system

Abstract

Provide a system. [Solution] A means of collecting data from internal communication tools, information sharing tools, and employee information management tools; A means for analyzing the collected data using natural language processing; A means of extracting the characteristics of each employee from the analyzed data, A means of matching employees with complementary characteristics, A way to propose 1-on-1 meetings between matched employees, A way to collect feedback after 1-on-1 meetings, A system including:

Description

[Technical Field]

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

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

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

[0004] In modern companies, communication between employees is a crucial factor that greatly influences work efficiency and productivity. However, it is not easy for employees to find the right people to communicate with effectively. In large organizations in particular, the exchange of information and opinions across departments and teams is often hindered, which can result in delays in work progress. Furthermore, existing employee information management systems and communication tools often lack the functionality to automatically match employees, which presents a challenge. [Means for solving the problem]

[0005] The present invention is a system that collects data from in-house communication tools, information sharing tools, and employee information management tools, and analyzes it using natural language processing. This system extracts the characteristics of each employee from the analyzed data and automatically matches employees with complementary characteristics. It also proposes one-on-one meetings between matched employees and collects feedback after the meetings. This promotes communication with appropriate partners and improves work efficiency. The present invention includes the following means.

[0006] Means of collecting data from internal communication tools, information sharing tools, and employee information management tools

[0007] A means of analyzing collected data using natural language processing

[0008] A means of extracting the characteristics of each employee from the analyzed data

[0009] A means of matching employees with complementary characteristics

[0010] A way to propose 1-on-1 meetings between matched employees

[0011] How to collect feedback after 1-on-1 meetings

[0012] This will effectively promote communication between employees, facilitate information exchange across departments and teams, and is expected to improve work progress and productivity.

[0013] "Internal communication tools" are electronic means used by employees to send and receive messages and share information, including chat tools and video conferencing software.

[0014] "Information sharing tools" are electronic means for efficiently sharing and accessing information and knowledge within an organization, including wikis and document management systems.

[0015] An "employee information management tool" is a system for managing data such as basic employee information, affiliation, and position, and includes human resources management systems and directory services.

[0016] "Means of collecting data" refers to the methods and technologies for obtaining and storing the necessary data from communication tools, information sharing tools, and employee information management tools.

[0017] "Natural language processing" refers to a set of techniques and methods that allow computers to understand, analyze, and process human language.

[0018] "Means for extracting features" refers to methods and techniques for recognizing specific attributes or behavioral patterns from analyzed data and extracting them as features.

[0019] "Matching means" refers to methods and techniques for appropriately selecting employees who complement each other based on the extracted characteristics.

[0020] "Means for proposing a one-on-one meeting" refers to the methods and techniques for notifying and proposing a one-on-one meeting to matched employees.

[0021] "Means of collecting feedback" refers to the methods and techniques used to collect and record impressions and evaluations from participants after one-on-one meetings. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, matches complementary employees, and proposes one-on-one meetings to promote appropriate communication between employees. This system consists of the following components:

[0044] 1. Data Collection

[0045] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[0046] 2. Data Analysis

[0047] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[0048] 3. Feature Extraction

[0049] The server extracts the characteristics of each employee from the analysis results. Characteristics refer to the employee's main areas of interest, areas of expertise, or current challenges they are facing. For example, it can be determined that Person A has the characteristic of being "very interested in AI technology."

[0050] 4. Matching

[0051] Based on the extracted characteristics, the server automatically matches employees with complementary traits. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology."

[0052] 5. Proposal for 1-on-1 meetings

[0053] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting.

[0054] 6. Gathering Feedback

[0055] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0056] Specific examples

[0057] For example, suppose there is "Person A who is struggling with the technical issues of Project A" and "Person B who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[0058] In this way, the system of the present invention can realize effective one-on-one meetings between employees and improve the quality of communication.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] Data collection

[0062] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[0063] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[0064] Step 2:

[0065] Data Preprocessing

[0066] The server cleans the collected data before natural language processing.

[0067] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[0068] Step 3:

[0069] Performing Natural Language Processing (NLP)

[0070] The server performs natural language processing on the preprocessed data.

[0071] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[0072] Step 4:

[0073] Feature Extraction

[0074] The server extracts the characteristics of each employee based on the results of NLP.

[0075] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[0076] Step 5:

[0077] Executing the matching algorithm

[0078] The server matches complementary employees using feature vectors.

[0079] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores.

[0080] Step 6:

[0081] Proposal for 1-on-1 meetings

[0082] The server sends a notification to the matched employees proposing a one-on-one meeting.

[0083] Specific operation: The server checks employees' calendars (e.g., Google (registered trademark) Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[0084] Step 7:

[0085] Meeting Approval

[0086] A user accepts or declines a proposed 1-on-1 meeting.

[0087] Specific behavior: When a user receives a notification, they click the link and select the accept or decline button for the meeting on a dedicated web page.

[0088] Step 8:

[0089] Gathering feedback

[0090] The device collects feedback from participants after one-on-one meetings.

[0091] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[0092] Step 9:

[0093] Feedback Analysis

[0094] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[0095] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[0096] Through these processing steps, the system sets up effective one-on-one meetings between employees and promotes communication within the organization.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] Traditional internal communication systems lack effective ways to promote appropriate interactions between employees. As a result, opportunities for employees to share their expertise and interests are reduced, making it difficult for employees to exchange knowledge and provide support to each other. In particular, matching one-on-one meetings that take into account employees' skills and interests is often done manually, which is inefficient.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using a natural language processing engine, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one interviews between matched employees, means for collecting feedback after the one-on-one interviews, and means for reflecting the feedback in the next match. This makes it possible to automate appropriate matching between employees and proposals for effective one-on-one meetings, thereby promoting knowledge sharing and support between employees.

[0102] "Internal communication" means a system for sending and receiving messages used within the workplace that facilitates communication between employees.

[0103] An "information sharing tool" is a system for organizing and sharing knowledge, materials, and information within the workplace, allowing employees to access the information they need.

[0104] "Employee information management means" is a system for managing employees' personal information, skills, positions, etc., and for aggregating and managing personnel data.

[0105] "Means of collecting data" refers to the methods and technologies for collecting the necessary data from internal communication means, information sharing means, and employee information management means.

[0106] A "natural language processing engine" is a computer program that analyzes collected text data and understands its meaning and sentiment.

[0107] "Means for extracting characteristics" refers to methods and techniques for identifying and recording characteristics such as each employee's areas of interest, areas of expertise, and challenges from the analyzed data.

[0108] "Mutually complementary" means that the characteristics of different staff members complement each other.

[0109] "Matching means" refers to methods and techniques for creating optimal matches based on extracted employee characteristics.

[0110] "Means for proposing one-on-one interviews" refers to the methods and techniques for sending interview proposals to matched staff members and notifying them of the date and content of the interviews.

[0111] "Means of collecting feedback" refers to the methods and techniques for collecting evaluations and impressions from participants after one-on-one interviews and using them to help with the next matchmaking.

[0112] "Means for incorporating feedback into the next match" refers to methods and technologies for adjusting the next match algorithm based on the collected feedback to achieve a more appropriate match.

[0113] This invention is a system for promoting appropriate communication between employees. This system collects and analyzes data from internal communication methods, information sharing methods, and employee information management methods, and matches mutually complementary employees to propose one-on-one meetings. The system consists of the following components:

[0114] Data collection

[0115] The server collects data from internal communication methods (e.g., messaging apps), information sharing methods (e.g., document management systems), and employee information management methods (e.g., personnel management systems). Specifically, the server periodically obtains data from these methods using APIs. For example, it collects message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from personnel management systems.

[0116] Data analysis

[0117] The server analyzes the collected data using a natural language processing (NLP) engine. Specific software used is a generative AI model such as OpenAI (registered trademark) or GPT-3 (registered trademark). The server passes the acquired data to the NLP engine, which performs topic classification and sentiment analysis of the messages. The analysis results include "Project X's technical challenges are frequently mentioned" and "positive comments."

[0118] Feature Extraction

[0119] The server extracts the characteristics of each employee from the analysis results. Based on the analysis results, the server applies an algorithm to determine each employee's areas of interest and expertise. For example, the server records such things as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X."

[0120] matching

[0121] Based on the extracted features, the server automatically matches employees with complementary characteristics. The server searches the feature database and runs an algorithm to find the optimal combination. For example, "Person A, who is interested in AI technology," and "Person B, who has extensive practical experience in AI technology," are matched as the optimal pair.

[0122] Proposal for 1-on-1 meetings

[0123] The server notifies the devices of the matched employees of a proposed one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting. If accepted, the meeting is added to the calendar.

[0124] Gathering feedback

[0125] The device collects feedback after the one-on-one meeting. After the meeting ends, the device automatically displays a feedback form, and the user enters their evaluation and thoughts. The collected feedback is sent to the server and reflected in future matches.

[0126] Specific examples

[0127] For example, consider two employees: "Employee A, who is struggling with the technical issues of Project X," and "Employee B, who is knowledgeable about Project X." The server collects messages about "Project X's technical issues" from a messaging app and uses an NLP engine to analyze "statements seeking advice on the technical issues." Meanwhile, it is analyzed that Person B is "providing technical knowledge about Project X." The server performs matching based on these characteristics and proposes a one-on-one meeting between Person A and Person B. This proposal is notified to both devices, and if the users approve the meeting, the meeting will be held at the specified date and time. After the meeting, the devices collect feedback and send the results to the server, which will be reflected in the matching algorithm for future meetings.

[0128] Prompt Sentence Examples

[0129] "Please explain the specific steps to match employee A, who is struggling with a technical issue in Project X, with employee B, who is knowledgeable about Project X."

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] The server collects data from internal communication methods, information sharing methods, and employee information management methods. The input data includes message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from the personnel management system. Specifically, the server periodically retrieves this data using APIs. The output is to store all collected data in the server's database.

[0133] Step 2:

[0134] The server analyzes the collected data using a natural language processing (NLP) engine. The input data is the collected messages, documents, and employee information. Specifically, the server passes this data to an NLP engine (e.g., OpenAI GPT-3) to perform topic classification and sentiment analysis of the messages. The output is metadata containing the topic and sentiment information as the analysis results. The analysis results are stored in the server's database.

[0135] Step 3:

[0136] The server extracts the characteristics of each employee from the analysis results. The input data is metadata analyzed by the NLP engine. Specifically, the server applies an algorithm to determine areas of interest and expertise. For example, the server extracts information such as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X." The output is data containing the characteristic information of each employee.

[0137] Step 4:

[0138] The server matches complementary employees based on the extracted characteristics. The input data is the characteristic information of each employee. Specifically, the server searches the characteristic database and executes an algorithm to find the optimal combination. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." The output is employee pair information as a matching result.

[0139] Step 5:

[0140] The server notifies the matched staff members of a proposal for a one-on-one meeting. The input data is the staff pair information resulting from the matching. Specifically, the server automatically generates the meeting proposal and sends a notification including the date, time, and purpose to the terminal. The user receives the notification and can accept or reject the meeting. If accepted, the meeting details are added to the calendar. The output is the status information of whether the meeting was accepted or rejected.

[0141] Step 6:

[0142] The device collects feedback after the one-on-one meeting. The input data is the evaluation and impressions entered by the user after the meeting. Specifically, the device automatically presents a feedback form, which the user fills out. The feedback is sent from the device to the server. The output is the collected feedback information.

[0143] Step 7:

[0144] The server reflects the collected feedback in subsequent matches. The input data is the feedback information. Specifically, the server adjusts the matching algorithm based on the feedback to improve the accuracy of the next match. The output is an updated matching algorithm.

[0145] (Application example 1)

[0146] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0147] In conventional factories, there was a lack of efficient cooperation between workers and factory robots. As a result, it was difficult to improve productivity and optimize work. Furthermore, there was no way to promote appropriate matching or communication between workers and robots, which led to problems such as a decline in work efficiency and an increase in work errors.

[0148] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0149] In this invention, the server includes means for collecting data from in-house communication tools, information sharing tools, and employee information management tools, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one meetings between the matched employees, means for collecting feedback after the one-on-one meetings, means for collecting and analyzing information on workers and factory robots in the factory, means for matching complementary workers and factory robots, means for proposing cooperative work to the matched workers and factory robots, and means for collecting feedback after the cooperative work. This enables efficient cooperation and optimal matching between workers and factory robots.

[0150] An "internal communication tool" is an electronic message exchange system used within a company, and is a tool primarily used to promote communication between employees.

[0151] An "information sharing tool" is an electronic platform that allows employees to efficiently collect, share, and refer to information.

[0152] An "employee information management tool" is a system that manages basic employee information, work performance, skill data, etc.

[0153] A "natural language processing engine" is a technology that uses computers to understand, analyze, and generate human language.

[0154] "Matching employees with complementary characteristics" is the process of selecting and combining employees who can complement each other's lacking skills and knowledge.

[0155] The "1-on-1 meeting proposal method" is a system that notifies matched employees to hold individual interviews and proposes a schedule.

[0156] "Feedback collection means" is a system for collecting impressions and evaluations from participants after one-on-one meetings or collaborative work.

[0157] "Factory workers" are employees in charge of production, manufacturing, and other tasks in a factory.

[0158] A "factory robot" is a mechanical device used to automate work in a factory.

[0159] The "cooperative work proposal means" is a mechanism that notifies the matched worker and robot of a proposal to work together.

[0160] The system for realizing this invention consists of a server, a terminal, and a user. The server has the following functions:

[0161] 1. Data Collection

[0162] The server collects data from in-house communication tools, information sharing tools, and employee information management tools, and accumulates a variety of data, such as messages, comments, and basic information about workers and robots.

[0163] 2. Data Analysis

[0164] The server analyzes the collected data using a natural language processing (NLP) engine. It uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of messages. For example, it analyzes "frequent mentions of the project" and "positive comments about technology."

[0165] 3. Feature Extraction

[0166] The server extracts the characteristics of each worker and robot from the analysis results. These characteristics refer to the areas in which the worker or robot is primarily interested, areas in which they excel, or challenges they are currently facing. For example, an analysis could show that a particular worker has a characteristic such as "being very interested in AI technology."

[0167] 4. Matching

[0168] Based on the extracted features, the server automatically matches workers and robots with complementary characteristics, for example, a worker who is interested in AI technology with a robot with extensive practical experience in AI technology.

[0169] 5. Proposal for collaboration

[0170] The server notifies the matched worker and robot of the proposed collaboration. The notification includes an overview and purpose of the proposed collaboration. The user receives this notification and can approve or reject the collaboration.

[0171] 6. Gathering Feedback

[0172] After the collaborative work is completed, the device collects feedback from the workers. This feedback will be used for future matching. For example, comments such as "The work was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0173] Specific examples

[0174] For example, suppose a worker in a factory who is very interested in AI technology is struggling with a technical issue in a certain project. At the same time, a robot with extensive knowledge of AI technology may be working on another project. The server collects this data and analyzes that the worker frequently posts messages seeking advice on technical issues. It also analyzes that the robot has a great deal of technical knowledge about AI technology. As a result, the server optimally matches the worker with the robot and proposes a collaborative task. After the task is completed, feedback from the worker is collected and reflected in the matching algorithm for the next task.

[0175] Example prompts to input to the generative AI model

[0176] Run a program that helps match workers who are highly interested in AI technology with robots that use AI technology to perform precision work, and automatically suggest a one-on-one meeting.

[0177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0178] Step 1:

[0179] The server collects data from the company's internal communication tools, information sharing tools, and employee information management tools. Specifically, data such as worker messages, comments, basic information, and robot operation status is sent to the server. Input data is in text format, and output data is saved in database format.

[0180] Step 2:

[0181] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of the messages. The input data is in text format, and the output data is saved as a feature vector.

[0182] Step 3:

[0183] The server extracts the characteristics of the worker and the robot from the analysis results. Specifically, it expresses information such as the worker's interests and areas of expertise, the current work situation, and the robot's characteristics and functions in vector format. The input data is the NLP analysis results, and the output data is a feature vector.

[0184] Step 4:

[0185] The server matches workers and robots with complementary characteristics based on the extracted features. Specifically, it uses sklearn's cosine_similarity function to calculate similarity scores and determine the optimal pair. The input data is a feature vector, and the output data is a pair list of matching results.

[0186] Step 5:

[0187] The server notifies the matched worker and robot of the proposed collaborative work. Specifically, it sends an overview and purpose of the collaborative work via email or a notification system. The input data is a list of matching results, and the output data is a notification message.

[0188] Step 6:

[0189] The terminal collects feedback from the workers after the collaborative work is completed. Specifically, a feedback form is provided to the workers, and they are asked to enter their impressions and evaluations. The input data are the responses to the feedback form, and the output data is stored in a feedback database.

[0190] Step 7:

[0191] The server reflects the collected feedback in the matching algorithm for the next time onward. Specifically, it analyzes the feedback data and adjusts the matching conditions. The input data is the feedback data, and the output data is the adjusted matching algorithm.

[0192] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0193] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, matches complementary employees, and proposes one-on-one meetings in order to promote appropriate communication between employees. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and optimizes matching and one-on-one meeting proposals based on that information.

[0194] 1. Data Collection

[0195] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[0196] 2. Data Analysis

[0197] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[0198] 3. Emotion recognition

[0199] The server uses an emotion engine to recognize the user's emotions from the analyzed data. For example, it can recognize the user's emotional state, such as "the user is feeling stressed" or "the user is motivated," from the tone and wording of the message.

[0200] 4. Feature Extraction

[0201] The server extracts each employee's characteristics based on the results of the NLP and emotion engine. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can be determined that Person A has the characteristics of being "very interested in AI technology" and "currently feeling stressed."

[0202] 5. Matching

[0203] The server automatically matches employees with complementary characteristics based on the extracted features. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other's emotions.

[0204] 6. Proposal for 1-on-1 meetings

[0205] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or decline the meeting.

[0206] 7. Gathering Feedback

[0207] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0208] Specific examples

[0209] For example, suppose there is "Person A, who is struggling with the technical issues of Project A," and "Person B, who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. Furthermore, the emotion engine recognizes that Person A is feeling stressed, and adjusts the timing of the meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[0210] In this way, the system of the present invention, which is combined with an emotion engine, can realize effective one-on-one meetings between employees and further improve the quality of communication.

[0211] The processing flow will be explained below.

[0212] Step 1:

[0213] Data collection

[0214] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[0215] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[0216] Step 2:

[0217] Data Preprocessing

[0218] The server cleans the collected data before natural language processing.

[0219] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[0220] Step 3:

[0221] Performing Natural Language Processing (NLP)

[0222] The server performs natural language processing on the preprocessed data.

[0223] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[0224] Step 4:

[0225] emotion recognition

[0226] The server uses an emotion engine to recognize the user's emotions from the data analyzed by natural language processing.

[0227] Specific operation: The server analyzes the tone and wording of the message and recognizes the user's emotional state, such as "the user is feeling stressed" or "the user is motivated."

[0228] Step 5:

[0229] Feature Extraction

[0230] The server extracts the characteristics of each employee based on the results of NLP and the emotion engine.

[0231] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[0232] Step 6:

[0233] Executing the matching algorithm

[0234] The server matches complementary employees using feature vectors and emotional states.

[0235] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores. It also prioritizes employees with similar emotional states.

[0236] Step 7:

[0237] Proposal for 1-on-1 meetings

[0238] The server sends a notification to the matched employees proposing a one-on-one meeting.

[0239] Specific operation: The server checks employees' calendars (e.g., Google Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[0240] Step 8:

[0241] Meeting Approval

[0242] A user accepts or declines a proposed 1-on-1 meeting.

[0243] Specific behavior: The user clicks the link in the notification they received and selects the Accept or Decline button for the meeting on a dedicated web page.

[0244] Step 9:

[0245] Gathering feedback

[0246] The device collects feedback from participants after one-on-one meetings.

[0247] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[0248] Step 10:

[0249] Feedback Analysis

[0250] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[0251] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[0252] Through these processing steps, the system sets up effective one-on-one meetings between employees, promotes communication within the organization, and achieves more effective matching by taking emotional states into account.

[0253] Example 2

[0254] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0255] In modern companies, proper communication between employees is essential for improving work efficiency and employee satisfaction. However, problems often arise due to a lack of communication between employees or meetings held at inappropriate times. Furthermore, there is an issue of ineffective one-on-one meetings being held because communication matching does not take into account employees' emotional states. To solve this, a system is needed that can identify the characteristics of employees, optimally match them, and suggest one-on-one meetings at times that take into account their emotional states.

[0256] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for recognizing employee emotions using emotion recognition means, means for matching employees who complement each other, means for proposing one-on-one meetings between matched employees, and means for collecting feedback after the one-on-one meetings. This promotes appropriate communication between employees and enables effective one-on-one meetings, thereby improving work efficiency and employee satisfaction.

[0257] "Communication tools" are means for exchanging messages or information in digital form, including chat tools, email systems, and instant messaging services.

[0258] "Information sharing tools" are means for aggregating information within an organization and providing it in a form that is easily accessible to members, and include wikis, document management systems, collaboration tools, etc.

[0259] "Employee information management means" refers to means for managing basic information, performance, skills, work history, etc., related to employees, and includes personnel management systems and databases.

[0260] "Natural language processing" is a technique for analyzing collected text data to understand, classify, or extract sentiment from its content.

[0261] "Feature extraction" is the process of identifying characteristics such as employees' areas of interest, areas of expertise, challenges they face, and emotional states from the analyzed data.

[0262] "Emotion recognition means" refers to technology for recognizing a user's emotional state based on text data, and includes machine learning algorithms and analysis engines.

[0263] A "matching method" is an algorithm or mechanism that automatically pairs employees with complementary characteristics based on the extracted characteristics.

[0264] "Method for proposing 1-on-1 meetings" is the process of sending notifications to matched employees to propose individual meetings.

[0265] "Means for collecting feedback" refers to a system for gathering opinions and impressions from participants after one-on-one meetings, and includes surveys and review systems.

[0266] This invention is a system for promoting appropriate communication between employees. This system is configured with a server at its core, and collects data from in-house communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., personnel management systems), and analyzes and processes this data to match mutually complementary employees and propose one-on-one meetings.

[0267] 1. Data Collection

[0268] The server uses API connections to collect data from chat tools (e.g., Slack), information sharing tools (e.g., Confluence), and human resources management systems (e.g., Workday). Specifically, data such as messages, comments, and basic information obtained from each tool is stored in the server's database. During this process, appropriate API calls and data format conversions are made.

[0269] 2. Data Analysis

[0270] The server then passes the collected data to a natural language processing (NLP) engine such as Google Cloud Natural Language API to analyze the meaning, sentiment, and topic of the messages, allowing it to extract, for example, "frequent mentions of technical challenges in Project A" or "positive comments about new technologies."

[0271] 3. Emotion recognition

[0272] The server then uses an emotion recognition engine like Affectiva to identify the user's emotions from the analyzed data, identifying emotional states such as "the user is stressed" or "the user is motivated" based on the tone and phrasing of the message.

[0273] 4. Feature Extraction

[0274] Based on the results of the NLP engine and emotion recognition engine, the server extracts the characteristics of each employee. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can reveal that employee A is "very interested in AI technology" and "currently feeling stressed."

[0275] 5. Matching

[0276] The server automatically matches employees with complementary traits based on the extracted characteristics. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." It also takes into account emotional states, forming pairs that are less likely to be influenced by each other's emotions.

[0277] 6. Proposal for 1-on-1 meetings

[0278] Once matching is complete, the server sends a notification proposing a one-on-one meeting to the devices of the employees. This notification includes the proposed date, time, and purpose of the meeting. Users can receive this notification and accept or reject the meeting. Specifically, the notification will say, "I propose a one-on-one meeting between Mr. A and Mr. B to discuss the technical issues of Project A."

[0279] 7. Gathering Feedback

[0280] After the one-on-one meeting ends, the device collects feedback from the user. This feedback is used to help with future matching. For example, specific opinions such as "The meeting was very meaningful" or "The topic we discussed was inappropriate" are collected, and the server analyzes them and reflects them in future matching algorithms.

[0281] Specific examples

[0282] For example, suppose employee A is struggling with "technical issues in Project A." The server collects employee A's messages from Slack or other services and analyzes them using the Google Cloud Natural Language API, determining that employee A is seeking advice on the technical issues. At the same time, it uses an emotion recognition engine such as Affectiva to determine that employee A is feeling stressed. The server then identifies employee B, who is knowledgeable about Project A, and matches employee A and employee B. Notifications of the proposed meeting are sent to the devices of employee A and employee B, including the proposed meeting date and time and purpose. After the meeting ends, feedback collected through the devices is reflected in the next match.

[0283] Prompt Sentence Examples

[0284] "What kind of support should you provide to an employee who is struggling with technical issues in Project A? Suggest collaboration with other employees who have technical knowledge about Project A."

[0285] This system promotes appropriate communication between employees and enables efficient and effective one-on-one meetings.

[0286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0287] Step 1: Data collection

[0288] The server connects to internal communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., human resources management systems), and collects data from these systems using APIs. Specifically, messages, comments, basic employee information, etc. are obtained from each tool through API calls and stored in the server's database. The input is raw data obtained from each tool, and the output is data stored in a structured format in the database.

[0289] Step 2: Data analysis

[0290] The server passes the collected data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input data is the text data collected in step 1, and the meaning, sentiment, and topic of each message are extracted as output. For example, "mentions about the technical challenges of Project A" and "positive comments about new technology" are extracted from the text data. Specific operations include the process of sending data to the API and obtaining the analysis results.

[0291] Step 3: Emotion Recognition

[0292] The server passes the data analyzed in step 2 to an emotion recognition engine (e.g., Affectiva) to identify the user's emotional state. The input data is the analysis result obtained in step 2, and the user's emotional state (e.g., "feeling stressed" or "motivated") is generated as the output. Specific operations include the process of sending the analyzed data to the emotion recognition engine and returning the emotional state.

[0293] Step 4: Feature extraction

[0294] The server extracts the characteristics of each employee based on the results of the natural language processing engine and emotion recognition engine. The input data is the output of steps 2 and 3, and the output identifies each employee's characteristics (e.g., "very interested in AI technology" or "currently feeling stressed"). Specifically, the server integrates the results of each analysis and identifies the characteristics based on the feature extraction algorithm defined in the program.

[0295] Step 5: Matching

[0296] The server automatically matches employees with complementary characteristics based on the results of feature extraction. The input data are the characteristics output in step 4, and the output is a pair of matched employees. Specifically, the algorithm identifies employees with complementary characteristics based on the feature data and creates a matching list.

[0297] Step 6: Propose a one-on-one meeting

[0298] The server sends a notification of a proposed 1-on-1 meeting to the devices of the employees who have completed matching. The input data is the matching list created in step 5, and the output is a notification message that will be displayed on each employee's device. Specifically, the server generates the date, time, location, and purpose of the proposed meeting to be included in the notification and sends it to the device of each employee.

[0299] Step 7: Gather feedback

[0300] After the one-on-one meeting is over, the device collects feedback from both parties. The input data is the feedback information provided by the employee, and the output is the feedback data stored on the server. Specifically, the device displays a feedback form on the screen and sends the information entered by the user to the server. The server stores this information and uses it for future matching.

[0301] (Application example 2)

[0302] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0303] In modern factories and companies, poor communication and a lack of appropriate information exchange negatively impact production efficiency and employee motivation. In addition, there are few opportunities for employees with the right skills to meet with the right people at the right time, which can delay problem resolution. Furthermore, matching and meeting proposals that do not take into account employees' emotional state can increase stress and dissatisfaction.

[0304] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from internal information exchange means, information provision means, and personal information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each individual from the analyzed data, means for matching individuals with complementary characteristics, means for proposing one-on-one meetings between the matched individuals, means for collecting opinions after the meeting, means for recognizing emotions from the data using an emotion engine, and means for proposing optimal matching and meetings based on the recognized emotions. This enables optimal matching and meeting proposals that take into account the emotional state of employees, thereby improving the quality of communication.

[0305] "Information exchange means" are the means by which employees and workers send messages and information to each other.

[0306] An "information means" is a system that allows each employee or worker to share and access information.

[0307] "Personal information management means" refers to a system that collects, stores, and manages personal information of employees and workers within a company.

[0308] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0309] An "emotion engine" is a technology that detects and analyzes a user's emotional state from text data and voice data.

[0310] A "one-on-one meeting" is a face-to-face meeting between two specific employees or workers.

[0311] "Matching" is the process of selecting the most suitable partner based on specific criteria and conditions.

[0312] "Data collection means" refers to a method or device for collecting data from various information exchange means, information provision means, and personal information management means.

[0313] "Opinion gathering means" is the method or system for gathering participant feedback and opinions after the meeting.

[0314] The present invention provides a system that combines data collection, data analysis, feature extraction, and emotion recognition to facilitate effective communication among employees and workers. Specific embodiments are described below.

[0315] First, the server collects data from the company's internal information exchange means, information provision means, and personal information management means. Specifically, it collects messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. As a result, a variety of data, such as workers' messages, comments, and basic information, is stored on the server.

[0316] The server then analyzes the collected data using a natural language processing (NLP) engine. Using technologies that allow computers to understand and analyze human language (e.g., SpaCy and BERT), the meaning, sentiment, and trending topics of messages are extracted. For example, analysis could reveal that "solving problems with a particular machine is frequently discussed" or "positive opinions about new work methods."

[0317] Furthermore, the server recognizes the user's emotions from the analyzed data using an emotion engine (e.g., DeepMoji). From the tone and wording of the message, the server can detect emotional states such as "the user is stressed" or "the user is motivated."

[0318] The server then extracts characteristics of each worker based on the results of the NLP and emotion engine. These characteristics include the worker's main areas of interest and expertise, the challenges they are currently facing, and their emotional state. For example, the resulting characteristics may include "Mr. A is very interested in robot maintenance" or "He is currently feeling stressed."

[0319] Based on the extracted features, the server automatically matches workers with complementary characteristics. For example, "Person A, who is interested in robot maintenance," with "Person B, who has extensive practical experience in robot maintenance." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other.

[0320] Once matched, workers will receive a notification proposing a one-on-one meeting, including the date, time, and purpose of the proposed meeting, and can accept or decline the meeting.

[0321] After the meeting, the server collects feedback from the workers. This feedback will be used for future matching. Feedback such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" is collected.

[0322] For example, the following prompts can be presented to the worker:

[0323] "Are you interested in robot maintenance?", "Are you feeling stressed about your work lately?", "Do you want someone to talk to about a technical issue?"

[0324] In this way, a system combined with an emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[0325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0326] Step 1:

[0327] The server collects data from information exchange means, information provision means, and personal information management means. Specifically, it obtains messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. The input is data from each system, and the output is a comprehensive data set of the collected data. The server manages this data in a unified manner.

[0328] Step 2:

[0329] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses NLP techniques such as SpaCy and BERT to extract the meaning of messages and trending topics. The input is the collected comprehensive dataset, and the output is the semantic analysis results and topic model after analysis. The server identifies relevant themes and keywords based on the content of each message.

[0330] Step 3:

[0331] The server recognizes the user's emotions from the data analyzed using an emotion engine. Specifically, it uses emotion analysis technologies such as DeepMoji to determine the user's emotional state from the tone and phrasing of the message. The input is data after semantic analysis, and the output is data indicating the user's emotional state. The server evaluates the emotional tone of each message and assigns an emotion tag such as positive, negative, or neutral.

[0332] Step 4:

[0333] The server extracts the characteristics of each worker based on the results of the NLP and emotion engine. Specifically, it compiles the worker's areas of interest, expertise, current problems, emotional state, etc. into a profile. The input is the analyzed semantic and emotional data, and the output is a feature profile for each worker. The server runs the feature extraction algorithm and generates a profile for each worker.

[0334] Step 5:

[0335] The server matches workers with complementary characteristics based on the extracted features. Specifically, it uses a feature matching algorithm to form pairs with complementary skills and areas of interest. The input is a feature profile, and the output is a list of matched worker pairs. The server compares each worker's profile and selects the best match.

[0336] Step 6:

[0337] The server sends a notification to the matched workers proposing a one-on-one meeting. Specifically, it sends a notification including the date, time, and purpose of the proposed meeting to the worker's device. The input is a list of matching pairs, and the output is a meeting proposal notification. The server uses a pre-configured schedule management system to suggest the optimal meeting time.

[0338] Step 7:

[0339] The user accepts or rejects the meeting proposal from the terminal. Specifically, the user checks their work schedule and decides whether the proposed meeting is appropriate. The input is the meeting proposal notification, and the output is feedback on whether the meeting is accepted or rejected. The user accepts or rejects the proposal using the terminal interface.

[0340] Step 8:

[0341] The server collects feedback from workers after the meeting. Specifically, it asks for feedback on whether the meeting was meaningful, whether the topics discussed were appropriate, etc. The input is the worker's feedback, and the output is feedback data that will be used to improve the matching algorithm for the next time onwards. The server analyzes the feedback and reflects it in improving the accuracy of the next match.

[0342] In this way, by using generative AI models and prompts, the system combined with the emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[0343] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0344] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0345] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0346] [Second embodiment]

[0347] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0348] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0349] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0350] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0351] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0352] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0353] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0354] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0355] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0356] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0357] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0358] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0359] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, and matches complementary employees with each other to propose one-on-one meetings in order to promote appropriate communication between employees. This system consists of the following components:

[0360] 1. Data Collection

[0361] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[0362] 2. Data Analysis

[0363] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[0364] 3. Feature Extraction

[0365] The server extracts the characteristics of each employee from the analysis results. Characteristics refer to the employee's main areas of interest, areas of expertise, or current challenges they are facing. For example, it can be determined that Person A has the characteristic of being "very interested in AI technology."

[0366] 4. Matching

[0367] Based on the extracted characteristics, the server automatically matches employees with complementary traits. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology."

[0368] 5. Proposal for 1-on-1 meetings

[0369] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting.

[0370] 6. Gathering Feedback

[0371] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0372] Specific examples

[0373] For example, suppose there is "Person A who is struggling with the technical issues of Project A" and "Person B who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[0374] In this way, the system of the present invention can realize effective one-on-one meetings between employees and improve the quality of communication.

[0375] The processing flow will be explained below.

[0376] Step 1:

[0377] Data collection

[0378] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[0379] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[0380] Step 2:

[0381] Data Preprocessing

[0382] The server cleans the collected data before natural language processing.

[0383] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[0384] Step 3:

[0385] Performing Natural Language Processing (NLP)

[0386] The server performs natural language processing on the preprocessed data.

[0387] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[0388] Step 4:

[0389] Feature Extraction

[0390] The server extracts the characteristics of each employee based on the results of NLP.

[0391] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[0392] Step 5:

[0393] Executing the matching algorithm

[0394] The server matches complementary employees using feature vectors.

[0395] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores.

[0396] Step 6:

[0397] Proposal for 1-on-1 meetings

[0398] The server sends a notification to the matched employees proposing a one-on-one meeting.

[0399] Specific operation: The server checks employees' calendars (e.g., Google Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[0400] Step 7:

[0401] Meeting Approval

[0402] A user accepts or declines a proposed 1-on-1 meeting.

[0403] Specific behavior: When a user receives a notification, they click the link and select the accept or decline button for the meeting on a dedicated web page.

[0404] Step 8:

[0405] Gathering feedback

[0406] The device collects feedback from participants after one-on-one meetings.

[0407] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[0408] Step 9:

[0409] Feedback Analysis

[0410] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[0411] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[0412] Through these processing steps, the system sets up effective one-on-one meetings between employees and promotes communication within the organization.

[0413] Example 1

[0414] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0415] Traditional internal communication systems lack effective ways to promote appropriate interactions between employees. As a result, opportunities for employees to share their expertise and interests are reduced, making it difficult for employees to exchange knowledge and provide support to each other. In particular, matching one-on-one meetings that take into account employees' skills and interests is often done manually, which is inefficient.

[0416] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0417] In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using a natural language processing engine, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one interviews between matched employees, means for collecting feedback after the one-on-one interviews, and means for reflecting the feedback in the next match. This makes it possible to automate appropriate matching between employees and proposals for effective one-on-one meetings, thereby promoting knowledge sharing and support between employees.

[0418] "Internal communication" means a system for sending and receiving messages used within the workplace that facilitates communication between employees.

[0419] An "information sharing tool" is a system for organizing and sharing knowledge, materials, and information within the workplace, allowing employees to access the information they need.

[0420] "Employee information management means" is a system for managing employees' personal information, skills, positions, etc., and for aggregating and managing personnel data.

[0421] "Means of collecting data" refers to the methods and technologies for collecting the necessary data from internal communication means, information sharing means, and employee information management means.

[0422] A "natural language processing engine" is a computer program that analyzes collected text data and understands its meaning and sentiment.

[0423] "Means for extracting characteristics" refers to methods and techniques for identifying and recording characteristics such as each employee's areas of interest, areas of expertise, and challenges from the analyzed data.

[0424] "Mutually complementary" means that the characteristics of different staff members complement each other.

[0425] "Matching means" refers to methods and techniques for creating optimal matches based on extracted employee characteristics.

[0426] "Means for proposing one-on-one interviews" refers to the methods and techniques for sending interview proposals to matched staff members and notifying them of the date and content of the interviews.

[0427] "Means of collecting feedback" refers to the methods and techniques for collecting evaluations and impressions from participants after one-on-one interviews and using them to help with the next matchmaking.

[0428] "Means for incorporating feedback into the next match" refers to methods and technologies for adjusting the next match algorithm based on the collected feedback to achieve a more appropriate match.

[0429] This invention is a system for promoting appropriate communication between employees. This system collects and analyzes data from internal communication methods, information sharing methods, and employee information management methods, and matches mutually complementary employees to propose one-on-one meetings. The system consists of the following components:

[0430] Data collection

[0431] The server collects data from internal communication methods (e.g., messaging apps), information sharing methods (e.g., document management systems), and employee information management methods (e.g., personnel management systems). Specifically, the server periodically obtains data from these methods using APIs. For example, it collects message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from personnel management systems.

[0432] Data analysis

[0433] The server analyzes the collected data using a natural language processing (NLP) engine. Specific software used is a generative AI model such as OpenAI GPT-3. The server passes the acquired data to the NLP engine, which performs topic classification and sentiment analysis of the messages. The analysis results include "Project X's technical challenges are frequently mentioned" and "positive comments."

[0434] Feature Extraction

[0435] The server extracts the characteristics of each employee from the analysis results. Based on the analysis results, the server applies an algorithm to determine each employee's areas of interest and expertise. For example, the server records such things as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X."

[0436] matching

[0437] Based on the extracted features, the server automatically matches employees with complementary characteristics. The server searches the feature database and runs an algorithm to find the optimal combination. For example, "Person A, who is interested in AI technology," and "Person B, who has extensive practical experience in AI technology," are matched as the optimal pair.

[0438] Proposal for 1-on-1 meetings

[0439] The server notifies the devices of the matched employees of a proposed one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting. If accepted, the meeting is added to the calendar.

[0440] Gathering feedback

[0441] The device collects feedback after the one-on-one meeting. After the meeting ends, the device automatically displays a feedback form, and the user enters their evaluation and thoughts. The collected feedback is sent to the server and reflected in future matches.

[0442] Specific examples

[0443] For example, consider two employees: "Employee A, who is struggling with the technical issues of Project X," and "Employee B, who is knowledgeable about Project X." The server collects messages about "Project X's technical issues" from a messaging app and uses an NLP engine to analyze "statements seeking advice on the technical issues." Meanwhile, it is analyzed that Person B is "providing technical knowledge about Project X." The server performs matching based on these characteristics and proposes a one-on-one meeting between Person A and Person B. This proposal is notified to both devices, and if the users approve the meeting, the meeting will be held at the specified date and time. After the meeting, the devices collect feedback and send the results to the server, which will be reflected in the matching algorithm for future meetings.

[0444] Prompt Sentence Examples

[0445] "Please explain the specific steps to match employee A, who is struggling with a technical issue in Project X, with employee B, who is knowledgeable about Project X."

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1:

[0448] The server collects data from internal communication methods, information sharing methods, and employee information management methods. The input data includes message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from the personnel management system. Specifically, the server periodically retrieves this data using APIs. The output is to store all collected data in the server's database.

[0449] Step 2:

[0450] The server analyzes the collected data using a natural language processing (NLP) engine. The input data is the collected messages, documents, and employee information. Specifically, the server passes this data to an NLP engine (e.g., OpenAI GPT-3) to perform topic classification and sentiment analysis of the messages. The output is metadata containing the topic and sentiment information as the analysis results. The analysis results are stored in the server's database.

[0451] Step 3:

[0452] The server extracts the characteristics of each employee from the analysis results. The input data is metadata analyzed by the NLP engine. Specifically, the server applies an algorithm to determine areas of interest and expertise. For example, the server extracts information such as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X." The output is data containing the characteristic information of each employee.

[0453] Step 4:

[0454] The server matches complementary employees based on the extracted characteristics. The input data is the characteristic information of each employee. Specifically, the server searches the characteristic database and executes an algorithm to find the optimal combination. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." The output is employee pair information as a matching result.

[0455] Step 5:

[0456] The server notifies the matched staff members of a proposal for a one-on-one meeting. The input data is the staff pair information resulting from the matching. Specifically, the server automatically generates the meeting proposal and sends a notification including the date, time, and purpose to the terminal. The user receives the notification and can accept or reject the meeting. If accepted, the meeting details are added to the calendar. The output is the status information of whether the meeting was accepted or rejected.

[0457] Step 6:

[0458] The device collects feedback after the one-on-one meeting. The input data is the evaluation and impressions entered by the user after the meeting. Specifically, the device automatically presents a feedback form, which the user fills out. The feedback is sent from the device to the server. The output is the collected feedback information.

[0459] Step 7:

[0460] The server reflects the collected feedback in subsequent matches. The input data is the feedback information. Specifically, the server adjusts the matching algorithm based on the feedback to improve the accuracy of the next match. The output is an updated matching algorithm.

[0461] (Application example 1)

[0462] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0463] In conventional factories, there was a lack of efficient cooperation between workers and factory robots. As a result, it was difficult to improve productivity and optimize work. Furthermore, there was no way to promote appropriate matching or communication between workers and robots, which led to problems such as a decline in work efficiency and an increase in work errors.

[0464] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0465] In this invention, the server includes means for collecting data from in-house communication tools, information sharing tools, and employee information management tools, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one meetings between the matched employees, means for collecting feedback after the one-on-one meetings, means for collecting and analyzing information on workers and factory robots in the factory, means for matching complementary workers and factory robots, means for proposing cooperative work to the matched workers and factory robots, and means for collecting feedback after the cooperative work. This enables efficient cooperation and optimal matching between workers and factory robots.

[0466] An "internal communication tool" is an electronic message exchange system used within a company, and is a tool primarily used to promote communication between employees.

[0467] An "information sharing tool" is an electronic platform that allows employees to efficiently collect, share, and refer to information.

[0468] An "employee information management tool" is a system that manages basic employee information, work performance, skill data, etc.

[0469] A "natural language processing engine" is a technology that uses computers to understand, analyze, and generate human language.

[0470] "Matching employees with complementary characteristics" is the process of selecting and combining employees who can complement each other's lacking skills and knowledge.

[0471] The "1-on-1 meeting proposal method" is a system that notifies matched employees to hold individual interviews and proposes a schedule.

[0472] "Feedback collection means" is a system for collecting impressions and evaluations from participants after one-on-one meetings or collaborative work.

[0473] "Factory workers" are employees in charge of production, manufacturing, and other tasks in a factory.

[0474] A "factory robot" is a mechanical device used to automate work in a factory.

[0475] The "cooperative work proposal means" is a mechanism that notifies the matched worker and robot of a proposal to work together.

[0476] The system for realizing this invention consists of a server, a terminal, and a user. The server has the following functions:

[0477] 1. Data Collection

[0478] The server collects data from in-house communication tools, information sharing tools, and employee information management tools, and accumulates a variety of data, such as messages, comments, and basic information about workers and robots.

[0479] 2. Data Analysis

[0480] The server analyzes the collected data using a natural language processing (NLP) engine. It uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of messages. For example, it analyzes "frequent mentions of the project" and "positive comments about technology."

[0481] 3. Feature Extraction

[0482] The server extracts the characteristics of each worker and robot from the analysis results. These characteristics refer to the areas in which the worker or robot is primarily interested, areas in which they excel, or challenges they are currently facing. For example, an analysis could show that a particular worker has a characteristic such as "being very interested in AI technology."

[0483] 4. Matching

[0484] Based on the extracted features, the server automatically matches workers and robots with complementary characteristics, for example, a worker who is interested in AI technology with a robot with extensive practical experience in AI technology.

[0485] 5. Proposal for collaboration

[0486] The server notifies the matched worker and robot of the proposed collaboration. The notification includes an overview and purpose of the proposed collaboration. The user receives this notification and can approve or reject the collaboration.

[0487] 6. Gathering Feedback

[0488] After the collaborative work is completed, the device collects feedback from the workers. This feedback will be used for future matching. For example, comments such as "The work was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0489] Specific examples

[0490] For example, suppose a worker in a factory who is very interested in AI technology is struggling with a technical issue in a certain project. At the same time, a robot with extensive knowledge of AI technology may be working on another project. The server collects this data and analyzes that the worker frequently posts messages seeking advice on technical issues. It also analyzes that the robot has a great deal of technical knowledge about AI technology. As a result, the server optimally matches the worker with the robot and proposes a collaborative task. After the task is completed, feedback from the worker is collected and reflected in the matching algorithm for the next task.

[0491] Example prompts to input to the generative AI model

[0492] Run a program that helps match workers who are highly interested in AI technology with robots that use AI technology to perform precision work, and automatically suggest a one-on-one meeting.

[0493] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0494] Step 1:

[0495] The server collects data from the company's internal communication tools, information sharing tools, and employee information management tools. Specifically, data such as worker messages, comments, basic information, and robot operation status is sent to the server. Input data is in text format, and output data is saved in database format.

[0496] Step 2:

[0497] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of the messages. The input data is in text format, and the output data is saved as a feature vector.

[0498] Step 3:

[0499] The server extracts the characteristics of the worker and the robot from the analysis results. Specifically, it expresses information such as the worker's interests and areas of expertise, the current work situation, and the robot's characteristics and functions in vector format. The input data is the NLP analysis results, and the output data is a feature vector.

[0500] Step 4:

[0501] The server matches workers and robots with complementary characteristics based on the extracted features. Specifically, it uses sklearn's cosine_similarity function to calculate similarity scores and determine the optimal pair. The input data is a feature vector, and the output data is a pair list of matching results.

[0502] Step 5:

[0503] The server notifies the matched worker and robot of the proposed collaborative work. Specifically, it sends an overview and purpose of the collaborative work via email or a notification system. The input data is a list of matching results, and the output data is a notification message.

[0504] Step 6:

[0505] The terminal collects feedback from the workers after the collaborative work is completed. Specifically, a feedback form is provided to the workers, and they are asked to enter their impressions and evaluations. The input data are the responses to the feedback form, and the output data is stored in a feedback database.

[0506] Step 7:

[0507] The server reflects the collected feedback in the matching algorithm for the next time onward. Specifically, it analyzes the feedback data and adjusts the matching conditions. The input data is the feedback data, and the output data is the adjusted matching algorithm.

[0508] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0509] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, matches complementary employees, and proposes one-on-one meetings in order to promote appropriate communication between employees. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and optimizes matching and one-on-one meeting proposals based on that information.

[0510] 1. Data Collection

[0511] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[0512] 2. Data Analysis

[0513] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[0514] 3. Emotion recognition

[0515] The server uses an emotion engine to recognize the user's emotions from the analyzed data. For example, it can recognize the user's emotional state, such as "the user is feeling stressed" or "the user is motivated," from the tone and wording of the message.

[0516] 4. Feature Extraction

[0517] The server extracts each employee's characteristics based on the results of the NLP and emotion engine. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can be determined that Person A has the characteristics of being "very interested in AI technology" and "currently feeling stressed."

[0518] 5. Matching

[0519] The server automatically matches employees with complementary characteristics based on the extracted features. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other's emotions.

[0520] 6. Proposal for 1-on-1 meetings

[0521] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or decline the meeting.

[0522] 7. Gathering Feedback

[0523] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0524] Specific examples

[0525] For example, suppose there is "Person A, who is struggling with the technical issues of Project A," and "Person B, who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. Furthermore, the emotion engine recognizes that Person A is feeling stressed, and adjusts the timing of the meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[0526] In this way, the system of the present invention, which is combined with an emotion engine, can realize effective one-on-one meetings between employees and further improve the quality of communication.

[0527] The processing flow will be explained below.

[0528] Step 1:

[0529] Data collection

[0530] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[0531] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[0532] Step 2:

[0533] Data Preprocessing

[0534] The server cleans the collected data before natural language processing.

[0535] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[0536] Step 3:

[0537] Performing Natural Language Processing (NLP)

[0538] The server performs natural language processing on the preprocessed data.

[0539] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[0540] Step 4:

[0541] emotion recognition

[0542] The server uses an emotion engine to recognize the user's emotions from the data analyzed by natural language processing.

[0543] Specific operation: The server analyzes the tone and wording of the message and recognizes the user's emotional state, such as "the user is feeling stressed" or "the user is motivated."

[0544] Step 5:

[0545] Feature Extraction

[0546] The server extracts the characteristics of each employee based on the results of NLP and the emotion engine.

[0547] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[0548] Step 6:

[0549] Executing the matching algorithm

[0550] The server matches complementary employees using feature vectors and emotional states.

[0551] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores. It also prioritizes employees with similar emotional states.

[0552] Step 7:

[0553] Proposal for 1-on-1 meetings

[0554] The server sends a notification to the matched employees proposing a one-on-one meeting.

[0555] Specific operation: The server checks employees' calendars (e.g., Google Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[0556] Step 8:

[0557] Meeting Approval

[0558] A user accepts or declines a proposed 1-on-1 meeting.

[0559] Specific behavior: The user clicks the link in the notification they received and selects the Accept or Decline button for the meeting on a dedicated web page.

[0560] Step 9:

[0561] Gathering feedback

[0562] The device collects feedback from participants after one-on-one meetings.

[0563] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[0564] Step 10:

[0565] Feedback Analysis

[0566] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[0567] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[0568] Through these processing steps, the system sets up effective one-on-one meetings between employees, promotes communication within the organization, and achieves more effective matching by taking emotional states into account.

[0569] Example 2

[0570] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0571] In modern companies, proper communication between employees is essential for improving work efficiency and employee satisfaction. However, problems often arise due to a lack of communication between employees or meetings held at inappropriate times. Furthermore, there is an issue of ineffective one-on-one meetings being held because communication matching does not take into account employees' emotional states. To solve this, a system is needed that can identify the characteristics of employees, optimally match them, and suggest one-on-one meetings at times that take into account their emotional states.

[0572] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for recognizing employee emotions using emotion recognition means, means for matching employees who complement each other, means for proposing one-on-one meetings between matched employees, and means for collecting feedback after the one-on-one meetings. This promotes appropriate communication between employees and enables effective one-on-one meetings, thereby improving work efficiency and employee satisfaction.

[0573] "Communication tools" are means for exchanging messages or information in digital form, including chat tools, email systems, and instant messaging services.

[0574] "Information sharing tools" are means for aggregating information within an organization and providing it in a form that is easily accessible to members, and include wikis, document management systems, collaboration tools, etc.

[0575] "Employee information management means" refers to means for managing basic information, performance, skills, work history, etc., related to employees, and includes personnel management systems and databases.

[0576] "Natural language processing" is a technique for analyzing collected text data to understand, classify, or extract sentiment from its content.

[0577] "Feature extraction" is the process of identifying characteristics such as employees' areas of interest, areas of expertise, challenges they face, and emotional states from the analyzed data.

[0578] "Emotion recognition means" refers to technology for recognizing a user's emotional state based on text data, and includes machine learning algorithms and analysis engines.

[0579] A "matching method" is an algorithm or mechanism that automatically pairs employees with complementary characteristics based on the extracted characteristics.

[0580] "Method for proposing 1-on-1 meetings" is the process of sending notifications to matched employees to propose individual meetings.

[0581] "Means for collecting feedback" refers to a system for gathering opinions and impressions from participants after one-on-one meetings, and includes surveys and review systems.

[0582] This invention is a system for promoting appropriate communication between employees. This system is configured with a server at its core, and collects data from in-house communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., personnel management systems), and analyzes and processes this data to match mutually complementary employees and propose one-on-one meetings.

[0583] 1. Data Collection

[0584] The server uses API connections to collect data from chat tools (e.g., Slack), information sharing tools (e.g., Confluence), and human resources management systems (e.g., Workday). Specifically, data such as messages, comments, and basic information obtained from each tool is stored in the server's database. During this process, appropriate API calls and data format conversions are made.

[0585] 2. Data Analysis

[0586] The server then passes the collected data to a natural language processing (NLP) engine such as Google Cloud Natural Language API to analyze the meaning, sentiment, and topic of the messages, allowing it to extract, for example, "frequent mentions of technical challenges in Project A" or "positive comments about new technologies."

[0587] 3. Emotion recognition

[0588] The server then uses an emotion recognition engine like Affectiva to identify the user's emotions from the analyzed data, identifying emotional states such as "the user is stressed" or "the user is motivated" based on the tone and phrasing of the message.

[0589] 4. Feature Extraction

[0590] Based on the results of the NLP engine and emotion recognition engine, the server extracts the characteristics of each employee. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can reveal that employee A is "very interested in AI technology" and "currently feeling stressed."

[0591] 5. Matching

[0592] The server automatically matches employees with complementary traits based on the extracted characteristics. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." It also takes into account emotional states, forming pairs that are less likely to be influenced by each other's emotions.

[0593] 6. Proposal for 1-on-1 meetings

[0594] Once matching is complete, the server sends a notification proposing a one-on-one meeting to the devices of the employees. This notification includes the proposed date, time, and purpose of the meeting. Users can receive this notification and accept or reject the meeting. Specifically, the notification will say, "I propose a one-on-one meeting between Mr. A and Mr. B to discuss the technical issues of Project A."

[0595] 7. Gathering Feedback

[0596] After the one-on-one meeting ends, the device collects feedback from the user. This feedback is used to help with future matching. For example, specific opinions such as "The meeting was very meaningful" or "The topic we discussed was inappropriate" are collected, and the server analyzes them and reflects them in future matching algorithms.

[0597] Specific examples

[0598] For example, suppose employee A is struggling with "technical issues in Project A." The server collects employee A's messages from Slack or other services and analyzes them using the Google Cloud Natural Language API, determining that employee A is seeking advice on the technical issues. At the same time, it uses an emotion recognition engine such as Affectiva to determine that employee A is feeling stressed. The server then identifies employee B, who is knowledgeable about Project A, and matches employee A and employee B. Notifications of the proposed meeting are sent to the devices of employee A and employee B, including the proposed meeting date and time and purpose. After the meeting ends, feedback collected through the devices is reflected in the next match.

[0599] Prompt Sentence Examples

[0600] "What kind of support should you provide to an employee who is struggling with technical issues in Project A? Suggest collaboration with other employees who have technical knowledge about Project A."

[0601] This system promotes appropriate communication between employees and enables efficient and effective one-on-one meetings.

[0602] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0603] Step 1: Data collection

[0604] The server connects to internal communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., human resources management systems), and collects data from these systems using APIs. Specifically, messages, comments, basic employee information, etc. are obtained from each tool through API calls and stored in the server's database. The input is raw data obtained from each tool, and the output is data stored in a structured format in the database.

[0605] Step 2: Data analysis

[0606] The server passes the collected data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input data is the text data collected in step 1, and the meaning, sentiment, and topic of each message are extracted as output. For example, "mentions about the technical challenges of Project A" and "positive comments about new technology" are extracted from the text data. Specific operations include the process of sending data to the API and obtaining the analysis results.

[0607] Step 3: Emotion Recognition

[0608] The server passes the data analyzed in step 2 to an emotion recognition engine (e.g., Affectiva) to identify the user's emotional state. The input data is the analysis result obtained in step 2, and the user's emotional state (e.g., "feeling stressed" or "motivated") is generated as the output. Specific operations include the process of sending the analyzed data to the emotion recognition engine and returning the emotional state.

[0609] Step 4: Feature extraction

[0610] The server extracts the characteristics of each employee based on the results of the natural language processing engine and emotion recognition engine. The input data is the output of steps 2 and 3, and the output identifies each employee's characteristics (e.g., "very interested in AI technology" or "currently feeling stressed"). Specifically, the server integrates the results of each analysis and identifies the characteristics based on the feature extraction algorithm defined in the program.

[0611] Step 5: Matching

[0612] The server automatically matches employees with complementary characteristics based on the results of feature extraction. The input data are the characteristics output in step 4, and the output is a pair of matched employees. Specifically, the algorithm identifies employees with complementary characteristics based on the feature data and creates a matching list.

[0613] Step 6: Propose a one-on-one meeting

[0614] The server sends a notification of a proposed 1-on-1 meeting to the devices of the employees who have completed matching. The input data is the matching list created in step 5, and the output is a notification message that will be displayed on each employee's device. Specifically, the server generates the date, time, location, and purpose of the proposed meeting to be included in the notification and sends it to the device of each employee.

[0615] Step 7: Gather feedback

[0616] After the one-on-one meeting is over, the device collects feedback from both parties. The input data is the feedback information provided by the employee, and the output is the feedback data stored on the server. Specifically, the device displays a feedback form on the screen and sends the information entered by the user to the server. The server stores this information and uses it for future matching.

[0617] (Application example 2)

[0618] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0619] In modern factories and companies, poor communication and a lack of appropriate information exchange negatively impact production efficiency and employee motivation. In addition, there are few opportunities for employees with the right skills to meet with the right people at the right time, which can delay problem resolution. Furthermore, matching and meeting proposals that do not take into account employees' emotional state can increase stress and dissatisfaction.

[0620] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from internal information exchange means, information provision means, and personal information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each individual from the analyzed data, means for matching individuals with complementary characteristics, means for proposing one-on-one meetings between the matched individuals, means for collecting opinions after the meeting, means for recognizing emotions from the data using an emotion engine, and means for proposing optimal matching and meetings based on the recognized emotions. This enables optimal matching and meeting proposals that take into account the emotional state of employees, thereby improving the quality of communication.

[0621] "Information exchange means" are the means by which employees and workers send messages and information to each other.

[0622] An "information means" is a system that allows each employee or worker to share and access information.

[0623] "Personal information management means" refers to a system that collects, stores, and manages personal information of employees and workers within a company.

[0624] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0625] An "emotion engine" is a technology that detects and analyzes a user's emotional state from text data and voice data.

[0626] A "one-on-one meeting" is a face-to-face meeting between two specific employees or workers.

[0627] "Matching" is the process of selecting the most suitable partner based on specific criteria and conditions.

[0628] "Data collection means" refers to a method or device for collecting data from various information exchange means, information provision means, and personal information management means.

[0629] "Opinion gathering means" is the method or system for gathering participant feedback and opinions after the meeting.

[0630] The present invention provides a system that combines data collection, data analysis, feature extraction, and emotion recognition to facilitate effective communication among employees and workers. Specific embodiments are described below.

[0631] First, the server collects data from the company's internal information exchange means, information provision means, and personal information management means. Specifically, it collects messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. As a result, a variety of data, such as workers' messages, comments, and basic information, is stored on the server.

[0632] The server then analyzes the collected data using a natural language processing (NLP) engine. Using technologies that allow computers to understand and analyze human language (e.g., SpaCy and BERT), the meaning, sentiment, and trending topics of messages are extracted. For example, analysis could reveal that "solving problems with a particular machine is frequently discussed" or "positive opinions about new work methods."

[0633] Furthermore, the server recognizes the user's emotions from the analyzed data using an emotion engine (e.g., DeepMoji). From the tone and wording of the message, the server can detect emotional states such as "the user is stressed" or "the user is motivated."

[0634] The server then extracts characteristics of each worker based on the results of the NLP and emotion engine. These characteristics include the worker's main areas of interest and expertise, the challenges they are currently facing, and their emotional state. For example, the resulting characteristics may include "Mr. A is very interested in robot maintenance" or "He is currently feeling stressed."

[0635] Based on the extracted features, the server automatically matches workers with complementary characteristics. For example, "Person A, who is interested in robot maintenance," with "Person B, who has extensive practical experience in robot maintenance." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other.

[0636] Once matched, workers will receive a notification proposing a one-on-one meeting, including the date, time, and purpose of the proposed meeting, and can accept or decline the meeting.

[0637] After the meeting, the server collects feedback from the workers. This feedback will be used for future matching. Feedback such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" is collected.

[0638] For example, the following prompts can be presented to the worker:

[0639] "Are you interested in robot maintenance?", "Are you feeling stressed about your work lately?", "Do you want someone to talk to about a technical issue?"

[0640] In this way, a system combined with an emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[0641] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0642] Step 1:

[0643] The server collects data from information exchange means, information provision means, and personal information management means. Specifically, it obtains messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. The input is data from each system, and the output is a comprehensive data set of the collected data. The server manages this data in a unified manner.

[0644] Step 2:

[0645] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses NLP techniques such as SpaCy and BERT to extract the meaning of messages and trending topics. The input is the collected comprehensive dataset, and the output is the semantic analysis results and topic model after analysis. The server identifies relevant themes and keywords based on the content of each message.

[0646] Step 3:

[0647] The server recognizes the user's emotions from the data analyzed using an emotion engine. Specifically, it uses emotion analysis technologies such as DeepMoji to determine the user's emotional state from the tone and phrasing of the message. The input is data after semantic analysis, and the output is data indicating the user's emotional state. The server evaluates the emotional tone of each message and assigns an emotion tag such as positive, negative, or neutral.

[0648] Step 4:

[0649] The server extracts the characteristics of each worker based on the results of the NLP and emotion engine. Specifically, it compiles the worker's areas of interest, expertise, current problems, emotional state, etc. into a profile. The input is the analyzed semantic and emotional data, and the output is a feature profile for each worker. The server runs the feature extraction algorithm and generates a profile for each worker.

[0650] Step 5:

[0651] The server matches workers with complementary characteristics based on the extracted features. Specifically, it uses a feature matching algorithm to form pairs with complementary skills and areas of interest. The input is a feature profile, and the output is a list of matched worker pairs. The server compares each worker's profile and selects the best match.

[0652] Step 6:

[0653] The server sends a notification to the matched workers proposing a one-on-one meeting. Specifically, it sends a notification including the date, time, and purpose of the proposed meeting to the worker's device. The input is a list of matching pairs, and the output is a meeting proposal notification. The server uses a pre-configured schedule management system to suggest the optimal meeting time.

[0654] Step 7:

[0655] The user accepts or rejects the meeting proposal from the terminal. Specifically, the user checks their work schedule and decides whether the proposed meeting is appropriate. The input is the meeting proposal notification, and the output is feedback on whether the meeting is accepted or rejected. The user accepts or rejects the proposal using the terminal interface.

[0656] Step 8:

[0657] The server collects feedback from workers after the meeting. Specifically, it asks for feedback on whether the meeting was meaningful, whether the topics discussed were appropriate, etc. The input is the worker's feedback, and the output is feedback data that will be used to improve the matching algorithm for the next time onwards. The server analyzes the feedback and reflects it in improving the accuracy of the next match.

[0658] In this way, by using generative AI models and prompts, the system combined with the emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[0659] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0660] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0661] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0662] [Third embodiment]

[0663] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0664] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0665] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0666] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0667] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0668] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0669] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0670] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0671] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0672] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0673] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0674] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0675] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, matches complementary employees, and proposes one-on-one meetings to promote appropriate communication between employees. This system consists of the following components:

[0676] 1. Data Collection

[0677] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[0678] 2. Data Analysis

[0679] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[0680] 3. Feature Extraction

[0681] The server extracts the characteristics of each employee from the analysis results. Characteristics refer to the employee's main areas of interest, areas of expertise, or current challenges they are facing. For example, it can be determined that Person A has the characteristic of being "very interested in AI technology."

[0682] 4. Matching

[0683] Based on the extracted characteristics, the server automatically matches employees with complementary traits. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology."

[0684] 5. Proposal for 1-on-1 meetings

[0685] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting.

[0686] 6. Gathering Feedback

[0687] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0688] Specific examples

[0689] For example, suppose there is "Person A who is struggling with the technical issues of Project A" and "Person B who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[0690] In this way, the system of the present invention can realize effective one-on-one meetings between employees and improve the quality of communication.

[0691] The processing flow will be explained below.

[0692] Step 1:

[0693] Data collection

[0694] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[0695] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[0696] Step 2:

[0697] Data Preprocessing

[0698] The server cleans the collected data before natural language processing.

[0699] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[0700] Step 3:

[0701] Performing Natural Language Processing (NLP)

[0702] The server performs natural language processing on the preprocessed data.

[0703] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[0704] Step 4:

[0705] Feature Extraction

[0706] The server extracts the characteristics of each employee based on the results of NLP.

[0707] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[0708] Step 5:

[0709] Executing the matching algorithm

[0710] The server matches complementary employees using feature vectors.

[0711] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores.

[0712] Step 6:

[0713] Proposal for 1-on-1 meetings

[0714] The server sends a notification to the matched employees proposing a one-on-one meeting.

[0715] Specific operation: The server checks employees' calendars (e.g., Google Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[0716] Step 7:

[0717] Meeting Approval

[0718] A user accepts or declines a proposed 1-on-1 meeting.

[0719] Specific behavior: When a user receives a notification, they click the link and select the accept or decline button for the meeting on a dedicated web page.

[0720] Step 8:

[0721] Gathering feedback

[0722] The device collects feedback from participants after one-on-one meetings.

[0723] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[0724] Step 9:

[0725] Feedback Analysis

[0726] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[0727] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[0728] Through these processing steps, the system sets up effective one-on-one meetings between employees and promotes communication within the organization.

[0729] Example 1

[0730] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0731] Traditional internal communication systems lack effective ways to promote appropriate interactions between employees. As a result, opportunities for employees to share their expertise and interests are reduced, making it difficult for employees to exchange knowledge and provide support to each other. In particular, matching one-on-one meetings that take into account employees' skills and interests is often done manually, which is inefficient.

[0732] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0733] In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using a natural language processing engine, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one interviews between matched employees, means for collecting feedback after the one-on-one interviews, and means for reflecting the feedback in the next match. This makes it possible to automate appropriate matching between employees and proposals for effective one-on-one meetings, thereby promoting knowledge sharing and support between employees.

[0734] "Internal communication" means a system for sending and receiving messages used within the workplace that facilitates communication between employees.

[0735] An "information sharing tool" is a system for organizing and sharing knowledge, materials, and information within the workplace, allowing employees to access the information they need.

[0736] "Employee information management means" is a system for managing employees' personal information, skills, positions, etc., and for aggregating and managing personnel data.

[0737] "Means of collecting data" refers to the methods and technologies for collecting the necessary data from internal communication means, information sharing means, and employee information management means.

[0738] A "natural language processing engine" is a computer program that analyzes collected text data and understands its meaning and sentiment.

[0739] "Means for extracting characteristics" refers to methods and techniques for identifying and recording characteristics such as each employee's areas of interest, areas of expertise, and challenges from the analyzed data.

[0740] "Mutually complementary" means that the characteristics of different staff members complement each other.

[0741] "Matching means" refers to methods and techniques for creating optimal matches based on extracted employee characteristics.

[0742] "Means for proposing one-on-one interviews" refers to the methods and techniques for sending interview proposals to matched staff members and notifying them of the date and content of the interviews.

[0743] "Means of collecting feedback" refers to the methods and techniques for collecting evaluations and impressions from participants after one-on-one interviews and using them to help with the next matchmaking.

[0744] "Means for incorporating feedback into the next match" refers to methods and technologies for adjusting the next match algorithm based on the collected feedback to achieve a more appropriate match.

[0745] This invention is a system for promoting appropriate communication between employees. This system collects and analyzes data from internal communication methods, information sharing methods, and employee information management methods, and matches mutually complementary employees to propose one-on-one meetings. The system consists of the following components:

[0746] Data collection

[0747] The server collects data from internal communication methods (e.g., messaging apps), information sharing methods (e.g., document management systems), and employee information management methods (e.g., personnel management systems). Specifically, the server periodically obtains data from these methods using APIs. For example, it collects message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from personnel management systems.

[0748] Data analysis

[0749] The server analyzes the collected data using a natural language processing (NLP) engine. Specific software used is a generative AI model such as OpenAI GPT-3. The server passes the acquired data to the NLP engine, which performs topic classification and sentiment analysis of the messages. The analysis results include "Project X's technical challenges are frequently mentioned" and "positive comments."

[0750] Feature Extraction

[0751] The server extracts the characteristics of each employee from the analysis results. Based on the analysis results, the server applies an algorithm to determine each employee's areas of interest and expertise. For example, the server records such things as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X."

[0752] matching

[0753] Based on the extracted features, the server automatically matches employees with complementary characteristics. The server searches the feature database and runs an algorithm to find the optimal combination. For example, "Person A, who is interested in AI technology," and "Person B, who has extensive practical experience in AI technology," are matched as the optimal pair.

[0754] Proposal for 1-on-1 meetings

[0755] The server notifies the devices of the matched employees of a proposed one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting. If accepted, the meeting is added to the calendar.

[0756] Gathering feedback

[0757] The device collects feedback after the one-on-one meeting. After the meeting ends, the device automatically displays a feedback form, and the user enters their evaluation and thoughts. The collected feedback is sent to the server and reflected in future matches.

[0758] Specific examples

[0759] For example, consider two employees: "Employee A, who is struggling with the technical issues of Project X," and "Employee B, who is knowledgeable about Project X." The server collects messages about "Project X's technical issues" from a messaging app and uses an NLP engine to analyze "statements seeking advice on the technical issues." Meanwhile, it is analyzed that Person B is "providing technical knowledge about Project X." The server performs matching based on these characteristics and proposes a one-on-one meeting between Person A and Person B. This proposal is notified to both devices, and if the users approve the meeting, the meeting will be held at the specified date and time. After the meeting, the devices collect feedback and send the results to the server, which will be reflected in the matching algorithm for future meetings.

[0760] Prompt Sentence Examples

[0761] "Please explain the specific steps to match employee A, who is struggling with a technical issue in Project X, with employee B, who is knowledgeable about Project X."

[0762] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0763] Step 1:

[0764] The server collects data from internal communication methods, information sharing methods, and employee information management methods. The input data includes message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from the personnel management system. Specifically, the server periodically retrieves this data using APIs. The output is to store all collected data in the server's database.

[0765] Step 2:

[0766] The server analyzes the collected data using a natural language processing (NLP) engine. The input data is the collected messages, documents, and employee information. Specifically, the server passes this data to an NLP engine (e.g., OpenAI GPT-3) to perform topic classification and sentiment analysis of the messages. The output is metadata containing the topic and sentiment information as the analysis results. The analysis results are stored in the server's database.

[0767] Step 3:

[0768] The server extracts the characteristics of each employee from the analysis results. The input data is metadata analyzed by the NLP engine. Specifically, the server applies an algorithm to determine areas of interest and expertise. For example, the server extracts information such as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X." The output is data containing the characteristic information of each employee.

[0769] Step 4:

[0770] The server matches complementary employees based on the extracted characteristics. The input data is the characteristic information of each employee. Specifically, the server searches the characteristic database and executes an algorithm to find the optimal combination. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." The output is employee pair information as a matching result.

[0771] Step 5:

[0772] The server notifies the matched staff members of a proposal for a one-on-one meeting. The input data is the staff pair information resulting from the matching. Specifically, the server automatically generates the meeting proposal and sends a notification including the date, time, and purpose to the terminal. The user receives the notification and can accept or reject the meeting. If accepted, the meeting details are added to the calendar. The output is the status information of whether the meeting was accepted or rejected.

[0773] Step 6:

[0774] The device collects feedback after the one-on-one meeting. The input data is the evaluation and impressions entered by the user after the meeting. Specifically, the device automatically presents a feedback form, which the user fills out. The feedback is sent from the device to the server. The output is the collected feedback information.

[0775] Step 7:

[0776] The server reflects the collected feedback in subsequent matches. The input data is the feedback information. Specifically, the server adjusts the matching algorithm based on the feedback to improve the accuracy of the next match. The output is an updated matching algorithm.

[0777] (Application example 1)

[0778] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0779] In conventional factories, there was a lack of efficient cooperation between workers and factory robots. As a result, it was difficult to improve productivity and optimize work. Furthermore, there was no way to promote appropriate matching or communication between workers and robots, which led to problems such as a decline in work efficiency and an increase in work errors.

[0780] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0781] In this invention, the server includes means for collecting data from in-house communication tools, information sharing tools, and employee information management tools, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one meetings between the matched employees, means for collecting feedback after the one-on-one meetings, means for collecting and analyzing information on workers and factory robots in the factory, means for matching complementary workers and factory robots, means for proposing cooperative work to the matched workers and factory robots, and means for collecting feedback after the cooperative work. This enables efficient cooperation and optimal matching between workers and factory robots.

[0782] An "internal communication tool" is an electronic message exchange system used within a company, and is a tool primarily used to promote communication between employees.

[0783] An "information sharing tool" is an electronic platform that allows employees to efficiently collect, share, and refer to information.

[0784] An "employee information management tool" is a system that manages basic employee information, work performance, skill data, etc.

[0785] A "natural language processing engine" is a technology that uses computers to understand, analyze, and generate human language.

[0786] "Matching employees with complementary characteristics" is the process of selecting and combining employees who can complement each other's lacking skills and knowledge.

[0787] The "1-on-1 meeting proposal method" is a system that notifies matched employees to hold individual interviews and proposes a schedule.

[0788] "Feedback collection means" is a system for collecting impressions and evaluations from participants after one-on-one meetings or collaborative work.

[0789] "Factory workers" are employees in charge of production, manufacturing, and other tasks in a factory.

[0790] A "factory robot" is a mechanical device used to automate work in a factory.

[0791] The "cooperative work proposal means" is a mechanism that notifies the matched worker and robot of a proposal to work together.

[0792] The system for realizing this invention consists of a server, a terminal, and a user. The server has the following functions:

[0793] 1. Data Collection

[0794] The server collects data from in-house communication tools, information sharing tools, and employee information management tools, and accumulates a variety of data, such as messages, comments, and basic information about workers and robots.

[0795] 2. Data Analysis

[0796] The server analyzes the collected data using a natural language processing (NLP) engine. It uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of messages. For example, it analyzes "frequent mentions of the project" and "positive comments about technology."

[0797] 3. Feature Extraction

[0798] The server extracts the characteristics of each worker and robot from the analysis results. These characteristics refer to the areas in which the worker or robot is primarily interested, areas in which they excel, or challenges they are currently facing. For example, an analysis could show that a particular worker has a characteristic such as "being very interested in AI technology."

[0799] 4. Matching

[0800] Based on the extracted features, the server automatically matches workers and robots with complementary characteristics, for example, a worker who is interested in AI technology with a robot with extensive practical experience in AI technology.

[0801] 5. Proposal for collaboration

[0802] The server notifies the matched worker and robot of the proposed collaboration. The notification includes an overview and purpose of the proposed collaboration. The user receives this notification and can approve or reject the collaboration.

[0803] 6. Gathering Feedback

[0804] After the collaborative work is completed, the device collects feedback from the workers. This feedback will be used for future matching. For example, comments such as "The work was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0805] Specific examples

[0806] For example, suppose a worker in a factory who is very interested in AI technology is struggling with a technical issue in a certain project. At the same time, a robot with extensive knowledge of AI technology may be working on another project. The server collects this data and analyzes that the worker frequently posts messages seeking advice on technical issues. It also analyzes that the robot has a great deal of technical knowledge about AI technology. As a result, the server optimally matches the worker with the robot and proposes a collaborative task. After the task is completed, feedback from the worker is collected and reflected in the matching algorithm for the next task.

[0807] Example prompts to input to the generative AI model

[0808] Run a program that helps match workers who are highly interested in AI technology with robots that use AI technology to perform precision work, and automatically suggest a one-on-one meeting.

[0809] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0810] Step 1:

[0811] The server collects data from the company's internal communication tools, information sharing tools, and employee information management tools. Specifically, data such as worker messages, comments, basic information, and robot operation status is sent to the server. Input data is in text format, and output data is saved in database format.

[0812] Step 2:

[0813] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of the messages. The input data is in text format, and the output data is saved as a feature vector.

[0814] Step 3:

[0815] The server extracts the characteristics of the worker and the robot from the analysis results. Specifically, it expresses information such as the worker's interests and areas of expertise, the current work situation, and the robot's characteristics and functions in vector format. The input data is the NLP analysis results, and the output data is a feature vector.

[0816] Step 4:

[0817] The server matches workers and robots with complementary characteristics based on the extracted features. Specifically, it uses sklearn's cosine_similarity function to calculate similarity scores and determine the optimal pair. The input data is a feature vector, and the output data is a pair list of matching results.

[0818] Step 5:

[0819] The server notifies the matched worker and robot of the proposed collaborative work. Specifically, it sends an overview and purpose of the collaborative work via email or a notification system. The input data is a list of matching results, and the output data is a notification message.

[0820] Step 6:

[0821] The terminal collects feedback from the workers after the collaborative work is completed. Specifically, a feedback form is provided to the workers, and they are asked to enter their impressions and evaluations. The input data are the responses to the feedback form, and the output data is stored in a feedback database.

[0822] Step 7:

[0823] The server reflects the collected feedback in the matching algorithm for the next time onward. Specifically, it analyzes the feedback data and adjusts the matching conditions. The input data is the feedback data, and the output data is the adjusted matching algorithm.

[0824] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0825] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, matches complementary employees, and proposes one-on-one meetings in order to promote appropriate communication between employees. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and optimizes matching and one-on-one meeting proposals based on that information.

[0826] 1. Data Collection

[0827] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[0828] 2. Data Analysis

[0829] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[0830] 3. Emotion recognition

[0831] The server uses an emotion engine to recognize the user's emotions from the analyzed data. For example, it can recognize the user's emotional state, such as "the user is feeling stressed" or "the user is motivated," from the tone and wording of the message.

[0832] 4. Feature Extraction

[0833] The server extracts each employee's characteristics based on the results of the NLP and emotion engine. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can be determined that Person A has the characteristics of being "very interested in AI technology" and "currently feeling stressed."

[0834] 5. Matching

[0835] The server automatically matches employees with complementary characteristics based on the extracted features. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other's emotions.

[0836] 6. Proposal for 1-on-1 meetings

[0837] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or decline the meeting.

[0838] 7. Gathering Feedback

[0839] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[0840] Specific examples

[0841] For example, suppose there is "Person A, who is struggling with the technical issues of Project A," and "Person B, who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. Furthermore, the emotion engine recognizes that Person A is feeling stressed, and adjusts the timing of the meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[0842] In this way, the system of the present invention, which is combined with an emotion engine, can realize effective one-on-one meetings between employees and further improve the quality of communication.

[0843] The processing flow will be explained below.

[0844] Step 1:

[0845] Data collection

[0846] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[0847] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[0848] Step 2:

[0849] Data Preprocessing

[0850] The server cleans the collected data before natural language processing.

[0851] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[0852] Step 3:

[0853] Performing Natural Language Processing (NLP)

[0854] The server performs natural language processing on the preprocessed data.

[0855] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[0856] Step 4:

[0857] emotion recognition

[0858] The server uses an emotion engine to recognize the user's emotions from the data analyzed by natural language processing.

[0859] Specific operation: The server analyzes the tone and wording of the message and recognizes the user's emotional state, such as "the user is feeling stressed" or "the user is motivated."

[0860] Step 5:

[0861] Feature Extraction

[0862] The server extracts the characteristics of each employee based on the results of NLP and the emotion engine.

[0863] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[0864] Step 6:

[0865] Executing the matching algorithm

[0866] The server matches complementary employees using feature vectors and emotional states.

[0867] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores. It also prioritizes employees with similar emotional states.

[0868] Step 7:

[0869] Proposal for 1-on-1 meetings

[0870] The server sends a notification to the matched employees proposing a one-on-one meeting.

[0871] Specific operation: The server checks employees' calendars (e.g., Google Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[0872] Step 8:

[0873] Meeting Approval

[0874] A user accepts or declines a proposed 1-on-1 meeting.

[0875] Specific behavior: The user clicks the link in the notification they received and selects the Accept or Decline button for the meeting on a dedicated web page.

[0876] Step 9:

[0877] Gathering feedback

[0878] The device collects feedback from participants after one-on-one meetings.

[0879] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[0880] Step 10:

[0881] Feedback Analysis

[0882] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[0883] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[0884] Through these processing steps, the system sets up effective one-on-one meetings between employees, promotes communication within the organization, and achieves more effective matching by taking emotional states into account.

[0885] Example 2

[0886] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0887] In modern companies, proper communication between employees is essential for improving work efficiency and employee satisfaction. However, problems often arise due to a lack of communication between employees or meetings held at inappropriate times. Furthermore, there is an issue of ineffective one-on-one meetings being held because communication matching does not take into account employees' emotional states. To solve this, a system is needed that can identify the characteristics of employees, optimally match them, and suggest one-on-one meetings at times that take into account their emotional states.

[0888] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for recognizing employee emotions using emotion recognition means, means for matching employees who complement each other, means for proposing one-on-one meetings between matched employees, and means for collecting feedback after the one-on-one meetings. This promotes appropriate communication between employees and enables effective one-on-one meetings, thereby improving work efficiency and employee satisfaction.

[0889] "Communication tools" are means for exchanging messages or information in digital form, including chat tools, email systems, and instant messaging services.

[0890] "Information sharing tools" are means for aggregating information within an organization and providing it in a form that is easily accessible to members, and include wikis, document management systems, collaboration tools, etc.

[0891] "Employee information management means" refers to means for managing basic information, performance, skills, work history, etc., related to employees, and includes personnel management systems and databases.

[0892] "Natural language processing" is a technique for analyzing collected text data to understand, classify, or extract sentiment from its content.

[0893] "Feature extraction" is the process of identifying characteristics such as employees' areas of interest, areas of expertise, challenges they face, and emotional states from the analyzed data.

[0894] "Emotion recognition means" refers to technology for recognizing a user's emotional state based on text data, and includes machine learning algorithms and analysis engines.

[0895] A "matching method" is an algorithm or mechanism that automatically pairs employees with complementary characteristics based on the extracted characteristics.

[0896] "Method for proposing 1-on-1 meetings" is the process of sending notifications to matched employees to propose individual meetings.

[0897] "Means for collecting feedback" refers to a system for gathering opinions and impressions from participants after one-on-one meetings, and includes surveys and review systems.

[0898] This invention is a system for promoting appropriate communication between employees. This system is configured with a server at its core, and collects data from in-house communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., personnel management systems), and analyzes and processes this data to match mutually complementary employees and propose one-on-one meetings.

[0899] 1. Data Collection

[0900] The server uses API connections to collect data from chat tools (e.g., Slack), information sharing tools (e.g., Confluence), and human resources management systems (e.g., Workday). Specifically, data such as messages, comments, and basic information obtained from each tool is stored in the server's database. During this process, appropriate API calls and data format conversions are made.

[0901] 2. Data Analysis

[0902] The server then passes the collected data to a natural language processing (NLP) engine such as Google Cloud Natural Language API to analyze the meaning, sentiment, and topic of the messages, allowing it to extract, for example, "frequent mentions of technical challenges in Project A" or "positive comments about new technologies."

[0903] 3. Emotion recognition

[0904] The server then uses an emotion recognition engine like Affectiva to identify the user's emotions from the analyzed data, identifying emotional states such as "the user is stressed" or "the user is motivated" based on the tone and phrasing of the message.

[0905] 4. Feature Extraction

[0906] Based on the results of the NLP engine and emotion recognition engine, the server extracts the characteristics of each employee. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can reveal that employee A is "very interested in AI technology" and "currently feeling stressed."

[0907] 5. Matching

[0908] The server automatically matches employees with complementary traits based on the extracted characteristics. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." It also takes into account emotional states, forming pairs that are less likely to be influenced by each other's emotions.

[0909] 6. Proposal for 1-on-1 meetings

[0910] Once matching is complete, the server sends a notification proposing a one-on-one meeting to the devices of the employees. This notification includes the proposed date, time, and purpose of the meeting. Users can receive this notification and accept or reject the meeting. Specifically, the notification will say, "I propose a one-on-one meeting between Mr. A and Mr. B to discuss the technical issues of Project A."

[0911] 7. Gathering Feedback

[0912] After the one-on-one meeting ends, the device collects feedback from the user. This feedback is used to help with future matching. For example, specific opinions such as "The meeting was very meaningful" or "The topic we discussed was inappropriate" are collected, and the server analyzes them and reflects them in future matching algorithms.

[0913] Specific examples

[0914] For example, suppose employee A is struggling with "technical issues in Project A." The server collects employee A's messages from Slack or other services and analyzes them using the Google Cloud Natural Language API, determining that employee A is seeking advice on the technical issues. At the same time, it uses an emotion recognition engine such as Affectiva to determine that employee A is feeling stressed. The server then identifies employee B, who is knowledgeable about Project A, and matches employee A and employee B. Notifications of the proposed meeting are sent to the devices of employee A and employee B, including the proposed meeting date and time and purpose. After the meeting ends, feedback collected through the devices is reflected in the next match.

[0915] Prompt Sentence Examples

[0916] "What kind of support should you provide to an employee who is struggling with technical issues in Project A? Suggest collaboration with other employees who have technical knowledge about Project A."

[0917] This system promotes appropriate communication between employees and enables efficient and effective one-on-one meetings.

[0918] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0919] Step 1: Data collection

[0920] The server connects to internal communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., human resources management systems), and collects data from these systems using APIs. Specifically, messages, comments, basic employee information, etc. are obtained from each tool through API calls and stored in the server's database. The input is raw data obtained from each tool, and the output is data stored in a structured format in the database.

[0921] Step 2: Data analysis

[0922] The server passes the collected data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input data is the text data collected in step 1, and the meaning, sentiment, and topic of each message are extracted as output. For example, "mentions about the technical challenges of Project A" and "positive comments about new technology" are extracted from the text data. Specific operations include the process of sending data to the API and obtaining the analysis results.

[0923] Step 3: Emotion Recognition

[0924] The server passes the data analyzed in step 2 to an emotion recognition engine (e.g., Affectiva) to identify the user's emotional state. The input data is the analysis result obtained in step 2, and the user's emotional state (e.g., "feeling stressed" or "motivated") is generated as the output. Specific operations include the process of sending the analyzed data to the emotion recognition engine and returning the emotional state.

[0925] Step 4: Feature extraction

[0926] The server extracts the characteristics of each employee based on the results of the natural language processing engine and emotion recognition engine. The input data is the output of steps 2 and 3, and the output identifies each employee's characteristics (e.g., "very interested in AI technology" or "currently feeling stressed"). Specifically, the server integrates the results of each analysis and identifies the characteristics based on the feature extraction algorithm defined in the program.

[0927] Step 5: Matching

[0928] The server automatically matches employees with complementary characteristics based on the results of feature extraction. The input data are the characteristics output in step 4, and the output is a pair of matched employees. Specifically, the algorithm identifies employees with complementary characteristics based on the feature data and creates a matching list.

[0929] Step 6: Propose a one-on-one meeting

[0930] The server sends a notification of a proposed 1-on-1 meeting to the devices of the employees who have completed matching. The input data is the matching list created in step 5, and the output is a notification message that will be displayed on each employee's device. Specifically, the server generates the date, time, location, and purpose of the proposed meeting to be included in the notification and sends it to the device of each employee.

[0931] Step 7: Gather feedback

[0932] After the one-on-one meeting is over, the device collects feedback from both parties. The input data is the feedback information provided by the employee, and the output is the feedback data stored on the server. Specifically, the device displays a feedback form on the screen and sends the information entered by the user to the server. The server stores this information and uses it for future matching.

[0933] (Application example 2)

[0934] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0935] In modern factories and companies, poor communication and a lack of appropriate information exchange negatively impact production efficiency and employee motivation. In addition, there are few opportunities for employees with the right skills to meet with the right people at the right time, which can delay problem resolution. Furthermore, matching and meeting proposals that do not take into account employees' emotional state can increase stress and dissatisfaction.

[0936] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from internal information exchange means, information provision means, and personal information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each individual from the analyzed data, means for matching individuals with complementary characteristics, means for proposing one-on-one meetings between the matched individuals, means for collecting opinions after the meeting, means for recognizing emotions from the data using an emotion engine, and means for proposing optimal matching and meetings based on the recognized emotions. This enables optimal matching and meeting proposals that take into account the emotional state of employees, thereby improving the quality of communication.

[0937] "Information exchange means" are the means by which employees and workers send messages and information to each other.

[0938] An "information means" is a system that allows each employee or worker to share and access information.

[0939] "Personal information management means" refers to a system that collects, stores, and manages personal information of employees and workers within a company.

[0940] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0941] An "emotion engine" is a technology that detects and analyzes a user's emotional state from text data and voice data.

[0942] A "one-on-one meeting" is a face-to-face meeting between two specific employees or workers.

[0943] "Matching" is the process of selecting the most suitable partner based on specific criteria and conditions.

[0944] "Data collection means" refers to a method or device for collecting data from various information exchange means, information provision means, and personal information management means.

[0945] "Opinion gathering means" is the method or system for gathering participant feedback and opinions after the meeting.

[0946] The present invention provides a system that combines data collection, data analysis, feature extraction, and emotion recognition to facilitate effective communication among employees and workers. Specific embodiments are described below.

[0947] First, the server collects data from the company's internal information exchange means, information provision means, and personal information management means. Specifically, it collects messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. As a result, a variety of data, such as workers' messages, comments, and basic information, is stored on the server.

[0948] The server then analyzes the collected data using a natural language processing (NLP) engine. Using technologies that allow computers to understand and analyze human language (e.g., SpaCy and BERT), the meaning, sentiment, and trending topics of messages are extracted. For example, analysis could reveal that "solving problems with a particular machine is frequently discussed" or "positive opinions about new work methods."

[0949] Furthermore, the server recognizes the user's emotions from the analyzed data using an emotion engine (e.g., DeepMoji). From the tone and wording of the message, the server can detect emotional states such as "the user is stressed" or "the user is motivated."

[0950] The server then extracts characteristics of each worker based on the results of the NLP and emotion engine. These characteristics include the worker's main areas of interest and expertise, the challenges they are currently facing, and their emotional state. For example, the resulting characteristics may include "Mr. A is very interested in robot maintenance" or "He is currently feeling stressed."

[0951] Based on the extracted features, the server automatically matches workers with complementary characteristics. For example, "Person A, who is interested in robot maintenance," with "Person B, who has extensive practical experience in robot maintenance." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other.

[0952] Once matched, workers will receive a notification proposing a one-on-one meeting, including the date, time, and purpose of the proposed meeting, and can accept or decline the meeting.

[0953] After the meeting, the server collects feedback from the workers. This feedback will be used for future matching. Feedback such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" is collected.

[0954] For example, the following prompts can be presented to the worker:

[0955] "Are you interested in robot maintenance?", "Are you feeling stressed about your work lately?", "Do you want someone to talk to about a technical issue?"

[0956] In this way, a system combined with an emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[0957] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0958] Step 1:

[0959] The server collects data from information exchange means, information provision means, and personal information management means. Specifically, it obtains messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. The input is data from each system, and the output is a comprehensive data set of the collected data. The server manages this data in a unified manner.

[0960] Step 2:

[0961] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses NLP techniques such as SpaCy and BERT to extract the meaning of messages and trending topics. The input is the collected comprehensive dataset, and the output is the semantic analysis results and topic model after analysis. The server identifies relevant themes and keywords based on the content of each message.

[0962] Step 3:

[0963] The server recognizes the user's emotions from the data analyzed using an emotion engine. Specifically, it uses emotion analysis technologies such as DeepMoji to determine the user's emotional state from the tone and phrasing of the message. The input is data after semantic analysis, and the output is data indicating the user's emotional state. The server evaluates the emotional tone of each message and assigns an emotion tag such as positive, negative, or neutral.

[0964] Step 4:

[0965] The server extracts the characteristics of each worker based on the results of the NLP and emotion engine. Specifically, it compiles the worker's areas of interest, expertise, current problems, emotional state, etc. into a profile. The input is the analyzed semantic and emotional data, and the output is a feature profile for each worker. The server runs the feature extraction algorithm and generates a profile for each worker.

[0966] Step 5:

[0967] The server matches workers with complementary characteristics based on the extracted features. Specifically, it uses a feature matching algorithm to form pairs with complementary skills and areas of interest. The input is a feature profile, and the output is a list of matched worker pairs. The server compares each worker's profile and selects the best match.

[0968] Step 6:

[0969] The server sends a notification to the matched workers proposing a one-on-one meeting. Specifically, it sends a notification including the date, time, and purpose of the proposed meeting to the worker's device. The input is a list of matching pairs, and the output is a meeting proposal notification. The server uses a pre-configured schedule management system to suggest the optimal meeting time.

[0970] Step 7:

[0971] The user accepts or rejects the meeting proposal from the terminal. Specifically, the user checks their work schedule and decides whether the proposed meeting is appropriate. The input is the meeting proposal notification, and the output is feedback on whether the meeting is accepted or rejected. The user accepts or rejects the proposal using the terminal interface.

[0972] Step 8:

[0973] The server collects feedback from workers after the meeting. Specifically, it asks for feedback on whether the meeting was meaningful, whether the topics discussed were appropriate, etc. The input is the worker's feedback, and the output is feedback data that will be used to improve the matching algorithm for the next time onwards. The server analyzes the feedback and reflects it in improving the accuracy of the next match.

[0974] In this way, by using generative AI models and prompts, the system combined with the emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[0975] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0976] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0977] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0978] [Fourth embodiment]

[0979] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0980] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0981] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0982] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0983] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0984] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0985] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0986] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0987] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0988] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0989] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0990] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0991] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0992] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, matches complementary employees, and proposes one-on-one meetings to promote appropriate communication between employees. This system consists of the following components:

[0993] 1. Data Collection

[0994] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[0995] 2. Data Analysis

[0996] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[0997] 3. Feature Extraction

[0998] The server extracts the characteristics of each employee from the analysis results. Characteristics refer to the employee's main areas of interest, areas of expertise, or current challenges they are facing. For example, it can be determined that Person A has the characteristic of being "very interested in AI technology."

[0999] 4. Matching

[1000] Based on the extracted characteristics, the server automatically matches employees with complementary traits. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology."

[1001] 5. Proposal for 1-on-1 meetings

[1002] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting.

[1003] 6. Gathering Feedback

[1004] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[1005] Specific examples

[1006] For example, suppose there is "Person A who is struggling with the technical issues of Project A" and "Person B who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[1007] In this way, the system of the present invention can realize effective one-on-one meetings between employees and improve the quality of communication.

[1008] The processing flow will be explained below.

[1009] Step 1:

[1010] Data collection

[1011] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[1012] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[1013] Step 2:

[1014] Data Preprocessing

[1015] The server cleans the collected data before natural language processing.

[1016] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[1017] Step 3:

[1018] Performing Natural Language Processing (NLP)

[1019] The server performs natural language processing on the preprocessed data.

[1020] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[1021] Step 4:

[1022] Feature Extraction

[1023] The server extracts the characteristics of each employee based on the results of NLP.

[1024] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[1025] Step 5:

[1026] Executing the matching algorithm

[1027] The server matches complementary employees using feature vectors.

[1028] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores.

[1029] Step 6:

[1030] Proposal for 1-on-1 meetings

[1031] The server sends a notification to the matched employees proposing a one-on-one meeting.

[1032] Specific operation: The server checks employees' calendars (e.g., Google Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[1033] Step 7:

[1034] Meeting Approval

[1035] A user accepts or declines a proposed 1-on-1 meeting.

[1036] Specific behavior: When a user receives a notification, they click the link and select the accept or decline button for the meeting on a dedicated web page.

[1037] Step 8:

[1038] Gathering feedback

[1039] The device collects feedback from participants after one-on-one meetings.

[1040] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[1041] Step 9:

[1042] Feedback Analysis

[1043] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[1044] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[1045] Through these processing steps, the system sets up effective one-on-one meetings between employees and promotes communication within the organization.

[1046] Example 1

[1047] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1048] Traditional internal communication systems lack effective ways to promote appropriate interactions between employees. As a result, opportunities for employees to share their expertise and interests are reduced, making it difficult for employees to exchange knowledge and provide support to each other. In particular, matching one-on-one meetings that take into account employees' skills and interests is often done manually, which is inefficient.

[1049] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1050] In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using a natural language processing engine, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one interviews between matched employees, means for collecting feedback after the one-on-one interviews, and means for reflecting the feedback in the next match. This makes it possible to automate appropriate matching between employees and proposals for effective one-on-one meetings, thereby promoting knowledge sharing and support between employees.

[1051] "Internal communication" means a system for sending and receiving messages used within the workplace that facilitates communication between employees.

[1052] An "information sharing tool" is a system for organizing and sharing knowledge, materials, and information within the workplace, allowing employees to access the information they need.

[1053] "Employee information management means" is a system for managing employees' personal information, skills, positions, etc., and for aggregating and managing personnel data.

[1054] "Means of collecting data" refers to the methods and technologies for collecting the necessary data from internal communication means, information sharing means, and employee information management means.

[1055] A "natural language processing engine" is a computer program that analyzes collected text data and understands its meaning and sentiment.

[1056] "Means for extracting characteristics" refers to methods and techniques for identifying and recording characteristics such as each employee's areas of interest, areas of expertise, and challenges from the analyzed data.

[1057] "Mutually complementary" means that the characteristics of different staff members complement each other.

[1058] "Matching means" refers to methods and techniques for creating optimal matches based on extracted employee characteristics.

[1059] "Means for proposing one-on-one interviews" refers to the methods and techniques for sending interview proposals to matched staff members and notifying them of the date and content of the interviews.

[1060] "Means of collecting feedback" refers to the methods and techniques for collecting evaluations and impressions from participants after one-on-one interviews and using them to help with the next matchmaking.

[1061] "Means for incorporating feedback into the next match" refers to methods and technologies for adjusting the next match algorithm based on the collected feedback to achieve a more appropriate match.

[1062] This invention is a system for promoting appropriate communication between employees. This system collects and analyzes data from internal communication methods, information sharing methods, and employee information management methods, and matches mutually complementary employees to propose one-on-one meetings. The system consists of the following components:

[1063] Data collection

[1064] The server collects data from internal communication methods (e.g., messaging apps), information sharing methods (e.g., document management systems), and employee information management methods (e.g., personnel management systems). Specifically, the server periodically obtains data from these methods using APIs. For example, it collects message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from personnel management systems.

[1065] Data analysis

[1066] The server analyzes the collected data using a natural language processing (NLP) engine. Specific software used is a generative AI model such as OpenAI GPT-3. The server passes the acquired data to the NLP engine, which performs topic classification and sentiment analysis of the messages. The analysis results include "Project X's technical challenges are frequently mentioned" and "positive comments."

[1067] Feature Extraction

[1068] The server extracts the characteristics of each employee from the analysis results. Based on the analysis results, the server applies an algorithm to determine each employee's areas of interest and expertise. For example, the server records such things as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X."

[1069] matching

[1070] Based on the extracted features, the server automatically matches employees with complementary characteristics. The server searches the feature database and runs an algorithm to find the optimal combination. For example, "Person A, who is interested in AI technology," and "Person B, who has extensive practical experience in AI technology," are matched as the optimal pair.

[1071] Proposal for 1-on-1 meetings

[1072] The server notifies the devices of the matched employees of a proposed one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or reject the meeting. If accepted, the meeting is added to the calendar.

[1073] Gathering feedback

[1074] The device collects feedback after the one-on-one meeting. After the meeting ends, the device automatically displays a feedback form, and the user enters their evaluation and thoughts. The collected feedback is sent to the server and reflected in future matches.

[1075] Specific examples

[1076] For example, consider two employees: "Employee A, who is struggling with the technical issues of Project X," and "Employee B, who is knowledgeable about Project X." The server collects messages about "Project X's technical issues" from a messaging app and uses an NLP engine to analyze "statements seeking advice on the technical issues." Meanwhile, it is analyzed that Person B is "providing technical knowledge about Project X." The server performs matching based on these characteristics and proposes a one-on-one meeting between Person A and Person B. This proposal is notified to both devices, and if the users approve the meeting, the meeting will be held at the specified date and time. After the meeting, the devices collect feedback and send the results to the server, which will be reflected in the matching algorithm for future meetings.

[1077] Prompt Sentence Examples

[1078] "Please explain the specific steps to match employee A, who is struggling with a technical issue in Project X, with employee B, who is knowledgeable about Project X."

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Step 1:

[1081] The server collects data from internal communication methods, information sharing methods, and employee information management methods. The input data includes message history from messaging apps, new pages and edit history from document management systems, and basic employee information and skill information from the personnel management system. Specifically, the server periodically retrieves this data using APIs. The output is to store all collected data in the server's database.

[1082] Step 2:

[1083] The server analyzes the collected data using a natural language processing (NLP) engine. The input data is the collected messages, documents, and employee information. Specifically, the server passes this data to an NLP engine (e.g., OpenAI GPT-3) to perform topic classification and sentiment analysis of the messages. The output is metadata containing the topic and sentiment information as the analysis results. The analysis results are stored in the server's database.

[1084] Step 3:

[1085] The server extracts the characteristics of each employee from the analysis results. The input data is metadata analyzed by the NLP engine. Specifically, the server applies an algorithm to determine areas of interest and expertise. For example, the server extracts information such as "Person A's characteristic is a high interest in AI technology" or "Person B's characteristic is technical knowledge of Project X." The output is data containing the characteristic information of each employee.

[1086] Step 4:

[1087] The server matches complementary employees based on the extracted characteristics. The input data is the characteristic information of each employee. Specifically, the server searches the characteristic database and executes an algorithm to find the optimal combination. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." The output is employee pair information as a matching result.

[1088] Step 5:

[1089] The server notifies the matched staff members of a proposal for a one-on-one meeting. The input data is the staff pair information resulting from the matching. Specifically, the server automatically generates the meeting proposal and sends a notification including the date, time, and purpose to the terminal. The user receives the notification and can accept or reject the meeting. If accepted, the meeting details are added to the calendar. The output is the status information of whether the meeting was accepted or rejected.

[1090] Step 6:

[1091] The device collects feedback after the one-on-one meeting. The input data is the evaluation and impressions entered by the user after the meeting. Specifically, the device automatically presents a feedback form, which the user fills out. The feedback is sent from the device to the server. The output is the collected feedback information.

[1092] Step 7:

[1093] The server reflects the collected feedback in subsequent matches. The input data is the feedback information. Specifically, the server adjusts the matching algorithm based on the feedback to improve the accuracy of the next match. The output is an updated matching algorithm.

[1094] (Application example 1)

[1095] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1096] In conventional factories, there was a lack of efficient cooperation between workers and factory robots. As a result, it was difficult to improve productivity and optimize work. Furthermore, there was no way to promote appropriate matching or communication between workers and robots, which led to problems such as a decline in work efficiency and an increase in work errors.

[1097] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1098] In this invention, the server includes means for collecting data from in-house communication tools, information sharing tools, and employee information management tools, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for matching employees with complementary characteristics, means for proposing one-on-one meetings between the matched employees, means for collecting feedback after the one-on-one meetings, means for collecting and analyzing information on workers and factory robots in the factory, means for matching complementary workers and factory robots, means for proposing cooperative work to the matched workers and factory robots, and means for collecting feedback after the cooperative work. This enables efficient cooperation and optimal matching between workers and factory robots.

[1099] An "internal communication tool" is an electronic message exchange system used within a company, and is a tool primarily used to promote communication between employees.

[1100] An "information sharing tool" is an electronic platform that allows employees to efficiently collect, share, and refer to information.

[1101] An "employee information management tool" is a system that manages basic employee information, work performance, skill data, etc.

[1102] A "natural language processing engine" is a technology that uses computers to understand, analyze, and generate human language.

[1103] "Matching employees with complementary characteristics" is the process of selecting and combining employees who can complement each other's lacking skills and knowledge.

[1104] The "1-on-1 meeting proposal method" is a system that notifies matched employees to hold individual interviews and proposes a schedule.

[1105] "Feedback collection means" is a system for collecting impressions and evaluations from participants after one-on-one meetings or collaborative work.

[1106] "Factory workers" are employees in charge of production, manufacturing, and other tasks in a factory.

[1107] A "factory robot" is a mechanical device used to automate work in a factory.

[1108] The "cooperative work proposal means" is a mechanism that notifies the matched worker and robot of a proposal to work together.

[1109] The system for realizing this invention consists of a server, a terminal, and a user. The server has the following functions:

[1110] 1. Data Collection

[1111] The server collects data from in-house communication tools, information sharing tools, and employee information management tools, and accumulates a variety of data, such as messages, comments, and basic information about workers and robots.

[1112] 2. Data Analysis

[1113] The server analyzes the collected data using a natural language processing (NLP) engine. It uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of messages. For example, it analyzes "frequent mentions of the project" and "positive comments about technology."

[1114] 3. Feature Extraction

[1115] The server extracts the characteristics of each worker and robot from the analysis results. These characteristics refer to the areas in which the worker or robot is primarily interested, areas in which they excel, or challenges they are currently facing. For example, an analysis could show that a particular worker has a characteristic such as "being very interested in AI technology."

[1116] 4. Matching

[1117] Based on the extracted features, the server automatically matches workers and robots with complementary characteristics, for example, a worker who is interested in AI technology with a robot with extensive practical experience in AI technology.

[1118] 5. Proposal for collaboration

[1119] The server notifies the matched worker and robot of the proposed collaboration. The notification includes an overview and purpose of the proposed collaboration. The user receives this notification and can approve or reject the collaboration.

[1120] 6. Gathering Feedback

[1121] After the collaborative work is completed, the device collects feedback from the workers. This feedback will be used for future matching. For example, comments such as "The work was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[1122] Specific examples

[1123] For example, suppose a worker in a factory who is very interested in AI technology is struggling with a technical issue in a certain project. At the same time, a robot with extensive knowledge of AI technology may be working on another project. The server collects this data and analyzes that the worker frequently posts messages seeking advice on technical issues. It also analyzes that the robot has a great deal of technical knowledge about AI technology. As a result, the server optimally matches the worker with the robot and proposes a collaborative task. After the task is completed, feedback from the worker is collected and reflected in the matching algorithm for the next task.

[1124] Example prompts to input to the generative AI model

[1125] Run a program that helps match workers who are highly interested in AI technology with robots that use AI technology to perform precision work, and automatically suggest a one-on-one meeting.

[1126] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1127] Step 1:

[1128] The server collects data from the company's internal communication tools, information sharing tools, and employee information management tools. Specifically, data such as worker messages, comments, basic information, and robot operation status is sent to the server. Input data is in text format, and output data is saved in database format.

[1129] Step 2:

[1130] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses Python's spaCy and sklearn to extract the meaning, sentiment, and trending topics of the messages. The input data is in text format, and the output data is saved as a feature vector.

[1131] Step 3:

[1132] The server extracts the characteristics of the worker and the robot from the analysis results. Specifically, it expresses information such as the worker's interests and areas of expertise, the current work situation, and the robot's characteristics and functions in vector format. The input data is the NLP analysis results, and the output data is a feature vector.

[1133] Step 4:

[1134] The server matches workers and robots with complementary characteristics based on the extracted features. Specifically, it uses sklearn's cosine_similarity function to calculate similarity scores and determine the optimal pair. The input data is a feature vector, and the output data is a pair list of matching results.

[1135] Step 5:

[1136] The server notifies the matched worker and robot of the proposed collaborative work. Specifically, it sends an overview and purpose of the collaborative work via email or a notification system. The input data is a list of matching results, and the output data is a notification message.

[1137] Step 6:

[1138] The terminal collects feedback from the workers after the collaborative work is completed. Specifically, a feedback form is provided to the workers, and they are asked to enter their impressions and evaluations. The input data are the responses to the feedback form, and the output data is stored in a feedback database.

[1139] Step 7:

[1140] The server reflects the collected feedback in the matching algorithm for the next time onward. Specifically, it analyzes the feedback data and adjusts the matching conditions. The input data is the feedback data, and the output data is the adjusted matching algorithm.

[1141] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1142] This invention provides a system that collects and analyzes data from in-house communication tools, information sharing tools, and employee information management tools, matches complementary employees, and proposes one-on-one meetings in order to promote appropriate communication between employees. Furthermore, by combining this system with an emotion engine, it recognizes the user's emotions and optimizes matching and one-on-one meeting proposals based on that information.

[1143] 1. Data Collection

[1144] The server collects data from internal communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems). As a result, a variety of data, such as employee messages, comments, and basic information, is stored on the server.

[1145] 2. Data Analysis

[1146] The server analyzes the collected data using a natural language processing (NLP) engine. Natural language processing extracts the meaning and sentiment of messages, as well as trending topics. For example, analysis could reveal "frequent mentions of technical challenges in Project A" or "active comments about new technologies."

[1147] 3. Emotion recognition

[1148] The server uses an emotion engine to recognize the user's emotions from the analyzed data. For example, it can recognize the user's emotional state, such as "the user is feeling stressed" or "the user is motivated," from the tone and wording of the message.

[1149] 4. Feature Extraction

[1150] The server extracts each employee's characteristics based on the results of the NLP and emotion engine. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can be determined that Person A has the characteristics of being "very interested in AI technology" and "currently feeling stressed."

[1151] 5. Matching

[1152] The server automatically matches employees with complementary characteristics based on the extracted features. For example, "Person A, who is interested in AI technology," with "Person B, who has extensive practical experience in AI technology." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other's emotions.

[1153] 6. Proposal for 1-on-1 meetings

[1154] The server then sends a notification to the devices of the matched employees proposing a one-on-one meeting. The notification includes the proposed date, time, and purpose of the meeting. The user receives this notification and can accept or decline the meeting.

[1155] 7. Gathering Feedback

[1156] After the one-on-one meeting, the device collects feedback from both parties. This feedback will be used for future matching. For example, comments such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" are collected.

[1157] Specific examples

[1158] For example, suppose there is "Person A, who is struggling with the technical issues of Project A," and "Person B, who is very knowledgeable about Project A." The server collects messages related to Project A and analyzes that Person A frequently posts "messages seeking advice on technical issues." It also analyzes that Person B "has a lot of technical knowledge about Project A." As a result, the server matches Person A and Person B and proposes a one-on-one meeting. Furthermore, the emotion engine recognizes that Person A is feeling stressed, and adjusts the timing of the meeting. After the meeting, feedback from Person A and Person B is collected and reflected in the matching algorithm for future meetings.

[1159] In this way, the system of the present invention, which is combined with an emotion engine, can realize effective one-on-one meetings between employees and further improve the quality of communication.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] Data collection

[1163] The server periodically collects the latest data from in-house communication tools (e.g., chat tools), information sharing tools (e.g., Wiki), and employee information management tools (e.g., personnel management systems).

[1164] Specific operation: The server calls the API of each tool, retrieves messages, comments, and employee information in JSON format, and stores them in the database.

[1165] Step 2:

[1166] Data Preprocessing

[1167] The server cleans the collected data before natural language processing.

[1168] What happens: The server checks the data for errors, normalizes it (e.g., lowercasing the text and removing special characters), and tokenizes it.

[1169] Step 3:

[1170] Performing Natural Language Processing (NLP)

[1171] The server performs natural language processing on the preprocessed data.

[1172] Specific operation: The server uses an NLP engine (e.g., spaCy or NLTK) to perform tokenization of text data, part-of-speech tagging, entity recognition, and sentiment analysis.

[1173] Step 4:

[1174] emotion recognition

[1175] The server uses an emotion engine to recognize the user's emotions from the data analyzed by natural language processing.

[1176] Specific operation: The server analyzes the tone and wording of the message and recognizes the user's emotional state, such as "the user is feeling stressed" or "the user is motivated."

[1177] Step 5:

[1178] Feature Extraction

[1179] The server extracts the characteristics of each employee based on the results of NLP and the emotion engine.

[1180] How it works: The server generates feature vectors based on keywords and phrases and lists them for each employee. For example, it extracts features such as "AI technology," "project management," and "technical support."

[1181] Step 6:

[1182] Executing the matching algorithm

[1183] The server matches complementary employees using feature vectors and emotional states.

[1184] Specific operation: The server calculates the cosine similarity and Euclidean distance between feature vectors and selects employee pairs with relatively high scores. It also prioritizes employees with similar emotional states.

[1185] Step 7:

[1186] Proposal for 1-on-1 meetings

[1187] The server sends a notification to the matched employees proposing a one-on-one meeting.

[1188] Specific operation: The server checks employees' calendars (e.g., Google Calendar or Outlook Calendar), finds common free time, and then sends a suggestion message using the chat tool's API.

[1189] Step 8:

[1190] Meeting Approval

[1191] A user accepts or declines a proposed 1-on-1 meeting.

[1192] Specific behavior: The user clicks the link in the notification they received and selects the Accept or Decline button for the meeting on a dedicated web page.

[1193] Step 9:

[1194] Gathering feedback

[1195] The device collects feedback from participants after one-on-one meetings.

[1196] Specific operation: When the meeting ends, the device sends a message to the user containing a link to a feedback form and sends the response to the server.

[1197] Step 10:

[1198] Feedback Analysis

[1199] The server analyzes the collected feedback and incorporates it into the next matching algorithm.

[1200] How it works: The server analyzes the feedback, categorizes it into positive and negative reviews, and adjusts the algorithm accordingly.

[1201] Through these processing steps, the system sets up effective one-on-one meetings between employees, promotes communication within the organization, and achieves more effective matching by taking emotional states into account.

[1202] Example 2

[1203] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1204] In modern companies, proper communication between employees is essential for improving work efficiency and employee satisfaction. However, problems often arise due to a lack of communication between employees or meetings held at inappropriate times. Furthermore, there is an issue of ineffective one-on-one meetings being held because communication matching does not take into account employees' emotional states. To solve this, a system is needed that can identify the characteristics of employees, optimally match them, and suggest one-on-one meetings at times that take into account their emotional states.

[1205] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from in-house communication means, information sharing means, and employee information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each employee from the analyzed data, means for recognizing employee emotions using emotion recognition means, means for matching employees who complement each other, means for proposing one-on-one meetings between matched employees, and means for collecting feedback after the one-on-one meetings. This promotes appropriate communication between employees and enables effective one-on-one meetings, thereby improving work efficiency and employee satisfaction.

[1206] "Communication tools" are means for exchanging messages or information in digital form, including chat tools, email systems, and instant messaging services.

[1207] "Information sharing tools" are means for aggregating information within an organization and providing it in a form that is easily accessible to members, and include wikis, document management systems, collaboration tools, etc.

[1208] "Employee information management means" refers to means for managing basic information, performance, skills, work history, etc., related to employees, and includes personnel management systems and databases.

[1209] "Natural language processing" is a technique for analyzing collected text data to understand, classify, or extract sentiment from its content.

[1210] "Feature extraction" is the process of identifying characteristics such as employees' areas of interest, areas of expertise, challenges they face, and emotional states from the analyzed data.

[1211] "Emotion recognition means" refers to technology for recognizing a user's emotional state based on text data, and includes machine learning algorithms and analysis engines.

[1212] A "matching method" is an algorithm or mechanism that automatically pairs employees with complementary characteristics based on the extracted characteristics.

[1213] "Method for proposing 1-on-1 meetings" is the process of sending notifications to matched employees to propose individual meetings.

[1214] "Means for collecting feedback" refers to a system for gathering opinions and impressions from participants after one-on-one meetings, and includes surveys and review systems.

[1215] This invention is a system for promoting appropriate communication between employees. This system is configured with a server at its core, and collects data from in-house communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., personnel management systems), and analyzes and processes this data to match mutually complementary employees and propose one-on-one meetings.

[1216] 1. Data Collection

[1217] The server uses API connections to collect data from chat tools (e.g., Slack), information sharing tools (e.g., Confluence), and human resources management systems (e.g., Workday). Specifically, data such as messages, comments, and basic information obtained from each tool is stored in the server's database. During this process, appropriate API calls and data format conversions are made.

[1218] 2. Data Analysis

[1219] The server then passes the collected data to a natural language processing (NLP) engine such as Google Cloud Natural Language API to analyze the meaning, sentiment, and topic of the messages, allowing it to extract, for example, "frequent mentions of technical challenges in Project A" or "positive comments about new technologies."

[1220] 3. Emotion recognition

[1221] The server then uses an emotion recognition engine like Affectiva to identify the user's emotions from the analyzed data, identifying emotional states such as "the user is stressed" or "the user is motivated" based on the tone and phrasing of the message.

[1222] 4. Feature Extraction

[1223] Based on the results of the NLP engine and emotion recognition engine, the server extracts the characteristics of each employee. These characteristics include the employee's main areas of interest, areas of expertise, current challenges, and emotional state. For example, it can reveal that employee A is "very interested in AI technology" and "currently feeling stressed."

[1224] 5. Matching

[1225] The server automatically matches employees with complementary traits based on the extracted characteristics. For example, it pairs "Person A, who is interested in AI technology" with "Person B, who has extensive practical experience in AI technology." It also takes into account emotional states, forming pairs that are less likely to be influenced by each other's emotions.

[1226] 6. Proposal for 1-on-1 meetings

[1227] Once matching is complete, the server sends a notification proposing a one-on-one meeting to the devices of the employees. This notification includes the proposed date, time, and purpose of the meeting. Users can receive this notification and accept or reject the meeting. Specifically, the notification will say, "I propose a one-on-one meeting between Mr. A and Mr. B to discuss the technical issues of Project A."

[1228] 7. Gathering Feedback

[1229] After the one-on-one meeting ends, the device collects feedback from the user. This feedback is used to help with future matching. For example, specific opinions such as "The meeting was very meaningful" or "The topic we discussed was inappropriate" are collected, and the server analyzes them and reflects them in future matching algorithms.

[1230] Specific examples

[1231] For example, suppose employee A is struggling with "technical issues in Project A." The server collects employee A's messages from Slack or other services and analyzes them using the Google Cloud Natural Language API, determining that employee A is seeking advice on the technical issues. At the same time, it uses an emotion recognition engine such as Affectiva to determine that employee A is feeling stressed. The server then identifies employee B, who is knowledgeable about Project A, and matches employee A and employee B. Notifications of the proposed meeting are sent to the devices of employee A and employee B, including the proposed meeting date and time and purpose. After the meeting ends, feedback collected through the devices is reflected in the next match.

[1232] Prompt Sentence Examples

[1233] "What kind of support should you provide to an employee who is struggling with technical issues in Project A? Suggest collaboration with other employees who have technical knowledge about Project A."

[1234] This system promotes appropriate communication between employees and enables efficient and effective one-on-one meetings.

[1235] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1236] Step 1: Data collection

[1237] The server connects to internal communication methods (e.g., chat tools), information sharing methods (e.g., wikis), and employee information management methods (e.g., human resources management systems), and collects data from these systems using APIs. Specifically, messages, comments, basic employee information, etc. are obtained from each tool through API calls and stored in the server's database. The input is raw data obtained from each tool, and the output is data stored in a structured format in the database.

[1238] Step 2: Data analysis

[1239] The server passes the collected data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input data is the text data collected in step 1, and the meaning, sentiment, and topic of each message are extracted as output. For example, "mentions about the technical challenges of Project A" and "positive comments about new technology" are extracted from the text data. Specific operations include the process of sending data to the API and obtaining the analysis results.

[1240] Step 3: Emotion Recognition

[1241] The server passes the data analyzed in step 2 to an emotion recognition engine (e.g., Affectiva) to identify the user's emotional state. The input data is the analysis result obtained in step 2, and the user's emotional state (e.g., "feeling stressed" or "motivated") is generated as the output. Specific operations include the process of sending the analyzed data to the emotion recognition engine and returning the emotional state.

[1242] Step 4: Feature extraction

[1243] The server extracts the characteristics of each employee based on the results of the natural language processing engine and emotion recognition engine. The input data is the output of steps 2 and 3, and the output identifies each employee's characteristics (e.g., "very interested in AI technology" or "currently feeling stressed"). Specifically, the server integrates the results of each analysis and identifies the characteristics based on the feature extraction algorithm defined in the program.

[1244] Step 5: Matching

[1245] The server automatically matches employees with complementary characteristics based on the results of feature extraction. The input data are the characteristics output in step 4, and the output is a pair of matched employees. Specifically, the algorithm identifies employees with complementary characteristics based on the feature data and creates a matching list.

[1246] Step 6: Propose a one-on-one meeting

[1247] The server sends a notification of a proposed 1-on-1 meeting to the devices of the employees who have completed matching. The input data is the matching list created in step 5, and the output is a notification message that will be displayed on each employee's device. Specifically, the server generates the date, time, location, and purpose of the proposed meeting to be included in the notification and sends it to the device of each employee.

[1248] Step 7: Gather feedback

[1249] After the one-on-one meeting is over, the device collects feedback from both parties. The input data is the feedback information provided by the employee, and the output is the feedback data stored on the server. Specifically, the device displays a feedback form on the screen and sends the information entered by the user to the server. The server stores this information and uses it for future matching.

[1250] (Application example 2)

[1251] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1252] In modern factories and companies, poor communication and a lack of appropriate information exchange negatively impact production efficiency and employee motivation. In addition, there are few opportunities for employees with the right skills to meet with the right people at the right time, which can delay problem resolution. Furthermore, matching and meeting proposals that do not take into account employees' emotional state can increase stress and dissatisfaction.

[1253] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from internal information exchange means, information provision means, and personal information management means, means for analyzing the collected data using natural language processing, means for extracting characteristics of each individual from the analyzed data, means for matching individuals with complementary characteristics, means for proposing one-on-one meetings between the matched individuals, means for collecting opinions after the meeting, means for recognizing emotions from the data using an emotion engine, and means for proposing optimal matching and meetings based on the recognized emotions. This enables optimal matching and meeting proposals that take into account the emotional state of employees, thereby improving the quality of communication.

[1254] "Information exchange means" are the means by which employees and workers send messages and information to each other.

[1255] An "information means" is a system that allows each employee or worker to share and access information.

[1256] "Personal information management means" refers to a system that collects, stores, and manages personal information of employees and workers within a company.

[1257] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1258] An "emotion engine" is a technology that detects and analyzes a user's emotional state from text data and voice data.

[1259] A "one-on-one meeting" is a face-to-face meeting between two specific employees or workers.

[1260] "Matching" is the process of selecting the most suitable partner based on specific criteria and conditions.

[1261] "Data collection means" refers to a method or device for collecting data from various information exchange means, information provision means, and personal information management means.

[1262] "Opinion gathering means" is the method or system for gathering participant feedback and opinions after the meeting.

[1263] The present invention provides a system that combines data collection, data analysis, feature extraction, and emotion recognition to facilitate effective communication among employees and workers. Specific embodiments are described below.

[1264] First, the server collects data from the company's internal information exchange means, information provision means, and personal information management means. Specifically, it collects messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. As a result, a variety of data, such as workers' messages, comments, and basic information, is stored on the server.

[1265] The server then analyzes the collected data using a natural language processing (NLP) engine. Using technologies that allow computers to understand and analyze human language (e.g., SpaCy and BERT), the meaning, sentiment, and trending topics of messages are extracted. For example, analysis could reveal that "solving problems with a particular machine is frequently discussed" or "positive opinions about new work methods."

[1266] Furthermore, the server recognizes the user's emotions from the analyzed data using an emotion engine (e.g., DeepMoji). From the tone and wording of the message, the server can detect emotional states such as "the user is stressed" or "the user is motivated."

[1267] The server then extracts characteristics of each worker based on the results of the NLP and emotion engine. These characteristics include the worker's main areas of interest and expertise, the challenges they are currently facing, and their emotional state. For example, the resulting characteristics may include "Mr. A is very interested in robot maintenance" or "He is currently feeling stressed."

[1268] Based on the extracted features, the server automatically matches workers with complementary characteristics. For example, "Person A, who is interested in robot maintenance," with "Person B, who has extensive practical experience in robot maintenance." Emotional states are also taken into consideration, and matching is performed to ensure that these states do not affect each other.

[1269] Once matched, workers will receive a notification proposing a one-on-one meeting, including the date, time, and purpose of the proposed meeting, and can accept or decline the meeting.

[1270] After the meeting, the server collects feedback from the workers. This feedback will be used for future matching. Feedback such as "The meeting was very meaningful" or "The topic to be discussed was inappropriate" is collected.

[1271] For example, the following prompts can be presented to the worker:

[1272] "Are you interested in robot maintenance?", "Are you feeling stressed about your work lately?", "Do you want someone to talk to about a technical issue?"

[1273] In this way, a system combined with an emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[1274] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1275] Step 1:

[1276] The server collects data from information exchange means, information provision means, and personal information management means. Specifically, it obtains messages, work records, and personal information from data sources such as chat tools, production management systems, and labor management systems. The input is data from each system, and the output is a comprehensive data set of the collected data. The server manages this data in a unified manner.

[1277] Step 2:

[1278] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it uses NLP techniques such as SpaCy and BERT to extract the meaning of messages and trending topics. The input is the collected comprehensive dataset, and the output is the semantic analysis results and topic model after analysis. The server identifies relevant themes and keywords based on the content of each message.

[1279] Step 3:

[1280] The server recognizes the user's emotions from the data analyzed using an emotion engine. Specifically, it uses emotion analysis technologies such as DeepMoji to determine the user's emotional state from the tone and phrasing of the message. The input is data after semantic analysis, and the output is data indicating the user's emotional state. The server evaluates the emotional tone of each message and assigns an emotion tag such as positive, negative, or neutral.

[1281] Step 4:

[1282] The server extracts the characteristics of each worker based on the results of the NLP and emotion engine. Specifically, it compiles the worker's areas of interest, expertise, current problems, emotional state, etc. into a profile. The input is the analyzed semantic and emotional data, and the output is a feature profile for each worker. The server runs the feature extraction algorithm and generates a profile for each worker.

[1283] Step 5:

[1284] The server matches workers with complementary characteristics based on the extracted features. Specifically, it uses a feature matching algorithm to form pairs with complementary skills and areas of interest. The input is a feature profile, and the output is a list of matched worker pairs. The server compares each worker's profile and selects the best match.

[1285] Step 6:

[1286] The server sends a notification to the matched workers proposing a one-on-one meeting. Specifically, it sends a notification including the date, time, and purpose of the proposed meeting to the worker's device. The input is a list of matching pairs, and the output is a meeting proposal notification. The server uses a pre-configured schedule management system to suggest the optimal meeting time.

[1287] Step 7:

[1288] The user accepts or rejects the meeting proposal from the terminal. Specifically, the user checks their work schedule and decides whether the proposed meeting is appropriate. The input is the meeting proposal notification, and the output is feedback on whether the meeting is accepted or rejected. The user accepts or rejects the proposal using the terminal interface.

[1289] Step 8:

[1290] The server collects feedback from workers after the meeting. Specifically, it asks for feedback on whether the meeting was meaningful, whether the topics discussed were appropriate, etc. The input is the worker's feedback, and the output is feedback data that will be used to improve the matching algorithm for the next time onwards. The server analyzes the feedback and reflects it in improving the accuracy of the next match.

[1291] In this way, by using generative AI models and prompts, the system combined with the emotion engine can realize effective one-on-one meetings between workers and improve the quality of communication.

[1292] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1293] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1294] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1295] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1296] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1297] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1298] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1299] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1300] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1301] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1302] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1303] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1304] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1305] 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.

[1306] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1307] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1308] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1309] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1310] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1311] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1312] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1313] The following is further disclosed regarding the above embodiment.

[1314] (Claim 1)

[1315] A means of collecting data from internal communication tools, information sharing tools, and employee information management tools;

[1316] A means for analyzing the collected data using natural language processing;

[1317] A means of extracting the characteristics of each employee from the analyzed data,

[1318] A means of matching employees with complementary characteristics,

[1319] A way to propose 1-on-1 meetings between matched employees,

[1320] A way to collect feedback after 1-on-1 meetings,

[1321] A system including:

[1322] (Claim 2)

[1323] 2. The system according to claim 1, wherein a chat tool is used as a communication tool.

[1324] (Claim 3)

[1325] 10. The system of claim 1, utilizing a natural language processing engine in analyzing the collected data.

[1326] "Example 1"

[1327] (Claim 1)

[1328] A means of collecting data from internal communication means, information sharing means, and employee information management means;

[1329] A means for analyzing the collected data using a natural language processing engine;

[1330] A means for extracting characteristics of each employee from the analyzed data;

[1331] A means of matching employees with complementary characteristics;

[1332] A method to propose one-on-one interviews between matched staff members,

[1333] A way to collect feedback after one-on-one interviews,

[1334] A way to reflect feedback in the next match,

[1335] A system including:

[1336] (Claim 2)

[1337] 2. The system according to claim 1, wherein a conversation means is used as a communication means.

[1338] (Claim 3)

[1339] 10. The system of claim 1, utilizing a generative AI model in analyzing the collected data.

[1340] "Application Example 1"

[1341] (Claim 1)

[1342] A means of collecting data from internal communication tools, information sharing tools, and employee information management tools;

[1343] A means for analyzing the collected data using natural language processing;

[1344] A means of extracting the characteristics of each employee from the analyzed data,

[1345] A means of matching employees with complementary characteristics,

[1346] A way to propose 1-on-1 meetings between matched employees,

[1347] A way to collect feedback after 1-on-1 meetings,

[1348] A means of collecting and analyzing information about workers and factory robots in the factory;

[1349] A means of matching complementary workers with factory robots;

[1350] A means for proposing cooperative work to the matched workers and factory robots;

[1351] a means of gathering feedback after the collaboration;

[1352] A system including:

[1353] (Claim 2)

[1354] 2. The system according to claim 1, wherein a chat tool is used as a communication tool.

[1355] (Claim 3)

[1356] 10. The system of claim 1, utilizing a natural language processing engine in analyzing the collected data.

[1357] "Example 2: Combining Emotion Engines"

[1358] (Claim 1)

[1359] A means for collecting data from internal communication means, information sharing means, and employee information management means;

[1360] A means for analyzing the collected data using natural language processing;

[1361] A means of extracting the characteristics of each employee from the analyzed data,

[1362] A means for recognizing employee emotions using an emotion recognition means;

[1363] A means of matching complementary employees with each other,

[1364] A way to propose 1-on-1 meetings between matched employees,

[1365] A way to collect feedback after 1-on-1 meetings,

[1366] A system including:

[1367] (Claim 2)

[1368] 2. The system according to claim 1, wherein a chat tool is used as a means of communication.

[1369] (Claim 3)

[1370] 10. The system of claim 1, utilizing a natural language processing engine to analyze the collected data.

[1371] "Application example 2 when combining emotion engines"

[1372] (Claim 1)

[1373] Means of collecting data from internal information exchange means, information provision means, and personal information management means;

[1374] A means for analyzing the collected data using natural language processing;

[1375] A means for extracting individual characteristics from the analyzed data;

[1376] a means of matching individuals with complementary characteristics;

[1377] A means to propose one-on-one meetings between matched individuals;

[1378] a means of gathering post-meeting feedback;

[1379] a means for recognizing emotions from data using an emotion engine;

[1380] a means for suggesting optimal matches and meetings based on perceived emotions;

[1381] A system including:

[1382] (Claim 2)

[1383] 2. The system of claim 1, wherein the information exchange means uses a message means.

[1384] (Claim 3)

[1385] 10. The system of claim 1, wherein the system utilizes NLPE in analyzing the collected data. [Explanation of symbols]

[1386] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data from internal communication tools, information sharing tools, and employee information management tools; A means for analyzing the collected data using natural language processing; A means of extracting the characteristics of each employee from the analyzed data, A means of matching employees with complementary characteristics, A way to propose 1-on-1 meetings between matched employees, A way to collect feedback after 1-on-1 meetings, A system including:

2. 2. The system according to claim 1, wherein a chat tool is used as a communication tool.

3. The system of claim 1 , which utilizes a natural language processing engine in analyzing the collected data.

Images