system

Abstract

We provide the system. [Solution] A device means for collecting emotional data, audio data, and video data, Processing means for preprocessing collected data, removing noise, and converting it into an analyzable format, An analysis device means for analyzing emotional states through text analysis, facial expression analysis, and voice analysis, and for calculating an emotional score, A display device for integrating emotional scores and data related to workload and visually displaying them for administrators, A support device for formulating an efficient work allocation strategy using visually displayed data, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern workplaces, the workload and emotional state of individual members have a great impact on the overall performance of the team. However, these factors are not easily visible, making it difficult for managers to respond quickly and appropriately. Therefore, there is a need for means to visualize the emotional and workload situations among members and facilitate efficient task allocation, in order to reduce individual stress and improve team cohesion.

Means for Solving the Problems

[0005] This invention provides a device for collecting emotional data, audio data, and video data, and a processing device for preprocessing this data into an analyzable format. It also provides an analysis device for analyzing emotional states and calculating emotional scores, and a display device for visually displaying this emotional score and data related to workload for administrators, thereby solving these problems. Furthermore, it combines this with a support device for formulating efficient and fair work distribution strategies based on the visually displayed data, aiming to improve the overall team performance.

[0006] "Emotional data" refers to data that indicates an individual's emotional state, extracted from text messages, facial expressions, voice tone, and other sources.

[0007] "Audio data" refers to recorded information of human speech collected through a microphone, and is used for speech tone analysis.

[0008] "Video data" refers to image information acquired through a camera, and is primarily used for facial expression analysis.

[0009] "Devices" is a general term for electronic devices and tools used to collect emotional data, audio data, and video data.

[0010] A "processing device" is a device that has the function of preprocessing collected data, removing noise, and converting it into an analyzable format.

[0011] An "analysis device" is a computing device that has the function of analyzing emotional states and calculating emotional scores.

[0012] An "emotion score" is a numerical index that indicates an emotional state, calculated by an analysis device.

[0013] A "display device" is a device that integrates emotional scores and workload data and displays them visually.

[0014] The "support device" is a device for supporting an efficient business distribution strategy based on visually displayed data.

[0015] The "integration device" is a device for combining and analyzing different types of data and visualizing the results.

[0016] The "machine learning algorithm" is a computational method for learning patterns from data and performing prediction and classification.

Brief Description of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the language used in the following description will be explained.

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] As an embodiment of the present invention, a system for team dynamics and workload evaluation utilizing multimodal sentiment analysis is described. This system supports efficient work distribution by visualizing the emotional state and workload of each member of a team, utilizing specific devices, processing devices, and analysis devices.

[0039] Data collection methods:

[0040] Devices: Each member's device continuously collects sentiment data from messaging applications and collaboration tools. This includes keyword extraction and pattern analysis from text messages.

[0041] Device: During video conferences, it collects video data using the camera to obtain information for facial expression analysis. It also collects audio data via the microphone to evaluate voice tone.

[0042] Forms of data analysis:

[0043] Server: Integrates collected data and analyzes emotional states using machine learning algorithms. The server calculates an emotional score for each member, expressing the degree of different emotions numerically.

[0044] Server: In addition to the emotion score, the workload is evaluated from user-provided survey data, and both sets of data are combined to understand the overall state of the team.

[0045] Visualization of results and forms of strategic planning:

[0046] Server: Generates an administrator visualization dashboard based on integrated data. This dashboard includes interactive graphics to identify sentiment scores, workload imbalances, and stress levels.

[0047] User (Administrator): Review analysis results through the dashboard and formulate strategies to optimize workload distribution. For example, if a particular member is overburdened, the administrator will adjust their workload and redistribute tasks to other members.

[0048] Specific example:

[0049] For example, suppose emotion scores reveal that a specific member of a team is regularly experiencing stress. In this case, the administrator can use the dashboard to examine the detailed analysis of the member's voice and video data to identify the source of the stress. They can then improve the work environment by reallocating workloads or suggesting leave as needed.

[0050] As described above, the system of the present invention is highly effective as a tool for accurately collecting and analyzing emotional and workload data to improve the overall performance of the team. This embodiment allows managers to quickly address problems within the team and manage the efficiency and stress levels of individual members in a balanced manner.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] Terminals: Each member's terminal collects text data from messaging applications. This includes a process of extracting keywords and phrases to estimate sentiment.

[0054] Step 2:

[0055] Device: Uses a webcam and microphone to collect video and audio data. Video data is used as material for facial expression analysis, and audio data is used for voice tone analysis.

[0056] Step 3:

[0057] Server: Preprocesses collected text, audio, and video data. Prepares the data for analysis through noise reduction and standardization of data formats.

[0058] Step 4:

[0059] Server: Uses machine learning algorithms to analyze emotional states from each data point. It calculates individual emotional scores for text, audio, and video data, and then integrates them.

[0060] Step 5:

[0061] Server: Analyzes emotional scores in conjunction with user-provided workload survey data. This allows for the evaluation of the correlation between workload balance among team members and their emotional state.

[0062] Step 6:

[0063] Server: Uses the analysis results to generate a dashboard for administrators. This dashboard displays graphs that visualize things like changes in emotional states over time and the distribution of workload.

[0064] Step 7:

[0065] User (Administrator): Refer to the dashboard to check for stress levels and workload imbalances among team members. Based on the problems identified, devise work reallocation and improvement measures.

[0066] Step 8:

[0067] Terminal: Notifies members of new work assignments and countermeasures decided by the administrator, and requests feedback through the system. Collect feedback and use it for continuous improvement.

[0068] (Example 1)

[0069] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0070] In today's workplace, accurately understanding the emotions and workload of team members and achieving efficient work distribution is essential. However, there is a lack of effective systems that can centrally analyze diverse information on emotions and workload, and easily formulate business strategies based on this information.

[0071] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0072] In this invention, the server includes device means for collecting emotional data, visual information, and acoustic information; processing means for standardizing the collected data, removing noise, and converting it into an analyzable format; and display means for integrating information related to emotional scales and workload and displaying it visually for the controller. This enables a detailed understanding of the emotional state and workload of team members, allowing managers to formulate appropriate work allocation strategies.

[0073] "Emotional data" refers to information that indicates an individual's emotional state, and is collected in various forms such as text, facial expressions, and voice.

[0074] "Visual information" refers to information acquired through images and videos, and is primarily data used for analyzing facial expressions.

[0075] "Acoustic information" refers to information acquired through sound, and is primarily data used to evaluate the tone and pitch of a voice.

[0076] The term "device" refers to a hardware or software component designed to perform a specific function.

[0077] A "processing machine" is a computer system or program used to preprocess collected data and convert it into an analyzable format.

[0078] An "analysis mechanism" is a system that analyzes collected data and employs methods to derive emotional evaluations and other information.

[0079] A "display device" is a device or application used to visually represent analysis results or integrated information.

[0080] A "support tool" is a means of providing information and support necessary when formulating strategies such as work allocation.

[0081] "Machine learning techniques" are algorithms and technologies used to automatically extract patterns and regularities from collected data.

[0082] An "integration device" is a means of combining different types of data, managing them centrally, and visually displaying their relationships.

[0083] This invention is a system that utilizes multimodal sentiment analysis to visualize the emotional state and workload of team members in the workplace, and is implemented to support the efficient distribution of tasks.

[0084] Data collection

[0085] Devices: Each member's device is equipped with messaging applications and collaboration tools, through which emotional data is acquired in real time. Specifically, keywords related to emotions are automatically extracted from text messages using a natural language processing node. In addition, facial expression data is captured using the camera during video conferences, and data that can be analyzed by facial recognition software is collected. Furthermore, voice data is acquired through the microphone, and the tone of voice is evaluated using a voice analysis algorithm.

[0086] Data Analysis

[0087] Server: The collected data is integrated on the server and converted into a standardized data format. Data processing languages ​​such as Python and R are used here. Then, a generative AI model calculates sentiment scores using machine learning algorithms. This model performs more advanced inference using SSMP (Sentiment State Modeling Protocol). For example, it analyzes emotional patterns within a team using prompts such as, "Is this member feeling stressed about recent project progress?"

[0088] Visualization and Strategy Planning

[0089] Server: Based on the analysis results, the server generates an interactive dashboard for administrators. This dashboard, developed using JavaScript® and the D3.js library, visually displays each member's sentiment score and workload. This allows administrators to easily understand the status of team members and redistribute tasks as needed, thereby improving overall team performance.

[0090] Examples and use of prompt statements

[0091] For example, if it's necessary to verify the proposition "Is Member A frequently experiencing stress?", the administrator would check the dashboard. The dashboard displays data such as facial expressions and changes in voice tone from recent video conferences as graphs, allowing for appropriate measures to be taken based on this information.

[0092] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0093] Step 1:

[0094] Terminals: Each member's terminal receives text messages from emails and chats as input and uses natural language processing technology to extract keywords related to emotions. A built-in keyword recognition algorithm is used for keyword extraction, and emotion data is generated as output. Specifically, a text analysis module operates during this extraction process to identify positive and negative emotional tones.

[0095] Step 2:

[0096] Terminal: During the meeting, the terminal's camera is activated to capture video footage as input. Face recognition software analyzes this footage and generates facial expression data as output. Specifically, the recorded video data is analyzed in real time, and a process is included in which specific facial expressions such as smiles and surprise are quantified.

[0097] Step 3:

[0098] Terminal: During meetings, the microphone is used to collect audio data as input. A voice analysis algorithm evaluates the tone and pitch of the voice and extracts emotional features from the audio data as output. Specifically, changes in tone pitch and speed are analyzed, and stress and satisfaction levels are estimated based on this.

[0099] Step 4:

[0100] Server: The collected text, facial expression, and audio data are integrated into a standardized format, and the processor removes noise. Here, data cleaning techniques are used to ensure the consistency of each input data, and the integrated dataset is output. Specifically, data merging techniques are used to ensure data consistency.

[0101] Step 5:

[0102] Server: Using integrated data as input, a machine learning algorithm calculates an emotion score. A generative AI model is used to analyze patterns in the collected data and output the emotional intensity of team members. For example, if the emotion score exceeds a certain threshold, the system generates a prompt message indicating that the user is experiencing stress.

[0103] Step 6:

[0104] Server: The visualization module takes integrated sentiment score and workload data as input and generates a dashboard for administrators. It provides interactive graphs and charts as output, supplying administrators with visual information to formulate business strategies. Specifically, data is visualized using JavaScript and D3.js, and an easy-to-use UI is provided.

[0105] Step 7:

[0106] User (Administrator): The administrator reviews the dashboard as input data and reallocates tasks as needed. Specifically, they adjust tasks for members with high workloads and reallocate them to other members. Through interactive feedback during this process, it is possible to optimize team performance.

[0107] (Application Example 1)

[0108] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0109] In modern manufacturing environments, maximizing the efficiency of workers and automated machinery while avoiding excessive burden and stress is a crucial challenge. However, visualizing and immediately addressing these conditions is difficult. Therefore, there is a need for a system that can grasp the emotional state and workload of individual workers and machines in real time, thereby improving overall production efficiency.

[0110] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0111] In this invention, the server includes information gathering device means for collecting emotional data, audio data, and video data; data processing device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and data analysis device means for analyzing emotional states through text analysis, facial expression analysis, and audio analysis, and calculating emotional scores. This makes it possible to visualize emotional states and workloads in the production site in real time and optimize the efficiency of each worker and machine.

[0112] An "information gathering device" is a device that can collect emotional data, audio data, and video data.

[0113] A "data processing device" is a device used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0114] A "data analysis device" is a device that analyzes emotional states through text analysis, facial expression analysis, and voice analysis, and calculates an emotional score.

[0115] A "visualization device" is a device that integrates information related to emotional scores and workload, and displays the analysis results visually.

[0116] A "support system" is a system that uses visually displayed information to formulate efficient work allocation strategies.

[0117] A "management device" is a device that monitors production activities in real time and supports optimization through a visual assistance device equipped with the system.

[0118] An "analysis system" is a system that applies machine learning algorithms based on collected data to estimate emotional patterns among workers.

[0119] An "integrated system" is a system that evaluates the workload of each worker and displays the information relating that workload to emotional information.

[0120] To implement this invention, the server operates as a configuration including an information gathering device, a data processing device, a data analysis device, a visualization device, and a support system. The information gathering device acquires audio data, video data, and environmental data through multiple sensors and cameras installed on the factory production floor. This makes it possible to continuously acquire real-time information from the site.

[0121] The server preprocesses the collected data using a data processing device, removing noise and converting the format. Specifically, it uses Python and TENSORFLOW® to perform data cleaning and conversion. This process prepares the data for analysis, allowing it to proceed to the next analysis step.

[0122] The server then uses data analysis equipment to perform text analysis, facial expression analysis, and voice analysis. These analysis techniques are used to output emotional states as emotional scores, which are numerical representations of emotional states. Generative AI models using machine learning (e.g., neural networks using Keras) are applied to the analysis. The results are quantified, and the emotional states of workers and machines are evaluated in real time.

[0123] The visualization device integrates emotion scores and workload-related data, visually displaying the information on an administrator dashboard. Users can then use this to develop strategies to optimize workload distribution in the field. This dashboard is projected onto smart glasses, enabling immediate action.

[0124] For example, if a worker shows an unusually high stress score, managers can immediately check the number through a dashboard and take countermeasures. For instance, if it is determined that the worker is overloaded, they can change the work shift or assign additional personnel.

[0125] An example of a prompt might be: "Design a method to analyze the team's emotional state in real time and optimize their workload, with a particular focus on managing the efficiency of robots and workers in the field."

[0126] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0127] Step 1:

[0128] The server acquires audio, video, and environmental data from the production site via multiple sensors and cameras from the information gathering device. This input data is captured in real time from the site and may contain noise or missing data. The server collects this data and prepares it for the next step.

[0129] Step 2:

[0130] The server preprocesses the collected data using a data processing device. This process removes noise and imputes missing data using Python scripts, etc. Audio and video are also converted to appropriate formats and prepared for analysis. As output, a clean and consistent dataset is sent to the next analysis step.

[0131] Step 3:

[0132] The server analyzes data that has been preprocessed by the data analysis device. Here, it performs text analysis, facial expression analysis, and speech analysis using a generative AI model. Specifically, it uses a neural network with Keras to quantify emotion scores. As a result of the analysis, numerical data representing the emotional state of each worker and device is output. This numerical data is used for visualization as an emotion score.

[0133] Step 4:

[0134] The server integrates and displays sentiment scores and workload data on the administrator's dashboard via a visualization device. The processed numerical data is visualized as interactive graphics, which users can view on the dashboard. This output allows administrators to intuitively understand the workload on the ground and obtain guidance for necessary countermeasures.

[0135] Step 5:

[0136] Users develop efficient work allocation strategies based on information displayed on the dashboard. These decisions take into account worker stress levels and equipment utilization efficiency. Users aim to optimize the work environment by adjusting work schedules and reallocating resources based on the visualized information.

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

[0138] This invention is a multimodal emotion analysis system that combines emotion engines, and aims to evaluate and improve team work dynamics and workload. By collecting and analyzing emotion data, audio data, and video data, this system recognizes the emotional state of team members in real time and improves the efficiency of work distribution.

[0139] Forms of data collection and emotion recognition:

[0140] Devices: Each member's device collects emotional data from text messages and emails, as well as video and audio data via webcam and microphone. This data is sent to the emotion engine to recognize the user's emotional state in real time.

[0141] Forms of data analysis and integration:

[0142] Server: The collected data is preprocessed on the server to remove noise. Then, using the emotion engine, text analysis, facial expression analysis, and voice analysis are performed to calculate individual emotion scores.

[0143] Server: Integrates calculated sentiment scores and workload data to generate a dashboard for displaying results in real time.

[0144] Forms of user feedback and strategic planning:

[0145] User (Administrator): Administrators can check each member's emotional state and workload through the dashboard. If a specific emotional change is detected, the emotion engine will automatically generate a notification requesting action.

[0146] Terminal: The terminal is used to communicate business improvement measures and new work assignments decided by the administrator to each member, and to collect feedback.

[0147] Specific example:

[0148] For example, consider a situation where a project deadline is approaching. In this case, it can be seen that a particular member's stress level is rising through their emotional engine. Based on this data, the manager can check the emotional score on a dashboard and identify which tasks are causing that member particular stress. The manager can then propose task redistribution to that member and arrange for the workload to be distributed among other members. As a result, emotional burden can be reduced while improving the overall performance of the team.

[0149] In this configuration, the system leverages an emotion engine to monitor the emotional state of team members in real time, providing powerful support for appropriate feedback and work improvement.

[0150] The following describes the processing flow.

[0151] Step 1:

[0152] Devices: Each user's device collects emotional data from text messages and emails. In addition, it acquires video data using a webcam and audio data through a microphone. This data is important for understanding the user's emotional state.

[0153] Step 2:

[0154] Server: Receives and preprocesses collected data. Removes noise and converts the data into a format suitable for analysis. This enables accurate analysis.

[0155] Step 3:

[0156] Server: Inputs pre-processed data into the emotion engine and performs text analysis, facial expression analysis, and voice analysis. Emotional states are evaluated from each data type, and an emotion score is calculated.

[0157] Step 4:

[0158] Server: Integrate emotion scores with workload data to assess the overall state of each member. This visualizes the relationship between emotion and workload.

[0159] Step 5:

[0160] Server: Based on the integration results, it generates an administrator dashboard. This dashboard displays real-time, fluctuating sentiment scores and workload graphs.

[0161] Step 6:

[0162] User (Administrator): Utilize the dashboard to check the emotional state and workload of specific members. If there is a significant change in emotional state, receive an automatic notification from the emotion engine and consider countermeasures.

[0163] Step 7:

[0164] Terminal: As needed, the administrator notifies members of any decided business improvement measures or instructions and sends the results to each member's terminal. At the same time, feedback on the measures is collected and used to improve future operations.

[0165] (Example 2)

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

[0167] In modern teamwork, understanding each member's emotional state and workload in real time and efficiently distributing tasks is a major challenge. In particular, emotional stress and overload can reduce work efficiency, making it essential to manage this information appropriately. However, conventional systems struggle to comprehensively evaluate emotional states and workloads, making it difficult to respond quickly and appropriately.

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

[0169] In this invention, the server includes device means for acquiring emotional information, acoustic information, and visual information; processing means for preprocessing the acquired information, removing unnecessary signals, and converting it into an analyzable format; and analysis device means for evaluating emotional states and calculating an emotional index through character information analysis, facial display analysis, and acoustic analysis. This makes it possible to comprehensively evaluate the emotional states and workload of team members in real time and to achieve optimal work distribution.

[0170] "Emotional information" refers to data that indicates emotions, extracted from the user's text, facial expressions, voice, etc.

[0171] "Acoustic information" refers to information about the characteristics and tone of sound obtained from the user's voice data.

[0172] "Visual information" refers to image and video data acquired through devices such as cameras.

[0173] "Device means" refers to hardware or software mechanisms used to acquire, process, and analyze data.

[0174] A "processing device" is a mechanism that performs processing to convert acquired data into a format suitable for analysis.

[0175] An "analysis device means" is a mechanism that analyzes acquired data and calculates a specific result.

[0176] The "emotional index" is a numerical value calculated through analysis that quantitatively indicates the emotional state of a user.

[0177] "Task distribution" is the process of efficiently distributing work among team members.

[0178] This embodiment of the invention is a system that uses emotional information, acoustic information, and visual information to evaluate the emotional state and workload of team members in real time, and to streamline the distribution of tasks.

[0179] Hardware and software for data collection:

[0180] Devices: Each member's device is equipped with a microphone and camera to collect audio and video data. In addition, text data is extracted from communication applications on the device.

[0181] Hardware and software for data processing and analysis:

[0182] Server: The collected data is preprocessed on the server and analyzed using an emotion engine. The server analyzes text using a natural language processing library, analyzes facial expressions using image processing algorithms, and analyzes acoustic information using speech analysis software.

[0183] The server calculates an emotional index from these analysis results and integrates it with workload data.

[0184] Displaying results and feedback:

[0185] Server to User (Administrator): The integrated data is visually displayed to administrators through a dashboard. The dashboard shows team sentiment and workload in graph and chart format.

[0186] User notifications: When a specific change in emotion is detected, the system automatically sends a notification to the administrator. This allows for quick adjustments to work processes.

[0187] Specific example:

[0188] If a project deadline is approaching and a particular member's emotional index indicates stress, the administrator can check this information through the dashboard. They can then redistribute the member's workload, spreading the burden across other members.

[0189] Example of a prompt:

[0190] "As the project deadline approaches, please tell us what changes you've observed in the team members' emotions."

[0191] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0192] Step 1:

[0193] The device collects acoustic and visual information using a microphone and camera. Furthermore, it acquires text data containing emotional information from communication applications. The input data consists of raw audio, video, and text, which, once collected, prepares the system to understand the user's emotional state. The output is a raw emotional dataset.

[0194] Step 2:

[0195] The server receives the collected data and performs noise reduction and data cleaning. Specifically, it removes background noise and standardizes the spelling and formatting of text data. The input is raw sentiment data sent from the terminal, and the output is pre-processed data suitable for analysis.

[0196] Step 3:

[0197] The server performs analysis on pre-processed data using an emotion engine. This includes text analysis using natural language processing, facial expression analysis using a face detection algorithm, and speech analysis using acoustic analysis software. The input is pre-processed data, and the output is an emotion index indicating emotional state.

[0198] Step 4:

[0199] The server integrates the calculated sentiment index with workload information. This generates an integrated report showing the relationship between emotional state and workload. The inputs are sentiment index and workload data, and the output is the integrated dashboard display data.

[0200] Step 5:

[0201] Users (administrators) use a dashboard to monitor each member's emotional state and workload. The dashboard visually presents information, and automatic notifications are triggered when specific emotional changes occur. Input is integrated dashboard display data, and output is decision-making information for business improvement.

[0202] (Application Example 2)

[0203] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0204] In modern industrial production environments, there is a need to improve production efficiency and ensure worker safety simultaneously by understanding workers' emotional states and workloads in real time. However, there is a challenge in the lack of means to accurately assess emotional states and automatically adjust work pace appropriately. This makes it easy for situations to arise where workers' stress levels increase or work efficiency decreases.

[0205] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0206] In this invention, the server includes terminal device means for collecting emotional data, audio data, and video data; control device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and operating device means having an automatic control function for adjusting the work pace based on the emotional state of the worker. This makes it possible to analyze the emotional state of the worker in real time and automatically adjust the work as needed.

[0207] "Emotional data" refers to information that indicates the emotional state of a worker, and includes features extracted from text, facial expressions, and voice.

[0208] "Voice data" refers to audio information collected to analyze the emotional state of workers, and includes characteristics such as tone and speed of voice.

[0209] "Video data" refers to visual information collected to analyze the facial expressions and movements of workers, and includes images or videos captured by cameras.

[0210] "Terminal device" refers to a device used to collect emotional data, audio data, and video data, and refers to hardware worn or used by workers.

[0211] A "control system" refers to a computer system used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0212] An "analysis device" is a system that uses collected data to analyze emotional states and calculate an emotional score.

[0213] A "display device" is a display or monitoring system for visually representing emotion scores and workload data.

[0214] A "support device" is a system that assists managers in formulating efficient work allocation strategies based on visually displayed data.

[0215] "Automatic control function" refers to a mechanism that automatically adjusts the work pace based on the worker's emotional state.

[0216] "Operating device" refers to equipment or programs used to automatically perform work adjustments.

[0217] This invention is a system that analyzes the emotional state and workload of workers in real time to improve productivity and safety. The system includes a terminal device, a control device, an analysis device, a display device, a support device, and an operating device with automatic control functions.

[0218] Terminal devices are devices worn or used by workers that collect emotional data, audio data, and video data. These include smart glasses and wearable devices. The collected data is preprocessed by a control device to remove noise before being sent to an analysis device.

[0219] The analysis device analyzes the collected data and evaluates the emotional state. This analysis uses cloud-based analysis services (e.g., Amazon Rekognition or Microsoft® Azure® Emotion API). The analysis results are calculated as an emotional score and then sent to the display device.

[0220] The display device visually represents emotion scores and workload data, allowing managers to view them in real time. This enables managers to grasp the current status of workers at a glance and easily make decisions to optimize work distribution based on the strategies presented by the support device.

[0221] The control device is equipped with an automatic control function that adjusts the work pace based on the analysis results. Specifically, it can temporarily slow down work if the worker's stress level increases, or redistribute tasks to other workers.

[0222] For example, if a worker on a production line is experiencing excessive stress, this information is detected through the system. An analysis device processes the data and notifies management of the need to adjust the work pace. As a result, the burden on workers is reduced, and a production environment that balances safety and efficiency is achieved.

[0223] An example of a prompt is: "Propose a factory worker emotion monitoring system. Explain how to use an emotion engine to detect worker emotions in real time and improve work efficiency and safety. Mention specific data collection methods, analysis techniques, and feedback mechanisms." Using this prompt, the generated AI model can propose specific control guidelines and provide more effective operational methods.

[0224] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0225] Step 1:

[0226] The terminal collects emotional data, audio data, and video data from the worker. This uses cameras and microphones built into smart glasses, and the data is captured in real time. The input data includes facial expressions as video and tone from audio, and the output is raw, unprocessed data.

[0227] Step 2:

[0228] The server receives raw, unprocessed data sent from the terminal and performs preprocessing. Specifically, it applies a noise reduction filter and converts the data into an analyzable format. The input is raw data, and the output is clear data with noise removed.

[0229] Step 3:

[0230] The server uses pre-processed data to perform analysis using a generative AI model. A cloud-based sentiment analysis service is used to calculate sentiment scores. The input is clear data, and the output is the analysis results, including each worker's sentiment score. Specifically, the process involves text analysis, facial expression analysis, and voice analysis.

[0231] Step 4:

[0232] The server integrates sentiment scores and workload data and sends it to a display device as visualized information. The input is sentiment scores and workload data, and the output is a visually easy-to-understand dashboard. Specifically, workload and sentiment status are displayed as graphs and charts.

[0233] Step 5:

[0234] The user (manager) reviews the displayed dashboard information and, if necessary, develops a work distribution strategy using support devices. The input is dashboard information, and the output is an optimized work distribution command. Specific actions include strategic decisions to adjust the workload balance for each worker.

[0235] Step 6:

[0236] The control device adjusts the work pace using automatic control functions based on work distribution commands from the user. The input is the work distribution command, and the output is the adjusted work pace. Specific actions include task redistribution and slowing down the work pace.

[0237] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0238] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0239] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0240] [Second Embodiment]

[0241] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0242] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0243] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0244] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0245] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0246] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0247] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0248] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0249] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0250] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0251] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0252] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0253] As an embodiment of the present invention, a system for team dynamics and workload evaluation utilizing multimodal sentiment analysis is described. This system supports efficient work distribution by visualizing the emotional state and workload of each member of a team, utilizing specific devices, processing devices, and analysis devices.

[0254] Data collection methods:

[0255] Devices: Each member's device continuously collects sentiment data from messaging applications and collaboration tools. This includes keyword extraction and pattern analysis from text messages.

[0256] Device: During video conferences, it collects video data using the camera to obtain information for facial expression analysis. It also collects audio data via the microphone to evaluate voice tone.

[0257] Forms of data analysis:

[0258] Server: Integrates collected data and analyzes emotional states using machine learning algorithms. The server calculates an emotional score for each member, expressing the degree of different emotions numerically.

[0259] Server: In addition to the emotion score, the workload is evaluated from user-provided survey data, and both sets of data are combined to understand the overall state of the team.

[0260] Visualization of results and forms of strategic planning:

[0261] Server: Generates an administrator visualization dashboard based on integrated data. This dashboard includes interactive graphics to identify sentiment scores, workload imbalances, and stress levels.

[0262] User (Administrator): Review analysis results through the dashboard and formulate strategies to optimize workload distribution. For example, if a particular member is overburdened, the administrator will adjust their workload and redistribute tasks to other members.

[0263] Specific example:

[0264] For example, suppose emotion scores reveal that a specific member of a team is regularly experiencing stress. In this case, the administrator can use the dashboard to examine the detailed analysis of the member's voice and video data to identify the source of the stress. They can then improve the work environment by reallocating workloads or suggesting leave as needed.

[0265] As described above, the system of the present invention is highly effective as a tool for accurately collecting and analyzing emotional and workload data to improve the overall performance of the team. This embodiment allows managers to quickly address problems within the team and manage the efficiency and stress levels of individual members in a balanced manner.

[0266] The following describes the processing flow.

[0267] Step 1:

[0268] Terminals: Each member's terminal collects text data from messaging applications. This includes a process of extracting keywords and phrases to estimate sentiment.

[0269] Step 2:

[0270] Device: Uses a webcam and microphone to collect video and audio data. Video data is used as material for facial expression analysis, and audio data is used for voice tone analysis.

[0271] Step 3:

[0272] Server: Preprocesses collected text, audio, and video data. Prepares the data for analysis through noise reduction and standardization of data formats.

[0273] Step 4:

[0274] Server: Using machine learning algorithms, analyze the emotional state from each piece of data. Calculate the emotional scores for each piece of data in text, voice, and video individually, and integrate them.

[0275] Step 5:

[0276] Server: Analyze by combining the emotional scores and the workload questionnaire data provided by the user. Thereby, evaluate the correlation between the workload balance and the emotional state among members.

[0277] Step 6:

[0278] Server: Use the analysis results to generate a dashboard for administrators. Here, graphs visualizing the time-series changes in the emotional state and the dispersion of the workload are displayed.

[0279] Step 7:

[0280] User (Administrator): Refer to the dashboard and check for stress and workload imbalance among members. Based on the discovered problems, devise business redistribution and improvement measures.

[0281] Step 8:

[0282] Terminal: Notify the members of the new business distribution and countermeasures determined by the administrator, and request feedback through the system. Collect the feedback and connect it to continuous improvement.

[0283] (Example 1)

[0284] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In a modern workplace environment, it is required to accurately grasp the emotions and workload status of team members and achieve efficient distribution of work. However, there is a lack of an effective system for comprehensively analyzing various information on emotional data and workload and easily formulating work strategies based on them.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0287] In this invention, the server includes device means for collecting emotional data, visual information, and acoustic information, processing machine means for standardizing the collected data, removing noise, and converting it into an analyzable form, and display machine means for integrating information related to emotional scales and workload and visually displaying it for the controller. Thereby, it becomes possible to comprehensively grasp the emotional state and workload of team members, and for the administrator to formulate an accurate work distribution strategy.

[0288] "Emotional data" refers to information indicating an individual's emotional state, and is data collected in forms such as text, expressions, and voices.

[0289] "Visual information" refers to information obtained through images and videos, and is mainly data for analyzing facial expressions.

[0290] "Acoustic information" refers to information obtained through voices, and is mainly data for evaluating the tone and pitch of voices.

[0291] "Device" refers to a concept that represents hardware or software components designed to perform specific functions.

[0292] "Processing machine" refers to a computer system or program for preprocessing the collected data and converting it into an analyzable form.

[0293] An "analysis mechanism" is a system that analyzes collected data and employs methods to derive emotional evaluations and other information.

[0294] A "display device" is a device or application used to visually represent analysis results or integrated information.

[0295] A "support tool" is a means of providing information and support necessary when formulating strategies such as work allocation.

[0296] "Machine learning techniques" are algorithms and technologies used to automatically extract patterns and regularities from collected data.

[0297] An "integration device" is a means of combining different types of data, managing them centrally, and visually displaying their relationships.

[0298] This invention is a system that utilizes multimodal sentiment analysis to visualize the emotional state and workload of team members in the workplace, and is implemented to support the efficient distribution of tasks.

[0299] Data collection

[0300] Devices: Each member's device is equipped with messaging applications and collaboration tools, through which emotional data is acquired in real time. Specifically, keywords related to emotions are automatically extracted from text messages using a natural language processing node. In addition, facial expression data is captured using the camera during video conferences, and data that can be analyzed by facial recognition software is collected. Furthermore, voice data is acquired through the microphone, and the tone of voice is evaluated using a voice analysis algorithm.

[0301] Data Analysis

[0302] Server: The collected data is integrated on the server and converted into a standardized data format. Data processing languages such as Python and R are used here. Then, using machine learning algorithms, the generative AI model calculates the sentiment scores. This model performs more advanced inferences by the SSMP (Sentiment State Modeling Protocol). For example, using prompt sentences such as "Is this member feeling stressed about the recent project progress?", it analyzes the sentiment patterns within the team.

[0303] Visualization and Strategy Formulation

[0304] Server: Based on the analysis results, the server generates an interactive dashboard for administrators. This dashboard is developed using the JavaScript and D3.js libraries and visually displays the sentiment scores and workloads of each member. As a result, administrators can easily grasp the status of team members and improve the overall performance of the team by redistributing tasks as needed.

[0305] Specific Examples and Use of Prompt Sentences

[0306] For example, when it is necessary to verify the proposition "Is member A frequently feeling stressed?", the administrator checks the dashboard. On the dashboard, facial expression data from recent video conferences and changes in voice tones are displayed as graphs, and appropriate measures can be taken based on this information.

[0307] The flow of specific processing in Example 1 will be described using Figure 11.

[0308] Step 1:

[0309] Terminals: Each member's terminal receives text messages from emails and chats as input and uses natural language processing technology to extract keywords related to emotions. A built-in keyword recognition algorithm is used for keyword extraction, and emotion data is generated as output. Specifically, a text analysis module operates during this extraction process to identify positive and negative emotional tones.

[0310] Step 2:

[0311] Terminal: During the meeting, the terminal's camera is activated to capture video footage as input. Face recognition software analyzes this footage and generates facial expression data as output. Specifically, the recorded video data is analyzed in real time, and a process is included in which specific facial expressions such as smiles and surprise are quantified.

[0312] Step 3:

[0313] Terminal: During meetings, the microphone is used to collect audio data as input. A voice analysis algorithm evaluates the tone and pitch of the voice and extracts emotional features from the audio data as output. Specifically, changes in tone pitch and speed are analyzed, and stress and satisfaction levels are estimated based on this.

[0314] Step 4:

[0315] Server: The collected text, facial expression, and audio data are integrated into a standardized format, and the processor removes noise. Here, data cleaning techniques are used to ensure the consistency of each input data, and the integrated dataset is output. Specifically, data merging techniques are used to ensure data consistency.

[0316] Step 5:

[0317] Server: Using integrated data as input, a machine learning algorithm calculates an emotion score. A generative AI model is used to analyze patterns in the collected data and output the emotional intensity of team members. For example, if the emotion score exceeds a certain threshold, the system generates a prompt message indicating that the user is experiencing stress.

[0318] Step 6:

[0319] Server: The visualization module takes integrated sentiment score and workload data as input and generates a dashboard for administrators. It provides interactive graphs and charts as output, supplying administrators with visual information to formulate business strategies. Specifically, data is visualized using JavaScript and D3.js, and an easy-to-use UI is provided.

[0320] Step 7:

[0321] User (Administrator): The administrator reviews the dashboard as input data and reallocates tasks as needed. Specifically, they adjust tasks for members with high workloads and reallocate them to other members. Through interactive feedback during this process, it is possible to optimize team performance.

[0322] (Application Example 1)

[0323] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0324] In modern manufacturing environments, maximizing the efficiency of workers and automated machinery while avoiding excessive burden and stress is a crucial challenge. However, visualizing and immediately addressing these conditions is difficult. Therefore, there is a need for a system that can grasp the emotional state and workload of individual workers and machines in real time, thereby improving overall production efficiency.

[0325] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0326] In this invention, the server includes information gathering device means for collecting emotional data, audio data, and video data; data processing device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and data analysis device means for analyzing emotional states through text analysis, facial expression analysis, and audio analysis, and calculating emotional scores. This makes it possible to visualize emotional states and workloads in the production site in real time and optimize the efficiency of each worker and machine.

[0327] An "information gathering device" is a device that can collect emotional data, audio data, and video data.

[0328] A "data processing device" is a device used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0329] A "data analysis device" is a device that analyzes emotional states through text analysis, facial expression analysis, and voice analysis, and calculates an emotional score.

[0330] A "visualization device" is a device that integrates information related to emotional scores and workload, and displays the analysis results visually.

[0331] A "support system" is a system that uses visually displayed information to formulate efficient work allocation strategies.

[0332] A "management device" is a device that monitors production activities in real time and supports optimization through a visual assistance device equipped with the system.

[0333] An "analysis system" is a system that applies machine learning algorithms based on collected data to estimate emotional patterns among workers.

[0334] An "integrated system" is a system that evaluates the workload of each worker and displays the information relating that workload to emotional information.

[0335] To implement this invention, the server operates as a configuration including an information gathering device, a data processing device, a data analysis device, a visualization device, and a support system. The information gathering device acquires audio data, video data, and environmental data through multiple sensors and cameras installed on the factory production floor. This makes it possible to continuously acquire real-time information from the site.

[0336] The server preprocesses the collected data using a data processing device, removing noise and converting the format. Specifically, it uses Python or TensorFlow for data cleaning and transformation. This process prepares the data for analysis, allowing it to proceed to the next analysis step.

[0337] The server then uses data analysis equipment to perform text analysis, facial expression analysis, and voice analysis. These analysis techniques are used to output emotional states as emotional scores, which are numerical representations of emotional states. Generative AI models using machine learning (e.g., neural networks using Keras) are applied to the analysis. The results are quantified, and the emotional states of workers and machines are evaluated in real time.

[0338] The visualization device integrates emotion scores and workload-related data, visually displaying the information on an administrator dashboard. Users can then use this to develop strategies to optimize workload distribution in the field. This dashboard is projected onto smart glasses, enabling immediate action.

[0339] For example, if a worker shows an unusually high stress score, managers can immediately check the number through a dashboard and take countermeasures. For instance, if it is determined that the worker is overloaded, they can change the work shift or assign additional personnel.

[0340] An example of a prompt might be: "Design a method to analyze the team's emotional state in real time and optimize their workload, with a particular focus on managing the efficiency of robots and workers in the field."

[0341] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0342] Step 1:

[0343] The server acquires audio, video, and environmental data from the production site via multiple sensors and cameras from the information gathering device. This input data is captured in real time from the site and may contain noise or missing data. The server collects this data and prepares it for the next step.

[0344] Step 2:

[0345] The server preprocesses the collected data using a data processing device. This process removes noise and imputes missing data using Python scripts, etc. Audio and video are also converted to appropriate formats and prepared for analysis. As output, a clean and consistent dataset is sent to the next analysis step.

[0346] Step 3:

[0347] The server analyzes data that has been preprocessed by the data analysis device. Here, it performs text analysis, facial expression analysis, and speech analysis using a generative AI model. Specifically, it uses a neural network with Keras to quantify emotion scores. As a result of the analysis, numerical data representing the emotional state of each worker and device is output. This numerical data is used for visualization as an emotion score.

[0348] Step 4:

[0349] The server integrates and displays sentiment scores and workload data on the administrator's dashboard via a visualization device. The processed numerical data is visualized as interactive graphics, which users can view on the dashboard. This output allows administrators to intuitively understand the workload on the ground and obtain guidance for necessary countermeasures.

[0350] Step 5:

[0351] Users develop efficient work allocation strategies based on information displayed on the dashboard. These decisions take into account worker stress levels and equipment utilization efficiency. Users aim to optimize the work environment by adjusting work schedules and reallocating resources based on the visualized information.

[0352] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0353] This invention is a multimodal emotion analysis system that combines emotion engines, and aims to evaluate and improve team work dynamics and workload. By collecting and analyzing emotion data, audio data, and video data, this system recognizes the emotional state of team members in real time and improves the efficiency of work distribution.

[0354] Forms of data collection and emotion recognition:

[0355] Devices: Each member's device collects emotional data from text messages and emails, as well as video and audio data via webcam and microphone. This data is sent to the emotion engine to recognize the user's emotional state in real time.

[0356] Forms of data analysis and integration:

[0357] Server: The collected data is preprocessed on the server to remove noise. Then, using the emotion engine, text analysis, facial expression analysis, and voice analysis are performed to calculate individual emotion scores.

[0358] Server: Integrates calculated sentiment scores and workload data to generate a dashboard for displaying results in real time.

[0359] Forms of user feedback and strategic planning:

[0360] User (Administrator): Administrators can check each member's emotional state and workload through the dashboard. If a specific emotional change is detected, the emotion engine will automatically generate a notification requesting action.

[0361] Terminal: The terminal is used to communicate business improvement measures and new work assignments decided by the administrator to each member, and to collect feedback.

[0362] Specific example:

[0363] For example, consider a situation where a project deadline is approaching. In this case, it can be seen that a particular member's stress level is rising through their emotional engine. Based on this data, the manager can check the emotional score on a dashboard and identify which tasks are causing that member particular stress. The manager can then propose task redistribution to that member and arrange for the workload to be distributed among other members. As a result, emotional burden can be reduced while improving the overall performance of the team.

[0364] In this configuration, the system leverages an emotion engine to monitor the emotional state of team members in real time, providing powerful support for appropriate feedback and work improvement.

[0365] The following describes the processing flow.

[0366] Step 1:

[0367] Devices: Each user's device collects emotional data from text messages and emails. In addition, it acquires video data using a webcam and audio data through a microphone. This data is important for understanding the user's emotional state.

[0368] Step 2:

[0369] Server: Receives and preprocesses collected data. Removes noise and converts the data into a format suitable for analysis. This enables accurate analysis.

[0370] Step 3:

[0371] Server: Inputs pre-processed data into the emotion engine and performs text analysis, facial expression analysis, and voice analysis. Emotional states are evaluated from each data type, and an emotion score is calculated.

[0372] Step 4:

[0373] Server: Integrate emotion scores with workload data to assess the overall state of each member. This visualizes the relationship between emotion and workload.

[0374] Step 5:

[0375] Server: Based on the integration results, it generates an administrator dashboard. This dashboard displays real-time, fluctuating sentiment scores and workload graphs.

[0376] Step 6:

[0377] User (Administrator): Utilize the dashboard to check the emotional state and workload of specific members. If there is a significant change in emotional state, receive an automatic notification from the emotion engine and consider countermeasures.

[0378] Step 7:

[0379] Terminal: As needed, the administrator notifies members of any decided business improvement measures or instructions and sends the results to each member's terminal. At the same time, feedback on the measures is collected and used to improve future operations.

[0380] (Example 2)

[0381] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0382] In modern teamwork, understanding each member's emotional state and workload in real time and efficiently distributing tasks is a major challenge. In particular, emotional stress and overload can reduce work efficiency, making it essential to manage this information appropriately. However, conventional systems struggle to comprehensively evaluate emotional states and workloads, making it difficult to respond quickly and appropriately.

[0383] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0384] In this invention, the server includes device means for acquiring emotional information, acoustic information, and visual information; processing means for preprocessing the acquired information, removing unnecessary signals, and converting it into an analyzable format; and analysis device means for evaluating emotional states and calculating an emotional index through character information analysis, facial display analysis, and acoustic analysis. This makes it possible to comprehensively evaluate the emotional states and workload of team members in real time and to achieve optimal work distribution.

[0385] "Emotional information" refers to data that indicates emotions, extracted from the user's text, facial expressions, voice, etc.

[0386] "Acoustic information" refers to information about the characteristics and tone of sound obtained from the user's voice data.

[0387] "Visual information" refers to image and video data acquired through devices such as cameras.

[0388] "Device means" refers to hardware or software mechanisms used to acquire, process, and analyze data.

[0389] A "processing device" is a mechanism that performs processing to convert acquired data into a format suitable for analysis.

[0390] An "analysis device means" is a mechanism that analyzes acquired data and calculates a specific result.

[0391] The "emotional index" is a numerical value calculated through analysis that quantitatively indicates the emotional state of a user.

[0392] "Task distribution" is the process of efficiently distributing work among team members.

[0393] This embodiment of the invention is a system that uses emotional information, acoustic information, and visual information to evaluate the emotional state and workload of team members in real time, and to streamline the distribution of tasks.

[0394] Hardware and software for data collection:

[0395] Devices: Each member's device is equipped with a microphone and camera to collect audio and video data. In addition, text data is extracted from communication applications on the device.

[0396] Hardware and software for data processing and analysis:

[0397] Server: The collected data is preprocessed on the server and analyzed using an emotion engine. The server analyzes text using a natural language processing library, analyzes facial expressions using image processing algorithms, and analyzes acoustic information using speech analysis software.

[0398] The server calculates an emotional index from these analysis results and integrates it with workload data.

[0399] Displaying results and feedback:

[0400] Server to User (Administrator): The integrated data is visually displayed to administrators through a dashboard. The dashboard shows team sentiment and workload in graph and chart format.

[0401] User Notifications: When a specific emotional shift is detected, the system automatically sends a notification to the administrator. This allows for quick adjustments to work processes.

[0402] Specific example:

[0403] If a project deadline is approaching and a particular member's emotional index indicates stress, the administrator can check this information through the dashboard. They can then redistribute the member's workload, spreading the burden across other members.

[0404] Example of a prompt:

[0405] "As the project deadline approaches, please tell us what changes you've observed in the team members' emotions."

[0406] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0407] Step 1:

[0408] The device collects acoustic and visual information using a microphone and camera. Furthermore, it acquires text data containing emotional information from communication applications. The input data consists of raw audio, video, and text, which, once collected, prepares the system to understand the user's emotional state. The output is a raw emotional dataset.

[0409] Step 2:

[0410] The server receives the collected data and performs noise reduction and data cleaning. Specifically, it removes background noise and standardizes the spelling and formatting of text data. The input is raw sentiment data sent from the terminal, and the output is pre-processed data suitable for analysis.

[0411] Step 3:

[0412] The server performs analysis on pre-processed data using an emotion engine. This includes text analysis using natural language processing, facial expression analysis using a face detection algorithm, and speech analysis using acoustic analysis software. The input is pre-processed data, and the output is an emotion index indicating emotional state.

[0413] Step 4:

[0414] The server integrates the calculated sentiment index with workload information. This generates an integrated report showing the relationship between emotional state and workload. The inputs are sentiment index and workload data, and the output is the integrated dashboard display data.

[0415] Step 5:

[0416] Users (administrators) use a dashboard to monitor each member's emotional state and workload. The dashboard visually presents information, and automatic notifications are triggered when specific emotional changes occur. Input is integrated dashboard display data, and output is decision-making information for business improvement.

[0417] (Application Example 2)

[0418] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0419] In modern industrial production environments, there is a need to improve production efficiency and ensure worker safety simultaneously by understanding workers' emotional states and workloads in real time. However, there is a challenge in the lack of means to accurately assess emotional states and automatically adjust work pace appropriately. This makes it easy for situations to arise where workers' stress levels increase or work efficiency decreases.

[0420] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0421] In this invention, the server includes terminal device means for collecting emotional data, audio data, and video data; control device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and operating device means having an automatic control function for adjusting the work pace based on the emotional state of the worker. This makes it possible to analyze the emotional state of the worker in real time and automatically adjust the work as needed.

[0422] "Emotional data" refers to information that indicates the emotional state of a worker, and includes features extracted from text, facial expressions, and voice.

[0423] "Voice data" refers to audio information collected to analyze the emotional state of workers, and includes characteristics such as tone and speed of voice.

[0424] "Video data" refers to visual information collected to analyze the facial expressions and movements of workers, and includes images or videos captured by cameras.

[0425] "Terminal device" refers to a device used to collect emotional data, audio data, and video data, and refers to hardware worn or used by workers.

[0426] A "control system" refers to a computer system used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0427] An "analysis device" is a system that uses collected data to analyze emotional states and calculate an emotional score.

[0428] A "display device" is a display or monitoring system for visually representing emotion scores and workload data.

[0429] A "support device" is a system that assists managers in formulating efficient work allocation strategies based on visually displayed data.

[0430] "Automatic control function" refers to a mechanism that automatically adjusts the work pace based on the worker's emotional state.

[0431] "Operating device" refers to equipment or programs used to automatically perform work adjustments.

[0432] This invention is a system that analyzes the emotional state and workload of workers in real time to improve productivity and safety. The system includes a terminal device, a control device, an analysis device, a display device, a support device, and an operating device with automatic control functions.

[0433] Terminal devices are devices worn or used by workers that collect emotional data, audio data, and video data. These include smart glasses and wearable devices. The collected data is preprocessed by a control device to remove noise before being sent to an analysis device.

[0434] The analysis device analyzes the collected data and evaluates the emotional state. This analysis uses cloud-based analysis services (e.g., Amazon Rekognition or Microsoft Azure Emotion API). The analysis results are calculated as an emotional score and then sent to the display device.

[0435] The display device visually represents emotion scores and workload data, allowing managers to view them in real time. This enables managers to grasp the current status of workers at a glance and easily make decisions to optimize work distribution based on the strategies presented by the support device.

[0436] The control device is equipped with an automatic control function that adjusts the work pace based on the analysis results. Specifically, it can temporarily slow down work if the worker's stress level increases, or redistribute tasks to other workers.

[0437] For example, if a worker on a production line is experiencing excessive stress, this information is detected through the system. An analysis device processes the data and notifies management of the need to adjust the work pace. As a result, the burden on workers is reduced, and a production environment that balances safety and efficiency is achieved.

[0438] An example of a prompt is: "Propose a factory worker emotion monitoring system. Explain how to use an emotion engine to detect worker emotions in real time and improve work efficiency and safety. Mention specific data collection methods, analysis techniques, and feedback mechanisms." Using this prompt, the generated AI model can propose specific control guidelines and provide more effective operational methods.

[0439] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0440] Step 1:

[0441] The terminal collects emotional data, audio data, and video data from the worker. This uses cameras and microphones built into smart glasses, and the data is captured in real time. The input data includes facial expressions as video and tone from audio, and the output is raw, unprocessed data.

[0442] Step 2:

[0443] The server receives raw, unprocessed data sent from the terminal and performs preprocessing. Specifically, it applies a noise reduction filter and converts the data into an analyzable format. The input is raw data, and the output is clear data with noise removed.

[0444] Step 3:

[0445] The server uses pre-processed data to perform analysis using a generative AI model. A cloud-based sentiment analysis service is used to calculate sentiment scores. The input is clear data, and the output is the analysis results, including each worker's sentiment score. Specifically, the process involves text analysis, facial expression analysis, and voice analysis.

[0446] Step 4:

[0447] The server integrates sentiment scores and workload data and sends it to a display device as visualized information. The input is sentiment scores and workload data, and the output is a visually easy-to-understand dashboard. Specifically, workload and sentiment status are displayed as graphs and charts.

[0448] Step 5:

[0449] The user (manager) reviews the displayed dashboard information and, if necessary, develops a work distribution strategy using support devices. The input is dashboard information, and the output is an optimized work distribution command. Specific actions include strategic decisions to adjust the workload balance for each worker.

[0450] Step 6:

[0451] The control device adjusts the work pace using automatic control functions based on work distribution commands from the user. The input is the work distribution command, and the output is the adjusted work pace. Specific actions include task redistribution and slowing down the work pace.

[0452] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0453] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0454] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0455] [Third Embodiment]

[0456] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0457] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0458] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0459] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0460] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0461] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0462] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0463] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0464] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0465] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0466] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0467] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0468] As an embodiment of the present invention, a system for team dynamics and workload evaluation utilizing multimodal sentiment analysis is described. This system supports efficient work distribution by visualizing the emotional state and workload of each member of a team, utilizing specific devices, processing devices, and analysis devices.

[0469] Data collection methods:

[0470] Devices: Each member's device continuously collects sentiment data from messaging applications and collaboration tools. This includes keyword extraction and pattern analysis from text messages.

[0471] Device: During video conferences, it collects video data using the camera to obtain information for facial expression analysis. It also collects audio data via the microphone to evaluate voice tone.

[0472] Forms of data analysis:

[0473] Server: Integrates collected data and analyzes emotional states using machine learning algorithms. The server calculates an emotional score for each member, expressing the degree of different emotions numerically.

[0474] Server: In addition to the emotion score, the workload is evaluated from user-provided survey data, and both sets of data are combined to understand the overall state of the team.

[0475] Visualization of results and forms of strategic planning:

[0476] Server: Generates an administrator visualization dashboard based on integrated data. This dashboard includes interactive graphics to identify sentiment scores, workload imbalances, and stress levels.

[0477] User (Administrator): Review analysis results through the dashboard and formulate strategies to optimize workload distribution. For example, if a particular member is overburdened, the administrator will adjust their workload and redistribute tasks to other members.

[0478] Specific example:

[0479] For example, suppose emotion scores reveal that a specific member of a team is regularly experiencing stress. In this case, the administrator can use the dashboard to examine the detailed analysis of the member's voice and video data to identify the source of the stress. They can then improve the work environment by reallocating workloads or suggesting leave as needed.

[0480] As described above, the system of the present invention is highly effective as a tool for accurately collecting and analyzing emotional and workload data to improve the overall performance of the team. This embodiment allows managers to quickly address problems within the team and manage the efficiency and stress levels of individual members in a balanced manner.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] Terminals: Each member's terminal collects text data from messaging applications. This includes a process of extracting keywords and phrases to estimate sentiment.

[0484] Step 2:

[0485] Device: Uses a webcam and microphone to collect video and audio data. Video data is used as material for facial expression analysis, and audio data is used for voice tone analysis.

[0486] Step 3:

[0487] Server: Preprocesses collected text, audio, and video data. Prepares the data for analysis through noise reduction and standardization of data formats.

[0488] Step 4:

[0489] Server: Uses machine learning algorithms to analyze emotional states from each data point. It calculates individual emotional scores for text, audio, and video data, and then integrates them.

[0490] Step 5:

[0491] Server: Analyzes emotional scores in conjunction with user-provided workload survey data. This allows for the evaluation of the correlation between workload balance among team members and their emotional state.

[0492] Step 6:

[0493] Server: Uses the analysis results to generate a dashboard for administrators. This dashboard displays graphs that visualize things like changes in emotional states over time and the distribution of workload.

[0494] Step 7:

[0495] User (Administrator): Refer to the dashboard to check for stress levels and workload imbalances among team members. Based on the problems identified, devise work reallocation and improvement measures.

[0496] Step 8:

[0497] Terminal: Notifies members of new work assignments and countermeasures decided by the administrator, and requests feedback through the system. Collect feedback and use it for continuous improvement.

[0498] (Example 1)

[0499] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] In today's workplace, accurately understanding the emotions and workload of team members and achieving efficient work distribution is essential. However, there is a lack of effective systems that can centrally analyze diverse information on emotions and workload, and easily formulate business strategies based on this information.

[0501] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0502] In this invention, the server includes device means for collecting emotional data, visual information, and acoustic information; processing means for standardizing the collected data, removing noise, and converting it into an analyzable format; and display means for integrating information related to emotional scales and workload and displaying it visually for the controller. This enables a detailed understanding of the emotional state and workload of team members, allowing managers to formulate appropriate work allocation strategies.

[0503] "Emotional data" refers to information that indicates an individual's emotional state, and is collected in various forms such as text, facial expressions, and voice.

[0504] "Visual information" refers to information acquired through images and videos, and is primarily data used for analyzing facial expressions.

[0505] "Acoustic information" refers to information acquired through sound, and is primarily data used to evaluate the tone and pitch of a voice.

[0506] The term "device" refers to a hardware or software component designed to perform a specific function.

[0507] A "processing machine" is a computer system or program used to preprocess collected data and convert it into an analyzable format.

[0508] An "analysis mechanism" is a system that analyzes collected data and employs methods to derive emotional evaluations and other information.

[0509] A "display device" is a device or application used to visually represent analysis results or integrated information.

[0510] A "support tool" is a means of providing information and support necessary when formulating strategies such as work allocation.

[0511] "Machine learning techniques" are algorithms and technologies used to automatically extract patterns and regularities from collected data.

[0512] An "integration device" is a means of combining different types of data, managing them centrally, and visually displaying their relationships.

[0513] This invention is a system that utilizes multimodal sentiment analysis to visualize the emotional state and workload of team members in the workplace, and is implemented to support the efficient distribution of tasks.

[0514] Data collection

[0515] Devices: Each member's device is equipped with messaging applications and collaboration tools, through which emotional data is acquired in real time. Specifically, keywords related to emotions are automatically extracted from text messages using a natural language processing node. In addition, facial expression data is captured using the camera during video conferences, and data that can be analyzed by facial recognition software is collected. Furthermore, voice data is acquired through the microphone, and the tone of voice is evaluated using a voice analysis algorithm.

[0516] Data Analysis

[0517] Server: The collected data is integrated on the server and converted into a standardized data format. Data processing languages ​​such as Python and R are used here. Then, a generative AI model calculates sentiment scores using machine learning algorithms. This model performs more advanced inference using SSMP (Sentiment State Modeling Protocol). For example, it analyzes emotional patterns within a team using prompts such as, "Is this member feeling stressed about recent project progress?"

[0518] Visualization and Strategy Planning

[0519] Server: Based on the analysis results, the server generates an interactive dashboard for administrators. This dashboard, developed using JavaScript and the D3.js library, visually displays each member's sentiment score and workload. This allows administrators to easily understand the status of team members and redistribute tasks as needed, thereby improving overall team performance.

[0520] Examples and use of prompt statements

[0521] For example, if it's necessary to verify the proposition "Is Member A frequently experiencing stress?", the administrator would check the dashboard. The dashboard displays data such as facial expressions and changes in voice tone from recent video conferences as graphs, allowing for appropriate measures to be taken based on this information.

[0522] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0523] Step 1:

[0524] Terminals: Each member's terminal receives text messages from emails and chats as input and uses natural language processing technology to extract keywords related to emotions. A built-in keyword recognition algorithm is used for keyword extraction, and emotion data is generated as output. Specifically, a text analysis module operates during this extraction process to identify positive and negative emotional tones.

[0525] Step 2:

[0526] Terminal: During the meeting, the terminal's camera is activated to capture video footage as input. Face recognition software analyzes this footage and generates facial expression data as output. Specifically, the recorded video data is analyzed in real time, and a process is included in which specific facial expressions such as smiles and surprise are quantified.

[0527] Step 3:

[0528] Terminal: During meetings, the microphone is used to collect audio data as input. A voice analysis algorithm evaluates the tone and pitch of the voice and extracts emotional features from the audio data as output. Specifically, changes in tone pitch and speed are analyzed, and stress and satisfaction levels are estimated based on this.

[0529] Step 4:

[0530] Server: The collected text, facial expression, and audio data are integrated into a standardized format, and the processor removes noise. Here, data cleaning techniques are used to ensure the consistency of each input data, and the integrated dataset is output. Specifically, data merging techniques are used to ensure data consistency.

[0531] Step 5:

[0532] Server: Using integrated data as input, a machine learning algorithm calculates an emotion score. A generative AI model is used to analyze patterns in the collected data and output the emotional intensity of team members. For example, if the emotion score exceeds a certain threshold, the system generates a prompt message indicating that the user is experiencing stress.

[0533] Step 6:

[0534] Server: The visualization module takes integrated sentiment score and workload data as input and generates a dashboard for administrators. It provides interactive graphs and charts as output, supplying administrators with visual information to formulate business strategies. Specifically, data is visualized using JavaScript and D3.js, and an easy-to-use UI is provided.

[0535] Step 7:

[0536] User (Administrator): The administrator reviews the dashboard as input data and reallocates tasks as needed. Specifically, they adjust tasks for members with high workloads and reallocate them to other members. Through interactive feedback during this process, it is possible to optimize team performance.

[0537] (Application Example 1)

[0538] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0539] In modern manufacturing environments, maximizing the efficiency of workers and automated machinery while avoiding excessive burden and stress is a crucial challenge. However, visualizing and immediately addressing these conditions is difficult. Therefore, there is a need for a system that can grasp the emotional state and workload of individual workers and machines in real time, thereby improving overall production efficiency.

[0540] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0541] In this invention, the server includes information gathering device means for collecting emotional data, audio data, and video data; data processing device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and data analysis device means for analyzing emotional states through text analysis, facial expression analysis, and audio analysis, and calculating emotional scores. This makes it possible to visualize emotional states and workloads in the production site in real time and optimize the efficiency of each worker and machine.

[0542] An "information gathering device" is a device that can collect emotional data, audio data, and video data.

[0543] A "data processing device" is a device used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0544] A "data analysis device" is a device that analyzes emotional states through text analysis, facial expression analysis, and voice analysis, and calculates an emotional score.

[0545] A "visualization device" is a device that integrates information related to emotional scores and workload, and displays the analysis results visually.

[0546] A "support system" is a system that uses visually displayed information to formulate efficient work allocation strategies.

[0547] A "management device" is a device that monitors production activities in real time and supports optimization through a visual assistance device equipped with the system.

[0548] An "analysis system" is a system that applies machine learning algorithms based on collected data to estimate emotional patterns among workers.

[0549] An "integrated system" is a system that evaluates the workload of each worker and displays the information relating that workload to emotional information.

[0550] To implement this invention, the server operates as a configuration including an information gathering device, a data processing device, a data analysis device, a visualization device, and a support system. The information gathering device acquires audio data, video data, and environmental data through multiple sensors and cameras installed on the factory production floor. This makes it possible to continuously acquire real-time information from the site.

[0551] The server preprocesses the collected data using a data processing device, removing noise and converting the format. Specifically, it uses Python or TensorFlow for data cleaning and transformation. This process prepares the data for analysis, allowing it to proceed to the next analysis step.

[0552] The server then uses data analysis equipment to perform text analysis, facial expression analysis, and voice analysis. These analysis techniques are used to output emotional states as emotional scores, which are numerical representations of emotional states. Generative AI models using machine learning (e.g., neural networks using Keras) are applied to the analysis. The results are quantified, and the emotional states of workers and machines are evaluated in real time.

[0553] The visualization device integrates emotion scores and workload-related data, visually displaying the information on an administrator dashboard. Users can then use this to develop strategies to optimize workload distribution in the field. This dashboard is projected onto smart glasses, enabling immediate action.

[0554] For example, if a worker shows an unusually high stress score, managers can immediately check the number through a dashboard and take countermeasures. For instance, if it is determined that the worker is overloaded, they can change the work shift or assign additional personnel.

[0555] An example of a prompt might be: "Design a method to analyze the team's emotional state in real time and optimize their workload, with a particular focus on managing the efficiency of robots and workers in the field."

[0556] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0557] Step 1:

[0558] The server acquires audio, video, and environmental data from the production site via multiple sensors and cameras from the information gathering device. This input data is captured in real time from the site and may contain noise or missing data. The server collects this data and prepares it for the next step.

[0559] Step 2:

[0560] The server preprocesses the collected data using a data processing device. This process removes noise and imputes missing data using Python scripts, etc. Audio and video are also converted to appropriate formats and prepared for analysis. As output, a clean and consistent dataset is sent to the next analysis step.

[0561] Step 3:

[0562] The server analyzes data that has been preprocessed by the data analysis device. Here, it performs text analysis, facial expression analysis, and speech analysis using a generative AI model. Specifically, it uses a neural network with Keras to quantify emotion scores. As a result of the analysis, numerical data representing the emotional state of each worker and device is output. This numerical data is used for visualization as an emotion score.

[0563] Step 4:

[0564] The server integrates and displays sentiment scores and workload data on the administrator's dashboard via a visualization device. The processed numerical data is visualized as interactive graphics, which users can view on the dashboard. This output allows administrators to intuitively understand the workload on the ground and obtain guidance for necessary countermeasures.

[0565] Step 5:

[0566] Users develop efficient work allocation strategies based on information displayed on the dashboard. These decisions take into account worker stress levels and equipment utilization efficiency. Users aim to optimize the work environment by adjusting work schedules and reallocating resources based on the visualized information.

[0567] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0568] This invention is a multimodal emotion analysis system that combines emotion engines, and aims to evaluate and improve team work dynamics and workload. By collecting and analyzing emotion data, audio data, and video data, this system recognizes the emotional state of team members in real time and improves the efficiency of work distribution.

[0569] Forms of data collection and emotion recognition:

[0570] Devices: Each member's device collects emotional data from text messages and emails, as well as video and audio data via webcam and microphone. This data is sent to the emotion engine to recognize the user's emotional state in real time.

[0571] Forms of data analysis and integration:

[0572] Server: The collected data is preprocessed on the server to remove noise. Then, using the emotion engine, text analysis, facial expression analysis, and voice analysis are performed to calculate individual emotion scores.

[0573] Server: Integrates calculated sentiment scores and workload data to generate a dashboard for displaying results in real time.

[0574] Forms of user feedback and strategic planning:

[0575] User (Administrator): Administrators can check each member's emotional state and workload through the dashboard. If a specific emotional change is detected, the emotion engine will automatically generate a notification requesting action.

[0576] Terminal: The terminal is used to communicate business improvement measures and new work assignments decided by the administrator to each member, and to collect feedback.

[0577] Specific example:

[0578] For example, consider a situation where a project deadline is approaching. In this case, it can be seen that a particular member's stress level is rising through their emotional engine. Based on this data, the manager can check the emotional score on a dashboard and identify which tasks are causing that member particular stress. The manager can then propose task redistribution to that member and arrange for the workload to be distributed among other members. As a result, emotional burden can be reduced while improving the overall performance of the team.

[0579] In this configuration, the system leverages an emotion engine to monitor the emotional state of team members in real time, providing powerful support for appropriate feedback and work improvement.

[0580] The following describes the processing flow.

[0581] Step 1:

[0582] Devices: Each user's device collects emotional data from text messages and emails. In addition, it acquires video data using a webcam and audio data through a microphone. This data is important for understanding the user's emotional state.

[0583] Step 2:

[0584] Server: Receives and preprocesses collected data. Removes noise and converts the data into a format suitable for analysis. This enables accurate analysis.

[0585] Step 3:

[0586] Server: Inputs pre-processed data into the emotion engine and performs text analysis, facial expression analysis, and voice analysis. Emotional states are evaluated from each data type, and an emotion score is calculated.

[0587] Step 4:

[0588] Server: Integrate emotion scores with workload data to assess the overall state of each member. This visualizes the relationship between emotion and workload.

[0589] Step 5:

[0590] Server: Based on the integration results, it generates an administrator dashboard. This dashboard displays real-time, fluctuating sentiment scores and workload graphs.

[0591] Step 6:

[0592] User (Administrator): Utilize the dashboard to check the emotional state and workload of specific members. If there is a significant change in emotional state, receive an automatic notification from the emotion engine and consider countermeasures.

[0593] Step 7:

[0594] Terminal: As needed, the administrator notifies members of any decided business improvement measures or instructions and sends the results to each member's terminal. At the same time, feedback on the measures is collected and used to improve future operations.

[0595] (Example 2)

[0596] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0597] In modern teamwork, understanding each member's emotional state and workload in real time and efficiently distributing tasks is a major challenge. In particular, emotional stress and overload can reduce work efficiency, making it essential to manage this information appropriately. However, conventional systems struggle to comprehensively evaluate emotional states and workloads, making it difficult to respond quickly and appropriately.

[0598] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0599] In this invention, the server includes device means for acquiring emotional information, acoustic information, and visual information; processing means for preprocessing the acquired information, removing unnecessary signals, and converting it into an analyzable format; and analysis device means for evaluating emotional states and calculating an emotional index through character information analysis, facial display analysis, and acoustic analysis. This makes it possible to comprehensively evaluate the emotional states and workload of team members in real time and to achieve optimal work distribution.

[0600] "Emotional information" refers to data that indicates emotions, extracted from the user's text, facial expressions, voice, etc.

[0601] "Acoustic information" refers to information about the characteristics and tone of sound obtained from the user's voice data.

[0602] "Visual information" refers to image and video data acquired through devices such as cameras.

[0603] "Device means" refers to hardware or software mechanisms used to acquire, process, and analyze data.

[0604] A "processing device" is a mechanism that performs processing to convert acquired data into a format suitable for analysis.

[0605] An "analysis device means" is a mechanism that analyzes acquired data and calculates a specific result.

[0606] The "emotional index" is a numerical value calculated through analysis that quantitatively indicates the emotional state of a user.

[0607] "Task distribution" is the process of efficiently distributing work among team members.

[0608] This embodiment of the invention is a system that uses emotional information, acoustic information, and visual information to evaluate the emotional state and workload of team members in real time, and to streamline the distribution of tasks.

[0609] Hardware and software for data collection:

[0610] Devices: Each member's device is equipped with a microphone and camera to collect audio and video data. In addition, text data is extracted from communication applications on the device.

[0611] Hardware and software for data processing and analysis:

[0612] Server: The collected data is preprocessed on the server and analyzed using an emotion engine. The server analyzes text using a natural language processing library, analyzes facial expressions using image processing algorithms, and analyzes acoustic information using speech analysis software.

[0613] The server calculates an emotional index from these analysis results and integrates it with workload data.

[0614] Displaying results and feedback:

[0615] Server to User (Administrator): The integrated data is visually displayed to administrators through a dashboard. The dashboard shows team sentiment and workload in graph and chart format.

[0616] User Notifications: When a specific emotional shift is detected, the system automatically sends a notification to the administrator. This allows for quick adjustments to work processes.

[0617] Specific example:

[0618] If a project deadline is approaching and a particular member's emotional index indicates stress, the administrator can check this information through the dashboard. They can then redistribute the member's workload, spreading the burden across other members.

[0619] Example of a prompt:

[0620] "As the project deadline approaches, please tell us what changes you've observed in the team members' emotions."

[0621] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0622] Step 1:

[0623] The device collects acoustic and visual information using a microphone and camera. Furthermore, it acquires text data containing emotional information from communication applications. The input data consists of raw audio, video, and text, which, once collected, prepares the system to understand the user's emotional state. The output is a raw emotional dataset.

[0624] Step 2:

[0625] The server receives the collected data and performs noise reduction and data cleaning. Specifically, it removes background noise and standardizes the spelling and formatting of text data. The input is raw sentiment data sent from the terminal, and the output is pre-processed data suitable for analysis.

[0626] Step 3:

[0627] The server performs analysis on pre-processed data using an emotion engine. This includes text analysis using natural language processing, facial expression analysis using a face detection algorithm, and speech analysis using acoustic analysis software. The input is pre-processed data, and the output is an emotion index indicating emotional state.

[0628] Step 4:

[0629] The server integrates the calculated sentiment index with workload information. This generates an integrated report showing the relationship between emotional state and workload. The inputs are sentiment index and workload data, and the output is the integrated dashboard display data.

[0630] Step 5:

[0631] Users (administrators) use a dashboard to monitor each member's emotional state and workload. The dashboard visually presents information, and automatic notifications are triggered when specific emotional changes occur. Input is integrated dashboard display data, and output is decision-making information for business improvement.

[0632] (Application Example 2)

[0633] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0634] In modern industrial production environments, there is a need to improve production efficiency and ensure worker safety simultaneously by understanding workers' emotional states and workloads in real time. However, there is a challenge in the lack of means to accurately assess emotional states and automatically adjust work pace appropriately. This makes it easy for situations to arise where workers' stress levels increase or work efficiency decreases.

[0635] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0636] In this invention, the server includes terminal device means for collecting emotional data, audio data, and video data; control device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and operating device means having an automatic control function for adjusting the work pace based on the emotional state of the worker. This makes it possible to analyze the emotional state of the worker in real time and automatically adjust the work as needed.

[0637] "Emotional data" refers to information that indicates the emotional state of a worker, and includes features extracted from text, facial expressions, and voice.

[0638] "Voice data" refers to audio information collected to analyze the emotional state of workers, and includes characteristics such as tone and speed of voice.

[0639] "Video data" refers to visual information collected to analyze the facial expressions and movements of workers, and includes images or videos captured by cameras.

[0640] "Terminal device" refers to a device used to collect emotional data, audio data, and video data, and refers to hardware worn or used by workers.

[0641] A "control system" refers to a computer system used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0642] An "analysis device" is a system that uses collected data to analyze emotional states and calculate an emotional score.

[0643] A "display device" is a display or monitoring system for visually representing emotion scores and workload data.

[0644] A "support device" is a system that assists managers in formulating efficient work allocation strategies based on visually displayed data.

[0645] "Automatic control function" refers to a mechanism that automatically adjusts the work pace based on the worker's emotional state.

[0646] "Operating device" refers to equipment or programs used to automatically perform work adjustments.

[0647] This invention is a system that analyzes the emotional state and workload of workers in real time to improve productivity and safety. The system includes a terminal device, a control device, an analysis device, a display device, a support device, and an operating device with automatic control functions.

[0648] Terminal devices are devices worn or used by workers that collect emotional data, audio data, and video data. These include smart glasses and wearable devices. The collected data is preprocessed by a control device to remove noise before being sent to an analysis device.

[0649] The analysis device analyzes the collected data and evaluates the emotional state. This analysis uses cloud-based analysis services (e.g., Amazon Rekognition or Microsoft Azure Emotion API). The analysis results are calculated as an emotional score and then sent to the display device.

[0650] The display device visually represents emotion scores and workload data, allowing managers to view them in real time. This enables managers to grasp the current status of workers at a glance and easily make decisions to optimize work distribution based on the strategies presented by the support device.

[0651] The control device is equipped with an automatic control function that adjusts the work pace based on the analysis results. Specifically, it can temporarily slow down work if the worker's stress level increases, or redistribute tasks to other workers.

[0652] For example, if a worker on a production line is experiencing excessive stress, this information is detected through the system. An analysis device processes the data and notifies management of the need to adjust the work pace. As a result, the burden on workers is reduced, and a production environment that balances safety and efficiency is achieved.

[0653] An example of a prompt is: "Propose a factory worker emotion monitoring system. Explain how to use an emotion engine to detect worker emotions in real time and improve work efficiency and safety. Mention specific data collection methods, analysis techniques, and feedback mechanisms." Using this prompt, the generated AI model can propose specific control guidelines and provide more effective operational methods.

[0654] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0655] Step 1:

[0656] The terminal collects emotional data, audio data, and video data from the worker. This uses cameras and microphones built into smart glasses, and the data is captured in real time. The input data includes facial expressions as video and tone from audio, and the output is raw, unprocessed data.

[0657] Step 2:

[0658] The server receives raw, unprocessed data sent from the terminal and performs preprocessing. Specifically, it applies a noise reduction filter and converts the data into an analyzable format. The input is raw data, and the output is clear data with noise removed.

[0659] Step 3:

[0660] The server uses pre-processed data to perform analysis using a generative AI model. A cloud-based sentiment analysis service is used to calculate sentiment scores. The input is clear data, and the output is the analysis results, including each worker's sentiment score. Specifically, the process involves text analysis, facial expression analysis, and voice analysis.

[0661] Step 4:

[0662] The server integrates sentiment scores and workload data and sends it to a display device as visualized information. The input is sentiment scores and workload data, and the output is a visually easy-to-understand dashboard. Specifically, workload and sentiment status are displayed as graphs and charts.

[0663] Step 5:

[0664] The user (manager) reviews the displayed dashboard information and, if necessary, develops a work distribution strategy using support devices. The input is dashboard information, and the output is an optimized work distribution command. Specific actions include strategic decisions to adjust the workload balance for each worker.

[0665] Step 6:

[0666] The control device adjusts the work pace using automatic control functions based on work distribution commands from the user. The input is the work distribution command, and the output is the adjusted work pace. Specific actions include task redistribution and slowing down the work pace.

[0667] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0668] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0669] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0670] [Fourth Embodiment]

[0671] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0672] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0673] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0674] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0675] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0676] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0677] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0678] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0679] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0680] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0681] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0682] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0683] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] As an embodiment of the present invention, a system for team dynamics and workload evaluation utilizing multimodal sentiment analysis is described. This system supports efficient work distribution by visualizing the emotional state and workload of each member of a team, utilizing specific devices, processing devices, and analysis devices.

[0685] Data collection methods:

[0686] Devices: Each member's device continuously collects sentiment data from messaging applications and collaboration tools. This includes keyword extraction and pattern analysis from text messages.

[0687] Device: During video conferences, it collects video data using the camera to obtain information for facial expression analysis. It also collects audio data via the microphone to evaluate voice tone.

[0688] Forms of data analysis:

[0689] Server: Integrates collected data and analyzes emotional states using machine learning algorithms. The server calculates an emotional score for each member, expressing the degree of different emotions numerically.

[0690] Server: In addition to the emotion score, the workload is evaluated from user-provided survey data, and both sets of data are combined to understand the overall state of the team.

[0691] Visualization of results and forms of strategic planning:

[0692] Server: Generates an administrator visualization dashboard based on integrated data. This dashboard includes interactive graphics to identify sentiment scores, workload imbalances, and stress levels.

[0693] User (Administrator): Review analysis results through the dashboard and formulate strategies to optimize workload distribution. For example, if a particular member is overburdened, the administrator will adjust their workload and redistribute tasks to other members.

[0694] Specific example:

[0695] For example, suppose emotion scores reveal that a specific member of a team is regularly experiencing stress. In this case, the administrator can use the dashboard to examine the detailed analysis of the member's voice and video data to identify the source of the stress. They can then improve the work environment by reallocating workloads or suggesting leave as needed.

[0696] As described above, the system of the present invention is highly effective as a tool for accurately collecting and analyzing emotional and workload data to improve the overall performance of the team. This embodiment allows managers to quickly address problems within the team and manage the efficiency and stress levels of individual members in a balanced manner.

[0697] The following describes the processing flow.

[0698] Step 1:

[0699] Terminals: Each member's terminal collects text data from messaging applications. This includes a process of extracting keywords and phrases to estimate sentiment.

[0700] Step 2:

[0701] Device: Uses a webcam and microphone to collect video and audio data. Video data is used as material for facial expression analysis, and audio data is used for voice tone analysis.

[0702] Step 3:

[0703] Server: Preprocesses collected text, audio, and video data. Prepares the data for analysis through noise reduction and standardization of data formats.

[0704] Step 4:

[0705] Server: Uses machine learning algorithms to analyze emotional states from each data point. It calculates individual emotional scores for text, audio, and video data, and then integrates them.

[0706] Step 5:

[0707] Server: Analyzes emotional scores in conjunction with user-provided workload survey data. This allows for the evaluation of the correlation between workload balance among team members and their emotional state.

[0708] Step 6:

[0709] Server: Uses the analysis results to generate a dashboard for administrators. This dashboard displays graphs that visualize things like changes in emotional states over time and the distribution of workload.

[0710] Step 7:

[0711] User (Administrator): Refer to the dashboard to check for stress levels and workload imbalances among team members. Based on the problems identified, devise work reallocation and improvement measures.

[0712] Step 8:

[0713] Terminal: Notifies members of new work assignments and countermeasures decided by the administrator, and requests feedback through the system. Collect feedback and use it for continuous improvement.

[0714] (Example 1)

[0715] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0716] In today's workplace, accurately understanding the emotions and workload of team members and achieving efficient work distribution is essential. However, there is a lack of effective systems that can centrally analyze diverse information on emotions and workload, and easily formulate business strategies based on this information.

[0717] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0718] In this invention, the server includes device means for collecting emotional data, visual information, and acoustic information; processing means for standardizing the collected data, removing noise, and converting it into an analyzable format; and display means for integrating information related to emotional scales and workload and displaying it visually for the controller. This enables a detailed understanding of the emotional state and workload of team members, allowing managers to formulate appropriate work allocation strategies.

[0719] "Emotional data" refers to information that indicates an individual's emotional state, and is collected in various forms such as text, facial expressions, and voice.

[0720] "Visual information" refers to information acquired through images and videos, and is primarily data used for analyzing facial expressions.

[0721] "Acoustic information" refers to information acquired through sound, and is primarily data used to evaluate the tone and pitch of a voice.

[0722] The term "device" refers to a hardware or software component designed to perform a specific function.

[0723] A "processing machine" is a computer system or program used to preprocess collected data and convert it into an analyzable format.

[0724] An "analysis mechanism" is a system that analyzes collected data and employs methods to derive emotional evaluations and other information.

[0725] A "display device" is a device or application used to visually represent analysis results or integrated information.

[0726] A "support tool" is a means of providing information and support necessary when formulating strategies such as work allocation.

[0727] "Machine learning techniques" are algorithms and technologies used to automatically extract patterns and regularities from collected data.

[0728] An "integration device" is a means of combining different types of data, managing them centrally, and visually displaying their relationships.

[0729] This invention is a system that utilizes multimodal sentiment analysis to visualize the emotional state and workload of team members in the workplace, and is implemented to support the efficient distribution of tasks.

[0730] Data collection

[0731] Devices: Each member's device is equipped with messaging applications and collaboration tools, through which emotional data is acquired in real time. Specifically, keywords related to emotions are automatically extracted from text messages using a natural language processing node. In addition, facial expression data is captured using the camera during video conferences, and data that can be analyzed by facial recognition software is collected. Furthermore, voice data is acquired through the microphone, and the tone of voice is evaluated using a voice analysis algorithm.

[0732] Data Analysis

[0733] Server: The collected data is integrated on the server and converted into a standardized data format. Data processing languages ​​such as Python and R are used here. Then, a generative AI model calculates sentiment scores using machine learning algorithms. This model performs more advanced inference using SSMP (Sentiment State Modeling Protocol). For example, it analyzes emotional patterns within a team using prompts such as, "Is this member feeling stressed about recent project progress?"

[0734] Visualization and Strategy Planning

[0735] Server: Based on the analysis results, the server generates an interactive dashboard for administrators. This dashboard, developed using JavaScript and the D3.js library, visually displays each member's sentiment score and workload. This allows administrators to easily understand the status of team members and redistribute tasks as needed, thereby improving overall team performance.

[0736] Examples and use of prompt statements

[0737] For example, if it's necessary to verify the proposition "Is Member A frequently experiencing stress?", the administrator would check the dashboard. The dashboard displays data such as facial expressions and changes in voice tone from recent video conferences as graphs, allowing for appropriate measures to be taken based on this information.

[0738] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0739] Step 1:

[0740] Terminals: Each member's terminal receives text messages from emails and chats as input and uses natural language processing technology to extract keywords related to emotions. A built-in keyword recognition algorithm is used for keyword extraction, and emotion data is generated as output. Specifically, a text analysis module operates during this extraction process to identify positive and negative emotional tones.

[0741] Step 2:

[0742] Terminal: During the meeting, the terminal's camera is activated to capture video footage as input. Face recognition software analyzes this footage and generates facial expression data as output. Specifically, the recorded video data is analyzed in real time, and a process is included in which specific facial expressions such as smiles and surprise are quantified.

[0743] Step 3:

[0744] Terminal: During meetings, the microphone is used to collect audio data as input. A voice analysis algorithm evaluates the tone and pitch of the voice and extracts emotional features from the audio data as output. Specifically, changes in tone pitch and speed are analyzed, and stress and satisfaction levels are estimated based on this.

[0745] Step 4:

[0746] Server: The collected text, facial expression, and audio data are integrated into a standardized format, and the processor removes noise. Here, data cleaning techniques are used to ensure the consistency of each input data, and the integrated dataset is output. Specifically, data merging techniques are used to ensure data consistency.

[0747] Step 5:

[0748] Server: Using integrated data as input, a machine learning algorithm calculates an emotion score. A generative AI model is used to analyze patterns in the collected data and output the emotional intensity of team members. For example, if the emotion score exceeds a certain threshold, the system generates a prompt message indicating that the user is experiencing stress.

[0749] Step 6:

[0750] Server: The visualization module takes integrated sentiment score and workload data as input and generates a dashboard for administrators. It provides interactive graphs and charts as output, supplying administrators with visual information to formulate business strategies. Specifically, data is visualized using JavaScript and D3.js, and an easy-to-use UI is provided.

[0751] Step 7:

[0752] User (Administrator): The administrator reviews the dashboard as input data and reallocates tasks as needed. Specifically, they adjust tasks for members with high workloads and reallocate them to other members. Through interactive feedback during this process, it is possible to optimize team performance.

[0753] (Application Example 1)

[0754] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0755] In modern manufacturing environments, maximizing the efficiency of workers and automated machinery while avoiding excessive burden and stress is a crucial challenge. However, visualizing and immediately addressing these conditions is difficult. Therefore, there is a need for a system that can grasp the emotional state and workload of individual workers and machines in real time, thereby improving overall production efficiency.

[0756] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0757] In this invention, the server includes information gathering device means for collecting emotional data, audio data, and video data; data processing device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and data analysis device means for analyzing emotional states through text analysis, facial expression analysis, and audio analysis, and calculating emotional scores. This makes it possible to visualize emotional states and workloads in the production site in real time and optimize the efficiency of each worker and machine.

[0758] An "information gathering device" is a device that can collect emotional data, audio data, and video data.

[0759] A "data processing device" is a device used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0760] A "data analysis device" is a device that analyzes emotional states through text analysis, facial expression analysis, and voice analysis, and calculates an emotional score.

[0761] A "visualization device" is a device that integrates information related to emotional scores and workload, and displays the analysis results visually.

[0762] A "support system" is a system that uses visually displayed information to formulate efficient work allocation strategies.

[0763] A "management device" is a device that monitors production activities in real time and supports optimization through a visual assistance device equipped with the system.

[0764] An "analysis system" is a system that applies machine learning algorithms based on collected data to estimate emotional patterns among workers.

[0765] An "integrated system" is a system that evaluates the workload of each worker and displays the information relating that workload to emotional information.

[0766] To implement this invention, the server operates as a configuration including an information gathering device, a data processing device, a data analysis device, a visualization device, and a support system. The information gathering device acquires audio data, video data, and environmental data through multiple sensors and cameras installed on the factory production floor. This makes it possible to continuously acquire real-time information from the site.

[0767] The server preprocesses the collected data using a data processing device, removing noise and converting the format. Specifically, it uses Python or TensorFlow for data cleaning and transformation. This process prepares the data for analysis, allowing it to proceed to the next analysis step.

[0768] The server then uses data analysis equipment to perform text analysis, facial expression analysis, and voice analysis. These analysis techniques are used to output emotional states as emotional scores, which are numerical representations of emotional states. Generative AI models using machine learning (e.g., neural networks using Keras) are applied to the analysis. The results are quantified, and the emotional states of workers and machines are evaluated in real time.

[0769] The visualization device integrates emotion scores and workload-related data, visually displaying the information on an administrator dashboard. Users can then use this to develop strategies to optimize workload distribution in the field. This dashboard is projected onto smart glasses, enabling immediate action.

[0770] For example, if a worker shows an unusually high stress score, managers can immediately check the number through a dashboard and take countermeasures. For instance, if it is determined that the worker is overloaded, they can change the work shift or assign additional personnel.

[0771] An example of a prompt might be: "Design a method to analyze the team's emotional state in real time and optimize their workload, with a particular focus on managing the efficiency of robots and workers in the field."

[0772] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0773] Step 1:

[0774] The server acquires audio, video, and environmental data from the production site via multiple sensors and cameras from the information gathering device. This input data is captured in real time from the site and may contain noise or missing data. The server collects this data and prepares it for the next step.

[0775] Step 2:

[0776] The server preprocesses the collected data using a data processing device. This process removes noise and imputes missing data using Python scripts, etc. Audio and video are also converted to appropriate formats and prepared for analysis. As output, a clean and consistent dataset is sent to the next analysis step.

[0777] Step 3:

[0778] The server analyzes data that has been preprocessed by the data analysis device. Here, it performs text analysis, facial expression analysis, and speech analysis using a generative AI model. Specifically, it uses a neural network with Keras to quantify emotion scores. As a result of the analysis, numerical data representing the emotional state of each worker and device is output. This numerical data is used for visualization as an emotion score.

[0779] Step 4:

[0780] The server integrates and displays sentiment scores and workload data on the administrator's dashboard via a visualization device. The processed numerical data is visualized as interactive graphics, which users can view on the dashboard. This output allows administrators to intuitively understand the workload on the ground and obtain guidance for necessary countermeasures.

[0781] Step 5:

[0782] Users develop efficient work allocation strategies based on information displayed on the dashboard. These decisions take into account worker stress levels and equipment utilization efficiency. Users aim to optimize the work environment by adjusting work schedules and reallocating resources based on the visualized information.

[0783] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0784] This invention is a multimodal emotion analysis system that combines emotion engines, and aims to evaluate and improve team work dynamics and workload. By collecting and analyzing emotion data, audio data, and video data, this system recognizes the emotional state of team members in real time and improves the efficiency of work distribution.

[0785] Forms of data collection and emotion recognition:

[0786] Devices: Each member's device collects emotional data from text messages and emails, as well as video and audio data via webcam and microphone. This data is sent to the emotion engine to recognize the user's emotional state in real time.

[0787] Forms of data analysis and integration:

[0788] Server: The collected data is preprocessed on the server to remove noise. Then, using the emotion engine, text analysis, facial expression analysis, and voice analysis are performed to calculate individual emotion scores.

[0789] Server: Integrates calculated sentiment scores and workload data to generate a dashboard for displaying results in real time.

[0790] Forms of user feedback and strategic planning:

[0791] User (Administrator): Administrators can check each member's emotional state and workload through the dashboard. If a specific emotional change is detected, the emotion engine will automatically generate a notification requesting action.

[0792] Terminal: The terminal is used to communicate business improvement measures and new work assignments decided by the administrator to each member, and to collect feedback.

[0793] Specific example:

[0794] For example, consider a situation where a project deadline is approaching. In this case, it can be seen that a particular member's stress level is rising through their emotional engine. Based on this data, the manager can check the emotional score on a dashboard and identify which tasks are causing that member particular stress. The manager can then propose task redistribution to that member and arrange for the workload to be distributed among other members. As a result, emotional burden can be reduced while improving the overall performance of the team.

[0795] In this configuration, the system leverages an emotion engine to monitor the emotional state of team members in real time, providing powerful support for appropriate feedback and work improvement.

[0796] The following describes the processing flow.

[0797] Step 1:

[0798] Devices: Each user's device collects emotional data from text messages and emails. In addition, it acquires video data using a webcam and audio data through a microphone. This data is important for understanding the user's emotional state.

[0799] Step 2:

[0800] Server: Receives and preprocesses collected data. Removes noise and converts the data into a format suitable for analysis. This enables accurate analysis.

[0801] Step 3:

[0802] Server: Inputs pre-processed data into the emotion engine and performs text analysis, facial expression analysis, and voice analysis. Emotional states are evaluated from each data type, and an emotion score is calculated.

[0803] Step 4:

[0804] Server: Integrate emotion scores with workload data to assess the overall state of each member. This visualizes the relationship between emotion and workload.

[0805] Step 5:

[0806] Server: Based on the integration results, it generates an administrator dashboard. This dashboard displays real-time, fluctuating sentiment scores and workload graphs.

[0807] Step 6:

[0808] User (Administrator): Utilize the dashboard to check the emotional state and workload of specific members. If there is a significant change in emotional state, receive an automatic notification from the emotion engine and consider countermeasures.

[0809] Step 7:

[0810] Terminal: As needed, the administrator notifies members of any decided business improvement measures or instructions and sends the results to each member's terminal. At the same time, feedback on the measures is collected and used to improve future operations.

[0811] (Example 2)

[0812] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0813] In modern teamwork, understanding each member's emotional state and workload in real time and efficiently distributing tasks is a major challenge. In particular, emotional stress and overload can reduce work efficiency, making it essential to manage this information appropriately. However, conventional systems struggle to comprehensively evaluate emotional states and workloads, making it difficult to respond quickly and appropriately.

[0814] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0815] In this invention, the server includes device means for acquiring emotional information, acoustic information, and visual information; processing means for preprocessing the acquired information, removing unnecessary signals, and converting it into an analyzable format; and analysis device means for evaluating emotional states and calculating an emotional index through character information analysis, facial display analysis, and acoustic analysis. This makes it possible to comprehensively evaluate the emotional states and workload of team members in real time and to achieve optimal work distribution.

[0816] "Emotional information" refers to data that indicates emotions, extracted from the user's text, facial expressions, voice, etc.

[0817] "Acoustic information" refers to information about the characteristics and tone of sound obtained from the user's voice data.

[0818] "Visual information" refers to image and video data acquired through devices such as cameras.

[0819] "Device means" refers to hardware or software mechanisms used to acquire, process, and analyze data.

[0820] A "processing device" is a mechanism that performs processing to convert acquired data into a format suitable for analysis.

[0821] An "analysis device means" is a mechanism that analyzes acquired data and calculates a specific result.

[0822] The "emotional index" is a numerical value calculated through analysis that quantitatively indicates the emotional state of a user.

[0823] "Task distribution" is the process of efficiently distributing work among team members.

[0824] This embodiment of the invention is a system that uses emotional information, acoustic information, and visual information to evaluate the emotional state and workload of team members in real time, and to streamline the distribution of tasks.

[0825] Hardware and software for data collection:

[0826] Devices: Each member's device is equipped with a microphone and camera to collect audio and video data. In addition, text data is extracted from communication applications on the device.

[0827] Hardware and software for data processing and analysis:

[0828] Server: The collected data is preprocessed on the server and analyzed using an emotion engine. The server analyzes text using a natural language processing library, analyzes facial expressions using image processing algorithms, and analyzes acoustic information using speech analysis software.

[0829] The server calculates an emotional index from these analysis results and integrates it with workload data.

[0830] Displaying results and feedback:

[0831] Server to User (Administrator): The integrated data is visually displayed to administrators through a dashboard. The dashboard shows team sentiment and workload in graph and chart format.

[0832] User Notifications: When a specific emotional shift is detected, the system automatically sends a notification to the administrator. This allows for quick adjustments to work processes.

[0833] Specific example:

[0834] If a project deadline is approaching and a particular member's emotional index indicates stress, the administrator can check this information through the dashboard. They can then redistribute the member's workload, spreading the burden across other members.

[0835] Example of a prompt:

[0836] "As the project deadline approaches, please tell us what changes you've observed in the team members' emotions."

[0837] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0838] Step 1:

[0839] The device collects acoustic and visual information using a microphone and camera. Furthermore, it acquires text data containing emotional information from communication applications. The input data consists of raw audio, video, and text, which, once collected, prepares the system to understand the user's emotional state. The output is a raw emotional dataset.

[0840] Step 2:

[0841] The server receives the collected data and performs noise reduction and data cleaning. Specifically, it removes background noise and standardizes the spelling and formatting of text data. The input is raw sentiment data sent from the terminal, and the output is pre-processed data suitable for analysis.

[0842] Step 3:

[0843] The server performs analysis on pre-processed data using an emotion engine. This includes text analysis using natural language processing, facial expression analysis using a face detection algorithm, and speech analysis using acoustic analysis software. The input is pre-processed data, and the output is an emotion index indicating emotional state.

[0844] Step 4:

[0845] The server integrates the calculated sentiment index with workload information. This generates an integrated report showing the relationship between emotional state and workload. The inputs are sentiment index and workload data, and the output is the integrated dashboard display data.

[0846] Step 5:

[0847] Users (administrators) use a dashboard to monitor each member's emotional state and workload. The dashboard visually presents information, and automatic notifications are triggered when specific emotional changes occur. Input is integrated dashboard display data, and output is decision-making information for business improvement.

[0848] (Application Example 2)

[0849] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0850] In modern industrial production environments, there is a need to improve production efficiency and ensure worker safety simultaneously by understanding workers' emotional states and workloads in real time. However, there is a challenge in the lack of means to accurately assess emotional states and automatically adjust work pace appropriately. This makes it easy for situations to arise where workers' stress levels increase or work efficiency decreases.

[0851] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0852] In this invention, the server includes terminal device means for collecting emotional data, audio data, and video data; control device means for preprocessing the collected data, removing noise, and converting it into an analyzable format; and operating device means having an automatic control function for adjusting the work pace based on the emotional state of the worker. This makes it possible to analyze the emotional state of the worker in real time and automatically adjust the work as needed.

[0853] "Emotional data" refers to information that indicates the emotional state of a worker, and includes features extracted from text, facial expressions, and voice.

[0854] "Voice data" refers to audio information collected to analyze the emotional state of workers, and includes characteristics such as tone and speed of voice.

[0855] "Video data" refers to visual information collected to analyze the facial expressions and movements of workers, and includes images or videos captured by cameras.

[0856] "Terminal device" refers to a device used to collect emotional data, audio data, and video data, and refers to hardware worn or used by workers.

[0857] A "control system" refers to a computer system used to preprocess collected data, remove noise, and convert it into an analyzable format.

[0858] An "analysis device" is a system that uses collected data to analyze emotional states and calculate an emotional score.

[0859] A "display device" is a display or monitoring system for visually representing emotion scores and workload data.

[0860] A "support device" is a system that assists managers in formulating efficient work allocation strategies based on visually displayed data.

[0861] "Automatic control function" refers to a mechanism that automatically adjusts the work pace based on the worker's emotional state.

[0862] "Operating device" refers to equipment or programs used to automatically perform work adjustments.

[0863] This invention is a system that analyzes the emotional state and workload of workers in real time to improve productivity and safety. The system includes a terminal device, a control device, an analysis device, a display device, a support device, and an operating device with automatic control functions.

[0864] Terminal devices are devices worn or used by workers that collect emotional data, audio data, and video data. These include smart glasses and wearable devices. The collected data is preprocessed by a control device to remove noise before being sent to an analysis device.

[0865] The analysis device analyzes the collected data and evaluates the emotional state. This analysis uses cloud-based analysis services (e.g., Amazon Rekognition or Microsoft Azure Emotion API). The analysis results are calculated as an emotional score and then sent to the display device.

[0866] The display device visually represents emotion scores and workload data, allowing managers to view them in real time. This enables managers to grasp the current status of workers at a glance and easily make decisions to optimize work distribution based on the strategies presented by the support device.

[0867] The control device is equipped with an automatic control function that adjusts the work pace based on the analysis results. Specifically, it can temporarily slow down work if the worker's stress level increases, or redistribute tasks to other workers.

[0868] For example, if a worker on a production line is experiencing excessive stress, this information is detected through the system. An analysis device processes the data and notifies management of the need to adjust the work pace. As a result, the burden on workers is reduced, and a production environment that balances safety and efficiency is achieved.

[0869] An example of a prompt is: "Propose a factory worker emotion monitoring system. Explain how to use an emotion engine to detect worker emotions in real time and improve work efficiency and safety. Mention specific data collection methods, analysis techniques, and feedback mechanisms." Using this prompt, the generated AI model can propose specific control guidelines and provide more effective operational methods.

[0870] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0871] Step 1:

[0872] The terminal collects emotional data, audio data, and video data from the worker. This uses cameras and microphones built into smart glasses, and the data is captured in real time. The input data includes facial expressions as video and tone from audio, and the output is raw, unprocessed data.

[0873] Step 2:

[0874] The server receives raw, unprocessed data sent from the terminal and performs preprocessing. Specifically, it applies a noise reduction filter and converts the data into an analyzable format. The input is raw data, and the output is clear data with noise removed.

[0875] Step 3:

[0876] The server uses pre-processed data to perform analysis using a generative AI model. A cloud-based sentiment analysis service is used to calculate sentiment scores. The input is clear data, and the output is the analysis results, including each worker's sentiment score. Specifically, the process involves text analysis, facial expression analysis, and voice analysis.

[0877] Step 4:

[0878] The server integrates sentiment scores and workload data and sends it to a display device as visualized information. The input is sentiment scores and workload data, and the output is a visually easy-to-understand dashboard. Specifically, workload and sentiment status are displayed as graphs and charts.

[0879] Step 5:

[0880] The user (manager) reviews the displayed dashboard information and, if necessary, develops a work distribution strategy using support devices. The input is dashboard information, and the output is an optimized work distribution command. Specific actions include strategic decisions to adjust the workload balance for each worker.

[0881] Step 6:

[0882] The control device adjusts the work pace using automatic control functions based on work distribution commands from the user. The input is the work distribution command, and the output is the adjusted work pace. Specific actions include task redistribution and slowing down the work pace.

[0883] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0884] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0885] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0886] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0887] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0888] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0889] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0890] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0891] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0892] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0893] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0894] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0895] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0896] 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.

[0897] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0898] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0899] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0900] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0901] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0902] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0903] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0904] The following is further disclosed regarding the embodiments described above.

[0905] (Claim 1)

[0906] A device means for collecting emotional data, audio data, and video data,

[0907] Processing means for preprocessing collected data, removing noise, and converting it into an analyzable format,

[0908] An analysis device means for analyzing emotional states through text analysis, facial expression analysis, and voice analysis, and for calculating an emotional score,

[0909] A display device for integrating emotional scores and data related to workload and visually displaying them for administrators,

[0910] A support device for formulating an efficient work allocation strategy using visually displayed data,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, further comprising an analysis device means for applying machine learning algorithms to various collected data and estimating emotional patterns among team members.

[0914] (Claim 3)

[0915] The system according to claim 1, further comprising an integrated device means for evaluating the workload of each member and displaying the workload data in association with emotional data.

[0916] "Example 1"

[0917] (Claim 1)

[0918] A device and means for collecting emotional data, visual information, and acoustic information,

[0919] A processing machine means for standardizing the collected data, removing noise, and converting it into an analyzable format,

[0920] An analytical mechanism for evaluating emotional states and calculating an emotional scale through the analysis of textual information, facial expression, and acoustic analysis,

[0921] A display device for integrating information related to emotional scales and workload, and visually displaying it for the controller,

[0922] A means of assisting the formulation of an efficient work allocation strategy using the displayed information,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, which applies machine learning techniques to a diverse range of collected information to evaluate the regularity of emotions among group members.

[0926] (Claim 3)

[0927] A system according to claim 1 for evaluating the workload of each member and displaying the workload information in association with emotional information.

[0928] "Application Example 1"

[0929] (Claim 1)

[0930] Information gathering device means for collecting emotional data, audio data, and video data,

[0931] A data processing device means for preprocessing collected data, removing noise, and converting it into an analyzable format,

[0932] A data analysis device means for analyzing emotional states and calculating emotional scores through text analysis, facial expression analysis, and voice analysis,

[0933] A visualization device means for integrating information related to emotional scores and workload, and for visually displaying the analysis results,

[0934] A support system for formulating efficient work allocation strategies using visually displayed information,

[0935] This system includes a management device that monitors in real time through a visual assistance device equipped with this system, and supports the optimization of production activities.

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, further comprising an analytical system means for applying machine learning algorithms using various collected data to estimate emotional patterns among workers and optimize the production process.

[0939] (Claim 3)

[0940] The system according to claim 1, further comprising an integrated system means for evaluating the workload of each worker, displaying the workload information in association with emotional information, and realizing work assignments according to the situation.

[0941] "Example 2 of combining an emotion engine"

[0942] (Claim 1)

[0943] A device and means for acquiring emotional information, acoustic information, and visual information,

[0944] Processing means for preprocessing acquired information, removing unnecessary signals, and converting it into an analyzable format,

[0945] An analysis device means for evaluating emotional states and calculating an emotional index through textual information analysis, facial display analysis, and acoustic analysis,

[0946] A display device for integrating information related to emotional index and workload and visually displaying it for administrators,

[0947] A support device means for formulating an optimal work distribution strategy using visually displayed information,

[0948] A system that includes this.

[0949] (Claim 2)

[0950] The system according to claim 1, further comprising an analysis device means for applying a machine learning algorithm using diverse acquired information to infer the emotional characteristics among team members.

[0951] (Claim 3)

[0952] The system according to claim 1, further comprising an integrated device means for evaluating the workload of each member and displaying the workload information in association with emotional information.

[0953] "Application example 2 of combining emotional engines"

[0954] (Claim 1)

[0955] A terminal device means for collecting emotional data, audio data, and video data,

[0956] A control device means for preprocessing the collected data, removing noise, and converting it into an analyzable format,

[0957] A processing device for analyzing emotional states through text analysis, facial expression analysis, and voice analysis, and for calculating an emotional score,

[0958] A display device for integrating emotional scores and data related to workload and visually displaying them for management,

[0959] A support device for formulating an efficient work allocation strategy using visually displayed data,

[0960] An operating device having an automatic control function for adjusting the work pace based on the emotional state of the worker,

[0961] A system that includes this.

[0962] (Claim 2)

[0963] The system according to claim 1, which is an analysis device for estimating emotional patterns among workers by applying a machine learning algorithm using various collected data.

[0964] (Claim 3)

[0965] The system according to claim 1, an integrated device for evaluating the workload of each worker and displaying the workload data in association with emotional data. [Explanation of Symbols]

[0966] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A device means for collecting emotional data, audio data, and video data, Processing means for preprocessing collected data, removing noise, and converting it into an analyzable format, An analysis device means for analyzing emotional states through text analysis, facial expression analysis, and voice analysis, and for calculating an emotional score, A display device for integrating emotional scores and data related to workload and visually displaying them for administrators, A support device for formulating an efficient work allocation strategy using visually displayed data, A system that includes this.

2. The system according to claim 1, further comprising an analysis device means for applying a machine learning algorithm to various collected data and estimating emotional patterns among team members.

3. The system according to claim 1, further comprising an integrated device means for evaluating the workload of each member and displaying the workload data in association with emotional data.

Images