System

Abstract

A system is provided.SOLUTION: A means for collecting communication data, a means for filtering the collected communication data, a means for extracting necessary information from the filtered data, a means for inputting the extracted data to a generative AI model and calculating a relationship value and a performance expected value between members, a means for simulating an optimal combination pattern of members based on the calculated relationship value and performance expected value, and a means for visualizing the simulated combination pattern and presenting the visualized combination pattern to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When it comes to organizational restructuring and personnel assignments, the lack of objective data to determine compatibility between team members is a problem. Currently, human resources departments and managers rely on fragmented information from regular meetings and social gatherings to make evaluations, making it difficult to find the right combinations to bring out optimal performance. Furthermore, because employees who get along well with each other do not necessarily perform optimally, more accurate personnel assignments are needed. [Means for solving the problem]

[0005] The present invention provides a means for collecting communication data, filtering the collected communication data, and extracting necessary information from the filtered data. It also includes a means for inputting the extracted data into a generative AI model and calculating the relationship values ​​and performance expectations between members. It also provides a means for simulating optimal member combination patterns based on the calculated relationship values ​​and performance expectations, and a means for visualizing the simulated combination patterns and presenting them to the user. This configuration allows human resources departments and managers to optimally allocate personnel based on objective data, thereby improving organizational performance.

[0006] "Communication data" refers to data related to communications collected from telephones, video conferencing, emails, chat tools, etc. used by members of an organization.

[0007] "Means of collection" refers to the functions and methods for transferring each member's telephone, video conference, email, and chat tool log data to the system.

[0008] "Filtering means" refers to a function or method that performs processing to remove unnecessary information from collected communication data and extract only necessary information.

[0009] "Means for extraction" refers to the functions and methods for obtaining important information such as specific speech content, speaker, frequency, and time from the filtered data.

[0010] A "generative AI model" refers to an artificial intelligence model that uses collected and extracted data as input to calculate relationship values ​​and performance expectations between members.

[0011] "Relationship value" refers to an indicator that quantifies the compatibility and quality of communication between members.

[0012] "Performance expectancy" refers to a numerical indicator that represents the level of work performance that a specific combination of members is expected to demonstrate as a team.

[0013] "Means for simulation" refers to the function or method of using a generative AI model to try out multiple combination patterns based on the relationship values ​​and performance expectations of members, and then selecting the optimal combination from among them.

[0014] "Means of visualization and presentation to users" refers to functions and methods that display the optimal personnel allocation patterns obtained through simulation and the reasons for them in diagrams, graphs, etc., in a form that is easy for the human resources department and managers to understand. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[0037] 1. Data Collection Module

[0038] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0039] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[0040] 2. Data Analysis Module

[0041] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[0042] Example: Remove the casual conversation between employee A and employee B and extract only the work-related conversation content.

[0043] 3. Generative AI Models

[0044] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0045] Example: Evaluate the collaboration and performance of two employees based on the conversation between Employee A, "How is this project progressing?" and Employee B, "It's going well."

[0046] 4. Optimization Algorithms

[0047] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. It tries and evaluates various scenarios to find the optimal combination.

[0048] Example: If employees A, B, and C are placed on the same team, find the combination that has the highest sum of relationship value and performance expectation.

[0049] 5. Results presentation module

[0050] Server: Visualizes optimal staffing and presents it to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm optimal staffing.

[0051] Users: HR and managers can access the dashboard to see the most efficient team composition. For example, they might see, "The optimal team composition is made up of employees A, B, and C," and the reasons for this are shown in graphs of relationship scores and performance expectations.

[0052] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. When implementing the invention, it is important to properly combine these modules and means.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] Data collection

[0056] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[0057] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[0058] Step 2:

[0059] Data filtering

[0060] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, it removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[0061] Step 3:

[0062] Information Extraction

[0063] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[0064] Step 4:

[0065] Input to generative AI models

[0066] Server: The extracted data is input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each member. For example, based on the above utterance, the relationship value between employee A and employee B is calculated to be 80 (out of 100).

[0067] Step 5:

[0068] Simulation using optimization algorithms

[0069] Server: Simulates multiple combination patterns based on relationship values ​​and performance expectations. Tries and evaluates various scenarios to find the optimal combination. For example, calculates the performance expectations when employees A, B, and C are placed on the same team.

[0070] Step 6:

[0071] Visualizing and presenting results

[0072] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and the reasons for this allocation (details of relationship values ​​and performance expectations) are shown in a graph.

[0073] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[0074] Example 1

[0075] 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."

[0076] This invention relates to a system for efficiently optimizing personnel allocation and team formation in companies and organizations. Conventional personnel allocation decisions often rely on subjective judgment, which can lead to inefficient allocation and poor communication. This invention aims to solve these issues by collecting and analyzing daily communication data and presenting optimal team formation based on objective data.

[0077] 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.

[0078] In this invention, the server includes: [means for filtering collected communication data;] [means for extracting necessary business information from the filtered data; and] [means for inputting the extracted business data into a generative AI model and calculating relationship values ​​and performance expectations between members.] This makes it possible [to optimally organize teams and assign personnel based on objective data, thereby improving the efficiency and performance of the entire organization].

[0079] "Devices" refers to communication tools (telephones, video conferencing equipment, email clients, messaging service applications) used by employees in their daily work.

[0080] "Communication Data" refers to voice data, video conference logs, emails, and messaging service data generated via the Terminal.

[0081] "Server" refers to a computer system that collects and analyzes communication data.

[0082] "Filtering" refers to the process of removing noise and unnecessary information from received communication data and extracting necessary business information.

[0083] "Generative AI model" refers to a model that uses natural language processing techniques and machine learning algorithms to analyze data and quantify relationship values ​​and performance expectations.

[0084] "Relationship value" refers to a numerical indicator that indicates the strength of the cooperative relationship between members.

[0085] "Performance expectations" refers to a numerical indicator that predicts each member's work performance.

[0086] "Optimization algorithm" refers to an algorithm that simulates and determines the optimal combination of members based on relationship values ​​and expected performance values.

[0087] "Dashboard" refers to an interface that visualizes the optimal staffing results calculated by the optimization algorithm and presents them to the user.

[0088] This invention is a system that supports efficient personnel allocation and optimization of team formation in companies and organizations. This system collects and analyzes communication data from daily work, and automates a series of processes to propose optimal personnel allocation based on the data.

[0089] Data Collection Module

[0090] Devices: We collect communication data generated through the communication tools employees use in their daily work, such as telephone, video conferencing, email, and messaging services.

[0091] Example: Employee A holds a video conference, and the audio data and text log are saved on the device. After the conference ends, this data is automatically sent to the server.

[0092] Data Analysis Module

[0093] Server: Received communication data is temporarily stored and then filtered to remove noise and unnecessary information (e.g., casual conversation) and extract only the important information.

[0094] Example: The server removes casual conversation from the conversation log between employees A and B and extracts only work-related content.

[0095] Generative AI Models

[0096] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0097] Example: A generative AI model analyzes Employee A's question, "How is this project going?" and Employee B's response, "It's going well," to assess the working relationship and performance expectations between the two.

[0098] Optimization Algorithm

[0099] Server: Based on the calculated relationship value and expected performance value, it simulates combination patterns of multiple members and evaluates them to find the optimal combination.

[0100] Example: The server tries dozens to hundreds of combinations of employees A, B, and C, and finds the combination with the highest sum of relationship value and performance expectation.

[0101] Result presentation module

[0102] Server: Visualizes the optimal member combination and presents it to the user in dashboard format.

[0103] Users: Managers and HR personnel can access the dashboard through a web browser to see the most efficient team composition. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for this will be displayed in graphs of relationship scores and performance expectations.

[0104] By combining and implementing each of the above modules, the system utilizes communication data within a company and proposes efficient staffing and team composition based on objective data. Examples of prompts include, "How is the progress on this project?" and "It's progressing smoothly." This will enable managers and human resources personnel to make optimal decisions in their daily work.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1:

[0107] Devices: Employees communicate via telephone, video conferencing, email, and messaging services. Devices collect communication data (audio logs, text logs, etc.).

[0108] Specific operation: Employee A holds a video conference, and the audio data and text of the conversation are saved on the device.

[0109] Input: Video conferencing, phone, email, and chat tool usage data

[0110] Output: Saved communication log data

[0111] Step 2:

[0112] Terminal: Periodically sends collected communication log data to the server.

[0113] Specific operation: After the video conference ends, the terminal automatically uploads the audio data and text log to the server.

[0114] Input: Communication log data saved on the device

[0115] Output: Communication data sent to the server

[0116] Step 3:

[0117] Server: The received data is stored in temporary storage and the filtering process begins, removing noise and unnecessary information and extracting important business information.

[0118] Specific operation: The server uses a noise removal algorithm to detect and remove chatter.

[0119] Input: Communication data sent to the server

[0120] Output: filtered and clean data

[0121] Step 4:

[0122] Server: Inputs the filtered data into the generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0123] Specific operation: The server supplies clean data to the generative AI model, and the NLP engine analyzes and quantifies the content of the speech.

[0124] Input: filtered clean data

[0125] Output: Quantified relationship values ​​and performance expectations

[0126] Step 5:

[0127] Server: Simulates optimal combinations of members based on relationship values ​​and performance expectations. Tries and evaluates multiple scenarios.

[0128] Specific operation: The server uses a simulation algorithm to evaluate various team composition patterns and calculate the optimal combination.

[0129] Inputs: Quantified relationship values ​​and performance expectations

[0130] Output: Optimal combination pattern

[0131] Step 6:

[0132] Server: Visualizes the optimal combination patterns and presents them to the user in a dashboard format.

[0133] Specific operation: The server uses a visualization tool to generate optimal staffing results in the form of graphs and charts.

[0134] Input: Optimal combination pattern

[0135] Output: Results visualized in a dashboard

[0136] Step 7:

[0137] Users: Managers and HR personnel access the dashboard to see the most efficient team structure.

[0138] Specific behavior: The user logs into the dashboard through a web browser and checks the suggested optimal team composition and the reasons for it.

[0139] Input: Results visualized in the dashboard

[0140] Output: Optimal team composition information confirmed

[0141] By sequentially executing each of the above steps, the system can effectively analyze communication data and suggest optimal staffing arrangements.

[0142] (Application example 1)

[0143] 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."

[0144] Logistics centers need to improve work efficiency and optimize staffing, but traditional methods make it difficult to accurately evaluate the performance of humans and robots and organize optimal teams. Furthermore, real-time data collection and analysis are not possible, which can lead to work delays and reduced efficiency.

[0145] 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.

[0146] In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into a generative AI model and calculating a relationship value and an expected performance value between members, means for simulating an optimal member combination pattern based on the calculated relationship value and expected performance value, means for visualizing the simulated combination pattern and presenting it to a user, and means for collecting item work log data and proposing an optimal work team formation. This improves work efficiency in a logistics center and enables accurate personnel allocation and work team formation.

[0147] "Communication data" refers to information sent and received via electronic devices or communication means.

[0148] "Filtering" is the process of removing noise and unnecessary information from collected data and extracting necessary information.

[0149] A "generative AI model" is an artificial intelligence model trained to handle a specific task, using natural language processing techniques and machine learning algorithms to analyze and predict data.

[0150] "Relationship value" is an indicator that quantifies the cooperative relationship and compatibility between members.

[0151] "Performance expectations" are numerical indicators that quantify the expected results and efficiency of members in specific tasks.

[0152] "Simulation" is the process of virtually testing results under different conditions to derive the optimal solution.

[0153] "Visualization" is a technique that makes data and information easier to understand by visually representing them.

[0154] "Item work log data" refers to detailed record data regarding the handling of items and the progress of work at a logistics center.

[0155] "Work team formation" is the process of arranging multiple workers and robots in optimal combinations to ensure efficient business operations.

[0156] A "dashboard" is an interface that aggregates data and displays it in a visually easy-to-understand manner.

[0157] The present invention relates to a system for improving work efficiency within a logistics center. This system collects communication data and work log data for items, and proposes optimal work team organization by analyzing, optimizing, and visualizing the data. Specific embodiments of the system are described below.

[0158] Data collection

[0159] The server collects communication data and item work log data in real time. Communication data includes telephone, video conference, email, and chat data. Item work log data includes, for example, the time and accuracy of picking, packing, and shipping work. This data is collected using devices such as smartphones, smart glasses, or robots.

[0160] Data analysis

[0161] The server stores the collected data in temporary storage and filters out noise and unnecessary information. It then extracts the necessary information and inputs it into a generative AI model. This model uses natural language processing techniques and machine learning algorithms to calculate relationship values ​​and performance expectations between members. The software used includes Python, Pandas, Scikit-learn, and Matplotlib.

[0162] simulation

[0163] The server simulates various combination patterns based on the calculated relationship values ​​and expected performance values. For example, if the combination of employees A and B and robot C is determined to be optimal, the reason for this is displayed in a graph of relationship values ​​and expected performance values.

[0164] Results presentation

[0165] Users can view the simulated optimal work team composition in a dashboard format, which visually displays the relationship values ​​and performance expectations of each member, making it easy for managers and human resources personnel to understand the optimal allocation.

[0166] Specific examples

[0167] For example, the following prompts can be fed into a generative AI model to determine optimal team composition:

[0168] "Please suggest the most efficient work team formation based on the work log data of the distribution center. The data includes work completion time, accuracy score, and team coordination score."

[0169] By inputting the above prompts, the generative AI model can suggest efficient team composition and visually represent the results in a dashboard.

[0170] Hardware and Software Used

[0171] A system for implementing the present invention uses the following hardware and software:

[0172] Hardware: Smartphones, smart glasses, robots, servers

[0173] Software: Python, Pandas, Scikit-learn, Matplotlib

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The terminals collect communication data and work log data related to work within the logistics center. Collected data includes telephone, video conference, email, chat data, and the time and accuracy of picking, packing, and shipping work. This data is sent to the server in real time. The input data is communication data and work log data in raw data format, and the output data is data stored on the server.

[0177] Step 2:

[0178] The server stores the received communication data and work log data in temporary storage and begins the filtering process. Noise and unnecessary information are removed, and only the necessary information is extracted. This process yields accurate data relevant to the business. The input is the data in temporary storage, and the output is the filtered data.

[0179] Step 3:

[0180] The server inputs the filtered data into a generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each worker. This process quantifies the degree of collaboration and work efficiency. The input is the filtered data, and the output is numerical data on the relationship value and performance expectation value.

[0181] Step 4:

[0182] The server simulates optimal work team combination patterns based on the calculated relationship values ​​and expected performance values. Through the simulation, various combination patterns are evaluated and the most efficient team placement is derived. The input is the numerical data of relationship values ​​and expected performance values, and the output is an optimal team composition plan.

[0183] Step 5:

[0184] The server visualizes the simulated optimal team composition and presents it to the user. The relationship values ​​and performance expectations of each member are visually displayed in a dashboard format for easy understanding. The input is the optimal team composition proposal, and the output is the visualized dashboard display information.

[0185] Step 6:

[0186] Users can refer to the dashboard to confirm the optimal work team formation. By reflecting this in the actual work allocation, efficient operations within the logistics center can be achieved. The input is the visualized dashboard information, and the output is the execution of the optimal work team formation.

[0187] 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.

[0188] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[0189] 1. Data Collection Module

[0190] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0191] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[0192] 2. Data Analysis Module

[0193] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[0194] Example: From the chat log between employee A and employee B, remove casual conversations such as "hello" and extract only the work-related conversation content.

[0195] 3. Emotion Engine

[0196] Server: The extracted data is input into the emotion engine to analyze the user's emotions. The emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text.

[0197] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[0198] 4. Generative AI Models

[0199] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[0200] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[0201] 5. Optimization Algorithms

[0202] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. Various scenarios are tried and evaluated to find the optimal combination. By taking emotional information into account, more accurate predictions are possible.

[0203] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[0204] 6. Results presentation module

[0205] Server: The simulated optimal staffing is visualized in charts and graphs and presented to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm the optimal staffing.

[0206] Users: Human resources and managers can access the dashboard to check optimal staffing and reorganize the organization based on the proposed staffing. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for the placement are shown in graphs of relationship values, performance expectations, and emotional states.

[0207] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. Using the emotion engine improves the accuracy of relationship values ​​and performance expectations, enabling more optimal team formation. When implementing the invention, it is important to correctly combine these modules and methods.

[0208] The processing flow will be explained below.

[0209] Step 1:

[0210] Data collection

[0211] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[0212] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[0213] Step 2:

[0214] Data filtering

[0215] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[0216] Server: Prepares the filtered data for analysis.

[0217] Step 3:

[0218] Information Extraction

[0219] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[0220] Step 4:

[0221] Emotion analysis using an emotion engine

[0222] Server: The extracted data is input into the emotion engine to analyze the user's emotional state. The emotion engine identifies the user's emotions (joy, anger, sadness, etc.) from the voice and text.

[0223] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[0224] Step 5:

[0225] Input to generative AI models

[0226] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[0227] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated as 70 (out of 100).

[0228] Step 6:

[0229] Simulation using optimization algorithms

[0230] Server: Simulates multiple combination patterns based on relationship values ​​and expected performance. Tries and evaluates various scenarios to find the optimal combination. Taking emotional information into account enables more accurate predictions.

[0231] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[0232] Step 7:

[0233] Visualizing and presenting results

[0234] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and provide the reasons for this allocation (details of relationship values, performance expectations, and emotional states).

[0235] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[0236] Example 2

[0237] 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."

[0238] In traditional organizational management, it was difficult to create optimal team composition that took into account the relationships between team members and the emotional state of each individual. This could lead to poor performance and hinder efficient business operations.

[0239] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion engine and analyzing the user's emotions, means for inputting the output of the emotion engine and the filtered data into a generative AI model and calculating relationship values ​​and expected performance values ​​between members, means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and means for visualizing the simulated combination patterns and presenting them to the user. This enables optimal team formation that takes into account the emotional states and relationships between members, thereby improving work efficiency and performance.

[0240] "Communication data" refers to information relating to communications such as telephone calls, video conferences, emails, and chat data conducted using a terminal.

[0241] "Filtering" is the process of removing unnecessary information (noise and meaningless conversations) from communication data and extracting necessary information.

[0242] An "emotion engine" is an analysis engine that has the ability to identify a user's emotional state (joy, anger, sadness, etc.) from voice and text.

[0243] A "generative AI model" is a model that uses natural language processing technology and machine learning algorithms to calculate relationship values ​​and performance expectations between members from input data.

[0244] "Relationship value" is an index that represents the relationship between members, and is a value evaluated based on the quality and frequency of communication, emotional state, etc.

[0245] "Performance expectations" are indicators of the performance expected when members work together.

[0246] "Simulation" is a process of trying out optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and evaluating the results.

[0247] "Visualization" refers to visually displaying the results of simulated combination patterns in the form of diagrams, graphs, etc.

[0248] The present invention relates to a system for collecting and analyzing communication data and forming an optimal team. Specific embodiments of the system will be described in detail below.

[0249] Data collection

[0250] Devices: Communication data is generated when employees use telephones, video conferencing, email, and chat tools. This data is automatically collected and sent to the server. For example, after employee A finishes a video conference, the audio data and text log of the conversation are transferred to the server.

[0251] Data analysis

[0252] Server: The received communication data is stored in temporary storage and the filtering process begins. Unnecessary information (such as small talk and noise such as "hello") is removed, and the necessary information is extracted. For example, only the work-related conversation content is extracted from the chat log between employee A and employee B.

[0253] Emotion analysis

[0254] Server: The extracted data is input into the emotion engine, which analyzes the user's emotions. This emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text. For example, when employee A says, "This project isn't going well," the emotion engine analyzes the user's emotion of dissatisfaction and returns the results to the server.

[0255] Using generative AI models

[0256] Server: The filtered data and the output of the emotion engine are input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectations between members. For example, if the content of Employee A's speech and emotional state are input into the model, the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[0257] Simulation and Optimization

[0258] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members. In this process, various scenarios are tried and evaluated. By taking emotional information into account, more accurate predictions are possible. For example, if employee A frequently feels dissatisfied, it takes into account that his relationship values ​​with other members will decline, and calculates the expected performance value for the combination of employees A, B, and C.

[0259] Visualizing the results

[0260] Server: The server visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user. Managers and human resources personnel can refer to this dashboard to confirm the optimal team composition. For example, it may display "The optimal team composition is made up of employees A, B, and C," and the reasons for this composition may be shown in graphs of relationship values, performance expectations, and emotional states.

[0261] Prompt Sentence Examples

[0262] Below is an example of a prompt sentence to be input to the generative AI model.

[0263] "Employee A expresses dissatisfaction during a project meeting. Please analyze the relationship between Employee A and Employee B and suggest the optimal team formation."

[0264] Through these processes, the system effectively analyzes communication data and supports optimal team formation and personnel allocation. In this way, by using the emotion engine, the present invention improves the accuracy of relationship values ​​and performance expectations, enabling more appropriate team formation.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1:

[0267] Data collection

[0268] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0269] Input: Communication data sent from the device (voice data, text logs, etc.).

[0270] Output: Raw communication data stored on the server.

[0271] Specific operation: After employee A finishes the video conference, the device converts the voice data into text and sends the log to the server.

[0272] Step 2:

[0273] Data analysis

[0274] Server: Received communication data is stored in temporary storage and filtering process begins. Unnecessary information (noise and chatter) is removed and necessary information is extracted.

[0275] Input: Raw communication data stored in temporary storage.

[0276] Output: The filtered data you want.

[0277] Specific operation: The server removes greetings such as "hello" from the voice data and extracts only business-related content.

[0278] Step 3:

[0279] Emotion analysis

[0280] Server: Inputs the extracted data into the emotion engine to analyze the user's emotions. The emotion engine identifies the emotional state from the voice and text.

[0281] Input: Filtered communication data.

[0282] Output: Sentiment analysis results (type and intensity of emotion).

[0283] Specific operation: The server analyzes employee A's statement, "This project isn't going well," and identifies it as an expression of dissatisfaction.

[0284] Step 4:

[0285] Using generative AI models

[0286] Server: The filtered data and the output of the emotion engine are input into the generative AI model, which calculates the relationship value and performance expectation for each member.

[0287] Input: Sentiment analysis results and filtered required data.

[0288] Output: Relationship values ​​and performance expectations.

[0289] Specific operation: Input the content of Employee A's speech and his emotional state, and calculate the relationship value between Employee A and Employee B as 70 (out of 100 points).

[0290] Step 5:

[0291] Optimization Simulation

[0292] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members, tries out various scenarios, and finds the optimal combination.

[0293] Inputs: Relationship value and performance expectation.

[0294] Output: Optimal member combination pattern.

[0295] Specific operation: Considering the impact that frequently dissatisfied employee A has on the team, simulate the optimal team composition based on the relationship values ​​with other members.

[0296] Step 6:

[0297] Visualizing the results

[0298] Server: Visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user.

[0299] Input: Optimal member combination pattern.

[0300] Output: A visualized dashboard.

[0301] Specific operation: The system displays a graph and explanatory text to the user showing the optimal team composition of employees A, B, and C. This allows the human resources department and managers to confirm the optimal composition and use it to formulate actual organizational compositions.

[0302] (Application example 2)

[0303] 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."

[0304] In modern factories, maximizing the operational efficiency of robots and machines is key to improving productivity. However, interactions between robots and communication with operators are complicated, making it difficult to find efficient work arrangements and collaboration structures. Furthermore, manually analyzing large amounts of data takes time and effort, making it impossible to determine optimal work patterns in real time. A system that can solve these issues is needed.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0306] In this invention, the server includes means for collecting machine operation data and communication logs, means for filtering the collected operation data and communication logs, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion analysis module and evaluating the status of the machines and personnel, means for inputting the evaluated data into a generative AI model and calculating cooperative relationships and performance expectations between the machines, means for simulating optimal machine combination patterns based on the calculated cooperative relationships and performance expectations, and means for visualizing the simulated combination patterns and presenting them to a user. This makes it possible to efficiently collect and analyze robot and machine operation data and communication logs and determine optimal work placement and cooperation systems in real time.

[0307] "Machine operation data" means information relating to the operating status and operation of robots and machines used in factories.

[0308] "Communication log" refers to a record of communication such as messages and instructions exchanged between robots and operators.

[0309] "Filtering" refers to the process of removing noise and unnecessary information from collected data and extracting necessary information.

[0310] "Emotion analysis module" refers to software that has the function of evaluating the operating status and stress level of robots and operators from input data.

[0311] "Generative AI model" means a model that uses natural language processing techniques and machine learning algorithms to calculate appropriate work patterns and collaboration relationships.

[0312] "Cooperative relationship" refers to the mutual relationship when multiple robots or machines work together to perform a task.

[0313] "Performance expectations" refers to expectations regarding the efficiency and productivity of a robot or machine when performing a specific task.

[0314] "Simulation" refers to the process of trying out multiple scenarios and simulating the optimal work arrangements and cooperation systems.

[0315] "Visualization" means displaying analysis or simulation results in a visual format such as a graph or diagram.

[0316] "User" refers to the manager or operator who uses the system to determine optimal work arrangements and cooperation structures and make decisions.

[0317] A specific system configuration and program processing will be described for an embodiment of the present invention.

[0318] System Program

[0319] The server performs the following steps:

[0320] 1. Data Collection Module

[0321] The server collects operational data and communication logs from the robots and machines used in the factory. The specific hardware used includes sensor devices (e.g., LIDAR and cameras), and the communication interface uses Wi-Fi and Bluetooth. The operational data includes information about operating status and behavior, while the communication log includes the content of communications between robots and with operators.

[0322] 2. Data Analysis Module

[0323] The server stores the collected operation data and communication logs in a database system (MySQL or PostgreSQL) and performs a filtering process to remove noise and unnecessary information and extract the necessary information.

[0324] 3. Sentiment Analysis Module

[0325] The filtered data is then fed into a sentiment analysis module, where the server analyzes the data using natural language processing libraries (SpaCy and BERT) to assess the operating status and stress levels of the robots and operators.

[0326] 4. Generative AI Models

[0327] The results of the sentiment analysis and filtered data are input into a generative AI model. The server uses machine learning frameworks (TensorFlow and PyTorch) to calculate appropriate work patterns and collaboration relationships. The generative AI model includes natural language processing technology and machine learning algorithms.

[0328] 5. Optimization Algorithms

[0329] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values ​​to find the optimal machine combination pattern. The calculated optimal placement is visualized in dashboard format using a web front end (React or Vue.js).

[0330] 6. User Presentation Module

[0331] The simulated results are displayed on a dashboard, allowing administrators to check them in real time. Data is passed and processed using a backend API (Flask or Node.js).

[0332] Specific examples

[0333] Next, we will show a specific example of operation. For example, after Robot A has been operating for a long period of time, its operation data is collected by a sensor device and sent to a server. The server filters the data to remove noise and unnecessary information. An emotion analysis module evaluates fatigue and stress levels, and the results are input into a generative AI model. The generative AI model calculates the cooperative relationship between Robot A and other robots B and C, and proposes optimal work patterns. The calculated results are displayed on a dashboard so that managers can check them.

[0334] Prompt Sentence Examples

[0335] A computergram has the following format:

[0336] Input collected sensor and communication data

[0337] sensor_data = {

[0338] "robot_a": {

[0339] "temperature": 65,

[0340] "movement": "assembly",

[0341] "operating_time": 320,

[0342] ...

[0343] },

[0344] ...

[0345] }

[0346] Input the output of the emotion engine

[0347] emotional_state = {

[0348] "robot_a": {

[0349] "fatigue_level": 0.8,

[0350] "stress_level": 0.4,

[0351] },

[0352] ...

[0353] }

[0354] Input to generative AI model

[0355] optimal_configuration = generate_optimal_configuration(sensor_data, emotional_state)

[0356] print(optimal_configuration)

[0357] This makes it possible to efficiently collect and analyze operation data and communication logs of robots and machines, and determine optimal work placement and cooperation systems in real time.

[0358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0359] Step 1:

[0360] The server collects operational data and communication logs from the robots and machines used in the factory through sensor devices (LIDAR and cameras) and communication interfaces (Wi-Fi and Bluetooth). This input data includes the robot's operating status, operational information, and communication between robots and with operators. This data is stored in a database (MySQL and PostgreSQL).

[0361] Step 2:

[0362] The server filters the operational data and communication logs stored in temporary storage. Specifically, it removes noise and unnecessary information and extracts only important information related to the business. For example, it removes noise recorded during movement and extracts only data related to part assembly. This process generates filtered data.

[0363] Step 3:

[0364] The server inputs the filtered data into an emotion analysis module to evaluate the operating status and stress levels of the robots and operators. For example, it uses a natural language processing library (SpaCy or BERT) to analyze the fatigue level of Robot A after a long period of operation. Emotion data is generated as the analysis result.

[0365] Step 4:

[0366] The server inputs the output of the emotion analysis module and filtered data into the generative AI model. It uses a machine learning framework (TensorFlow or PyTorch) to calculate appropriate work patterns and cooperative relationships between robots. For example, if robot A and robot B have a strong cooperative relationship, the expected performance of the cooperative work will be calculated to be high. The generated performance data is then output.

[0367] Step 5:

[0368] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values. It then uses an optimization algorithm to find the optimal machine combination pattern. For example, it considers the fatigue level of robot A and evaluates the optimal combination with robots B and C. This generates the optimal deployment pattern.

[0369] Step 6:

[0370] The server visualizes the simulated results in the form of a dashboard and presents it to the user. This uses a web front end (React or Vue.js) and provides data to the user through a backend API (Flask or Node.js). For example, an administrator can view the dashboard and confirm that the combination of robots A and B is optimal. This displays the presented optimization data.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] [Second embodiment]

[0375] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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."

[0387] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[0388] 1. Data Collection Module

[0389] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0390] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[0391] 2. Data Analysis Module

[0392] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[0393] Example: Remove the casual conversation between employee A and employee B and extract only the work-related conversation content.

[0394] 3. Generative AI Models

[0395] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0396] Example: Evaluate the collaboration and performance of two employees based on the conversation between Employee A, "How is this project progressing?" and Employee B, "It's going well."

[0397] 4. Optimization Algorithms

[0398] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. It tries and evaluates various scenarios to find the optimal combination.

[0399] Example: If employees A, B, and C are placed on the same team, find the combination that has the highest sum of relationship value and performance expectation.

[0400] 5. Results presentation module

[0401] Server: Visualizes optimal staffing and presents it to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm optimal staffing.

[0402] Users: HR and managers can access the dashboard to see the most efficient team composition. For example, they might see, "The optimal team composition is made up of employees A, B, and C," and the reasons for this are shown in graphs of relationship scores and performance expectations.

[0403] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. When implementing the invention, it is important to properly combine these modules and means.

[0404] The processing flow will be explained below.

[0405] Step 1:

[0406] Data collection

[0407] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[0408] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[0409] Step 2:

[0410] Data filtering

[0411] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, it removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[0412] Step 3:

[0413] Information Extraction

[0414] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[0415] Step 4:

[0416] Input to generative AI models

[0417] Server: The extracted data is input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each member. For example, based on the above utterance, the relationship value between employee A and employee B is calculated to be 80 (out of 100).

[0418] Step 5:

[0419] Simulation using optimization algorithms

[0420] Server: Simulates multiple combination patterns based on relationship values ​​and performance expectations. Tries and evaluates various scenarios to find the optimal combination. For example, calculates the performance expectations when employees A, B, and C are placed on the same team.

[0421] Step 6:

[0422] Visualizing and presenting results

[0423] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and the reasons for this allocation (details of relationship values ​​and performance expectations) are shown in a graph.

[0424] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[0425] Example 1

[0426] 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."

[0427] This invention relates to a system for efficiently optimizing personnel allocation and team formation in companies and organizations. Conventional personnel allocation decisions often rely on subjective judgment, which can lead to inefficient allocation and poor communication. This invention aims to solve these issues by collecting and analyzing daily communication data and presenting optimal team formation based on objective data.

[0428] 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.

[0429] In this invention, the server includes: [means for filtering collected communication data;] [means for extracting necessary business information from the filtered data; and] [means for inputting the extracted business data into a generative AI model and calculating relationship values ​​and performance expectations between members.] This makes it possible [to optimally organize teams and assign personnel based on objective data, thereby improving the efficiency and performance of the entire organization].

[0430] "Devices" refers to communication tools (telephones, video conferencing equipment, email clients, messaging service applications) used by employees in their daily work.

[0431] "Communication Data" refers to voice data, video conference logs, emails, and messaging service data generated via the Terminal.

[0432] "Server" refers to a computer system that collects and analyzes communication data.

[0433] "Filtering" refers to the process of removing noise and unnecessary information from received communication data and extracting necessary business information.

[0434] "Generative AI model" refers to a model that uses natural language processing techniques and machine learning algorithms to analyze data and quantify relationship values ​​and performance expectations.

[0435] "Relationship value" refers to a numerical indicator that indicates the strength of the cooperative relationship between members.

[0436] "Performance expectations" refers to a numerical indicator that predicts each member's work performance.

[0437] "Optimization algorithm" refers to an algorithm that simulates and determines the optimal combination of members based on relationship values ​​and expected performance values.

[0438] "Dashboard" refers to an interface that visualizes the optimal staffing results calculated by the optimization algorithm and presents them to the user.

[0439] This invention is a system that supports efficient personnel allocation and optimization of team formation in companies and organizations. This system collects and analyzes communication data from daily work, and automates a series of processes to propose optimal personnel allocation based on the data.

[0440] Data Collection Module

[0441] Devices: We collect communication data generated through the communication tools employees use in their daily work, such as telephone, video conferencing, email, and messaging services.

[0442] Example: Employee A holds a video conference, and the audio data and text log are saved on the device. After the conference ends, this data is automatically sent to the server.

[0443] Data Analysis Module

[0444] Server: Received communication data is temporarily stored and then filtered to remove noise and unnecessary information (e.g., casual conversation) and extract only the important information.

[0445] Example: The server removes casual conversation from the conversation log between employees A and B and extracts only work-related content.

[0446] Generative AI Models

[0447] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0448] Example: A generative AI model analyzes Employee A's question, "How is this project going?" and Employee B's response, "It's going well," to assess the working relationship and performance expectations between the two.

[0449] Optimization Algorithm

[0450] Server: Based on the calculated relationship value and expected performance value, it simulates combination patterns of multiple members and evaluates them to find the optimal combination.

[0451] Example: The server tries dozens to hundreds of combinations of employees A, B, and C, and finds the combination with the highest sum of relationship value and performance expectation.

[0452] Result presentation module

[0453] Server: Visualizes the optimal member combination and presents it to the user in dashboard format.

[0454] Users: Managers and HR personnel can access the dashboard through a web browser to see the most efficient team composition. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for this will be displayed in graphs of relationship scores and performance expectations.

[0455] By combining and implementing each of the above modules, the system utilizes communication data within a company and proposes efficient staffing and team composition based on objective data. Examples of prompts include, "How is the progress on this project?" and "It's progressing smoothly." This will enable managers and human resources personnel to make optimal decisions in their daily work.

[0456] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0457] Step 1:

[0458] Devices: Employees communicate via telephone, video conferencing, email, and messaging services. Devices collect communication data (audio logs, text logs, etc.).

[0459] Specific operation: Employee A holds a video conference, and the audio data and text of the conversation are saved on the device.

[0460] Input: Video conferencing, phone, email, and chat tool usage data

[0461] Output: Saved communication log data

[0462] Step 2:

[0463] Terminal: Periodically sends collected communication log data to the server.

[0464] Specific operation: After the video conference ends, the terminal automatically uploads the audio data and text log to the server.

[0465] Input: Communication log data saved on the device

[0466] Output: Communication data sent to the server

[0467] Step 3:

[0468] Server: The received data is stored in temporary storage and the filtering process begins, removing noise and unnecessary information and extracting important business information.

[0469] Specific operation: The server uses a noise removal algorithm to detect and remove chatter.

[0470] Input: Communication data sent to the server

[0471] Output: filtered and clean data

[0472] Step 4:

[0473] Server: Inputs the filtered data into the generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0474] Specific operation: The server supplies clean data to the generative AI model, and the NLP engine analyzes and quantifies the content of the speech.

[0475] Input: filtered clean data

[0476] Output: Quantified relationship values ​​and performance expectations

[0477] Step 5:

[0478] Server: Simulates optimal combinations of members based on relationship values ​​and performance expectations. Tries and evaluates multiple scenarios.

[0479] Specific operation: The server uses a simulation algorithm to evaluate various team composition patterns and calculate the optimal combination.

[0480] Inputs: Quantified relationship values ​​and performance expectations

[0481] Output: Optimal combination pattern

[0482] Step 6:

[0483] Server: Visualizes the optimal combination patterns and presents them to the user in a dashboard format.

[0484] Specific operation: The server uses a visualization tool to generate optimal staffing results in the form of graphs and charts.

[0485] Input: Optimal combination pattern

[0486] Output: Results visualized in a dashboard

[0487] Step 7:

[0488] Users: Managers and HR personnel access the dashboard to see the most efficient team structure.

[0489] Specific behavior: The user logs into the dashboard through a web browser and checks the suggested optimal team composition and the reasons for it.

[0490] Input: Results visualized in the dashboard

[0491] Output: Optimal team composition information confirmed

[0492] By sequentially executing each of the above steps, the system can effectively analyze communication data and suggest optimal staffing arrangements.

[0493] (Application example 1)

[0494] 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."

[0495] Logistics centers need to improve work efficiency and optimize staffing, but traditional methods make it difficult to accurately evaluate the performance of humans and robots and organize optimal teams. Furthermore, real-time data collection and analysis are not possible, which can lead to work delays and reduced efficiency.

[0496] 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.

[0497] In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into a generative AI model and calculating a relationship value and an expected performance value between members, means for simulating an optimal member combination pattern based on the calculated relationship value and expected performance value, means for visualizing the simulated combination pattern and presenting it to a user, and means for collecting item work log data and proposing an optimal work team formation. This improves work efficiency in a logistics center and enables accurate personnel allocation and work team formation.

[0498] "Communication data" refers to information sent and received via electronic devices or communication means.

[0499] "Filtering" is the process of removing noise and unnecessary information from collected data and extracting necessary information.

[0500] A "generative AI model" is an artificial intelligence model trained to handle a specific task, using natural language processing techniques and machine learning algorithms to analyze and predict data.

[0501] "Relationship value" is an indicator that quantifies the cooperative relationship and compatibility between members.

[0502] "Performance expectations" are numerical indicators that quantify the expected results and efficiency of members in specific tasks.

[0503] "Simulation" is the process of virtually testing results under different conditions to derive the optimal solution.

[0504] "Visualization" is a technique that makes data and information easier to understand by visually representing them.

[0505] "Item work log data" refers to detailed record data regarding the handling of items and the progress of work at a logistics center.

[0506] "Work team formation" is the process of arranging multiple workers and robots in optimal combinations to ensure efficient business operations.

[0507] A "dashboard" is an interface that aggregates data and displays it in a visually easy-to-understand manner.

[0508] The present invention relates to a system for improving work efficiency within a logistics center. This system collects communication data and work log data for items, and proposes optimal work team organization by analyzing, optimizing, and visualizing the data. Specific embodiments of the system are described below.

[0509] Data collection

[0510] The server collects communication data and item work log data in real time. Communication data includes telephone, video conference, email, and chat data. Item work log data includes, for example, the time and accuracy of picking, packing, and shipping work. This data is collected using devices such as smartphones, smart glasses, or robots.

[0511] Data analysis

[0512] The server stores the collected data in temporary storage and filters out noise and unnecessary information. It then extracts the necessary information and inputs it into a generative AI model. This model uses natural language processing techniques and machine learning algorithms to calculate relationship values ​​and performance expectations between members. The software used includes Python, Pandas, Scikit-learn, and Matplotlib.

[0513] simulation

[0514] The server simulates various combination patterns based on the calculated relationship values ​​and expected performance values. For example, if the combination of employees A and B and robot C is determined to be optimal, the reason for this is displayed in a graph of relationship values ​​and expected performance values.

[0515] Results presentation

[0516] Users can view the simulated optimal work team composition in a dashboard format, which visually displays the relationship values ​​and performance expectations of each member, making it easy for managers and human resources personnel to understand the optimal allocation.

[0517] Specific examples

[0518] For example, the following prompts can be fed into a generative AI model to determine optimal team composition:

[0519] "Please suggest the most efficient work team formation based on the work log data of the distribution center. The data includes work completion time, accuracy score, and team coordination score."

[0520] By inputting the above prompts, the generative AI model can suggest efficient team composition and visually represent the results in a dashboard.

[0521] Hardware and Software Used

[0522] A system for implementing the present invention uses the following hardware and software:

[0523] Hardware: Smartphones, smart glasses, robots, servers

[0524] Software: Python, Pandas, Scikit-learn, Matplotlib

[0525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0526] Step 1:

[0527] The terminals collect communication data and work log data related to work within the logistics center. Collected data includes telephone, video conference, email, chat data, and the time and accuracy of picking, packing, and shipping work. This data is sent to the server in real time. The input data is communication data and work log data in raw data format, and the output data is data stored on the server.

[0528] Step 2:

[0529] The server stores the received communication data and work log data in temporary storage and begins the filtering process. Noise and unnecessary information are removed, and only the necessary information is extracted. This process yields accurate data relevant to the business. The input is the data in temporary storage, and the output is the filtered data.

[0530] Step 3:

[0531] The server inputs the filtered data into a generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each worker. This process quantifies the degree of collaboration and work efficiency. The input is the filtered data, and the output is numerical data on the relationship value and performance expectation value.

[0532] Step 4:

[0533] The server simulates optimal work team combination patterns based on the calculated relationship values ​​and expected performance values. Through the simulation, various combination patterns are evaluated and the most efficient team placement is derived. The input is the numerical data of relationship values ​​and expected performance values, and the output is an optimal team composition plan.

[0534] Step 5:

[0535] The server visualizes the simulated optimal team composition and presents it to the user. The relationship values ​​and performance expectations of each member are visually displayed in a dashboard format for easy understanding. The input is the optimal team composition proposal, and the output is the visualized dashboard display information.

[0536] Step 6:

[0537] Users can refer to the dashboard to confirm the optimal work team formation. By reflecting this in the actual work allocation, efficient operations within the logistics center can be achieved. The input is the visualized dashboard information, and the output is the execution of the optimal work team formation.

[0538] 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.

[0539] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[0540] 1. Data Collection Module

[0541] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0542] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[0543] 2. Data Analysis Module

[0544] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[0545] Example: From the chat log between employee A and employee B, remove casual conversations such as "hello" and extract only the work-related conversation content.

[0546] 3. Emotion Engine

[0547] Server: The extracted data is input into the emotion engine to analyze the user's emotions. The emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text.

[0548] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[0549] 4. Generative AI Models

[0550] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[0551] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[0552] 5. Optimization Algorithms

[0553] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. Various scenarios are tried and evaluated to find the optimal combination. By taking emotional information into account, more accurate predictions are possible.

[0554] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[0555] 6. Results presentation module

[0556] Server: The simulated optimal staffing is visualized in charts and graphs and presented to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm the optimal staffing.

[0557] Users: Human resources and managers can access the dashboard to check optimal staffing and reorganize the organization based on the proposed staffing. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for the placement are shown in graphs of relationship values, performance expectations, and emotional states.

[0558] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. Using the emotion engine improves the accuracy of relationship values ​​and performance expectations, enabling more optimal team formation. When implementing the invention, it is important to correctly combine these modules and methods.

[0559] The processing flow will be explained below.

[0560] Step 1:

[0561] Data collection

[0562] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[0563] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[0564] Step 2:

[0565] Data filtering

[0566] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[0567] Server: Prepares the filtered data for analysis.

[0568] Step 3:

[0569] Information Extraction

[0570] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[0571] Step 4:

[0572] Emotion analysis using an emotion engine

[0573] Server: The extracted data is input into the emotion engine to analyze the user's emotional state. The emotion engine identifies the user's emotions (joy, anger, sadness, etc.) from the voice and text.

[0574] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[0575] Step 5:

[0576] Input to generative AI models

[0577] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[0578] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated as 70 (out of 100).

[0579] Step 6:

[0580] Simulation using optimization algorithms

[0581] Server: Simulates multiple combination patterns based on relationship values ​​and expected performance. Tries and evaluates various scenarios to find the optimal combination. Taking emotional information into account enables more accurate predictions.

[0582] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[0583] Step 7:

[0584] Visualizing and presenting results

[0585] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and provide the reasons for this allocation (details of relationship values, performance expectations, and emotional states).

[0586] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[0587] Example 2

[0588] 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."

[0589] In traditional organizational management, it was difficult to create optimal team composition that took into account the relationships between team members and the emotional state of each individual. This could lead to poor performance and hinder efficient business operations.

[0590] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion engine and analyzing the user's emotions, means for inputting the output of the emotion engine and the filtered data into a generative AI model and calculating relationship values ​​and expected performance values ​​between members, means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and means for visualizing the simulated combination patterns and presenting them to the user. This enables optimal team formation that takes into account the emotional states and relationships between members, thereby improving work efficiency and performance.

[0591] "Communication data" refers to information relating to communications such as telephone calls, video conferences, emails, and chat data conducted using a terminal.

[0592] "Filtering" is the process of removing unnecessary information (noise and meaningless conversations) from communication data and extracting necessary information.

[0593] An "emotion engine" is an analysis engine that has the ability to identify a user's emotional state (joy, anger, sadness, etc.) from voice and text.

[0594] A "generative AI model" is a model that uses natural language processing technology and machine learning algorithms to calculate relationship values ​​and performance expectations between members from input data.

[0595] "Relationship value" is an index that represents the relationship between members, and is a value evaluated based on the quality and frequency of communication, emotional state, etc.

[0596] "Performance expectations" are indicators of the performance expected when members work together.

[0597] "Simulation" is a process of trying out optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and evaluating the results.

[0598] "Visualization" refers to visually displaying the results of simulated combination patterns in the form of diagrams, graphs, etc.

[0599] The present invention relates to a system for collecting and analyzing communication data and forming an optimal team. Specific embodiments of the system will be described in detail below.

[0600] Data collection

[0601] Devices: Communication data is generated when employees use telephones, video conferencing, email, and chat tools. This data is automatically collected and sent to the server. For example, after employee A finishes a video conference, the audio data and text log of the conversation are transferred to the server.

[0602] Data analysis

[0603] Server: The received communication data is stored in temporary storage and the filtering process begins. Unnecessary information (such as small talk and noise such as "hello") is removed, and the necessary information is extracted. For example, only the work-related conversation content is extracted from the chat log between employee A and employee B.

[0604] Emotion analysis

[0605] Server: The extracted data is input into the emotion engine, which analyzes the user's emotions. This emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text. For example, when employee A says, "This project isn't going well," the emotion engine analyzes the user's emotion of dissatisfaction and returns the results to the server.

[0606] Using generative AI models

[0607] Server: The filtered data and the output of the emotion engine are input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectations between members. For example, if the content of Employee A's speech and emotional state are input into the model, the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[0608] Simulation and Optimization

[0609] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members. In this process, various scenarios are tried and evaluated. By taking emotional information into account, more accurate predictions are possible. For example, if employee A frequently feels dissatisfied, it takes into account that his relationship values ​​with other members will decline, and calculates the expected performance value for the combination of employees A, B, and C.

[0610] Visualizing the results

[0611] Server: The server visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user. Managers and human resources personnel can refer to this dashboard to confirm the optimal team composition. For example, it may display "The optimal team composition is made up of employees A, B, and C," and the reasons for this composition may be shown in graphs of relationship values, performance expectations, and emotional states.

[0612] Prompt Sentence Examples

[0613] Below is an example of a prompt sentence to be input to the generative AI model.

[0614] "Employee A expresses dissatisfaction during a project meeting. Please analyze the relationship between Employee A and Employee B and suggest the optimal team formation."

[0615] Through these processes, the system effectively analyzes communication data and supports optimal team formation and personnel allocation. In this way, by using the emotion engine, the present invention improves the accuracy of relationship values ​​and performance expectations, enabling more appropriate team formation.

[0616] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0617] Step 1:

[0618] Data collection

[0619] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0620] Input: Communication data sent from the device (voice data, text logs, etc.).

[0621] Output: Raw communication data stored on the server.

[0622] Specific operation: After employee A finishes the video conference, the device converts the voice data into text and sends the log to the server.

[0623] Step 2:

[0624] Data analysis

[0625] Server: Received communication data is stored in temporary storage and filtering process begins. Unnecessary information (noise and chatter) is removed and necessary information is extracted.

[0626] Input: Raw communication data stored in temporary storage.

[0627] Output: The filtered data you want.

[0628] Specific operation: The server removes greetings such as "hello" from the voice data and extracts only business-related content.

[0629] Step 3:

[0630] Emotion analysis

[0631] Server: Inputs the extracted data into the emotion engine to analyze the user's emotions. The emotion engine identifies the emotional state from the voice and text.

[0632] Input: Filtered communication data.

[0633] Output: Sentiment analysis results (type and intensity of emotion).

[0634] Specific operation: The server analyzes employee A's statement, "This project isn't going well," and identifies it as an expression of dissatisfaction.

[0635] Step 4:

[0636] Using generative AI models

[0637] Server: The filtered data and the output of the emotion engine are input into the generative AI model, which calculates the relationship value and performance expectation for each member.

[0638] Input: Sentiment analysis results and filtered required data.

[0639] Output: Relationship values ​​and performance expectations.

[0640] Specific operation: Input the content of Employee A's speech and his emotional state, and calculate the relationship value between Employee A and Employee B as 70 (out of 100 points).

[0641] Step 5:

[0642] Optimization Simulation

[0643] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members, tries out various scenarios, and finds the optimal combination.

[0644] Inputs: Relationship value and performance expectation.

[0645] Output: Optimal member combination pattern.

[0646] Specific operation: Considering the impact that frequently dissatisfied employee A has on the team, simulate the optimal team composition based on the relationship values ​​with other members.

[0647] Step 6:

[0648] Visualizing the results

[0649] Server: Visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user.

[0650] Input: Optimal member combination pattern.

[0651] Output: A visualized dashboard.

[0652] Specific operation: The system displays a graph and explanatory text to the user showing the optimal team composition of employees A, B, and C. This allows the human resources department and managers to confirm the optimal composition and use it to formulate actual organizational compositions.

[0653] (Application example 2)

[0654] 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."

[0655] In modern factories, maximizing the operational efficiency of robots and machines is key to improving productivity. However, interactions between robots and communication with operators are complicated, making it difficult to find efficient work arrangements and collaboration structures. Furthermore, manually analyzing large amounts of data takes time and effort, making it impossible to determine optimal work patterns in real time. A system that can solve these issues is needed.

[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0657] In this invention, the server includes means for collecting machine operation data and communication logs, means for filtering the collected operation data and communication logs, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion analysis module and evaluating the status of the machines and personnel, means for inputting the evaluated data into a generative AI model and calculating cooperative relationships and performance expectations between the machines, means for simulating optimal machine combination patterns based on the calculated cooperative relationships and performance expectations, and means for visualizing the simulated combination patterns and presenting them to a user. This makes it possible to efficiently collect and analyze robot and machine operation data and communication logs and determine optimal work placement and cooperation systems in real time.

[0658] "Machine operation data" means information relating to the operating status and operation of robots and machines used in factories.

[0659] "Communication log" refers to a record of communication such as messages and instructions exchanged between robots and operators.

[0660] "Filtering" refers to the process of removing noise and unnecessary information from collected data and extracting necessary information.

[0661] "Emotion analysis module" refers to software that has the function of evaluating the operating status and stress level of robots and operators from input data.

[0662] "Generative AI model" means a model that uses natural language processing techniques and machine learning algorithms to calculate appropriate work patterns and collaboration relationships.

[0663] "Cooperative relationship" refers to the mutual relationship when multiple robots or machines work together to perform a task.

[0664] "Performance expectations" refers to expectations regarding the efficiency and productivity of a robot or machine when performing a specific task.

[0665] "Simulation" refers to the process of trying out multiple scenarios and simulating the optimal work arrangements and cooperation systems.

[0666] "Visualization" means displaying analysis or simulation results in a visual format such as a graph or diagram.

[0667] "User" refers to the manager or operator who uses the system to determine optimal work arrangements and cooperation structures and make decisions.

[0668] A specific system configuration and program processing will be described for an embodiment of the present invention.

[0669] System Program

[0670] The server performs the following steps:

[0671] 1. Data Collection Module

[0672] The server collects operational data and communication logs from the robots and machines used in the factory. The specific hardware used includes sensor devices (e.g., LIDAR and cameras), and the communication interface uses Wi-Fi and Bluetooth. The operational data includes information about operating status and behavior, while the communication log includes the content of communications between robots and with operators.

[0673] 2. Data Analysis Module

[0674] The server stores the collected operation data and communication logs in a database system (MySQL or PostgreSQL) and performs a filtering process to remove noise and unnecessary information and extract the necessary information.

[0675] 3. Sentiment Analysis Module

[0676] The filtered data is then fed into a sentiment analysis module, where the server analyzes the data using natural language processing libraries (SpaCy and BERT) to assess the operating status and stress levels of the robots and operators.

[0677] 4. Generative AI Models

[0678] The results of the sentiment analysis and filtered data are input into a generative AI model. The server uses machine learning frameworks (TensorFlow and PyTorch) to calculate appropriate work patterns and collaboration relationships. The generative AI model includes natural language processing technology and machine learning algorithms.

[0679] 5. Optimization Algorithms

[0680] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values ​​to find the optimal machine combination pattern. The calculated optimal placement is visualized in dashboard format using a web front end (React or Vue.js).

[0681] 6. User Presentation Module

[0682] The simulated results are displayed on a dashboard, allowing administrators to check them in real time. Data is passed and processed using a backend API (Flask or Node.js).

[0683] Specific examples

[0684] Next, we will show a specific example of operation. For example, after Robot A has been operating for a long period of time, its operation data is collected by a sensor device and sent to a server. The server filters the data to remove noise and unnecessary information. An emotion analysis module evaluates fatigue and stress levels, and the results are input into a generative AI model. The generative AI model calculates the cooperative relationship between Robot A and other robots B and C, and proposes optimal work patterns. The calculated results are displayed on a dashboard so that managers can check them.

[0685] Prompt Sentence Examples

[0686] A computergram has the following format:

[0687] Input collected sensor and communication data

[0688] sensor_data = {

[0689] "robot_a": {

[0690] "temperature": 65,

[0691] "movement": "assembly",

[0692] "operating_time": 320,

[0693] ...

[0694] },

[0695] ...

[0696] }

[0697] Input the output of the emotion engine

[0698] emotional_state = {

[0699] "robot_a": {

[0700] "fatigue_level": 0.8,

[0701] "stress_level": 0.4,

[0702] },

[0703] ...

[0704] }

[0705] Input to generative AI model

[0706] optimal_configuration = generate_optimal_configuration(sensor_data, emotional_state)

[0707] print(optimal_configuration)

[0708] This makes it possible to efficiently collect and analyze operation data and communication logs of robots and machines, and determine optimal work placement and cooperation systems in real time.

[0709] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0710] Step 1:

[0711] The server collects operational data and communication logs from the robots and machines used in the factory through sensor devices (LIDAR and cameras) and communication interfaces (Wi-Fi and Bluetooth). This input data includes the robot's operating status, operational information, and communication between robots and with operators. This data is stored in a database (MySQL and PostgreSQL).

[0712] Step 2:

[0713] The server filters the operational data and communication logs stored in temporary storage. Specifically, it removes noise and unnecessary information and extracts only important information related to the business. For example, it removes noise recorded during movement and extracts only data related to part assembly. This process generates filtered data.

[0714] Step 3:

[0715] The server inputs the filtered data into an emotion analysis module to evaluate the operating status and stress levels of the robots and operators. For example, it uses a natural language processing library (SpaCy or BERT) to analyze the fatigue level of Robot A after a long period of operation. Emotion data is generated as the analysis result.

[0716] Step 4:

[0717] The server inputs the output of the emotion analysis module and filtered data into the generative AI model. It uses a machine learning framework (TensorFlow or PyTorch) to calculate appropriate work patterns and cooperative relationships between robots. For example, if robot A and robot B have a strong cooperative relationship, the expected performance of the cooperative work will be calculated to be high. The generated performance data is then output.

[0718] Step 5:

[0719] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values. It then uses an optimization algorithm to find the optimal machine combination pattern. For example, it considers the fatigue level of robot A and evaluates the optimal combination with robots B and C. This generates the optimal deployment pattern.

[0720] Step 6:

[0721] The server visualizes the simulated results in the form of a dashboard and presents it to the user. This uses a web front end (React or Vue.js) and provides data to the user through a backend API (Flask or Node.js). For example, an administrator can view the dashboard and confirm that the combination of robots A and B is optimal. This displays the presented optimization data.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] [Third embodiment]

[0726] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0727] 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.

[0728] 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).

[0729] 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.

[0730] 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.

[0731] 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).

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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."

[0738] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[0739] 1. Data Collection Module

[0740] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0741] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[0742] 2. Data Analysis Module

[0743] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[0744] Example: Remove the casual conversation between employee A and employee B and extract only the work-related conversation content.

[0745] 3. Generative AI Models

[0746] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0747] Example: Evaluate the collaboration and performance of two employees based on the conversation between Employee A, "How is this project progressing?" and Employee B, "It's going well."

[0748] 4. Optimization Algorithms

[0749] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. It tries and evaluates various scenarios to find the optimal combination.

[0750] Example: If employees A, B, and C are placed on the same team, find the combination that has the highest sum of relationship value and performance expectation.

[0751] 5. Results presentation module

[0752] Server: Visualizes optimal staffing and presents it to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm optimal staffing.

[0753] Users: HR and managers can access the dashboard to see the most efficient team composition. For example, they might see, "The optimal team composition is made up of employees A, B, and C," and the reasons for this are shown in graphs of relationship scores and performance expectations.

[0754] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. When implementing the invention, it is important to properly combine these modules and means.

[0755] The processing flow will be explained below.

[0756] Step 1:

[0757] Data collection

[0758] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[0759] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[0760] Step 2:

[0761] Data filtering

[0762] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, it removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[0763] Step 3:

[0764] Information Extraction

[0765] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[0766] Step 4:

[0767] Input to generative AI models

[0768] Server: The extracted data is input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each member. For example, based on the above utterance, the relationship value between employee A and employee B is calculated to be 80 (out of 100).

[0769] Step 5:

[0770] Simulation using optimization algorithms

[0771] Server: Simulates multiple combination patterns based on relationship values ​​and performance expectations. Tries and evaluates various scenarios to find the optimal combination. For example, calculates the performance expectations when employees A, B, and C are placed on the same team.

[0772] Step 6:

[0773] Visualizing and presenting results

[0774] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and the reasons for this allocation (details of relationship values ​​and performance expectations) are shown in a graph.

[0775] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[0776] Example 1

[0777] 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."

[0778] This invention relates to a system for efficiently optimizing personnel allocation and team formation in companies and organizations. Conventional personnel allocation decisions often rely on subjective judgment, which can lead to inefficient allocation and poor communication. This invention aims to solve these issues by collecting and analyzing daily communication data and presenting optimal team formation based on objective data.

[0779] 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.

[0780] In this invention, the server includes: [means for filtering collected communication data;] [means for extracting necessary business information from the filtered data; and] [means for inputting the extracted business data into a generative AI model and calculating relationship values ​​and performance expectations between members.] This makes it possible [to optimally organize teams and assign personnel based on objective data, thereby improving the efficiency and performance of the entire organization].

[0781] "Devices" refers to communication tools (telephones, video conferencing equipment, email clients, messaging service applications) used by employees in their daily work.

[0782] "Communication Data" refers to voice data, video conference logs, emails, and messaging service data generated via the Terminal.

[0783] "Server" refers to a computer system that collects and analyzes communication data.

[0784] "Filtering" refers to the process of removing noise and unnecessary information from received communication data and extracting necessary business information.

[0785] "Generative AI model" refers to a model that uses natural language processing techniques and machine learning algorithms to analyze data and quantify relationship values ​​and performance expectations.

[0786] "Relationship value" refers to a numerical indicator that indicates the strength of the cooperative relationship between members.

[0787] "Performance expectations" refers to a numerical indicator that predicts each member's work performance.

[0788] "Optimization algorithm" refers to an algorithm that simulates and determines the optimal combination of members based on relationship values ​​and expected performance values.

[0789] "Dashboard" refers to an interface that visualizes the optimal staffing results calculated by the optimization algorithm and presents them to the user.

[0790] This invention is a system that supports efficient personnel allocation and optimization of team formation in companies and organizations. This system collects and analyzes communication data from daily work, and automates a series of processes to propose optimal personnel allocation based on the data.

[0791] Data Collection Module

[0792] Devices: We collect communication data generated through the communication tools employees use in their daily work, such as telephone, video conferencing, email, and messaging services.

[0793] Example: Employee A holds a video conference, and the audio data and text log are saved on the device. After the conference ends, this data is automatically sent to the server.

[0794] Data Analysis Module

[0795] Server: Received communication data is temporarily stored and then filtered to remove noise and unnecessary information (e.g., casual conversation) and extract only the important information.

[0796] Example: The server removes casual conversation from the conversation log between employees A and B and extracts only work-related content.

[0797] Generative AI Models

[0798] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0799] Example: A generative AI model analyzes Employee A's question, "How is this project going?" and Employee B's response, "It's going well," to assess the working relationship and performance expectations between the two.

[0800] Optimization Algorithm

[0801] Server: Based on the calculated relationship value and expected performance value, it simulates combination patterns of multiple members and evaluates them to find the optimal combination.

[0802] Example: The server tries dozens to hundreds of combinations of employees A, B, and C, and finds the combination with the highest sum of relationship value and performance expectation.

[0803] Result presentation module

[0804] Server: Visualizes the optimal member combination and presents it to the user in dashboard format.

[0805] Users: Managers and HR personnel can access the dashboard through a web browser to see the most efficient team composition. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for this will be displayed in graphs of relationship scores and performance expectations.

[0806] By combining and implementing each of the above modules, the system utilizes communication data within a company and proposes efficient staffing and team composition based on objective data. Examples of prompts include, "How is the progress on this project?" and "It's progressing smoothly." This will enable managers and human resources personnel to make optimal decisions in their daily work.

[0807] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0808] Step 1:

[0809] Devices: Employees communicate via telephone, video conferencing, email, and messaging services. Devices collect communication data (audio logs, text logs, etc.).

[0810] Specific operation: Employee A holds a video conference, and the audio data and text of the conversation are saved on the device.

[0811] Input: Video conferencing, phone, email, and chat tool usage data

[0812] Output: Saved communication log data

[0813] Step 2:

[0814] Terminal: Periodically sends collected communication log data to the server.

[0815] Specific operation: After the video conference ends, the terminal automatically uploads the audio data and text log to the server.

[0816] Input: Communication log data saved on the device

[0817] Output: Communication data sent to the server

[0818] Step 3:

[0819] Server: The received data is stored in temporary storage and the filtering process begins, removing noise and unnecessary information and extracting important business information.

[0820] Specific operation: The server uses a noise removal algorithm to detect and remove chatter.

[0821] Input: Communication data sent to the server

[0822] Output: filtered and clean data

[0823] Step 4:

[0824] Server: Inputs the filtered data into the generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[0825] Specific operation: The server supplies clean data to the generative AI model, and the NLP engine analyzes and quantifies the content of the speech.

[0826] Input: filtered clean data

[0827] Output: Quantified relationship values ​​and performance expectations

[0828] Step 5:

[0829] Server: Simulates optimal combinations of members based on relationship values ​​and performance expectations. Tries and evaluates multiple scenarios.

[0830] Specific operation: The server uses a simulation algorithm to evaluate various team composition patterns and calculate the optimal combination.

[0831] Inputs: Quantified relationship values ​​and performance expectations

[0832] Output: Optimal combination pattern

[0833] Step 6:

[0834] Server: Visualizes the optimal combination patterns and presents them to the user in a dashboard format.

[0835] Specific operation: The server uses a visualization tool to generate optimal staffing results in the form of graphs and charts.

[0836] Input: Optimal combination pattern

[0837] Output: Results visualized in a dashboard

[0838] Step 7:

[0839] Users: Managers and HR personnel access the dashboard to see the most efficient team structure.

[0840] Specific behavior: The user logs into the dashboard through a web browser and checks the suggested optimal team composition and the reasons for it.

[0841] Input: Results visualized in the dashboard

[0842] Output: Optimal team composition information confirmed

[0843] By sequentially executing each of the above steps, the system can effectively analyze communication data and suggest optimal staffing arrangements.

[0844] (Application example 1)

[0845] 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."

[0846] Logistics centers need to improve work efficiency and optimize staffing, but traditional methods make it difficult to accurately evaluate the performance of humans and robots and organize optimal teams. Furthermore, real-time data collection and analysis are not possible, which can lead to work delays and reduced efficiency.

[0847] 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.

[0848] In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into a generative AI model and calculating a relationship value and an expected performance value between members, means for simulating an optimal member combination pattern based on the calculated relationship value and expected performance value, means for visualizing the simulated combination pattern and presenting it to a user, and means for collecting item work log data and proposing an optimal work team formation. This improves work efficiency in a logistics center and enables accurate personnel allocation and work team formation.

[0849] "Communication data" refers to information sent and received via electronic devices or communication means.

[0850] "Filtering" is the process of removing noise and unnecessary information from collected data and extracting necessary information.

[0851] A "generative AI model" is an artificial intelligence model trained to handle a specific task, using natural language processing techniques and machine learning algorithms to analyze and predict data.

[0852] "Relationship value" is an indicator that quantifies the cooperative relationship and compatibility between members.

[0853] "Performance expectations" are numerical indicators that quantify the expected results and efficiency of members in specific tasks.

[0854] "Simulation" is the process of virtually testing results under different conditions to derive the optimal solution.

[0855] "Visualization" is a technique that makes data and information easier to understand by visually representing them.

[0856] "Item work log data" refers to detailed record data regarding the handling of items and the progress of work at a logistics center.

[0857] "Work team formation" is the process of arranging multiple workers and robots in optimal combinations to ensure efficient business operations.

[0858] A "dashboard" is an interface that aggregates data and displays it in a visually easy-to-understand manner.

[0859] The present invention relates to a system for improving work efficiency within a logistics center. This system collects communication data and work log data for items, and proposes optimal work team organization by analyzing, optimizing, and visualizing the data. Specific embodiments of the system are described below.

[0860] Data collection

[0861] The server collects communication data and item work log data in real time. Communication data includes telephone, video conference, email, and chat data. Item work log data includes, for example, the time and accuracy of picking, packing, and shipping work. This data is collected using devices such as smartphones, smart glasses, or robots.

[0862] Data analysis

[0863] The server stores the collected data in temporary storage and filters out noise and unnecessary information. It then extracts the necessary information and inputs it into a generative AI model. This model uses natural language processing techniques and machine learning algorithms to calculate relationship values ​​and performance expectations between members. The software used includes Python, Pandas, Scikit-learn, and Matplotlib.

[0864] simulation

[0865] The server simulates various combination patterns based on the calculated relationship values ​​and expected performance values. For example, if the combination of employees A and B and robot C is determined to be optimal, the reason for this is displayed in a graph of relationship values ​​and expected performance values.

[0866] Results presentation

[0867] Users can view the simulated optimal work team composition in a dashboard format, which visually displays the relationship values ​​and performance expectations of each member, making it easy for managers and human resources personnel to understand the optimal allocation.

[0868] Specific examples

[0869] For example, the following prompts can be fed into a generative AI model to determine optimal team composition:

[0870] "Please suggest the most efficient work team formation based on the work log data of the distribution center. The data includes work completion time, accuracy score, and team coordination score."

[0871] By inputting the above prompts, the generative AI model can suggest efficient team composition and visually represent the results in a dashboard.

[0872] Hardware and Software Used

[0873] A system for implementing the present invention uses the following hardware and software:

[0874] Hardware: Smartphones, smart glasses, robots, servers

[0875] Software: Python, Pandas, Scikit-learn, Matplotlib

[0876] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0877] Step 1:

[0878] The terminals collect communication data and work log data related to work within the logistics center. Collected data includes telephone, video conference, email, chat data, and the time and accuracy of picking, packing, and shipping work. This data is sent to the server in real time. The input data is communication data and work log data in raw data format, and the output data is data stored on the server.

[0879] Step 2:

[0880] The server stores the received communication data and work log data in temporary storage and begins the filtering process. Noise and unnecessary information are removed, and only the necessary information is extracted. This process yields accurate data relevant to the business. The input is the data in temporary storage, and the output is the filtered data.

[0881] Step 3:

[0882] The server inputs the filtered data into a generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each worker. This process quantifies the degree of collaboration and work efficiency. The input is the filtered data, and the output is numerical data on the relationship value and performance expectation value.

[0883] Step 4:

[0884] The server simulates optimal work team combination patterns based on the calculated relationship values ​​and expected performance values. Through the simulation, various combination patterns are evaluated and the most efficient team placement is derived. The input is the numerical data of relationship values ​​and expected performance values, and the output is an optimal team composition plan.

[0885] Step 5:

[0886] The server visualizes the simulated optimal team composition and presents it to the user. The relationship values ​​and performance expectations of each member are visually displayed in a dashboard format for easy understanding. The input is the optimal team composition proposal, and the output is the visualized dashboard display information.

[0887] Step 6:

[0888] Users can refer to the dashboard to confirm the optimal work team formation. By reflecting this in the actual work allocation, efficient operations within the logistics center can be achieved. The input is the visualized dashboard information, and the output is the execution of the optimal work team formation.

[0889] 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.

[0890] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[0891] 1. Data Collection Module

[0892] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0893] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[0894] 2. Data Analysis Module

[0895] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[0896] Example: From the chat log between employee A and employee B, remove casual conversations such as "hello" and extract only the work-related conversation content.

[0897] 3. Emotion Engine

[0898] Server: The extracted data is input into the emotion engine to analyze the user's emotions. The emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text.

[0899] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[0900] 4. Generative AI Models

[0901] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[0902] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[0903] 5. Optimization Algorithms

[0904] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. Various scenarios are tried and evaluated to find the optimal combination. By taking emotional information into account, more accurate predictions are possible.

[0905] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[0906] 6. Results presentation module

[0907] Server: The simulated optimal staffing is visualized in charts and graphs and presented to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm the optimal staffing.

[0908] Users: Human resources and managers can access the dashboard to check optimal staffing and reorganize the organization based on the proposed staffing. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for the placement are shown in graphs of relationship values, performance expectations, and emotional states.

[0909] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. Using the emotion engine improves the accuracy of relationship values ​​and performance expectations, enabling more optimal team formation. When implementing the invention, it is important to correctly combine these modules and methods.

[0910] The processing flow will be explained below.

[0911] Step 1:

[0912] Data collection

[0913] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[0914] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[0915] Step 2:

[0916] Data filtering

[0917] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[0918] Server: Prepares the filtered data for analysis.

[0919] Step 3:

[0920] Information Extraction

[0921] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[0922] Step 4:

[0923] Emotion analysis using an emotion engine

[0924] Server: The extracted data is input into the emotion engine to analyze the user's emotional state. The emotion engine identifies the user's emotions (joy, anger, sadness, etc.) from the voice and text.

[0925] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[0926] Step 5:

[0927] Input to generative AI models

[0928] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[0929] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated as 70 (out of 100).

[0930] Step 6:

[0931] Simulation using optimization algorithms

[0932] Server: Simulates multiple combination patterns based on relationship values ​​and expected performance. Tries and evaluates various scenarios to find the optimal combination. Taking emotional information into account enables more accurate predictions.

[0933] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[0934] Step 7:

[0935] Visualizing and presenting results

[0936] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and provide the reasons for this allocation (details of relationship values, performance expectations, and emotional states).

[0937] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[0938] Example 2

[0939] 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."

[0940] In traditional organizational management, it was difficult to create optimal team composition that took into account the relationships between team members and the emotional state of each individual. This could lead to poor performance and hinder efficient business operations.

[0941] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion engine and analyzing the user's emotions, means for inputting the output of the emotion engine and the filtered data into a generative AI model and calculating relationship values ​​and expected performance values ​​between members, means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and means for visualizing the simulated combination patterns and presenting them to the user. This enables optimal team formation that takes into account the emotional states and relationships between members, thereby improving work efficiency and performance.

[0942] "Communication data" refers to information relating to communications such as telephone calls, video conferences, emails, and chat data conducted using a terminal.

[0943] "Filtering" is the process of removing unnecessary information (noise and meaningless conversations) from communication data and extracting necessary information.

[0944] An "emotion engine" is an analysis engine that has the ability to identify a user's emotional state (joy, anger, sadness, etc.) from voice and text.

[0945] A "generative AI model" is a model that uses natural language processing technology and machine learning algorithms to calculate relationship values ​​and performance expectations between members from input data.

[0946] "Relationship value" is an index that represents the relationship between members, and is a value evaluated based on the quality and frequency of communication, emotional state, etc.

[0947] "Performance expectations" are indicators of the performance expected when members work together.

[0948] "Simulation" is a process of trying out optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and evaluating the results.

[0949] "Visualization" refers to visually displaying the results of simulated combination patterns in the form of diagrams, graphs, etc.

[0950] The present invention relates to a system for collecting and analyzing communication data and forming an optimal team. Specific embodiments of the system will be described in detail below.

[0951] Data collection

[0952] Devices: Communication data is generated when employees use telephones, video conferencing, email, and chat tools. This data is automatically collected and sent to the server. For example, after employee A finishes a video conference, the audio data and text log of the conversation are transferred to the server.

[0953] Data analysis

[0954] Server: The received communication data is stored in temporary storage and the filtering process begins. Unnecessary information (such as small talk and noise such as "hello") is removed, and the necessary information is extracted. For example, only the work-related conversation content is extracted from the chat log between employee A and employee B.

[0955] Emotion analysis

[0956] Server: The extracted data is input into the emotion engine, which analyzes the user's emotions. This emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text. For example, when employee A says, "This project isn't going well," the emotion engine analyzes the user's emotion of dissatisfaction and returns the results to the server.

[0957] Using generative AI models

[0958] Server: The filtered data and the output of the emotion engine are input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectations between members. For example, if the content of Employee A's speech and emotional state are input into the model, the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[0959] Simulation and Optimization

[0960] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members. In this process, various scenarios are tried and evaluated. By taking emotional information into account, more accurate predictions are possible. For example, if employee A frequently feels dissatisfied, it takes into account that his relationship values ​​with other members will decline, and calculates the expected performance value for the combination of employees A, B, and C.

[0961] Visualizing the results

[0962] Server: The server visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user. Managers and human resources personnel can refer to this dashboard to confirm the optimal team composition. For example, it may display "The optimal team composition is made up of employees A, B, and C," and the reasons for this composition may be shown in graphs of relationship values, performance expectations, and emotional states.

[0963] Prompt Sentence Examples

[0964] Below is an example of a prompt sentence to be input to the generative AI model.

[0965] "Employee A expresses dissatisfaction during a project meeting. Please analyze the relationship between Employee A and Employee B and suggest the optimal team formation."

[0966] Through these processes, the system effectively analyzes communication data and supports optimal team formation and personnel allocation. In this way, by using the emotion engine, the present invention improves the accuracy of relationship values ​​and performance expectations, enabling more appropriate team formation.

[0967] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0968] Step 1:

[0969] Data collection

[0970] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[0971] Input: Communication data sent from the device (voice data, text logs, etc.).

[0972] Output: Raw communication data stored on the server.

[0973] Specific operation: After employee A finishes the video conference, the device converts the voice data into text and sends the log to the server.

[0974] Step 2:

[0975] Data analysis

[0976] Server: Received communication data is stored in temporary storage and filtering process begins. Unnecessary information (noise and chatter) is removed and necessary information is extracted.

[0977] Input: Raw communication data stored in temporary storage.

[0978] Output: The filtered data you want.

[0979] Specific operation: The server removes greetings such as "hello" from the voice data and extracts only business-related content.

[0980] Step 3:

[0981] Emotion analysis

[0982] Server: Inputs the extracted data into the emotion engine to analyze the user's emotions. The emotion engine identifies the emotional state from the voice and text.

[0983] Input: Filtered communication data.

[0984] Output: Sentiment analysis results (type and intensity of emotion).

[0985] Specific operation: The server analyzes employee A's statement, "This project isn't going well," and identifies it as an expression of dissatisfaction.

[0986] Step 4:

[0987] Using generative AI models

[0988] Server: The filtered data and the output of the emotion engine are input into the generative AI model, which calculates the relationship value and performance expectation for each member.

[0989] Input: Sentiment analysis results and filtered required data.

[0990] Output: Relationship values ​​and performance expectations.

[0991] Specific operation: Input the content of Employee A's speech and his emotional state, and calculate the relationship value between Employee A and Employee B as 70 (out of 100 points).

[0992] Step 5:

[0993] Optimization Simulation

[0994] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members, tries out various scenarios, and finds the optimal combination.

[0995] Inputs: Relationship value and performance expectation.

[0996] Output: Optimal member combination pattern.

[0997] Specific operation: Considering the impact that frequently dissatisfied employee A has on the team, simulate the optimal team composition based on the relationship values ​​with other members.

[0998] Step 6:

[0999] Visualizing the results

[1000] Server: Visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user.

[1001] Input: Optimal member combination pattern.

[1002] Output: A visualized dashboard.

[1003] Specific operation: The system displays a graph and explanatory text to the user showing the optimal team composition of employees A, B, and C. This allows the human resources department and managers to confirm the optimal composition and use it to formulate actual organizational compositions.

[1004] (Application example 2)

[1005] 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."

[1006] In modern factories, maximizing the operational efficiency of robots and machines is key to improving productivity. However, interactions between robots and communication with operators are complicated, making it difficult to find efficient work arrangements and collaboration structures. Furthermore, manually analyzing large amounts of data takes time and effort, making it impossible to determine optimal work patterns in real time. A system that can solve these issues is needed.

[1007] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1008] In this invention, the server includes means for collecting machine operation data and communication logs, means for filtering the collected operation data and communication logs, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion analysis module and evaluating the status of the machines and personnel, means for inputting the evaluated data into a generative AI model and calculating cooperative relationships and performance expectations between the machines, means for simulating optimal machine combination patterns based on the calculated cooperative relationships and performance expectations, and means for visualizing the simulated combination patterns and presenting them to a user. This makes it possible to efficiently collect and analyze robot and machine operation data and communication logs and determine optimal work placement and cooperation systems in real time.

[1009] "Machine operation data" means information relating to the operating status and operation of robots and machines used in factories.

[1010] "Communication log" refers to a record of communication such as messages and instructions exchanged between robots and operators.

[1011] "Filtering" refers to the process of removing noise and unnecessary information from collected data and extracting necessary information.

[1012] "Emotion analysis module" refers to software that has the function of evaluating the operating status and stress level of robots and operators from input data.

[1013] "Generative AI model" means a model that uses natural language processing techniques and machine learning algorithms to calculate appropriate work patterns and collaboration relationships.

[1014] "Cooperative relationship" refers to the mutual relationship when multiple robots or machines work together to perform a task.

[1015] "Performance expectations" refers to expectations regarding the efficiency and productivity of a robot or machine when performing a specific task.

[1016] "Simulation" refers to the process of trying out multiple scenarios and simulating the optimal work arrangements and cooperation systems.

[1017] "Visualization" means displaying analysis or simulation results in a visual format such as a graph or diagram.

[1018] "User" refers to the manager or operator who uses the system to determine optimal work arrangements and cooperation structures and make decisions.

[1019] A specific system configuration and program processing will be described for an embodiment of the present invention.

[1020] System Program

[1021] The server performs the following steps:

[1022] 1. Data Collection Module

[1023] The server collects operational data and communication logs from the robots and machines used in the factory. The specific hardware used includes sensor devices (e.g., LIDAR and cameras), and the communication interface uses Wi-Fi and Bluetooth. The operational data includes information about operating status and behavior, while the communication log includes the content of communications between robots and with operators.

[1024] 2. Data Analysis Module

[1025] The server stores the collected operation data and communication logs in a database system (MySQL or PostgreSQL) and performs a filtering process to remove noise and unnecessary information and extract the necessary information.

[1026] 3. Sentiment Analysis Module

[1027] The filtered data is then fed into a sentiment analysis module, where the server analyzes the data using natural language processing libraries (SpaCy and BERT) to assess the operating status and stress levels of the robots and operators.

[1028] 4. Generative AI Models

[1029] The results of the sentiment analysis and filtered data are input into a generative AI model. The server uses machine learning frameworks (TensorFlow and PyTorch) to calculate appropriate work patterns and collaboration relationships. The generative AI model includes natural language processing technology and machine learning algorithms.

[1030] 5. Optimization Algorithms

[1031] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values ​​to find the optimal machine combination pattern. The calculated optimal placement is visualized in dashboard format using a web front end (React or Vue.js).

[1032] 6. User Presentation Module

[1033] The simulated results are displayed on a dashboard, allowing administrators to check them in real time. Data is passed and processed using a backend API (Flask or Node.js).

[1034] Specific examples

[1035] Next, we will show a specific example of operation. For example, after Robot A has been operating for a long period of time, its operation data is collected by a sensor device and sent to a server. The server filters the data to remove noise and unnecessary information. An emotion analysis module evaluates fatigue and stress levels, and the results are input into a generative AI model. The generative AI model calculates the cooperative relationship between Robot A and other robots B and C, and proposes optimal work patterns. The calculated results are displayed on a dashboard so that managers can check them.

[1036] Prompt Sentence Examples

[1037] A computergram has the following format:

[1038] Input collected sensor and communication data

[1039] sensor_data = {

[1040] "robot_a": {

[1041] "temperature": 65,

[1042] "movement": "assembly",

[1043] "operating_time": 320,

[1044] ...

[1045] },

[1046] ...

[1047] }

[1048] Input the output of the emotion engine

[1049] emotional_state = {

[1050] "robot_a": {

[1051] "fatigue_level": 0.8,

[1052] "stress_level": 0.4,

[1053] },

[1054] ...

[1055] }

[1056] Input to generative AI model

[1057] optimal_configuration = generate_optimal_configuration(sensor_data, emotional_state)

[1058] print(optimal_configuration)

[1059] This makes it possible to efficiently collect and analyze operation data and communication logs of robots and machines, and determine optimal work placement and cooperation systems in real time.

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

[1061] Step 1:

[1062] The server collects operational data and communication logs from the robots and machines used in the factory through sensor devices (LIDAR and cameras) and communication interfaces (Wi-Fi and Bluetooth). This input data includes the robot's operating status, operational information, and communication between robots and with operators. This data is stored in a database (MySQL and PostgreSQL).

[1063] Step 2:

[1064] The server filters the operational data and communication logs stored in temporary storage. Specifically, it removes noise and unnecessary information and extracts only important information related to the business. For example, it removes noise recorded during movement and extracts only data related to part assembly. This process generates filtered data.

[1065] Step 3:

[1066] The server inputs the filtered data into an emotion analysis module to evaluate the operating status and stress levels of the robots and operators. For example, it uses a natural language processing library (SpaCy or BERT) to analyze the fatigue level of Robot A after a long period of operation. Emotion data is generated as the analysis result.

[1067] Step 4:

[1068] The server inputs the output of the emotion analysis module and filtered data into the generative AI model. It uses a machine learning framework (TensorFlow or PyTorch) to calculate appropriate work patterns and cooperative relationships between robots. For example, if robot A and robot B have a strong cooperative relationship, the expected performance of the cooperative work will be calculated to be high. The generated performance data is then output.

[1069] Step 5:

[1070] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values. It then uses an optimization algorithm to find the optimal machine combination pattern. For example, it considers the fatigue level of robot A and evaluates the optimal combination with robots B and C. This generates the optimal deployment pattern.

[1071] Step 6:

[1072] The server visualizes the simulated results in the form of a dashboard and presents it to the user. This uses a web front end (React or Vue.js) and provides data to the user through a backend API (Flask or Node.js). For example, an administrator can view the dashboard and confirm that the combination of robots A and B is optimal. This displays the presented optimization data.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] [Fourth embodiment]

[1077] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1078] 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.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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."

[1090] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[1091] 1. Data Collection Module

[1092] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[1093] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[1094] 2. Data Analysis Module

[1095] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[1096] Example: Remove the casual conversation between employee A and employee B and extract only the work-related conversation content.

[1097] 3. Generative AI Models

[1098] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[1099] Example: Evaluate the collaboration and performance of two employees based on the conversation between Employee A, "How is this project progressing?" and Employee B, "It's going well."

[1100] 4. Optimization Algorithms

[1101] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. It tries and evaluates various scenarios to find the optimal combination.

[1102] Example: If employees A, B, and C are placed on the same team, find the combination that has the highest sum of relationship value and performance expectation.

[1103] 5. Results presentation module

[1104] Server: Visualizes optimal staffing and presents it to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm optimal staffing.

[1105] Users: HR and managers can access the dashboard to see the most efficient team composition. For example, they might see, "The optimal team composition is made up of employees A, B, and C," and the reasons for this are shown in graphs of relationship scores and performance expectations.

[1106] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. When implementing the invention, it is important to properly combine these modules and means.

[1107] The processing flow will be explained below.

[1108] Step 1:

[1109] Data collection

[1110] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[1111] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[1112] Step 2:

[1113] Data filtering

[1114] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, it removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[1115] Step 3:

[1116] Information Extraction

[1117] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[1118] Step 4:

[1119] Input to generative AI models

[1120] Server: The extracted data is input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each member. For example, based on the above utterance, the relationship value between employee A and employee B is calculated to be 80 (out of 100).

[1121] Step 5:

[1122] Simulation using optimization algorithms

[1123] Server: Simulates multiple combination patterns based on relationship values ​​and performance expectations. Tries and evaluates various scenarios to find the optimal combination. For example, calculates the performance expectations when employees A, B, and C are placed on the same team.

[1124] Step 6:

[1125] Visualizing and presenting results

[1126] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and the reasons for this allocation (details of relationship values ​​and performance expectations) are shown in a graph.

[1127] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[1128] Example 1

[1129] 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."

[1130] This invention relates to a system for efficiently optimizing personnel allocation and team formation in companies and organizations. Conventional personnel allocation decisions often rely on subjective judgment, which can lead to inefficient allocation and poor communication. This invention aims to solve these issues by collecting and analyzing daily communication data and presenting optimal team formation based on objective data.

[1131] 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.

[1132] In this invention, the server includes: [means for filtering collected communication data;] [means for extracting necessary business information from the filtered data; and] [means for inputting the extracted business data into a generative AI model and calculating relationship values ​​and performance expectations between members.] This makes it possible [to optimally organize teams and assign personnel based on objective data, thereby improving the efficiency and performance of the entire organization].

[1133] "Devices" refers to communication tools (telephones, video conferencing equipment, email clients, messaging service applications) used by employees in their daily work.

[1134] "Communication Data" refers to voice data, video conference logs, emails, and messaging service data generated via the Terminal.

[1135] "Server" refers to a computer system that collects and analyzes communication data.

[1136] "Filtering" refers to the process of removing noise and unnecessary information from received communication data and extracting necessary business information.

[1137] "Generative AI model" refers to a model that uses natural language processing techniques and machine learning algorithms to analyze data and quantify relationship values ​​and performance expectations.

[1138] "Relationship value" refers to a numerical indicator that indicates the strength of the cooperative relationship between members.

[1139] "Performance expectations" refers to a numerical indicator that predicts each member's work performance.

[1140] "Optimization algorithm" refers to an algorithm that simulates and determines the optimal combination of members based on relationship values ​​and expected performance values.

[1141] "Dashboard" refers to an interface that visualizes the optimal staffing results calculated by the optimization algorithm and presents them to the user.

[1142] This invention is a system that supports efficient personnel allocation and optimization of team formation in companies and organizations. This system collects and analyzes communication data from daily work, and automates a series of processes to propose optimal personnel allocation based on the data.

[1143] Data Collection Module

[1144] Devices: We collect communication data generated through the communication tools employees use in their daily work, such as telephone, video conferencing, email, and messaging services.

[1145] Example: Employee A holds a video conference, and the audio data and text log are saved on the device. After the conference ends, this data is automatically sent to the server.

[1146] Data Analysis Module

[1147] Server: Received communication data is temporarily stored and then filtered to remove noise and unnecessary information (e.g., casual conversation) and extract only the important information.

[1148] Example: The server removes casual conversation from the conversation log between employees A and B and extracts only work-related content.

[1149] Generative AI Models

[1150] Server: Inputs the filtered data into a generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[1151] Example: A generative AI model analyzes Employee A's question, "How is this project going?" and Employee B's response, "It's going well," to assess the working relationship and performance expectations between the two.

[1152] Optimization Algorithm

[1153] Server: Based on the calculated relationship value and expected performance value, it simulates combination patterns of multiple members and evaluates them to find the optimal combination.

[1154] Example: The server tries dozens to hundreds of combinations of employees A, B, and C, and finds the combination with the highest sum of relationship value and performance expectation.

[1155] Result presentation module

[1156] Server: Visualizes the optimal member combination and presents it to the user in dashboard format.

[1157] Users: Managers and HR personnel can access the dashboard through a web browser to see the most efficient team composition. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for this will be displayed in graphs of relationship scores and performance expectations.

[1158] By combining and implementing each of the above modules, the system utilizes communication data within a company and proposes efficient staffing and team composition based on objective data. Examples of prompts include, "How is the progress on this project?" and "It's progressing smoothly." This will enable managers and human resources personnel to make optimal decisions in their daily work.

[1159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1160] Step 1:

[1161] Devices: Employees communicate via telephone, video conferencing, email, and messaging services. Devices collect communication data (audio logs, text logs, etc.).

[1162] Specific operation: Employee A holds a video conference, and the audio data and text of the conversation are saved on the device.

[1163] Input: Video conferencing, phone, email, and chat tool usage data

[1164] Output: Saved communication log data

[1165] Step 2:

[1166] Terminal: Periodically sends collected communication log data to the server.

[1167] Specific operation: After the video conference ends, the terminal automatically uploads the audio data and text log to the server.

[1168] Input: Communication log data saved on the device

[1169] Output: Communication data sent to the server

[1170] Step 3:

[1171] Server: The received data is stored in temporary storage and the filtering process begins, removing noise and unnecessary information and extracting important business information.

[1172] Specific operation: The server uses a noise removal algorithm to detect and remove chatter.

[1173] Input: Communication data sent to the server

[1174] Output: filtered and clean data

[1175] Step 4:

[1176] Server: Inputs the filtered data into the generative AI model, which uses natural language processing techniques and machine learning algorithms to quantify the relationship value and performance expectations of each member.

[1177] Specific operation: The server supplies clean data to the generative AI model, and the NLP engine analyzes and quantifies the content of the speech.

[1178] Input: filtered clean data

[1179] Output: Quantified relationship values ​​and performance expectations

[1180] Step 5:

[1181] Server: Simulates optimal combinations of members based on relationship values ​​and performance expectations. Tries and evaluates multiple scenarios.

[1182] Specific operation: The server uses a simulation algorithm to evaluate various team composition patterns and calculate the optimal combination.

[1183] Inputs: Quantified relationship values ​​and performance expectations

[1184] Output: Optimal combination pattern

[1185] Step 6:

[1186] Server: Visualizes the optimal combination patterns and presents them to the user in a dashboard format.

[1187] Specific operation: The server uses a visualization tool to generate optimal staffing results in the form of graphs and charts.

[1188] Input: Optimal combination pattern

[1189] Output: Results visualized in a dashboard

[1190] Step 7:

[1191] Users: Managers and HR personnel access the dashboard to see the most efficient team structure.

[1192] Specific behavior: The user logs into the dashboard through a web browser and checks the suggested optimal team composition and the reasons for it.

[1193] Input: Results visualized in the dashboard

[1194] Output: Optimal team composition information confirmed

[1195] By sequentially executing each of the above steps, the system can effectively analyze communication data and suggest optimal staffing arrangements.

[1196] (Application example 1)

[1197] 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."

[1198] Logistics centers need to improve work efficiency and optimize staffing, but traditional methods make it difficult to accurately evaluate the performance of humans and robots and organize optimal teams. Furthermore, real-time data collection and analysis are not possible, which can lead to work delays and reduced efficiency.

[1199] 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.

[1200] In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into a generative AI model and calculating a relationship value and an expected performance value between members, means for simulating an optimal member combination pattern based on the calculated relationship value and expected performance value, means for visualizing the simulated combination pattern and presenting it to a user, and means for collecting item work log data and proposing an optimal work team formation. This improves work efficiency in a logistics center and enables accurate personnel allocation and work team formation.

[1201] "Communication data" refers to information sent and received via electronic devices or communication means.

[1202] "Filtering" is the process of removing noise and unnecessary information from collected data and extracting necessary information.

[1203] A "generative AI model" is an artificial intelligence model trained to handle a specific task, using natural language processing techniques and machine learning algorithms to analyze and predict data.

[1204] "Relationship value" is an indicator that quantifies the cooperative relationship and compatibility between members.

[1205] "Performance expectations" are numerical indicators that quantify the expected results and efficiency of members in specific tasks.

[1206] "Simulation" is the process of virtually testing results under different conditions to derive the optimal solution.

[1207] "Visualization" is a technique that makes data and information easier to understand by visually representing them.

[1208] "Item work log data" refers to detailed record data regarding the handling of items and the progress of work at a logistics center.

[1209] "Work team formation" is the process of arranging multiple workers and robots in optimal combinations to ensure efficient business operations.

[1210] A "dashboard" is an interface that aggregates data and displays it in a visually easy-to-understand manner.

[1211] The present invention relates to a system for improving work efficiency within a logistics center. This system collects communication data and work log data for items, and proposes optimal work team organization by analyzing, optimizing, and visualizing the data. Specific embodiments of the system are described below.

[1212] Data collection

[1213] The server collects communication data and item work log data in real time. Communication data includes telephone, video conference, email, and chat data. Item work log data includes, for example, the time and accuracy of picking, packing, and shipping work. This data is collected using devices such as smartphones, smart glasses, or robots.

[1214] Data analysis

[1215] The server stores the collected data in temporary storage and filters out noise and unnecessary information. It then extracts the necessary information and inputs it into a generative AI model. This model uses natural language processing techniques and machine learning algorithms to calculate relationship values ​​and performance expectations between members. The software used includes Python, Pandas, Scikit-learn, and Matplotlib.

[1216] simulation

[1217] The server simulates various combination patterns based on the calculated relationship values ​​and expected performance values. For example, if the combination of employees A and B and robot C is determined to be optimal, the reason for this is displayed in a graph of relationship values ​​and expected performance values.

[1218] Results presentation

[1219] Users can view the simulated optimal work team composition in a dashboard format, which visually displays the relationship values ​​and performance expectations of each member, making it easy for managers and human resources personnel to understand the optimal allocation.

[1220] Specific examples

[1221] For example, the following prompts can be fed into a generative AI model to determine optimal team composition:

[1222] "Please suggest the most efficient work team formation based on the work log data of the distribution center. The data includes work completion time, accuracy score, and team coordination score."

[1223] By inputting the above prompts, the generative AI model can suggest efficient team composition and visually represent the results in a dashboard.

[1224] Hardware and Software Used

[1225] A system for implementing the present invention uses the following hardware and software:

[1226] Hardware: Smartphones, smart glasses, robots, servers

[1227] Software: Python, Pandas, Scikit-learn, Matplotlib

[1228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1229] Step 1:

[1230] The terminals collect communication data and work log data related to work within the logistics center. Collected data includes telephone, video conference, email, chat data, and the time and accuracy of picking, packing, and shipping work. This data is sent to the server in real time. The input data is communication data and work log data in raw data format, and the output data is data stored on the server.

[1231] Step 2:

[1232] The server stores the received communication data and work log data in temporary storage and begins the filtering process. Noise and unnecessary information are removed, and only the necessary information is extracted. This process yields accurate data relevant to the business. The input is the data in temporary storage, and the output is the filtered data.

[1233] Step 3:

[1234] The server inputs the filtered data into a generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectation value for each worker. This process quantifies the degree of collaboration and work efficiency. The input is the filtered data, and the output is numerical data on the relationship value and performance expectation value.

[1235] Step 4:

[1236] The server simulates optimal work team combination patterns based on the calculated relationship values ​​and expected performance values. Through the simulation, various combination patterns are evaluated and the most efficient team placement is derived. The input is the numerical data of relationship values ​​and expected performance values, and the output is an optimal team composition plan.

[1237] Step 5:

[1238] The server visualizes the simulated optimal team composition and presents it to the user. The relationship values ​​and performance expectations of each member are visually displayed in a dashboard format for easy understanding. The input is the optimal team composition proposal, and the output is the visualized dashboard display information.

[1239] Step 6:

[1240] Users can refer to the dashboard to confirm the optimal work team formation. By reflecting this in the actual work allocation, efficient operations within the logistics center can be achieved. The input is the visualized dashboard information, and the output is the execution of the optimal work team formation.

[1241] 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.

[1242] The system program and its processing flow will be described in detail in natural language for the embodiment of the present invention.

[1243] 1. Data Collection Module

[1244] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[1245] Example: After employee A holds a video conference, the audio data and text log of the conversation are transferred to a server.

[1246] 2. Data Analysis Module

[1247] Server: Stores the received log data in temporary storage and starts the filtering process, removing unnecessary information (noise and meaningless conversations) and extracting necessary information.

[1248] Example: From the chat log between employee A and employee B, remove casual conversations such as "hello" and extract only the work-related conversation content.

[1249] 3. Emotion Engine

[1250] Server: The extracted data is input into the emotion engine to analyze the user's emotions. The emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text.

[1251] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[1252] 4. Generative AI Models

[1253] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[1254] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[1255] 5. Optimization Algorithms

[1256] Server: Based on the calculated relationship value and expected performance, it simulates combination patterns of multiple members. Various scenarios are tried and evaluated to find the optimal combination. By taking emotional information into account, more accurate predictions are possible.

[1257] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[1258] 6. Results presentation module

[1259] Server: The simulated optimal staffing is visualized in charts and graphs and presented to users in the form of a dashboard. Managers and HR personnel can refer to this dashboard to confirm the optimal staffing.

[1260] Users: Human resources and managers can access the dashboard to check optimal staffing and reorganize the organization based on the proposed staffing. For example, it might say, "The optimal team composition is employees A, B, and C," and the reasons for the placement are shown in graphs of relationship values, performance expectations, and emotional states.

[1261] Following this flow, the system analyzes daily communication data and supports optimal organizational design and personnel allocation. Using the emotion engine improves the accuracy of relationship values ​​and performance expectations, enabling more optimal team formation. When implementing the invention, it is important to correctly combine these modules and methods.

[1262] The processing flow will be explained below.

[1263] Step 1:

[1264] Data collection

[1265] Terminal: Every time an employee uses a telephone, video conference, email, or chat tool, the log data is transferred to the system. For example, after employee A holds a video conference, the audio data of the conversation is automatically sent to the server.

[1266] Server: Stores the received log data in temporary storage and prepares it for the next analysis step.

[1267] Step 2:

[1268] Data filtering

[1269] Server: Retrieves log data from temporary storage and deletes unnecessary information (noise and irrelevant messages). For example, removes casual conversations such as "Hello" from the chat log between employee A and employee B.

[1270] Server: Prepares the filtered data for analysis.

[1271] Step 3:

[1272] Information Extraction

[1273] Server: Extracts necessary information (speech content, speaker, frequency, time, etc.) from the filtered data. For example, extracts the content when employee A says, "How is this project progressing?" and employee B responds, "It's going smoothly."

[1274] Step 4:

[1275] Emotion analysis using an emotion engine

[1276] Server: The extracted data is input into the emotion engine to analyze the user's emotional state. The emotion engine identifies the user's emotions (joy, anger, sadness, etc.) from the voice and text.

[1277] Example: When employee A says, "This project isn't going well," the emotion engine analyzes the emotion of dissatisfaction and returns the results to the server.

[1278] Step 5:

[1279] Input to generative AI models

[1280] Server: Inputs the filtered data and the output of the emotion engine into the generative AI model, which uses natural language processing techniques and machine learning algorithms to calculate the relationship value and performance expectation for each member.

[1281] Example: Employee A's speech content and emotional state (dissatisfaction) are input into the model, and the relationship value between Employee A and Employee B is calculated as 70 (out of 100).

[1282] Step 6:

[1283] Simulation using optimization algorithms

[1284] Server: Simulates multiple combination patterns based on relationship values ​​and expected performance. Tries and evaluates various scenarios to find the optimal combination. Taking emotional information into account enables more accurate predictions.

[1285] Example: If employee A frequently feels dissatisfied, his / her relationship value with other members will decline. Considering this, calculate the performance expectation value for the combination of employees A, B, and C.

[1286] Step 7:

[1287] Visualizing and presenting results

[1288] Server: The simulated optimal personnel allocation is visualized in diagrams and graphs and presented to the user in a dashboard format. For example, it might say, "The team composition of employees A, B, and C is optimal," and provide the reasons for this allocation (details of relationship values, performance expectations, and emotional states).

[1289] Users: HR and managers access the dashboard to see the best staffing recommendations and make organizational changes accordingly.

[1290] Example 2

[1291] 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."

[1292] In traditional organizational management, it was difficult to create optimal team composition that took into account the relationships between team members and the emotional state of each individual. This could lead to poor performance and hinder efficient business operations.

[1293] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication data, means for filtering the collected communication data, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion engine and analyzing the user's emotions, means for inputting the output of the emotion engine and the filtered data into a generative AI model and calculating relationship values ​​and expected performance values ​​between members, means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and means for visualizing the simulated combination patterns and presenting them to the user. This enables optimal team formation that takes into account the emotional states and relationships between members, thereby improving work efficiency and performance.

[1294] "Communication data" refers to information relating to communications such as telephone calls, video conferences, emails, and chat data conducted using a terminal.

[1295] "Filtering" is the process of removing unnecessary information (noise and meaningless conversations) from communication data and extracting necessary information.

[1296] An "emotion engine" is an analysis engine that has the ability to identify a user's emotional state (joy, anger, sadness, etc.) from voice and text.

[1297] A "generative AI model" is a model that uses natural language processing technology and machine learning algorithms to calculate relationship values ​​and performance expectations between members from input data.

[1298] "Relationship value" is an index that represents the relationship between members, and is a value evaluated based on the quality and frequency of communication, emotional state, etc.

[1299] "Performance expectations" are indicators of the performance expected when members work together.

[1300] "Simulation" is a process of trying out optimal member combination patterns based on the calculated relationship values ​​and expected performance values, and evaluating the results.

[1301] "Visualization" refers to visually displaying the results of simulated combination patterns in the form of diagrams, graphs, etc.

[1302] The present invention relates to a system for collecting and analyzing communication data and forming an optimal team. Specific embodiments of the system will be described in detail below.

[1303] Data collection

[1304] Devices: Communication data is generated when employees use telephones, video conferencing, email, and chat tools. This data is automatically collected and sent to the server. For example, after employee A finishes a video conference, the audio data and text log of the conversation are transferred to the server.

[1305] Data analysis

[1306] Server: The received communication data is stored in temporary storage and the filtering process begins. Unnecessary information (such as small talk and noise such as "hello") is removed, and the necessary information is extracted. For example, only the work-related conversation content is extracted from the chat log between employee A and employee B.

[1307] Emotion analysis

[1308] Server: The extracted data is input into the emotion engine, which analyzes the user's emotions. This emotion engine has the ability to identify the user's emotional state (joy, anger, sadness, etc.) from voice and text. For example, when employee A says, "This project isn't going well," the emotion engine analyzes the user's emotion of dissatisfaction and returns the results to the server.

[1309] Using generative AI models

[1310] Server: The filtered data and the output of the emotion engine are input into the generative AI model. The generative AI model uses natural language processing technology and machine learning algorithms to calculate the relationship value and performance expectations between members. For example, if the content of Employee A's speech and emotional state are input into the model, the relationship value between Employee A and Employee B is calculated to be 70 (out of 100).

[1311] Simulation and Optimization

[1312] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members. In this process, various scenarios are tried and evaluated. By taking emotional information into account, more accurate predictions are possible. For example, if employee A frequently feels dissatisfied, it takes into account that his relationship values ​​with other members will decline, and calculates the expected performance value for the combination of employees A, B, and C.

[1313] Visualizing the results

[1314] Server: The server visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user. Managers and human resources personnel can refer to this dashboard to confirm the optimal team composition. For example, it may display "The optimal team composition is made up of employees A, B, and C," and the reasons for this composition may be shown in graphs of relationship values, performance expectations, and emotional states.

[1315] Prompt Sentence Examples

[1316] Below is an example of a prompt sentence to be input to the generative AI model.

[1317] "Employee A expresses dissatisfaction during a project meeting. Please analyze the relationship between Employee A and Employee B and suggest the optimal team formation."

[1318] Through these processes, the system effectively analyzes communication data and supports optimal team formation and personnel allocation. In this way, by using the emotion engine, the present invention improves the accuracy of relationship values ​​and performance expectations, enabling more appropriate team formation.

[1319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1320] Step 1:

[1321] Data collection

[1322] Devices: Employees communicate using telephone, video conferencing, email, and chat tools. This communication log data is automatically collected and sent to the server.

[1323] Input: Communication data sent from the device (voice data, text logs, etc.).

[1324] Output: Raw communication data stored on the server.

[1325] Specific operation: After employee A finishes the video conference, the device converts the voice data into text and sends the log to the server.

[1326] Step 2:

[1327] Data analysis

[1328] Server: Received communication data is stored in temporary storage and filtering process begins. Unnecessary information (noise and chatter) is removed and necessary information is extracted.

[1329] Input: Raw communication data stored in temporary storage.

[1330] Output: The filtered data you want.

[1331] Specific operation: The server removes greetings such as "hello" from the voice data and extracts only business-related content.

[1332] Step 3:

[1333] Emotion analysis

[1334] Server: Inputs the extracted data into the emotion engine to analyze the user's emotions. The emotion engine identifies the emotional state from the voice and text.

[1335] Input: Filtered communication data.

[1336] Output: Sentiment analysis results (type and intensity of emotion).

[1337] Specific operation: The server analyzes employee A's statement, "This project isn't going well," and identifies it as an expression of dissatisfaction.

[1338] Step 4:

[1339] Using generative AI models

[1340] Server: The filtered data and the output of the emotion engine are input into the generative AI model, which calculates the relationship value and performance expectation for each member.

[1341] Input: Sentiment analysis results and filtered required data.

[1342] Output: Relationship values ​​and performance expectations.

[1343] Specific operation: Input the content of Employee A's speech and his emotional state, and calculate the relationship value between Employee A and Employee B as 70 (out of 100 points).

[1344] Step 5:

[1345] Optimization Simulation

[1346] Server: Based on the calculated relationship values ​​and expected performance values, it simulates combination patterns of multiple members, tries out various scenarios, and finds the optimal combination.

[1347] Inputs: Relationship value and performance expectation.

[1348] Output: Optimal member combination pattern.

[1349] Specific operation: Considering the impact that frequently dissatisfied employee A has on the team, simulate the optimal team composition based on the relationship values ​​with other members.

[1350] Step 6:

[1351] Visualizing the results

[1352] Server: Visualizes the simulated optimal member combination patterns in diagrams and graphs and presents them to the user.

[1353] Input: Optimal member combination pattern.

[1354] Output: A visualized dashboard.

[1355] Specific operation: The system displays a graph and explanatory text to the user showing the optimal team composition of employees A, B, and C. This allows the human resources department and managers to confirm the optimal composition and use it to formulate actual organizational compositions.

[1356] (Application example 2)

[1357] 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."

[1358] In modern factories, maximizing the operational efficiency of robots and machines is key to improving productivity. However, interactions between robots and communication with operators are complicated, making it difficult to find efficient work arrangements and collaboration structures. Furthermore, manually analyzing large amounts of data takes time and effort, making it impossible to determine optimal work patterns in real time. A system that can solve these issues is needed.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1360] In this invention, the server includes means for collecting machine operation data and communication logs, means for filtering the collected operation data and communication logs, means for extracting necessary information from the filtered data, means for inputting the extracted data into an emotion analysis module and evaluating the status of the machines and personnel, means for inputting the evaluated data into a generative AI model and calculating cooperative relationships and performance expectations between the machines, means for simulating optimal machine combination patterns based on the calculated cooperative relationships and performance expectations, and means for visualizing the simulated combination patterns and presenting them to a user. This makes it possible to efficiently collect and analyze robot and machine operation data and communication logs and determine optimal work placement and cooperation systems in real time.

[1361] "Machine operation data" means information relating to the operating status and operation of robots and machines used in factories.

[1362] "Communication log" refers to a record of communication such as messages and instructions exchanged between robots and operators.

[1363] "Filtering" refers to the process of removing noise and unnecessary information from collected data and extracting necessary information.

[1364] "Emotion analysis module" refers to software that has the function of evaluating the operating status and stress level of robots and operators from input data.

[1365] "Generative AI model" means a model that uses natural language processing techniques and machine learning algorithms to calculate appropriate work patterns and collaboration relationships.

[1366] "Cooperative relationship" refers to the mutual relationship when multiple robots or machines work together to perform a task.

[1367] "Performance expectations" refers to expectations regarding the efficiency and productivity of a robot or machine when performing a specific task.

[1368] "Simulation" refers to the process of trying out multiple scenarios and simulating the optimal work arrangements and cooperation systems.

[1369] "Visualization" means displaying analysis or simulation results in a visual format such as a graph or diagram.

[1370] "User" refers to the manager or operator who uses the system to determine optimal work arrangements and cooperation structures and make decisions.

[1371] A specific system configuration and program processing will be described for an embodiment of the present invention.

[1372] System Program

[1373] The server performs the following steps:

[1374] 1. Data Collection Module

[1375] The server collects operational data and communication logs from the robots and machines used in the factory. The specific hardware used includes sensor devices (e.g., LIDAR and cameras), and the communication interface uses Wi-Fi and Bluetooth. The operational data includes information about operating status and behavior, while the communication log includes the content of communications between robots and with operators.

[1376] 2. Data Analysis Module

[1377] The server stores the collected operation data and communication logs in a database system (MySQL or PostgreSQL) and performs a filtering process to remove noise and unnecessary information and extract the necessary information.

[1378] 3. Sentiment Analysis Module

[1379] The filtered data is then fed into a sentiment analysis module, where the server analyzes the data using natural language processing libraries (SpaCy and BERT) to assess the operating status and stress levels of the robots and operators.

[1380] 4. Generative AI Models

[1381] The results of the sentiment analysis and filtered data are input into a generative AI model. The server uses machine learning frameworks (TensorFlow and PyTorch) to calculate appropriate work patterns and collaboration relationships. The generative AI model includes natural language processing technology and machine learning algorithms.

[1382] 5. Optimization Algorithms

[1383] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values ​​to find the optimal machine combination pattern. The calculated optimal placement is visualized in dashboard format using a web front end (React or Vue.js).

[1384] 6. User Presentation Module

[1385] The simulated results are displayed on a dashboard, allowing administrators to check them in real time. Data is passed and processed using a backend API (Flask or Node.js).

[1386] Specific examples

[1387] Next, we will show a specific example of operation. For example, after Robot A has been operating for a long period of time, its operation data is collected by a sensor device and sent to a server. The server filters the data to remove noise and unnecessary information. An emotion analysis module evaluates fatigue and stress levels, and the results are input into a generative AI model. The generative AI model calculates the cooperative relationship between Robot A and other robots B and C, and proposes optimal work patterns. The calculated results are displayed on a dashboard so that managers can check them.

[1388] Prompt Sentence Examples

[1389] A computergram has the following format:

[1390] Input collected sensor and communication data

[1391] sensor_data = {

[1392] "robot_a": {

[1393] "temperature": 65,

[1394] "movement": "assembly",

[1395] "operating_time": 320,

[1396] ...

[1397] },

[1398] ...

[1399] }

[1400] Input the output of the emotion engine

[1401] emotional_state = {

[1402] "robot_a": {

[1403] "fatigue_level": 0.8,

[1404] "stress_level": 0.4,

[1405] },

[1406] ...

[1407] }

[1408] Input to generative AI model

[1409] optimal_configuration = generate_optimal_configuration(sensor_data, emotional_state)

[1410] print(optimal_configuration)

[1411] This makes it possible to efficiently collect and analyze operation data and communication logs of robots and machines, and determine optimal work placement and cooperation systems in real time.

[1412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1413] Step 1:

[1414] The server collects operational data and communication logs from the robots and machines used in the factory through sensor devices (LIDAR and cameras) and communication interfaces (Wi-Fi and Bluetooth). This input data includes the robot's operating status, operational information, and communication between robots and with operators. This data is stored in a database (MySQL and PostgreSQL).

[1415] Step 2:

[1416] The server filters the operational data and communication logs stored in temporary storage. Specifically, it removes noise and unnecessary information and extracts only important information related to the business. For example, it removes noise recorded during movement and extracts only data related to part assembly. This process generates filtered data.

[1417] Step 3:

[1418] The server inputs the filtered data into an emotion analysis module to evaluate the operating status and stress levels of the robots and operators. For example, it uses a natural language processing library (SpaCy or BERT) to analyze the fatigue level of Robot A after a long period of operation. Emotion data is generated as the analysis result.

[1419] Step 4:

[1420] The server inputs the output of the emotion analysis module and filtered data into the generative AI model. It uses a machine learning framework (TensorFlow or PyTorch) to calculate appropriate work patterns and cooperative relationships between robots. For example, if robot A and robot B have a strong cooperative relationship, the expected performance of the cooperative work will be calculated to be high. The generated performance data is then output.

[1421] Step 5:

[1422] The server simulates multiple scenarios based on the calculated cooperative relationships and expected performance values. It then uses an optimization algorithm to find the optimal machine combination pattern. For example, it considers the fatigue level of robot A and evaluates the optimal combination with robots B and C. This generates the optimal deployment pattern.

[1423] Step 6:

[1424] The server visualizes the simulated results in the form of a dashboard and presents it to the user. This uses a web front end (React or Vue.js) and provides data to the user through a backend API (Flask or Node.js). For example, an administrator can view the dashboard and confirm that the combination of robots A and B is optimal. This displays the presented optimization data.

[1425] 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.

[1426] 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.

[1427] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1428] 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.

[1429] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1430] 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.

[1431] 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).

[1432] 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.

[1433] 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."

[1434] 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.

[1435] 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).

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] The following is further disclosed regarding the above embodiment.

[1447] (Claim 1)

[1448] [Means for collecting communications data;

[1449] [Means for filtering collected communications data; and

[1450] [Means for extracting necessary information from the filtered data; and

[1451] [Means for inputting the extracted data into a generative AI model to calculate the relationship value and performance expectation value between members;

[1452] [Means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values; and

[1453] [Means for visualizing the simulated combination patterns and presenting them to the user;

[1454] A system including:

[1455] (Claim 2)

[1456] [The system of claim 1, wherein the communication data includes telephone, video conference, email, and chat data.

[1457] (Claim 3)

[1458] The system of claim 1, wherein the generative AI model includes natural language processing techniques and machine learning algorithms.

[1459] "Example 1"

[1460] (Claim 1)

[1461] [Means for collecting communication data from the terminal;

[1462] [Means for filtering collected communication data on the server;

[1463] [Means for extracting necessary business information from the filtered data;

[1464] [Means for inputting the extracted business data into a generative AI model and calculating the relationship value and performance expectation value between members;

[1465] [Means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values; and

[1466] [Means for visualizing the simulated combination patterns and presenting them to the user in a dashboard format;

[1467] A system including:

[1468] (Claim 2)

[1469] [The system of claim 1, wherein the communication data includes voice data, video conference logs, email, and messaging service data.

[1470] (Claim 3)

[1471] The system of claim 1, wherein the generative AI model includes natural language processing techniques and machine learning algorithms.

[1472] "Application Example 1"

[1473] (Claim 1)

[1474] [Means for collecting communications data;

[1475] [Means for filtering collected communications data; and

[1476] [Means for extracting necessary information from the filtered data; and

[1477] [Means for inputting the extracted data into a generative AI model to calculate the relationship value and performance expectation value between members;

[1478] [Means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values; and

[1479] [Means for visualizing the simulated combination patterns and presenting them to the user;

[1480] [Means for collecting work log data of items and proposing optimal work team formation;

[1481] A system including:

[1482] (Claim 2)

[1483] [The system of claim 1, wherein the communication data includes telephone, video conference, email, and chat data.

[1484] (Claim 3)

[1485] The system of claim 1, wherein the generative AI model includes natural language processing techniques and machine learning algorithms.

[1486] "Example 2: Combining Emotion Engines"

[1487] (Claim 1)

[1488] [Means for collecting communications data;

[1489] [Means for filtering collected communications data; and

[1490] [Means for extracting necessary information from the filtered data; and

[1491] [Means for inputting the extracted data into an emotion engine and analyzing the user's emotions;

[1492] [Means for inputting the output of the emotion engine and filtered data into a generative AI model to calculate the relationship value and performance expectation value between members;

[1493] [Means for simulating optimal member combination patterns based on the calculated relationship values ​​and expected performance values; and

[1494] [Means for visualizing the simulated combination patterns and presenting them to the user;

[1495] A system including:

[1496] (Claim 2)

[1497] The system of claim 1, wherein the communication data includes telephone, video conference, email, and chat data.

[1498] (Claim 3)

[1499] The system of claim 1, wherein the generative AI model includes natural language processing techniques and machine learning algorithms.

[1500] "Application example 2 when combining emotion engines"

[1501] (Claim 1)

[1502] [Means for collecting machine operation data and communication logs;

[1503] [Means for filtering collected operational data and communication logs; and

[1504] [Means for extracting necessary information from the filtered data; and

[1505] [Means of inputting the extracted data into an emotion analysis module to evaluate the state of the machine or personnel;

[1506] [Means for inputting the evaluated data into a generative AI model to calculate machine-to-machine cooperation and performance expectations;

[1507] [Means for simulating optimal machine combination patterns based on the calculated cooperative relationships and performance expectations; and

[1508] [Means for visualizing the simulated combination patterns and presenting them to the user;

[1509] A system including:

[1510] (Claim 2)

[1511] [The system of claim 1, wherein the operational data includes input from sensor devices, and the communication logs include communications between machines and communications with operators.

[1512] (Claim 3)

[1513] The system of claim 1, wherein the generative AI model includes natural language processing techniques and machine learning algorithms. [Explanation of symbols]

[1514] 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. means for collecting communications data; means for filtering the collected communications data; A means for extracting necessary information from the filtered data; A means for inputting the extracted data into a generative AI model to calculate the relationship value and performance expectation value between members; A means for simulating an optimal member combination pattern based on the calculated relationship value and expected performance value; a means for visualizing the simulated combination patterns and presenting them to a user; A system including:

2. The system of claim 1 , wherein the communication data includes telephone, video conference, email, and chat data.

3. 10. The system of claim 1, wherein the generative AI model includes natural language processing techniques and machine learning algorithms.

Images