terminal operation

[0562] The terminal visualizes matching results and sentiment recognition information received from the server for the user. The user can review the presented experts and select the best members for the project. Furthermore, the terminal provides real-time sentiment-based feedback to facilitate smooth communication. If the user's emotions are recognized, the terminal changes the interface's color scheme and layout as needed to make adjustments that reduce stress.

[0563] User actions

[0564] Users input project proposals via their devices, and experts are matched based on these proposals. Users can then check the emotional state of each member before beginning collaboration with the matched experts. Throughout the project, users utilize feedback provided by the emotional engine to maintain engagement among all project participants. This improves communication efficiency and increases the project's success rate.

[0565] Specific example

[0566] A company plans a new product development project and will use this system. The user inputs project details as a proposal, and the server uses this information to match appropriate marketing, design, and engineering experts. During expert meetings, the emotion engine analyzes the participants' emotions and adjusts the environment in real time, such as changing the interface to calmer colors if tension is high. This allows participants to exchange ideas in a more relaxed state and fosters creative ideas.

[0567] The following describes the processing flow.

[0568] Step 1:

[0569] The user enters detailed project proposals via a terminal. This includes the project name, objectives, required expertise, and expected outcomes. This data is then transmitted from the terminal to the server.

[0570] Step 2:

[0571] The server analyzes project proposal information received from users. Using natural language processing, it extracts keywords and technical terms from the proposal and identifies the specialized fields required for the project.

[0572] Step 3:

[0573] The server searches the database for relevant expert profiles based on the analysis results. Using a dedicated algorithm that evaluates the skill information and past project history contained in each profile, it generates a list of the most suitable experts.

[0574] Step 4:

[0575] The server utilizes machine learning algorithms to calculate the degree of match and optimize the list of experts. This process selects the expert best suited to the project's needs.

[0576] Step 5:

[0577] The server analyzes voice and text data using an emotion engine to determine the user's emotional state. Simultaneously, it monitors emotional changes within the communication in real time.

[0578] Step 6:

[0579] The terminal presents the user with matching results and sentiment recognition information obtained from the server. The user can then review the detailed profiles of the presented experts and select the members who will join the project.

[0580] Step 7:

[0581] The device will create a real-time collaborative environment with selected team members. This environment will include chat, video conferencing, multilingual translation, and real-time sentiment feedback.

[0582] Step 8:

[0583] Users communicate through their devices based on emotional feedback and advance the project by adjusting the interface as needed. This adjustment includes changing the screen's color tone and the priority of information presentation.

[0584] The above describes the processing steps of a platform that uses an emotion engine.

[0585] (Example 2)

[0586] Next, we will describe Example 2. 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."

[0587] In collaborations between engineers from different fields, inefficiencies can arise due to emotional and communication mismatches. In particular, when using different languages, misunderstandings and communication breakdowns are more likely, leading to a decrease in project success rates. Solutions are needed to address this challenge and improve the quality of collaboration.

[0588] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0589] In this invention, the server includes means for receiving information about project proposals from users, means for selecting engineers with relevant expertise from an information set, means for using an emotion engine to analyze the user's emotional state, and means for adjusting the display of the collaborative work environment based on the emotion data. This enables real-time and effective collaboration among engineers and improves communication that transcends emotional and language barriers.

[0590] A "user" refers to an individual or organization that uses the system to propose projects and collaborate with engineers.

[0591] A "project proposal" is information entered by the user through the system, describing the specific tasks and objectives of the collaborative project.

[0592] "Area of ​​expertise" refers to the field of specialized knowledge and skills possessed by an engineer, and serves as a criterion for selecting relevant engineers according to the content of the project proposal.

[0593] An "engineer" refers to an individual who possesses specialized knowledge and skills in a specific field and is selected based on their project proposal.

[0594] An "information set" refers to a database or information resource about engineers, a collection of data that holds engineers' profiles and skill information.

[0595] "Intelligent functions" refer to artificial intelligence technologies used to effectively combine selected engineers and optimize collaboration with users.

[0596] An "emotion engine" refers to a technology that analyzes a user's emotional state and provides it as data, enabling real-time emotion recognition.

[0597] A "collaborative work environment" refers to a workspace where multiple users can cooperate in real time, supporting communication and enabling the efficient execution of projects.

[0598] "Display adjustment" refers to changing the appearance and layout of the user interface based on emotional data, and is an operation performed to improve user comfort and reduce stress.

[0599] This invention is a platform for engineers from different fields to collaborate efficiently, incorporating an emotion engine that recognizes user emotions. This enables comprehensive support, from project proposals and engineer matching to the provision of a collaborative work environment.

[0600] The server receives project proposal information from users and analyzes its content using natural language processing and training algorithms. Specifically, Python's natural language processing libraries and related libraries are applied. Based on the analysis results, the server searches for and selects appropriate engineers from the information set. In this process, artificial intelligence is used to determine the most suitable engineer. Simultaneously, the server analyzes the user's voice and text data using an emotion engine and quantifies their emotional state. This data is used to optimize the display of the collaborative work environment.

[0601] The terminal visualizes the matching results and emotion recognition information of engineers received from the server for the user. The user interface is built using web technologies, particularly frameworks such as React.js. Users can review the presented engineers and select the most suitable collaborators. Furthermore, the terminal provides real-time emotion-based feedback to support smooth communication. If the emotion is negative, the UI's colors and layout are changed to reduce stress.

[0602] Users can input project proposals via their devices and view the results of engineer matching performed on the server side. Based on this information, users can check the emotional state of each member before the project starts and prepare the optimal collaborative structure. During the project, users can utilize the feedback obtained through the emotional engine to maintain and improve team member engagement.

[0603] For example, if an organization plans to develop a new product, the server matches them with engineers who possess the appropriate expertise after they input the project details. During a meeting, the emotion engine analyzes participants' facial expressions and voices, and softens the UI's color scheme if tension is detected. This promotes relaxation among participants and enables more creative discussion.

[0604] An example of a prompt to input into the generating AI model is as follows: "Please tell me how to select the best engineers for a new product development project and build a system that analyzes the emotions of meeting participants and adjusts the UI accordingly."

[0605] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0606] Step 1:

[0607] The server receives project proposal information from the user. As input, it receives text data entered by the user via a terminal. This information includes a summary of the proposal and the required technical fields. The received text data is prepared for natural language processing.

[0608] Step 2:

[0609] The server analyzes the project proposal using natural language processing (NLP) techniques. Specifically, it uses Python's natural language processing library to tokenize, tag, and extract keywords from the text data. The input is the text data received in step 1, and the output is a keyword list that describes the proposal. Based on these analysis results, the server identifies the relevant technical fields.

[0610] Step 3:

[0611] The server uses the analysis results to select appropriate engineers from the information set. It applies a machine learning algorithm (e.g., using Scikit-learn) to search for experts in relevant fields from an engineer database. The input is the keyword list from step 2, and the output is a list of suitable engineer candidates. This list provides engineers who match the project requirements, scored accordingly.

[0612] Step 4:

[0613] The terminal visualizes the engineer matching results received from the server for the user. A UI is built using web technologies to display a list of candidate engineers on the screen. The input is the list of candidate engineers generated in step 3, and the output is the visual information displayed on the user's screen. Based on this list, the user can select the most suitable collaborators for their project.

[0614] Step 5:

[0615] The server transmits user communication data to the emotion engine in real time and analyzes the emotional state. It takes in voice and text data, applies an emotion recognition algorithm, and quantifies emotions such as joy, anger, sadness, and happiness. The input is user voice and text data acquired in real time, and the output is numerical data indicating the emotional state.

[0616] Step 6:

[0617] The device adjusts the display of the collaborative work environment based on emotional data. It changes the UI's color scheme and layout as needed to reduce user stress. The input is the emotional state data generated in step 5, and the output is the modified UI. This adjustment allows users to collaborate in a more comfortable environment.

[0618] (Application Example 2)

[0619] Next, we will explain application example 2. In the following explanation, 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."

[0620] In collaborations between users with different areas of expertise, emotional disagreements and communication breakdowns are likely to occur, potentially impacting project progress. Furthermore, maintaining smooth communication is difficult in multilingual environments and across different cultural backgrounds. There is a need to improve these situations and provide an efficient and smooth collaborative environment.

[0621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0622] In this invention, the server includes means for receiving information on work proposals from users, means for selecting experts with relevant expertise from a data storage device, means for matching experts using artificial intelligence, means for providing a common work environment in which multiple users can cooperate in real time, and means including an emotion understanding engine for analyzing the emotional state of users. This makes it possible to minimize communication obstacles and realize an effective collaborative environment by providing feedback that takes into account the emotional state of users.

[0623] "Different areas of expertise" refers to fields with distinct technical or knowledge systems, encompassing multiple areas, each possessing specific knowledge and skills.

[0624] "User" refers to an individual or group that uses the system to propose projects or engage in collaborative activities.

[0625] A "work proposal" refers to information that includes the project's goals, objectives, and progress plan and intentions, and collaboration proceeds based on this proposal.

[0626] A "specialist" refers to a person who possesses advanced knowledge and skills in a specific area of ​​expertise and who utilizes that knowledge to contribute to a project.

[0627] A "data storage device" refers to an information recording device that stores and saves information about experts and allows it to be retrieved as needed.

[0628] "Artificial intelligence" refers to the technology used to enable computer systems to think like humans and solve problems or make decisions.

[0629] A "shared work environment" refers to a workspace or interface provided for users to collaborate in real time, and includes features such as multilingual support and adjustment functions based on sentiment analysis.

[0630] An "emotion understanding engine" refers to a computer program or process that analyzes data extracted from a user's voice and facial expressions to determine the user's emotional state.

[0631] "Feedback" refers to the responses and guidelines provided by a system based on the user's behavior and emotional state, and is used to facilitate smoother collaboration.

[0632] The server cross-references the work proposal information received from the user with expert information stored in data storage, and uses artificial intelligence to select the most suitable expert. Natural language processing technology and machine learning algorithms are used to analyze the received text data. This method enables accurate expert selection based on the project content. Furthermore, it utilizes an emotion understanding engine to analyze voice and text data acquired during communication, grasping the user's emotional state in real time.

[0633] The terminal visualizes and presents to the user information regarding matching results and emotional states provided by the server. Based on the acquired information, the terminal adjusts the interface's color scheme and layout according to the emotional state, thereby reducing user stress and supporting smooth communication.

[0634] Users enter project proposals using their devices and begin collaborating with matched experts. Throughout the project, feedback provided by the sentiment understanding engine is utilized to maintain engagement among all participants. This improves project efficiency and success rates.

[0635] As a concrete example, a consumer robot installed in a home can analyze conversations between family members using an emotion-understanding engine and provide feedback, such as playing calming music if tension is present, thereby making the living environment more comfortable. In this way, it becomes possible to improve the user experience.

[0636] An example of a prompt is: "Generate prompts for developing an application for a consumer robot that analyzes the user's emotional state and adjusts the dialogue accordingly."

[0637] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0638] Step 1:

[0639] The server receives work proposals from users. As input, it obtains information about the project's purpose and details, which the user enters via their terminal. This information is received as text data and temporarily stored in a database. The server then processes this data to retrieve it in the correct format.

[0640] Step 2:

[0641] The server analyzes received work proposals using natural language processing techniques. It uses the received text data as input. The text data is tokenized, keywords are extracted, and the server determines which areas of expertise the project content relates to, generating analysis results. The output is data containing the specific keywords and themes analyzed.

[0642] Step 3:

[0643] The server searches for experts with relevant expertise from its data storage based on the analysis results. The keywords and themes extracted in step 2 are provided as input. A database search algorithm is applied to generate a list of relevant experts based on this information. The output is a list of candidate experts.

[0644] Step 4:

[0645] The server uses artificial intelligence to select the most suitable expert for a specific project. The input consists of a list of candidates and each expert's profile data. A machine learning model evaluates the experts' skill sets and historical performance data to rank the most suitable candidates. The output is a final list of matched experts.

[0646] Step 5:

[0647] The terminal receives matching results from the server and presents them visually to the user. It receives matching result data from the server as input. It uses UI components to format the data in a visually easy-to-understand way. The user reviews the list of candidates and makes a selection.

[0648] Step 6:

[0649] The server uses an emotion understanding engine to analyze real-time voice and text data received from the terminal. The input is voice and text data acquired during communication. This data is processed by an emotion analysis algorithm to generate data that determines the user's current emotional state. The output is data indicating the recognized emotional state.

[0650] Step 7:

[0651] The device adjusts the interface's color scheme and layout for the user based on sentiment analysis data. It uses sentiment data obtained from an sentiment understanding engine as input. The device uses dynamic UI components to make the necessary adjustments. The output is the adjusted interface, optimized to reduce user stress.

[0652] Step 8:

[0653] Users leverage feedback provided during project progress to improve the efficiency of collaboration. They receive feedback based on emotional states provided by their devices. Based on this feedback, users adjust their communication methods and project progress. As a result, highly engaged collaboration is achieved.

[0654] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0655] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0656] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0657] [Fourth Embodiment]

[0658] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0659] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0660] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0661] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0662] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0663] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0664] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0665] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0666] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0667] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0668] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0669] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0670] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0671] This invention provides a platform for users with diverse areas of expertise to collaborate and advance projects. The system includes functions for selecting appropriate experts based on user proposals and effectively matching them. It also provides a multilingual collaborative work environment to facilitate real-time communication.

[0672] Server operation

[0673] The server receives information from the user regarding project proposals. This information includes the project's objectives, required expertise, and expected outcomes. Based on the received information, the server extracts experts with relevant expertise from its database. Next, the server uses artificial intelligence to match the candidate experts with the project's needs in the most appropriate way. In this process, natural language processing and machine learning algorithms are used to analyze each expert's profile in detail. The resulting matching information is then presented to the user.

[0674] Terminal operation

[0675] The terminal receives matching results from the server and provides an interface that visually presents them to the user. Users can review detailed profiles of the presented experts and select project members they wish to participate in. The terminal also includes features such as chat, video conferencing, and document sharing to enable real-time collaboration. In particular, the multilingual real-time translation function facilitates smooth communication between users speaking different languages.

[0676] User actions

[0677] Users input information via their device to plan projects and find the necessary experts. This includes detailed project requirements and schedules. After reviewing the experts and their profiles displayed for each proposal, users select the required members and join the collaborative environment. This allows users to track project progress in real time and make adjustments as needed.

[0678] Specific example

[0679] For example, suppose a user working in the research and development department of a pharmaceutical company starts a new drug development project. The user uses the platform to find experts in chemistry, bioinformatics, and drug regulatory affairs necessary for this project. The server analyzes the project requirements and matches the user with the most suitable experts via AI. The user can then leverage the real-time translation function to communicate smoothly with international experts and proceed with development.

[0680] Thus, this invention presents a concrete model for enabling experts from different fields to collaborate efficiently and smoothly advance projects.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The user creates a project proposal using a terminal, entering detailed information about the project's objectives, required expertise, and expected outcomes. This information is then sent from the terminal to the server.

[0684] Step 2:

[0685] The server analyzes project proposal information received from users. Natural language processing is used for the analysis to extract relevant keywords and technical terms from the text and identify the specialized fields required for the project.

[0686] Step 3:

[0687] The server searches the database for relevant expert profiles based on the extracted expertise information. A dedicated search algorithm is then used to generate a list of appropriate experts.

[0688] Step 4:

[0689] The server optimizes the list of experts obtained using artificial intelligence. It uses machine learning algorithms to calculate the degree of match between project proposals and each expert's profile, selecting the expert with the highest score.

[0690] Step 5:

[0691] The terminal visualizes the matching results received from the server for the user. The user can review the profile information of the presented experts and select which experts to include in the project.

[0692] Step 6:

[0693] The server determines the project team based on user selection and creates a dedicated real-time collaborative environment for the project. This environment includes chat, video conferencing, and multilingual translation capabilities.

[0694] Step 7:

[0695] Users can communicate within the project team via their devices and utilize real-time translation features to smoothly communicate with team members who speak different languages, enabling them to advance the project.

[0696] (Example 1)

[0697] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In modern technology projects, the selection and rapid matching of appropriate experts are crucial for efficient collaboration among specialists with diverse technical backgrounds. However, traditional systems often lack sufficient expert profile analysis and struggle with real-time communication between experts who speak different languages. This situation can lead to project delays and the risk of inappropriate expert selection.

[0699] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0700] In this invention, the server includes means for receiving information regarding a plan proposal from a user, means for selecting experts with relevant technical fields from an information storage device based on the plan proposal, and means for utilizing intelligent functions to match the selected experts. This enables the rapid and accurate selection and matching of experts in different technical fields, and further enables immediate communication in a multilingual environment.

[0701] A "platform" is a system that serves as a foundation for users with different technical skills to collaborate.

[0702] "Users" refers to individual participants who submit project proposals through the platform and input information for selecting experts.

[0703] A "project proposal" is a document that includes the project's objectives, requirements, and necessary expertise, and serves as the criteria for selecting experts on the platform.

[0704] An "information storage device" is a digital storage system used to retain expert profile information and past achievements.

[0705] "Intelligent function" refers to the technology that applies computational techniques to analyze the profiles of experts and make appropriate selections.

[0706] A "collaborative work environment" is a form of workspace that provides a space where multiple users can work on a project in real time.

[0707] "Multilingual translation functionality" is a language conversion technology that enables smooth communication between users who speak different languages.

[0708] This invention provides a system that offers a platform for users with different technical skills to collaborate and advance projects. This system utilizes the following hardware and software to provide expert selection and a collaborative work environment.

[0709] First, the server receives information about the project proposal from the user. This information is typically sent via an API in a data format such as JSON and parsed using a web framework such as Flask or Django. This information includes the project's objectives, required technical fields, and expected outcomes.

[0710] Next, the server uses an information storage device (e.g., PostgreSQL, MongoDB) to extract experts with relevant technical skills based on selection criteria. This process involves quickly searching existing information in the database to identify experts.

[0711] Furthermore, intelligent functions are used to optimally match selected experts. These functions leverage language processing technologies (e.g., spaCy, NLTK) and learning algorithms (e.g., TensorFlow, PyTorch) to analyze each expert's profile in detail. This analysis ensures optimal matching, and the results are presented to the user.

[0712] The terminal utilizes front-end technologies such as React and Vue.js to visually present the matching results received from the server to the user. Furthermore, the terminal provides a collaborative work environment combining WebRTC and other communication technologies to enable immediate user cooperation, and also integrates multilingual translation functionality.

[0713] Users can review the profiles of presented experts through their devices and select members to participate in the project. During this process, they can directly communicate with the selected members to adjust the project schedule and division of roles. Furthermore, the ability to communicate immediately allows for continuous monitoring of the project's progress and course corrections as needed.

[0714] As a concrete example, consider a case where a researcher launches a new drug development project. This researcher uses the platform to find experts in chemistry, bioinformatics, and pharmaceutical regulatory affairs necessary for the project. The server analyzes the researcher's proposed plan and matches them with the most suitable experts. The researcher can utilize the instant translation function to communicate smoothly with multinational experts.

[0715] An example of a prompt statement is: "We need experts in chemistry, bioinformatics, and pharmaceutical regulations for a new drug development project. The project objectives and timeframe are as follows..." In this way, users can use prompt statements to appropriately find the necessary experts and maximize the efficiency of the project.

[0716] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0717] Step 1:

[0718] The server receives information about project proposals from users. This input includes the project objectives, required technical fields, and expected outcomes. The received data is sent via the API in JSON format and parsed using frameworks such as Flask or Django. The parsing results identify the project requirements, which are then output as foundational data for selecting experts in the next step.

[0719] Step 2:

[0720] The server selects relevant experts from its information storage system based on the proposed plan. This step uses a database management system (e.g., PostgreSQL, MongoDB) to search for experts matching the received project requirements. Queries are written based on technical areas and expertise, and an initial list of selected experts is output as a response.

[0721] Step 3:

[0722] The server utilizes intelligent functions to analyze the profiles of selected experts. The list of experts obtained in step 2 is used as input data. This analysis employs natural language processing tools (e.g., spaCy, NLTK) and machine learning algorithms (e.g., TensorFlow, PyTorch). These are used to evaluate each expert's expertise and past achievements, select the most suitable members for the project, and output the matching results.

[0723] Step 4:

[0724] The terminal receives the matching results from the server and presents them visually to the user. The terminal has an interface developed using React and Vue.js, displaying the profile information of the selected experts to the user. Based on the presented profiles, the user can review detailed information and proceed with selecting project members. The user's selection results are output as input data for the next step.

[0725] Step 5:

[0726] Users review the profiles of selected experts on their devices and choose the members to participate in the project. Through the device's GUI, users compare each expert's experience and skill set to determine the most suitable members. As a result, a list of members capable of real-time communication within the platform is output.

[0727] Step 6:

[0728] The terminal provides a collaborative environment that enables selected members and users to work together in real time. Key features include video conferencing using WebRTC and other communication technologies, chat, and document sharing. Furthermore, it integrates multilingual translation capabilities, enabling smooth communication between users who speak different languages. Users can leverage this environment to make immediate adjustments and provide feedback on ongoing projects.

[0729] (Application Example 1)

[0730] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0731] When experts from different fields collaborate, there is a lack of an environment that effectively matches experts and facilitates smooth communication through multilingual support. Furthermore, in projects such as urban function improvement projects, efficient matching of experts and management and sharing of project progress are difficult.

[0732] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0733] In this invention, the server includes means for receiving information on project proposals from users, means for selecting experts with relevant expertise from a database, and means for using artificial intelligence to match the selected experts. This enables real-time collaboration and efficient project management among experts from different fields.

[0734] "Different fields of expertise" refers to a variety of technical and academic fields, such as information technology, urban planning, and environmental science.

[0735] A "user" refers to an individual or group that proposes a project and seeks experts from different fields.

[0736] A "project proposal" is information that outlines the activities and processes planned to achieve a specific objective.

[0737] An "expert" is an individual who possesses advanced knowledge and experience in a specific field.

[0738] A "database" refers to a collection of information that systematically stores profiles and related information about experts.

[0739] "Artificial intelligence" is a technology in which machines imitate human intelligence, and in particular, it is used to select experts through natural language processing and machine learning.

[0740] "Matching" is the process of selecting and appropriately connecting experts who are suitable for the project's requirements.

[0741] "Multilingual support" refers to a function that enables smooth communication between individuals who use different languages.

[0742] A "collaborative work environment" is a system that provides a virtual workspace where multiple users can work together efficiently.

[0743] A "city function improvement project" refers to a project related to smart cities that aims to improve the urban environment.

[0744] "Progress tracking" refers to the activity of monitoring the progress of a project and making necessary adjustments.

[0745] "Shared resources" refer to data, documents, deliverables, etc., related to a project, and are made accessible to all stakeholders.

[0746] The system for implementing this invention effectively matches experts with different fields of expertise and provides a multilingual collaborative work environment.

[0747] The server receives information about project proposals from users. The Flask framework, written in Python, functions as the server's API, collecting data on project objectives and required skills. The database also stores information on multiple experts, and artificial intelligence is used to analyze these profiles and select the most suitable expert for the project. Natural language processing and machine learning algorithms utilizing TensorFlow are used to evaluate the experts' skills and experience.

[0748] On the device, an application developed using React Native runs, visually presenting matching results to the user. This application includes features such as chat, video conferencing, and document sharing, and utilizes real-time multilingual translation capabilities via the Google Translate API to facilitate smooth communication between users.

[0749] Through this interface, users can plan urban function improvement projects, track their progress, and manage shared resources. This system facilitates the efficient execution of urban development projects.

[0750] As a concrete example, consider a city planning a project to implement a smart transportation system. The user would use this system to efficiently match and select the necessary experts in transportation engineering, environmental science, and IT infrastructure, thereby supporting the progress of the project.

[0751] Example prompts for generative AI models:

[0752] "You are planning a smart city traffic management project. This project requires experts in traffic engineering, environmental science, and IT infrastructure. We would like to utilize a platform that can efficiently match these experts."

[0753] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0754] Step 1:

[0755] The server receives project proposal information from the user. The user inputs the project objectives, required areas of expertise, expected outcomes, etc. The server receives this input data and prepares to access the database. At this stage, the proposal is saved and the initial data is organized.

[0756] Step 2:

[0757] The server selects experts with relevant expertise from its database based on the received project proposal information. It extracts a list of experts by executing database queries. The input is the skill set required for the project, and the output is a list of candidate experts who match that skill set.

[0758] Step 3:

[0759] The server uses artificial intelligence to analyze the profiles of selected experts. Specifically, it leverages natural language processing and machine learning algorithms using TensorFlow. It receives profile data as input and analyzes and evaluates their expertise and skill levels. The output is a priority list of experts best suited to the project.

[0760] Step 4:

[0761] The server generates matching results and sends them to the terminal. Data processing involves assigning rankings and suitability scores to experts from a list of experts and converting them into a format that can be presented to the user.

[0762] Step 5:

[0763] The terminal visually displays the matching results received from the server to the user. Based on this information, the user proceeds with the process of selecting appropriate experts as project members. The input is data from the server, and the output is a list of experts that the user can select.

[0764] Step 6:

[0765] The device provides multilingual chat and video conferencing capabilities to enable real-time communication with experts selected by the user. Using the Google Translate API, input messages are automatically translated into the required language. The output consists of translated messages and conversation transcripts.

[0766] Step 7:

[0767] Users track project progress via their devices and adjust project parameters as needed. This phase supports decision-making based on the display and analysis of progress data. The input is project progress data, and the output is the adjusted project plan.

[0768] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0769] This invention is a system that combines a platform for users with different areas of expertise to collaborate efficiently with an emotion engine that recognizes users' emotions. In addition to providing a collaborative work environment, this system aims to improve the quality of communication by recognizing users' emotional states in real time, as well as providing project proposals, expert matching, and collaborative work environments.

[0770] Server operation

[0771] The server first receives project proposal information from the user and analyzes its content using natural language processing and machine learning. Based on this analysis, it searches for appropriate experts in the database and uses artificial intelligence to select the expert best suited to the project. Simultaneously, the server analyzes voice and text data acquired during communication with the user using an emotion engine to determine the user's emotional state. The data obtained from emotion recognition is used to adjust the interface of the collaborative work environment.

[0772] Terminal operation

[0773] The terminal visualizes matching results and sentiment recognition information received from the server for the user. The user can review the presented experts and select the best members for the project. Furthermore, the terminal provides real-time sentiment-based feedback to facilitate smooth communication. If the user's emotions are recognized, the terminal changes the interface's color scheme and layout as needed to make adjustments that reduce stress.

[0774] User actions

[0775] Users input project proposals via their devices, and experts are matched based on these proposals. Users can then check the emotional state of each member before beginning collaboration with the matched experts. Throughout the project, users utilize feedback provided by the emotional engine to maintain engagement among all project participants. This improves communication efficiency and increases the project's success rate.

[0776] Specific example

[0777] A company plans a new product development project and utilizes this system. The user inputs project details as a proposal, and the server uses this information to match them with appropriate marketing, design, and engineering experts. During expert meetings, the emotion engine analyzes the participants' emotions and adjusts the environment in real time, such as changing the interface to calmer colors if tension is high. This allows participants to exchange ideas in a more relaxed state and fosters creative thinking.

[0778] The following describes the processing flow.

[0779] Step 1:

[0780] The user enters detailed project proposals via a terminal. This includes the project name, objectives, required expertise, and expected outcomes. This data is then transmitted from the terminal to the server.

[0781] Step 2:

[0782] The server analyzes project proposal information received from users. Using natural language processing, it extracts keywords and technical terms from the proposal and identifies the specialized fields required for the project.

[0783] Step 3:

[0784] The server searches the database for relevant expert profiles based on the analysis results. Using a dedicated algorithm that evaluates the skill information and past project history contained in each profile, it generates a list of the most suitable experts.

[0785] Step 4:

[0786] The server utilizes machine learning algorithms to calculate the degree of match and optimize the list of experts. This process selects the expert best suited to the project's needs.

[0787] Step 5:

[0788] The server analyzes voice and text data using an emotion engine to determine the user's emotional state. Simultaneously, it monitors emotional changes within the communication in real time.

[0789] Step 6:

[0790] The terminal presents the user with matching results and sentiment recognition information obtained from the server. The user can then review the detailed profiles of the presented experts and select the members who will join the project.

[0791] Step 7:

[0792] The device will create a real-time collaborative environment with selected team members. This environment will include chat, video conferencing, multilingual translation, and real-time sentiment feedback.

[0793] Step 8:

[0794] Users communicate through their devices based on emotional feedback and advance the project by adjusting the interface as needed. This adjustment includes changing the screen's color tone and the priority of information presentation.

[0795] The above describes the processing steps of a platform that uses an emotion engine.

[0796] (Example 2)

[0797] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0798] In collaborations between engineers from different fields, inefficiencies can arise due to emotional and communication mismatches. In particular, when using different languages, misunderstandings and communication breakdowns are more likely, leading to a decrease in project success rates. Solutions are needed to address this challenge and improve the quality of collaboration.

[0799] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0800] In this invention, the server includes means for receiving information about project proposals from users, means for selecting engineers with relevant expertise from an information set, means for using an emotion engine to analyze the user's emotional state, and means for adjusting the display of the collaborative work environment based on the emotion data. This enables real-time and effective collaboration among engineers and improves communication that transcends emotional and language barriers.

[0801] A "user" refers to an individual or organization that uses the system to propose projects and collaborate with engineers.

[0802] A "project proposal" is information entered by the user through the system, describing the specific tasks and objectives of the collaborative project.

[0803] "Area of ​​expertise" refers to the field of specialized knowledge and skills possessed by an engineer, and serves as a criterion for selecting relevant engineers according to the content of the project proposal.

[0804] An "engineer" refers to an individual who possesses specialized knowledge and skills in a specific field and is selected based on their project proposal.

[0805] An "information set" refers to a database or information resource about engineers, a collection of data that holds engineers' profiles and skill information.

[0806] "Intelligent functions" refer to artificial intelligence technologies used to effectively combine selected engineers and optimize collaboration with users.

[0807] An "emotion engine" refers to a technology that analyzes a user's emotional state and provides it as data, enabling real-time emotion recognition.

[0808] A "collaborative work environment" refers to a workspace where multiple users can cooperate in real time, supporting communication and enabling the efficient execution of projects.

[0809] "Display adjustment" refers to changing the appearance and layout of the user interface based on emotional data, and is an operation performed to improve user comfort and reduce stress.

[0810] This invention is a platform for engineers from different fields to collaborate efficiently, incorporating an emotion engine that recognizes user emotions. This enables comprehensive support, from project proposals and engineer matching to the provision of a collaborative work environment.

[0811] The server receives project proposal information from users and analyzes its content using natural language processing and training algorithms. Specifically, Python's natural language processing libraries and related libraries are applied. Based on the analysis results, the server searches for and selects appropriate engineers from the information set. In this process, artificial intelligence is used to determine the most suitable engineer. Simultaneously, the server analyzes the user's voice and text data using an emotion engine and quantifies their emotional state. This data is used to optimize the display of the collaborative work environment.

[0812] The terminal visualizes the matching results and emotion recognition information of engineers received from the server for the user. The user interface is built using web technologies, particularly frameworks such as React.js. Users can review the presented engineers and select the most suitable collaborators. Furthermore, the terminal provides real-time emotion-based feedback to support smooth communication. If the emotion is negative, the UI's colors and layout are changed to reduce stress.

[0813] Users can input project proposals via their devices and view the results of engineer matching performed on the server side. Based on this information, users can check the emotional state of each member before the project starts and prepare the optimal collaborative structure. During the project, users can utilize the feedback obtained through the emotional engine to maintain and improve team member engagement.

[0814] For example, if an organization plans to develop a new product, the server matches them with engineers who possess the appropriate expertise after they input the project details. During a meeting, the emotion engine analyzes participants' facial expressions and voices, and softens the UI's color scheme if tension is detected. This promotes relaxation among participants and enables more creative discussion.

[0815] An example of a prompt to input into the generating AI model is as follows: "Please tell me how to select the best engineers for a new product development project and build a system that analyzes the emotions of meeting participants and adjusts the UI accordingly."

[0816] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0817] Step 1:

[0818] The server receives project proposal information from the user. As input, it receives text data entered by the user via a terminal. This information includes a summary of the proposal and the required technical fields. The received text data is prepared for natural language processing.

[0819] Step 2:

[0820] The server analyzes the project proposal using natural language processing (NLP) techniques. Specifically, it uses Python's natural language processing library to tokenize, tag, and extract keywords from the text data. The input is the text data received in step 1, and the output is a keyword list that describes the proposal. Based on these analysis results, the server identifies the relevant technical fields.

[0821] Step 3:

[0822] The server uses the analysis results to select appropriate engineers from the information set. It applies a machine learning algorithm (e.g., using Scikit-learn) to search for experts in relevant fields from an engineer database. The input is the keyword list from step 2, and the output is a list of suitable engineer candidates. This list provides engineers who match the project requirements, scored accordingly.

[0823] Step 4:

[0824] The terminal visualizes the engineer matching results received from the server for the user. A UI is built using web technologies to display a list of candidate engineers on the screen. The input is the list of candidate engineers generated in step 3, and the output is the visual information displayed on the user's screen. Based on this list, the user can select the most suitable collaborators for their project.

[0825] Step 5:

[0826] The server transmits user communication data to the emotion engine in real time and analyzes the emotional state. It takes in voice and text data, applies an emotion recognition algorithm, and quantifies emotions such as joy, anger, sadness, and happiness. The input is user voice and text data acquired in real time, and the output is numerical data indicating the emotional state.

[0827] Step 6:

[0828] The device adjusts the display of the collaborative work environment based on emotional data. It changes the UI's color scheme and layout as needed to reduce user stress. The input is the emotional state data generated in step 5, and the output is the modified UI. This adjustment allows users to collaborate in a more comfortable environment.

[0829] (Application Example 2)

[0830] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0831] In collaborations between users with different areas of expertise, emotional disagreements and communication breakdowns are likely to occur, potentially impacting project progress. Furthermore, maintaining smooth communication is difficult in multilingual environments and across different cultural backgrounds. There is a need to improve these situations and provide an efficient and smooth collaborative environment.

[0832] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0833] In this invention, the server includes means for receiving information on work proposals from users, means for selecting experts with relevant expertise from a data storage device, means for matching experts using artificial intelligence, means for providing a common work environment in which multiple users can cooperate in real time, and means including an emotion understanding engine for analyzing the emotional state of users. This makes it possible to minimize communication obstacles and realize an effective collaborative environment by providing feedback that takes into account the emotional state of users.

[0834] "Different areas of expertise" refers to fields with distinct technical or knowledge systems, encompassing multiple areas, each possessing specific knowledge and skills.

[0835] "User" refers to an individual or group that uses the system to propose projects or engage in collaborative activities.

[0836] A "work proposal" refers to information that includes the project's goals, objectives, and progress plan and intentions, and collaboration proceeds based on this proposal.

[0837] A "specialist" refers to a person who possesses advanced knowledge and skills in a specific area of ​​expertise and who utilizes that knowledge to contribute to a project.

[0838] A "data storage device" refers to an information recording device that stores and saves information about experts and allows it to be retrieved as needed.

[0839] "Artificial intelligence" refers to the technology used to enable computer systems to think like humans and solve problems or make decisions.

[0840] A "shared work environment" refers to a workspace or interface provided for users to collaborate in real time, and includes features such as multilingual support and adjustment functions based on sentiment analysis.

[0841] An "emotion understanding engine" refers to a computer program or process that analyzes data extracted from a user's voice and facial expressions to determine the user's emotional state.

[0842] "Feedback" refers to the responses and guidelines provided by a system based on the user's behavior and emotional state, and is used to facilitate smoother collaboration.

[0843] The server cross-references the work proposal information received from the user with expert information stored in data storage, and uses artificial intelligence to select the most suitable expert. Natural language processing technology and machine learning algorithms are used to analyze the received text data. This method enables accurate expert selection based on the project content. Furthermore, it utilizes an emotion understanding engine to analyze voice and text data acquired during communication, grasping the user's emotional state in real time.

[0844] The terminal visualizes and presents to the user information regarding matching results and emotional states provided by the server. Based on the acquired information, the terminal adjusts the interface's color scheme and layout according to the emotional state, thereby reducing user stress and supporting smooth communication.

[0845] Users enter project proposals using their devices and begin collaborating with matched experts. Throughout the project, feedback provided by the sentiment understanding engine is utilized to maintain engagement among all participants. This improves project efficiency and success rates.

[0846] As a concrete example, a consumer robot installed in a home can analyze conversations between family members using an emotion-understanding engine and provide feedback, such as playing calming music if tension is present, thereby making the living environment more comfortable. In this way, it becomes possible to improve the user experience.

[0847] An example of a prompt is: "Generate prompts for developing an application for a consumer robot that analyzes the user's emotional state and adjusts the dialogue accordingly."

[0848] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0849] Step 1:

[0850] The server receives work proposals from users. As input, it obtains information about the project's purpose and details, which the user enters via their terminal. This information is received as text data and temporarily stored in a database. The server then processes this data to retrieve it in the correct format.

[0851] Step 2:

[0852] The server analyzes received work proposals using natural language processing techniques. It uses the received text data as input. The text data is tokenized, keywords are extracted, and the server determines which areas of expertise the project content relates to, generating analysis results. The output is data containing the specific keywords and themes analyzed.

[0853] Step 3:

[0854] The server searches for experts with relevant expertise from its data storage based on the analysis results. The keywords and themes extracted in step 2 are provided as input. A database search algorithm is applied to generate a list of relevant experts based on this information. The output is a list of candidate experts.

[0855] Step 4:

[0856] The server uses artificial intelligence to select the most suitable expert for a specific project. The input consists of a list of candidates and each expert's profile data. A machine learning model evaluates the experts' skill sets and historical performance data to rank the most suitable candidates. The output is a final list of matched experts.

[0857] Step 5:

[0858] The terminal receives matching results from the server and presents them visually to the user. It receives matching result data from the server as input. It uses UI components to format the data in a visually easy-to-understand way. The user reviews the list of candidates and makes a selection.

[0859] Step 6:

[0860] The server uses an emotion understanding engine to analyze real-time voice and text data received from the terminal. The input is voice and text data acquired during communication. This data is processed by an emotion analysis algorithm to generate data that determines the user's current emotional state. The output is data indicating the recognized emotional state.

[0861] Step 7:

[0862] The device adjusts the interface's color scheme and layout for the user based on sentiment analysis data. It uses sentiment data obtained from an sentiment understanding engine as input. The device uses dynamic UI components to make the necessary adjustments. The output is the adjusted interface, optimized to reduce user stress.

[0863] Step 8:

[0864] Users leverage feedback provided during project progress to improve the efficiency of collaboration. They receive feedback based on emotional states provided by their devices. Based on this feedback, users adjust their communication methods and project progress. As a result, highly engaged collaboration is achieved.

[0865] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0866] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0867] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0868] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0869] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0870] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0871] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0872] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0873] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0874] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0875] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0876] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0877] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0878] 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.

[0879] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0880] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0881] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0882] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0883] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0884] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0885] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0886] The following is further disclosed regarding the embodiments described above.

[0887] (Claim 1)

[0888] A platform for promoting collaboration among users with different areas of expertise,

[0889] A means of receiving information about project proposals from users,

[0890] Based on the aforementioned project proposal, a means for selecting experts with relevant expertise from a database,

[0891] A method of using artificial intelligence to match selected experts,

[0892] A means of presenting matching results to the user,

[0893] A means of providing a multilingual collaborative work environment where multiple users can cooperate in real time,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, characterized in that the artificial intelligence analyzes the profiles of each expert using natural language processing and machine learning algorithms.

[0897] (Claim 3)

[0898] The system according to claim 1, characterized in that the collaborative work environment includes a real-time multilingual translation function.

[0899] "Example 1"

[0900] (Claim 1)

[0901] A platform for facilitating collaboration among users with different technical fields,

[0902] A means of receiving information regarding plan proposals from users,

[0903] Based on the aforementioned plan proposal, a means for selecting experts with relevant technical fields from an information storage device,

[0904] A means of utilizing intelligent functions to match selected experts,

[0905] A means of presenting the matching results to the user,

[0906] A means of providing a multilingual collaborative work environment that enables multiple users to cooperate instantly,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, characterized in that the intelligent function analyzes the profiles of each expert using language processing technology and learning algorithms.

[0910] (Claim 3)

[0911] The system according to claim 1, characterized in that the collaborative work environment includes an instant multilingual translation function.

[0912] "Application Example 1"

[0913] (Claim 1)

[0914] A platform for promoting collaboration among users with different areas of expertise,

[0915] A means of receiving information about project proposals from users,

[0916] Based on the aforementioned project proposal, a means for selecting experts with relevant expertise from a database,

[0917] A method of using artificial intelligence to match selected experts,

[0918] A means of presenting matching results to the user,

[0919] A means of providing a multilingual collaborative work environment where multiple users can cooperate in real time,

[0920] A means to enable efficient matching of experts in urban function improvement projects,

[0921] A means for users to track the progress of urban development and easily manage shared resources,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, characterized in that the artificial intelligence analyzes the profiles of each expert using natural language processing and machine learning algorithms.

[0925] (Claim 3)

[0926] The system according to claim 1, characterized in that the collaborative work environment includes a real-time multilingual translation function.

[0927] "Example 2 of combining an emotion engine"

[0928] (Claim 1)

[0929] A means of receiving information about project proposals from users,

[0930] Based on the aforementioned project proposal, a means for selecting engineers with relevant expertise from a set of information,

[0931] A means of utilizing intelligent functions to combine selected engineers,

[0932] A means of presenting the combination results to the user,

[0933] A means of providing a multilingual collaborative work environment where multiple users can cooperate in real time,

[0934] A means of using an emotion engine to analyze the user's emotional state,

[0935] A means of adjusting the display of the collaborative work environment based on sentiment data,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, characterized in that the intelligent function analyzes the profile of each engineer using natural language processing and training algorithms, and analyzes the emotional state of the user based on the results.

[0939] (Claim 3)

[0940] The system according to claim 1, characterized in that the collaborative work environment includes a real-time language translation function and an interface adjustment function based on emotional feedback.

[0941] "Application example 2 when combining with an emotional engine"

[0942] (Claim 1)

[0943] An information infrastructure for promoting collaboration among users with different areas of expertise,

[0944] A means of receiving information regarding work proposals from users,

[0945] Based on the aforementioned work proposal, a means for selecting experts with relevant expertise from a data storage device,

[0946] A means of using artificial intelligence to match selected experts,

[0947] A means of presenting matching results to users,

[0948] A means of providing a multilingual, shared work environment where multiple users can collaborate in real time,

[0949] A means including an emotion understanding engine for analyzing the emotional state of users,

[0950] A means for providing user-specific feedback based on information analyzed by the aforementioned emotion understanding engine,

[0951] A system that includes this.

[0952] (Claim 2)

[0953] The system according to claim 1, characterized in that the artificial intelligence analyzes information from each expert using natural language processing and machine learning techniques.

[0954] (Claim 3)

[0955] The system according to claim 1, characterized in that the common work environment includes a real-time multilingual translation function and an emotion-responsive interface adjustment function. [Explanation of symbols]

[0956] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A platform for promoting collaboration among users with different areas of expertise, A means of receiving information about project proposals from users, Based on the aforementioned project proposal, a means for selecting experts with relevant expertise from a database, A method of using artificial intelligence to match selected experts, A means of presenting matching results to the user, A means of providing a multilingual collaborative work environment where multiple users can work together in real time, A means to enable efficient matching of experts in urban function improvement projects, A means for users to track the progress of urban development and easily manage shared resources, A system that includes this.

2. The system according to claim 1, characterized in that the artificial intelligence analyzes the profiles of each expert using natural language processing and machine learning algorithms.

3. The system according to claim 1, characterized in that the collaborative work environment includes a real-time multilingual translation function.

Images