system

Abstract

Provide a system. 【Solution means】 Means for collecting voice information and business management information using communication means, Acoustic recognition means for converting the collected voice information into character information, Means for analyzing character information and business management information by natural language processing, Generating means for evaluating the contribution of the operator based on the analysis result and generating commendation information, Sentiment analysis means for analyzing the emotional state of the operator, Display means for visualizing the analysis result as a visual display device, Means for notifying the commendation information to the terminal device of the operator, In the work process, means for promoting the cooperation between robots and humans in order to enhance work efficiency, A system including

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including 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] With the spread of remote work, the opportunities for individual team members to receive direct evaluation and praise have decreased. As a result, self-evaluation has declined, leading to a loss of confidence in one's own abilities and a decrease in motivation for work. In such a situation, there is a risk of insufficient workplace communication and collaboration, and deterioration of work efficiency. To solve this problem, it is necessary to introduce a system that allows members to grasp and re-recognize their own contributions and values even in a non-face-to-face environment.

Means for Solving the Problems

[0005] This invention collects voice data and project management data using a communication network and converts it into text data using speech recognition technology. The converted text data and project management data are analyzed using natural language processing to evaluate the contributions of individual members and generate praise messages. Furthermore, sentiment analysis technology is used to understand the emotional state of members, and the analysis results are provided as a dashboard to promote mutual evaluation and respect among members. In addition, the generated praise messages are notified to members' devices, making their contributions visible and leading to increased motivation.

[0006] A "communication network" is an infrastructure for sending and receiving voice data and project management data between multiple devices and servers.

[0007] "Speech recognition" is a technology that acquires speech data and converts it into text data.

[0008] "Project management data" refers to data used to manage information such as project progress, task assignments, and deadlines.

[0009] "Natural language processing" is an artificial intelligence technology that analyzes text data to understand its meaning and extract information.

[0010] A "praise message" is a feedback message generated to recognize and appreciate the contributions of individual members.

[0011] "Sentiment analysis" is a technology that detects and analyzes emotional states from text and audio data.

[0012] A "dashboard" is an interface that visually displays analysis results, allowing users to intuitively understand the information.

[0013] A "terminal" is a device used to receive generated messages and notifications, such as a smartphone or a personal computer. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled 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), etc.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] A system for carrying out this invention consists of a server and terminals that include multiple modules for acquiring voice data and project management data via a communication network, and for analyzing and visualizing them.

[0036] First, the server collects audio and project management data from the meeting system and project management tools. The server then converts the audio data into text using speech recognition technology. This allows users to later review the meeting content in text format.

[0037] The server then uses natural language processing techniques to analyze text data and project management data. The purpose of the analysis is to evaluate the contributions of individual members and generate messages of appreciation. For example, if a member proposes an effective idea in a meeting, that contribution will be identified and a message of appreciation will be generated.

[0038] Furthermore, the server uses sentiment analysis technology to analyze members' emotional states from their statements and reactions. This allows for an understanding of stress levels and trends in positive emotions within the team. The results of this analysis are visually displayed on the terminal as a dashboard. The dashboard uses radar charts and bar graphs to show members' contributions and emotional states at a glance.

[0039] Finally, the generated praise message is sent from the server to each member's terminal. Upon receiving this notification, users feel their contributions are recognized, leading to increased motivation. This system promotes respect and communication among members, even in a remote work environment, contributing to improved work productivity.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server communicates with the conferencing system and project management tools, collecting audio and project data in real time. Audio data is streamed directly, while project data is retrieved via an API.

[0043] Step 2:

[0044] The server converts the acquired audio data into text data using speech recognition technology. This process saves the meeting content as text information, which can then be used for later analysis.

[0045] Step 3:

[0046] The server utilizes natural language processing technology to analyze text data and project management data. This involves extracting key keywords and performing contextual analysis to identify member contributions and important statements.

[0047] Step 4:

[0048] Based on the analysis results, the server uses a generation AI to automatically generate a message of praise. For example, a message such as "User A's suggestion made the project more efficient" might be created.

[0049] Step 5:

[0050] The server applies sentiment analysis technology to analyze the emotional state of members from text data. This determines emotional categories such as positive, negative, and neutral.

[0051] Step 6:

[0052] The terminal receives analysis results and praise messages sent from the server and displays them visually on the dashboard. Each member's contribution and emotional state are represented using radar charts and bar graphs.

[0053] Step 7:

[0054] Users see the praise message notified on their device and understand that their contributions have been recognized. This increases user motivation and encourages them to engage in further work.

[0055] (Example 1)

[0056] 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."

[0057] In remote work environments, smooth communication among team members is often hindered, making it difficult to accurately grasp members' contributions and emotional states. Furthermore, there is a lack of mechanisms to properly evaluate members' contributions and thereby improve motivation. As a result, the efficiency of remote work decreases, and productivity is less likely to improve.

[0058] 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.

[0059] In this invention, the server includes means for collecting voice information and work progress information via a communication network, voice recognition means for converting the collected voice information into text information, and means for analyzing the text information and work progress information using natural language processing. This enables accurate evaluation of members' contributions, generation and notification of praise messages, thereby facilitating communication within the team and improving the productivity of remote work.

[0060] A "communication network" is the infrastructure used to send and receive information between electronic devices.

[0061] "Audio information" refers to information that records or transmits human speech as acoustic signals.

[0062] "Work progress information" refers to data that shows the progress of a project or task.

[0063] "Speech recognition means" refers to a technology or device that analyzes speech signals and converts them into corresponding textual information.

[0064] "Textual information" refers to data expressed in characters in a format usable by humans or machines.

[0065] "Natural language processing" is a technology that uses computers to understand, interpret, and generate human language.

[0066] "Sentiment analysis methods" refer to technologies or devices that estimate an individual's emotions and psychological state from text or audio.

[0067] "Display means" refers to a technology or device that presents data or information to humans visually.

[0068] A "praise message" is a written or spoken message that evaluates and positively communicates a specific action or achievement.

[0069] "Communication means" refers to the technology or equipment used to send and receive information.

[0070] The system for implementing this invention includes a server and terminals and is designed to streamline team communication in a remote work environment.

[0071] First, the server collects audio and work progress information from conferencing systems and project management tools via the communication network. The audio information is converted into text information using general speech recognition technology. Specifically, a "speech recognition API" is used as the speech recognition software. At this stage, the server temporarily stores the audio files and retrieves the corresponding text information using the API.

[0072] Next, the server uses natural language processing technology to analyze textual information and work progress information. For this, the "Text Analysis API" is used as the natural language processing library. Based on the analysis results, the server evaluates each member's contribution based on their statements and automatically generates praise messages based on prompts. Sentiment analysis technology is also used to evaluate the participants' psychological state from their statements. This allows the server to understand the members' motivation and stress levels.

[0073] The analysis results are transmitted to the terminal and visualized as a dashboard on the display device. Users can view the visualized data in real time through the terminal. Specifically, the dashboard is displayed in the form of radar charts and bar graphs using a "data visualization tool," allowing users to see at a glance the contributions and emotional trends of team members.

[0074] Finally, the server notifies each member's device of the generated praise message. This allows users to confirm that their contributions are being recognized, which can boost their motivation.

[0075] As a concrete example, suppose a member proposes an efficient way to manage a new project during a remote meeting. This member's contribution is evaluated by the system, and a message of praise is generated using a prompt, such as, "We look forward to hearing your ideas at the next meeting!"

[0076] Examples of prompts for a generative AI model:

[0077] "Analyze the key statements made during the meeting and create commendation messages for members who made excellent suggestions."

[0078] Through this configuration, the system aims to visualize members' contributions and emotions, and to facilitate communication in a remote work environment.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server retrieves audio information from the conferencing system and work progress information from the project management tool via the communication network. Inputs include audio files and task lists for each participant, while outputs include raw audio data and progress data. Specifically, the server calls an API to download audio data and retrieve work progress information.

[0082] Step 2:

[0083] The server uses speech recognition technology to convert the acquired audio data into text data. The input is the audio data obtained in step 1, and the output is the corresponding text data. This conversion utilizes a speech recognition API, and the audio file is uploaded to obtain the text information.

[0084] Step 3:

[0085] The server analyzes text data and work progress information using natural language processing technology. The input for the analysis is text data and progress information, and the output is the analysis results. Specifically, the server uses a natural language processing library to extract important keywords and phrases contained in the text and evaluate the content of members' statements and their level of task completion.

[0086] Step 4:

[0087] The server uses sentiment analysis technology to analyze the psychological state of members from their statements. The input is the text data converted in step 2, and the output is the sentiment analysis result. Using the sentiment analysis API, the text is analyzed to determine the type and intensity of emotion.

[0088] Step 5:

[0089] The terminal receives analysis results sent from the server and visualizes them as a dashboard. Here, the input is the analysis result data, and the output is the visualized data. The terminal uses data visualization tools to generate radar charts and bar graphs, allowing users to review their evaluations.

[0090] Step 6:

[0091] The server uses a generative AI model to generate praise messages for high-contributing members. The input is the contribution evaluation score from the analysis results, and the output is the generated praise message. A prompt is given to the generative AI model, instructing it to "create a message that evaluates this emphasis point," and the message is generated.

[0092] Step 7:

[0093] The server notifies each member's device of the generated praise message. The input here is the praise message, and the output is a notification displayed on each member's device. A message sending API is used to send messages to users' devices in real time, facilitating smooth communication among members.

[0094] (Application Example 1)

[0095] 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."

[0096] In remote work environments and manufacturing sites, it is necessary to appropriately evaluate the contributions and emotions of team members and workers, thereby improving motivation and promoting efficient work execution. In particular, in collaborative work between robots and humans, it is essential to improve the quality of communication and coordination between both parties. The challenge lies in improving work efficiency, reducing worker stress, and facilitating smooth team communication.

[0097] 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.

[0098] In this invention, the server includes means for collecting voice information and work management information using communication means, acoustic recognition means for converting voice information into text information, and means for analyzing text information and work management information using natural language processing. This makes it possible to enhance work efficiency, evaluate the contributions of workers and team members, and notify them with appropriate recognition information. In addition, by using emotion analysis means, the emotional state of workers can be analyzed, appropriate support can be provided, and the quality of collaborative work between robots and humans can be improved. Furthermore, the analysis results can be visualized using display means, promoting cooperation in the work process.

[0099] "Communication means" refers to a technological device that transmits and receives information data via a network.

[0100] "Audio information" refers to data of language or sound waves recorded as sound.

[0101] "Project management information" refers to data that includes information on the progress and tasks related to project and work execution.

[0102] "Acoustic recognition means" refers to a device that converts audio data into text data.

[0103] "Character information" refers to data that is represented as a string of characters.

[0104] "Natural language processing" is a computer technology that analyzes text data and makes it understandable to humans.

[0105] A "generation means" is a technological device that generates new information based on the analysis results.

[0106] "Award information" refers to data that represents praise and commendation for the contributions of workers and team members.

[0107] A "sentiment analysis tool" is a technological device that extracts and evaluates the emotions of workers from data.

[0108] A "visual display device" is a technological device used to display data as graphs or diagrams on a monitor or other display.

[0109] A "terminal device" is an electronic device that receives, displays, or processes data.

[0110] "Means of promoting collaboration" refer to technological devices that support smooth cooperation between different equipment and workers.

[0111] The system implementing this invention aims to improve the efficiency of teamwork and enhance worker motivation in remote environments and manufacturing sites. Specifically, the system consists of a server that collects voice information and work management information via communication means. Next, the server converts the voice information into text information using acoustic recognition means. Google® Speech Recognition API is often used in this process.

[0112] The converted text information and business management information are analyzed on the server using natural language processing. The Hugging Face Transformers library is used for text analysis. Then, the contributions of team members are analyzed using a generation method, and recognition information is generated. For example, if a worker demonstrates outstanding performance, their contribution is analyzed, and recognition information is generated at the appropriate time.

[0113] Furthermore, the server evaluates the emotional state of workers and team members through sentiment analysis tools. This makes it possible to provide support for reducing work-related stress and creating a positive work environment. The analysis results are displayed on the terminal as dashboards and graphs via a visual display device, allowing users to immediately grasp the situation.

[0114] Ultimately, the generated award information is notified to the terminal device, allowing workers to feel that their contributions have been recognized. This improves the efficiency and quality of work. As a concrete example, if a worker on a manufacturing line makes a suggestion to optimize a work process, and as a result, efficiency improves, this will be evaluated and recognized in real time.

[0115] Furthermore, an example of a prompt based on a generative AI model is, "Please explain how to analyze audio and text data to evaluate each member's contribution and generate a message of appreciation." Using this example, it is possible to obtain more detailed analysis and responses.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server collects voice information and business management information using communication methods. It receives data as input from online meeting systems and business management tools, and stores this data. The output is data in a format that can be processed by acoustic recognition means.

[0119] Step 2:

[0120] The server converts audio information collected using acoustic recognition into text information. Here, the Google Speech Recognition API is utilized to convert audio data into text data. The input is an audio file, and the output is data in the corresponding text format.

[0121] Step 3:

[0122] The server analyzes textual and business management information using natural language processing. The Hugging Face Transformers library is used for natural language processing, evaluating the text content and recognizing specific keywords and phrases. The input is the text data created in the previous stage, and the output is the analyzed data.

[0123] Step 4:

[0124] The server uses a generation mechanism to evaluate the worker's contribution based on the analysis results and generates commendation information. At this stage, it automatically recognizes particularly high-contributing actions and generates commendation messages based on them. The input is the analyzed data, and the output is the generated commendation message.

[0125] Step 5:

[0126] The server analyzes the worker's emotional state using sentiment analysis tools. Sentiment analysis employs techniques that evaluate emotional status based on text data. Input is the result of natural language processing and award information, while output is data indicating the worker's emotional state.

[0127] Step 6:

[0128] The terminal displays analysis results from the server on a visual display device. Analysis results, award information, and emotional states are visualized in dashboard and graph formats. This allows users to intuitively understand important information. Input is visualized data from the server, and output is the visual display on the terminal.

[0129] Step 7:

[0130] Users receive commendation information addressed to them through a terminal device. The server delivers a generated commendation message, and the worker feels that their contribution has been recognized. The input is the commendation information data, and the output is the message that the user confirms.

[0131] 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.

[0132] The system for implementing this invention collects and analyzes voice data, text data, and project management data via a server and terminals incorporating an emotion engine. The aim is to recognize user emotions and improve communication within the team.

[0133] First, the server acquires audio and project management data from the conference system and project management tools via the communication network. The server converts this audio data into text data using speech recognition technology, and then analyzes the results using natural language processing technology. This analysis identifies members' contributions and important statements.

[0134] Next, the emotion engine is applied to the text and audio data to recognize the user's emotional state in real time. For example, emotions such as "joy," "anxiety," and "calmness" are detected from the user's statements. This information optimizes the praise messages generated by the server, customizing them to match the user's emotions.

[0135] Furthermore, the analysis results and emotional states are sent to the device and displayed as a dashboard that visualizes each member's strengths, contributions, and emotional state. This display deepens mutual understanding among members and strengthens team collaboration.

[0136] The terminal also notifies the user of praise messages sent from the server. Receiving these messages lets the user know their contributions are recognized, resulting in increased motivation. This system is expected to promote communication and respect among users, even in remote work environments, and improve overall workplace efficiency.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server accesses the conference system and project management tools via the communication network to collect audio and project management data. At this stage, the audio data is captured in a streaming format and transferred to the server in real time.

[0140] Step 2:

[0141] The server uses speech recognition technology to instantly convert the streamed audio data into text data. The converted text data is stored in a format that accurately records the content of the meeting.

[0142] Step 3:

[0143] The server utilizes natural language processing technology to analyze text data and project management data. This analysis extracts key phrases and important issues from discussions, and quantifies members' contributions.

[0144] Step 4:

[0145] Based on the generated analysis data, the server applies an emotion engine. This identifies the emotional state from the user's conversation and makes evaluations such as "User A is positive" or "User B is feeling anxious."

[0146] Step 5:

[0147] Taking into account the analyzed contribution and emotional state, the server automatically generates a message of praise. Here, the message is customized for each member, providing content tailored to their individual emotional state.

[0148] Step 6:

[0149] The device receives analysis results and praise messages sent from the server and visualizes them as a dashboard. Users can view each member's contribution level and emotional state as radar charts and timelines.

[0150] Step 7:

[0151] Users can review the praise messages notified on their devices and understand how their contributions and feelings were appreciated. This fosters cognitive and emotional engagement among users, improving motivation and efficiency in the workplace.

[0152] (Example 2)

[0153] 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".

[0154] In today's work environment, remote work and non-face-to-face communication are increasing. In this situation, it is difficult to accurately grasp the emotions and contributions of team members and to provide appropriate feedback, making team collaboration and motivation improvement challenges.

[0155] 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.

[0156] In this invention, the server includes means for acquiring voice information and business management information via a communication network, voice conversion means for converting the acquired voice information into text information, and means for interpreting the text information and business management information by language processing. This enables efficient analysis of team members' emotions and contributions even in a remote environment, and allows for the generation of evaluation messages and visualization of emotions.

[0157] A "communication network" refers to the network infrastructure used for sending and receiving digital data, and is a means of efficiently handling voice information and business management information.

[0158] "Audio information" refers to data that is recorded or transmitted in audio format and forms the basis for electronically processing human speech.

[0159] "Business management information" refers to data that records the progress of work and project details within an organization, and is used for efficient business operations.

[0160] "Speech conversion means" refers to technology that converts speech information into text information, and is a device or program that uses speech recognition technology to convert human speech into text format.

[0161] "Textual information" refers to text data recorded in digital format, which can be used for language processing, searching, and storage.

[0162] "Language processing" refers to the techniques used to analyze human language and mechanically understand its structure and meaning, and is also known as natural language processing.

[0163] "Interpretation methods" refer to techniques or processes for analyzing acquired data and understanding its meaning and trends.

[0164] "Emotional interpretation methods" refer to technologies that analyze a user's emotional state from data and evaluate it quantitatively or qualitatively.

[0165] A "display panel" refers to a digital interface for visually displaying interpretation results, providing the analyzed information in the form of graphs and charts.

[0166] "Means of transmission" refers to the technology or system used to send generated messages or information to the terminal of a designated recipient.

[0167] The system for implementing this invention aims to improve team communication by efficiently collecting voice information and business management information using a digital network, and by processing and analyzing it. The embodiments are described in detail below.

[0168] Server operation

[0169] The server acquires audio information from conferencing systems and task management systems via the communication network. During this process, it captures the audio information using a common API and converts it into text using a speech recognition service such as Google Cloud Speech-to-Text. The converted text is then analyzed using a natural language processing engine (e.g., spaCy). This natural language processing performs keyword extraction from the utterances, determines the speaker's level of involvement, and automatically recognizes important statements.

[0170] Emotional interpretation and generation

[0171] The server uses an emotion interpretation engine to analyze the user's emotional state from acquired text and audio information. During this process, it uses an emotion analysis API (e.g., IBM Watson®) to identify emotions such as "joy," "anxiety," and "calmness" in real time. Based on this, the server generates appropriately tailored evaluation messages for the user, providing feedback that aligns with the member's emotions.

[0172] Terminal processing

[0173] The terminal displays analysis results sent from the server as a dashboard, visually representing the team's dynamics. Here, each user's contribution and emotional state are visualized in chart format, facilitating mutual understanding among team members. The terminal also notifies users of evaluation messages generated by the server, ensuring that their individual contributions are appropriately recognized.

[0174] Specific example

[0175] User A participates in a remote meeting, and the audio information of that meeting is collected by a server. The audio is converted into text information via a speech-to-text converter and analyzed by a language processing device. The analysis determines that User A actively participated in the meeting and made useful contributions. Furthermore, because User A's emotional state is analyzed as "joyful," a message of praise such as "Thank you for your creative suggestions" is sent to the device.

[0176] Example of a prompt

[0177] "Design a program to estimate team members' emotions based on user conversations and evaluate their project contributions. It needs to provide specific emotion labels (e.g., joy, anxiety, calmness) and personalized praise messages based on those labels."

[0178] Thus, the present invention provides a means to improve teamwork through effective information analysis and emotion recognition.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server retrieves audio and project management information from conference systems and task management systems via the communication network. Audio files from meetings and project management data are provided as input. Audio information is typically retrieved using an API, automatically fetching data from the system. The output consists of raw audio data stored on the server and project-related management data.

[0182] Step 2:

[0183] The server converts the acquired audio information into text information using a speech-to-text conversion method. This process utilizes services such as Google Cloud Speech-to-Text. The input is raw audio data, which is then converted into text format. Specifically, the audio file is sent to the cloud service, and the returned text data is retrieved. The output is text information.

[0184] Step 3:

[0185] The server performs language processing using textual information and business management information. A natural language processing engine, such as spaCy, is used to analyze specific keywords, contributions, and roles. The input consists of textual information and business management information obtained in step 2. Based on this information, data tagging and statistical analysis are performed. The output consists of syntactic analysis results and contribution data for each member.

[0186] Step 4:

[0187] The server uses an emotion interpretation engine to identify the user's emotional state from the text information. The input includes the text information generated in step 3. Emotion analysis APIs such as IBM Watson are utilized for emotion interpretation. Specifically, it calculates positive, negative, and neutral emotion scores for the text. The output is quantitative data on the user's emotional state.

[0188] Step 5:

[0189] The server generates an evaluation message based on the analysis results. The analysis results, as input, include emotional state and contribution level. A generative AI model is used to create individually tailored messages. The output is a customized evaluation message.

[0190] Step 6:

[0191] The terminal receives analysis results and evaluation messages sent from the server and visualizes them in a dashboard format. Inputs include evaluation messages generated in step 5 and contribution data from step 3. Specifically, it displays information using graphs and charts and notifies the user. Outputs include a dashboard display and message notifications that the user can visually confirm.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] In remote work environments and at home, smooth communication is often difficult, posing a challenge in accurately evaluating and appreciating team members' collaboration and contributions. There is a need for methods to improve the quality of communication in remote work and home environments by providing appropriate responses and encouragement through emotional recognition within the home.

[0195] 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.

[0196] In this invention, the server includes means for collecting voice data and management data via a communication network, voice recognition means for converting the collected voice data into text data, and means for analyzing the text data and management data by language processing. This makes it possible to facilitate smooth communication in a home environment, accurately evaluate members' contributions, and provide appropriate emotional responses.

[0197] A "communication network" is a digital information transfer route for collecting and transmitting voice data and management data.

[0198] "Audio data" refers to data that records human speech and ambient sounds in digital format.

[0199] "Management data" refers to data that includes information related to a project or task.

[0200] "Character data" refers to discrete text information converted by speech recognition.

[0201] "Speech recognition means" refers to technology that analyzes speech data and converts it into text data.

[0202] "Language processing" is the technology used to analyze natural language and understand its meaning and emotions.

[0203] A "member" is an individual who participates as a member of a specific group or team.

[0204] "Contribution" refers to the support and results achieved for a group or project.

[0205] "Emotional response" refers to appropriate actions and messages generated in accordance with the user's emotional state.

[0206] "Home environment" refers to the circumstances surrounding an individual's daily life in the place where they live.

[0207] To implement this invention, it is necessary to build a system centered on a server and terminals. The server collects voice data and management data using a communication network. Voice data is acquired via a terminal equipped with a microphone and transmitted to the server. The server converts the voice data into text data using speech recognition technology and then performs analysis using a language processing engine.

[0208] The information obtained through analysis is used to evaluate members' contributions and emotional states. To analyze emotional states, an emotion analysis engine is used to identify characteristic emotions from the user's voice and text. For example, if a text contains many positive words, it will be processed as "joyful."

[0209] This system generates emotional responses from home automated devices and delivers them to the user at the appropriate time. For example, if the system detects that the user is feeling stressed, the robot will immediately provide an encouraging message. This response is optimized for the user's specific situation and is generated based on emotional analysis and historical data.

[0210] An example of a prompt message would be, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement." This message is sent to a generative AI model and used as a guide for generating appropriate messages. This enables smoother communication within the family environment and increases the contribution of family members.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The terminal collects voice data through its microphone and sends that data to the server. Real-time voice data is the input, and the audio data, converted to a digital format, is sent to the server as output. Specifically, the microphone captures the user's speech and sends it to the server via a data communication protocol.

[0214] Step 2:

[0215] The server converts received audio data into text data using speech recognition technology. It receives digital audio data as input and generates corresponding text data as output. Specifically, the speech recognition engine performs phoneme-to-text conversion, checks for errors, and generates consistent text data.

[0216] Step 3:

[0217] The server analyzes the generated character data using a language processing engine. The input is character data, and the output is the result of the analysis of emotion and meaning. The specific analysis operation involves detecting the emotions used from the content of the text; for example, it calculates the frequency of positive words to extract emotions such as "joy."

[0218] Step 4:

[0219] The server generates a response message based on the sentiment analysis results and sends it to the home automated device. The input is the sentiment analysis results, and the output is a response message suitable for the automated device. Specifically, it uses a generative AI model to create the message best suited to the sentiment data and optimizes it according to the prompt statement, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement."

[0220] Step 5:

[0221] Home automated devices present received response messages to the user with appropriate voice and actions. The input is the generated response message, and the output is the message content as perceived by the user. Specifically, the action involves a speech synthesis engine uttering the message and performing related actions (e.g., displaying it on a screen or turning on a light).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] A system for carrying out this invention consists of a server and terminals that include multiple modules for acquiring voice data and project management data via a communication network, and for analyzing and visualizing them.

[0239] First, the server collects audio and project management data from the meeting system and project management tools. The server then converts the audio data into text using speech recognition technology. This allows users to later review the meeting content in text format.

[0240] The server then uses natural language processing techniques to analyze text data and project management data. The purpose of the analysis is to evaluate the contributions of individual members and generate messages of appreciation. For example, if a member proposes an effective idea in a meeting, that contribution will be identified and a message of appreciation will be generated.

[0241] Furthermore, the server uses sentiment analysis technology to analyze members' emotional states from their statements and reactions. This allows for an understanding of stress levels and trends in positive emotions within the team. The results of this analysis are visually displayed on the terminal as a dashboard. The dashboard uses radar charts and bar graphs to show members' contributions and emotional states at a glance.

[0242] Finally, the generated praise message is sent from the server to each member's terminal. Upon receiving this notification, users feel their contributions are recognized, leading to increased motivation. This system promotes respect and communication among members, even in a remote work environment, contributing to improved work productivity.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server communicates with the conferencing system and project management tools, collecting audio and project data in real time. Audio data is streamed directly, while project data is retrieved via an API.

[0246] Step 2:

[0247] The server converts the acquired audio data into text data using speech recognition technology. This process saves the meeting content as text information, which can then be used for later analysis.

[0248] Step 3:

[0249] The server utilizes natural language processing technology to analyze text data and project management data. This involves extracting key keywords and performing contextual analysis to identify member contributions and important statements.

[0250] Step 4:

[0251] Based on the analysis results, the server uses a generation AI to automatically generate a message of praise. For example, a message such as "User A's suggestion made the project more efficient" might be created.

[0252] Step 5:

[0253] The server applies sentiment analysis technology to analyze the emotional state of members from text data. This determines emotional categories such as positive, negative, and neutral.

[0254] Step 6:

[0255] The terminal receives analysis results and praise messages sent from the server and displays them visually on the dashboard. Each member's contribution and emotional state are represented using radar charts and bar graphs.

[0256] Step 7:

[0257] Users see the praise message notified on their device and understand that their contributions have been recognized. This increases user motivation and encourages them to engage in further work.

[0258] (Example 1)

[0259] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0260] In remote work environments, smooth communication among team members is often hindered, making it difficult to accurately grasp members' contributions and emotional states. Furthermore, there is a lack of mechanisms to properly evaluate members' contributions and thereby improve motivation. As a result, the efficiency of remote work decreases, and productivity is less likely to improve.

[0261] 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.

[0262] In this invention, the server includes means for collecting voice information and work progress information via a communication network, voice recognition means for converting the collected voice information into text information, and means for analyzing the text information and work progress information using natural language processing. This enables accurate evaluation of members' contributions, generation and notification of praise messages, thereby facilitating communication within the team and improving the productivity of remote work.

[0263] A "communication network" is the infrastructure used to send and receive information between electronic devices.

[0264] "Audio information" refers to information that records or transmits human speech as acoustic signals.

[0265] "Work progress information" refers to data that shows the progress of a project or task.

[0266] "Speech recognition means" refers to a technology or device that analyzes speech signals and converts them into corresponding textual information.

[0267] "Textual information" refers to data expressed in characters in a format usable by humans or machines.

[0268] "Natural language processing" is a technology that uses computers to understand, interpret, and generate human language.

[0269] "Sentiment analysis methods" refer to technologies or devices that estimate an individual's emotions and psychological state from text or audio.

[0270] "Display means" refers to a technology or device that presents data or information to humans visually.

[0271] A "praise message" is a written or spoken message that evaluates and positively communicates a specific action or achievement.

[0272] "Communication means" refers to the technology or equipment used to send and receive information.

[0273] The system for implementing this invention includes a server and terminals and is designed to streamline team communication in a remote work environment.

[0274] First, the server collects audio and work progress information from conferencing systems and project management tools via the communication network. The audio information is converted into text information using general speech recognition technology. Specifically, a "speech recognition API" is used as the speech recognition software. At this stage, the server temporarily stores the audio files and retrieves the corresponding text information using the API.

[0275] Next, the server uses natural language processing technology to analyze textual information and work progress information. For this, the "Text Analysis API" is used as the natural language processing library. Based on the analysis results, the server evaluates each member's contribution based on their statements and automatically generates praise messages based on prompts. Sentiment analysis technology is also used to evaluate the participants' psychological state from their statements. This allows the server to understand the members' motivation and stress levels.

[0276] The analysis results are transmitted to the terminal and visualized as a dashboard on the display device. Users can view the visualized data in real time through the terminal. Specifically, the dashboard is displayed in the form of radar charts and bar graphs using a "data visualization tool," allowing users to see at a glance the contributions and emotional trends of team members.

[0277] Finally, the server notifies each member's device of the generated praise message. This allows users to confirm that their contributions are being recognized, which can boost their motivation.

[0278] As a concrete example, suppose a member proposes an efficient way to manage a new project during a remote meeting. This member's contribution is evaluated by the system, and a message of praise is generated using a prompt, such as, "We look forward to hearing your ideas at the next meeting!"

[0279] Examples of prompts for a generative AI model:

[0280] "Analyze the key statements made during the meeting and create commendation messages for members who made excellent suggestions."

[0281] Through this configuration, the system aims to visualize members' contributions and emotions, and to facilitate communication in a remote work environment.

[0282] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0283] Step 1:

[0284] The server obtains voice information from the conferencing system and collects work progress information from the project management tool via the communication network. The inputs are voice files and the task list of each participant, and the outputs are raw voice data and progress data. Specifically, the server calls an API to download the voice data and obtain the work progress information.

[0285] Step 2:

[0286] The server uses voice recognition technology to convert the obtained voice data into text data. The input is the voice data obtained in Step 1, and the output is the corresponding text data. For this conversion, a voice recognition API is utilized to upload the voice file and obtain the character information.

[0287] Step 3:

[0288] The server analyzes the text data and work progress information using natural language processing technology. The inputs for the analysis are the text data and the progress information, and the output is the analysis result. Specifically, the server uses a natural language processing library to extract important keywords and phrases contained in the text and evaluate the speech content of the members and the task achievement level.

[0289] Step 4:

[0290] The server uses sentiment analysis technology to analyze the psychological state from the members' speeches. The input is the text data converted in Step 2, and the output is the sentiment analysis result. Using a sentiment analysis API, the text is analyzed to determine the type and intensity of the sentiment.

[0291] Step 5:

[0292] The terminal receives the analysis result sent from the server and visualizes it as a dashboard. Here, the input is the data of the analysis result, and the output is the visualized data. The terminal uses a data visualization tool to generate a radar chart or a bar graph to enable the user to confirm the evaluation.

[0293] Step 6:

[0294] The server uses a generative AI model to generate praise messages for high-contributing members. The input is the contribution evaluation score from the analysis results, and the output is the generated praise message. A prompt is given to the generative AI model, instructing it to "create a message that evaluates this emphasis point," and the message is generated.

[0295] Step 7:

[0296] The server notifies each member's device of the generated praise message. The input here is the praise message, and the output is a notification displayed on each member's device. A message sending API is used to send messages to users' devices in real time, facilitating smooth communication among members.

[0297] (Application Example 1)

[0298] 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."

[0299] In remote work environments and manufacturing sites, it is necessary to appropriately evaluate the contributions and emotions of team members and workers, thereby improving motivation and promoting efficient work execution. In particular, in collaborative work between robots and humans, it is essential to improve the quality of communication and coordination between both parties. The challenge lies in improving work efficiency, reducing worker stress, and facilitating smooth team communication.

[0300] 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.

[0301] In this invention, the server includes means for collecting voice information and business management information using communication means, acoustic recognition means for converting voice information into character information, and means for analyzing the character information and business management information by natural language processing. As a result, it becomes possible to enhance business efficiency, evaluate the contribution of workers and team members, and notify appropriate commendation information. In addition, by using sentiment analysis means, it is possible to analyze the emotional state of workers, provide appropriate support, and improve the quality of collaborative work between robots and humans. Also, the analysis results can be visualized using display means to promote cooperation in the work process.

[0302] The "communication means" is a technical device for transmitting and receiving information data via a network.

[0303] The "voice information" is data of language or sound waves recorded as sound.

[0304] The "business management information" is data including progress and task information regarding projects and business execution.

[0305] The "acoustic recognition means" is a technical device for converting voice data into text data.

[0306] The "character information" is data expressed as a character string.

[0307] The "natural language processing" is computer technology for analyzing text data and understanding human language.

[0308] The "generation means" is a technical device for generating new information based on the analysis results.

[0309] The "commendation information" is data representing words of praise and admiration for the contributions of workers and team members.

[0310] The "sentiment analysis means" is a technical device for extracting and evaluating the emotions of workers from data.

[0311] A "visual display device" is a technological device used to display data as graphs or diagrams on a monitor or other display.

[0312] A "terminal device" is an electronic device that receives, displays, or processes data.

[0313] "Means of promoting collaboration" refer to technological devices that support smooth cooperation between different equipment and workers.

[0314] The system implementing this invention aims to improve the efficiency of teamwork and enhance worker motivation in remote environments and manufacturing sites. Specifically, the system consists of a server that collects voice information and work management information via communication means. Next, the server converts the voice information into text information using acoustic recognition means. The Google Speech Recognition API is often used in this process.

[0315] The converted text information and business management information are analyzed on the server using natural language processing. The Hugging Face Transformers library is used for text analysis. Then, the contributions of team members are analyzed using a generation method, and recognition information is generated. For example, if a worker demonstrates outstanding performance, their contribution is analyzed, and recognition information is generated at the appropriate time.

[0316] Furthermore, the server evaluates the emotional state of workers and team members through sentiment analysis tools. This makes it possible to provide support for reducing work-related stress and creating a positive work environment. The analysis results are displayed on the terminal as dashboards and graphs via a visual display device, allowing users to immediately grasp the situation.

[0317] Ultimately, the generated award information is notified to the terminal device, allowing workers to feel that their contributions have been recognized. This improves the efficiency and quality of work. As a concrete example, if a worker on a manufacturing line makes a suggestion to optimize a work process, and as a result, efficiency improves, this will be evaluated and recognized in real time.

[0318] Furthermore, an example of a prompt based on a generative AI model is, "Please explain how to analyze audio and text data to evaluate each member's contribution and generate a message of appreciation." Using this example, it is possible to obtain more detailed analysis and responses.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The server collects voice information and business management information using communication methods. It receives data as input from online meeting systems and business management tools, and stores this data. The output is data in a format that can be processed by acoustic recognition means.

[0322] Step 2:

[0323] The server converts audio information collected using acoustic recognition into text information. Here, the Google Speech Recognition API is utilized to convert audio data into text data. The input is an audio file, and the output is data in the corresponding text format.

[0324] Step 3:

[0325] The server analyzes textual and business management information using natural language processing. The Hugging Face Transformers library is used for natural language processing, evaluating the text content and recognizing specific keywords and phrases. The input is the text data created in the previous stage, and the output is the analyzed data.

[0326] Step 4:

[0327] The server uses a generation mechanism to evaluate the worker's contribution based on the analysis results and generates commendation information. At this stage, it automatically recognizes particularly high-contributing actions and generates commendation messages based on them. The input is the analyzed data, and the output is the generated commendation message.

[0328] Step 5:

[0329] The server analyzes the worker's emotional state using sentiment analysis tools. Sentiment analysis employs techniques that evaluate emotional status based on text data. Input is the result of natural language processing and award information, while output is data indicating the worker's emotional state.

[0330] Step 6:

[0331] The terminal displays analysis results from the server on a visual display device. Analysis results, award information, and emotional states are visualized in dashboard and graph formats. This allows users to intuitively understand important information. Input is visualized data from the server, and output is the visual display on the terminal.

[0332] Step 7:

[0333] Users receive commendation information addressed to them through a terminal device. The server delivers a generated commendation message, and the worker feels that their contribution has been recognized. The input is the commendation information data, and the output is the message that the user confirms.

[0334] 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.

[0335] The system for implementing this invention collects and analyzes voice data, text data, and project management data via a server and terminals incorporating an emotion engine. The aim is to recognize user emotions and improve communication within the team.

[0336] First, the server acquires audio and project management data from the conference system and project management tools via the communication network. The server converts this audio data into text data using speech recognition technology, and then analyzes the results using natural language processing technology. This analysis identifies members' contributions and important statements.

[0337] Next, the emotion engine is applied to the text and audio data to recognize the user's emotional state in real time. For example, emotions such as "joy," "anxiety," and "calmness" are detected from the user's statements. This information optimizes the praise messages generated by the server, customizing them to match the user's emotions.

[0338] Furthermore, the analysis results and emotional states are sent to the device and displayed as a dashboard that visualizes each member's strengths, contributions, and emotional state. This display deepens mutual understanding among members and strengthens team collaboration.

[0339] The terminal also notifies the user of praise messages sent from the server. Receiving these messages lets the user know their contributions are recognized, resulting in increased motivation. This system is expected to promote communication and respect among users, even in remote work environments, and improve overall workplace efficiency.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The server accesses the conference system and project management tools via the communication network to collect audio and project management data. At this stage, the audio data is captured in a streaming format and transferred to the server in real time.

[0343] Step 2:

[0344] The server uses speech recognition technology to instantly convert the streamed audio data into text data. The converted text data is stored in a format that accurately records the content of the meeting.

[0345] Step 3:

[0346] The server utilizes natural language processing technology to analyze text data and project management data. This analysis extracts key phrases and important issues from discussions, and quantifies members' contributions.

[0347] Step 4:

[0348] Based on the generated analysis data, the server applies an emotion engine. This identifies the emotional state from the user's conversation and makes evaluations such as "User A is positive" or "User B is feeling anxious."

[0349] Step 5:

[0350] Taking into account the analyzed contribution and emotional state, the server automatically generates a message of praise. Here, the message is customized for each member, providing content tailored to their individual emotional state.

[0351] Step 6:

[0352] The device receives analysis results and praise messages sent from the server and visualizes them as a dashboard. Users can view each member's contribution level and emotional state as radar charts and timelines.

[0353] Step 7:

[0354] Users can review the praise messages notified on their devices and understand how their contributions and feelings were appreciated. This fosters cognitive and emotional engagement among users, improving motivation and efficiency in the workplace.

[0355] (Example 2)

[0356] 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".

[0357] In today's work environment, remote work and non-face-to-face communication are increasing. In this situation, it is difficult to accurately grasp the emotions and contributions of team members and to provide appropriate feedback, making team collaboration and motivation improvement challenges.

[0358] 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.

[0359] In this invention, the server includes means for acquiring voice information and business management information via a communication network, voice conversion means for converting the acquired voice information into text information, and means for interpreting the text information and business management information by language processing. This enables efficient analysis of team members' emotions and contributions even in a remote environment, and allows for the generation of evaluation messages and visualization of emotions.

[0360] A "communication network" refers to the network infrastructure used for sending and receiving digital data, and is a means of efficiently handling voice information and business management information.

[0361] "Audio information" refers to data that is recorded or transmitted in audio format and forms the basis for electronically processing human speech.

[0362] "Business management information" refers to data that records the progress of work and project details within an organization, and is used for efficient business operations.

[0363] "Speech conversion means" refers to technology that converts speech information into text information, and is a device or program that uses speech recognition technology to convert human speech into text format.

[0364] "Textual information" refers to text data recorded in digital format, which can be used for language processing, searching, and storage.

[0365] "Language processing" refers to the techniques used to analyze human language and mechanically understand its structure and meaning, and is also known as natural language processing.

[0366] "Interpretation methods" refer to techniques or processes for analyzing acquired data and understanding its meaning and trends.

[0367] "Emotional interpretation methods" refer to technologies that analyze a user's emotional state from data and evaluate it quantitatively or qualitatively.

[0368] A "display panel" refers to a digital interface for visually displaying interpretation results, providing the analyzed information in the form of graphs and charts.

[0369] "Means of transmission" refers to the technology or system used to send generated messages or information to the terminal of a designated recipient.

[0370] The system for implementing this invention aims to improve team communication by efficiently collecting voice information and business management information using a digital network, and by processing and analyzing it. The embodiments are described in detail below.

[0371] Server operation

[0372] The server acquires audio information from conferencing systems and task management systems via the communication network. During this process, it captures the audio information using a common API and converts it into text using a speech recognition service such as Google Cloud Speech-to-Text. The converted text is then analyzed using a natural language processing engine (e.g., spaCy). This natural language processing performs keyword extraction from the utterances, determines the speaker's level of involvement, and automatically recognizes important statements.

[0373] Emotional interpretation and generation

[0374] The server uses an emotion interpretation engine to analyze the user's emotional state from acquired text and audio information. During this process, it uses an emotion analysis API (e.g., IBM Watson) to identify emotions such as "joy," "anxiety," and "calmness" in real time. Based on this, the server generates appropriately tailored evaluation messages for the user, providing feedback that aligns with the member's emotions.

[0375] Terminal processing

[0376] The terminal displays analysis results sent from the server as a dashboard, visually representing the team's dynamics. Here, each user's contribution and emotional state are visualized in chart format, facilitating mutual understanding among team members. The terminal also notifies users of evaluation messages generated by the server, ensuring that their individual contributions are appropriately recognized.

[0377] Specific example

[0378] User A participates in a remote meeting, and the audio information of that meeting is collected by a server. The audio is converted into text information via a speech-to-text converter and analyzed by a language processing device. The analysis determines that User A actively participated in the meeting and made useful contributions. Furthermore, because User A's emotional state is analyzed as "joyful," a message of praise such as "Thank you for your creative suggestions" is sent to the device.

[0379] Example of a prompt

[0380] "Design a program to estimate team members' emotions based on user conversations and evaluate their project contributions. It needs to provide specific emotion labels (e.g., joy, anxiety, calmness) and personalized praise messages based on those labels."

[0381] Thus, the present invention provides a means to improve teamwork through effective information analysis and emotion recognition.

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The server retrieves audio and project management information from conference systems and task management systems via the communication network. Audio files from meetings and project management data are provided as input. Audio information is typically retrieved using an API, automatically fetching data from the system. The output consists of raw audio data stored on the server and project-related management data.

[0385] Step 2:

[0386] The server converts the acquired audio information into text information using a speech-to-text conversion method. This process utilizes services such as Google Cloud Speech-to-Text. The input is raw audio data, which is then converted into text format. Specifically, the audio file is sent to the cloud service, and the returned text data is retrieved. The output is text information.

[0387] Step 3:

[0388] The server performs language processing using textual information and business management information. A natural language processing engine, such as spaCy, is used to analyze specific keywords, contributions, and roles. The input consists of textual information and business management information obtained in step 2. Based on this information, data tagging and statistical analysis are performed. The output consists of syntactic analysis results and contribution data for each member.

[0389] Step 4:

[0390] The server uses an emotion interpretation engine to identify the user's emotional state from the text information. The input includes the text information generated in step 3. Emotion analysis APIs such as IBM Watson are utilized for emotion interpretation. Specifically, it calculates positive, negative, and neutral emotion scores for the text. The output is quantitative data on the user's emotional state.

[0391] Step 5:

[0392] The server generates an evaluation message based on the analysis results. The analysis results, as input, include emotional state and contribution level. A generative AI model is used to create individually tailored messages. The output is a customized evaluation message.

[0393] Step 6:

[0394] The terminal receives analysis results and evaluation messages sent from the server and visualizes them in a dashboard format. Inputs include evaluation messages generated in step 5 and contribution data from step 3. Specifically, it displays information using graphs and charts and notifies the user. Outputs include a dashboard display and message notifications that the user can visually confirm.

[0395] (Application Example 2)

[0396] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0397] In remote work environments and at home, smooth communication is often difficult, posing a challenge in accurately evaluating and appreciating team members' collaboration and contributions. There is a need for methods to improve the quality of communication in remote work and home environments by providing appropriate responses and encouragement through emotional recognition within the home.

[0398] 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.

[0399] In this invention, the server includes means for collecting voice data and management data via a communication network, voice recognition means for converting the collected voice data into text data, and means for analyzing the text data and management data by language processing. This makes it possible to facilitate smooth communication in a home environment, accurately evaluate members' contributions, and provide appropriate emotional responses.

[0400] A "communication network" is a digital information transfer route for collecting and transmitting voice data and management data.

[0401] "Audio data" refers to data that records human speech and ambient sounds in digital format.

[0402] "Management data" refers to data that includes information related to a project or task.

[0403] "Character data" refers to discrete text information converted by speech recognition.

[0404] "Speech recognition means" refers to technology that analyzes speech data and converts it into text data.

[0405] "Language processing" is the technology used to analyze natural language and understand its meaning and emotions.

[0406] A "member" is an individual who participates as a member of a specific group or team.

[0407] "Contribution" refers to the support and results achieved for a group or project.

[0408] "Emotional response" refers to appropriate actions and messages generated in accordance with the user's emotional state.

[0409] "Home environment" refers to the circumstances surrounding an individual's daily life in the place where they live.

[0410] To implement this invention, it is necessary to build a system centered on a server and terminals. The server collects voice data and management data using a communication network. Voice data is acquired via a terminal equipped with a microphone and transmitted to the server. The server converts the voice data into text data using speech recognition technology and then performs analysis using a language processing engine.

[0411] The information obtained through analysis is used to evaluate members' contributions and emotional states. To analyze emotional states, an emotion analysis engine is used to identify characteristic emotions from the user's voice and text. For example, if a text contains many positive words, it will be processed as "joyful."

[0412] This system generates emotional responses from home automated devices and delivers them to the user at the appropriate time. For example, if the system detects that the user is feeling stressed, the robot will immediately provide an encouraging message. This response is optimized for the user's specific situation and is generated based on emotional analysis and historical data.

[0413] An example of a prompt message would be, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement." This message is sent to a generative AI model and used as a guide for generating appropriate messages. This enables smoother communication within the family environment and increases the contribution of family members.

[0414] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0415] Step 1:

[0416] The terminal collects voice data through its microphone and sends that data to the server. Real-time voice data is the input, and the audio data, converted to a digital format, is sent to the server as output. Specifically, the microphone captures the user's speech and sends it to the server via a data communication protocol.

[0417] Step 2:

[0418] The server converts received audio data into text data using speech recognition technology. It receives digital audio data as input and generates corresponding text data as output. Specifically, the speech recognition engine performs phoneme-to-text conversion, checks for errors, and generates consistent text data.

[0419] Step 3:

[0420] The server analyzes the generated character data using a language processing engine. The input is character data, and the output is the result of the analysis of emotion and meaning. The specific analysis operation involves detecting the emotions used from the content of the text; for example, it calculates the frequency of positive words to extract emotions such as "joy."

[0421] Step 4:

[0422] The server generates a response message based on the sentiment analysis results and sends it to the home automated device. The input is the sentiment analysis results, and the output is a response message suitable for the automated device. Specifically, it uses a generative AI model to create the message best suited to the sentiment data and optimizes it according to the prompt statement, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement."

[0423] Step 5:

[0424] Home automated devices present received response messages to the user with appropriate voice and actions. The input is the generated response message, and the output is the message content as perceived by the user. Specifically, the action involves a speech synthesis engine uttering the message and performing related actions (e.g., displaying it on a screen or turning on a light).

[0425] 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.

[0426] 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.

[0427] 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.

[0428] [Third Embodiment]

[0429] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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".

[0441] A system for carrying out this invention consists of a server and terminals that include multiple modules for acquiring voice data and project management data via a communication network, and for analyzing and visualizing them.

[0442] First, the server collects audio and project management data from the meeting system and project management tools. The server then converts the audio data into text using speech recognition technology. This allows users to later review the meeting content in text format.

[0443] The server then uses natural language processing techniques to analyze text data and project management data. The purpose of the analysis is to evaluate the contributions of individual members and generate messages of appreciation. For example, if a member proposes an effective idea in a meeting, that contribution will be identified and a message of appreciation will be generated.

[0444] Furthermore, the server uses sentiment analysis technology to analyze members' emotional states from their statements and reactions. This allows for an understanding of stress levels and trends in positive emotions within the team. The results of this analysis are visually displayed on the terminal as a dashboard. The dashboard uses radar charts and bar graphs to show members' contributions and emotional states at a glance.

[0445] Finally, the generated praise message is sent from the server to each member's terminal. Upon receiving this notification, users feel their contributions are recognized, leading to increased motivation. This system promotes respect and communication among members, even in a remote work environment, contributing to improved work productivity.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server communicates with the conferencing system and project management tools, collecting audio and project data in real time. Audio data is streamed directly, while project data is retrieved via an API.

[0449] Step 2:

[0450] The server converts the acquired audio data into text data using speech recognition technology. This process saves the meeting content as text information, which can then be used for later analysis.

[0451] Step 3:

[0452] The server utilizes natural language processing technology to analyze text data and project management data. This involves extracting key keywords and performing contextual analysis to identify member contributions and important statements.

[0453] Step 4:

[0454] Based on the analysis results, the server uses a generation AI to automatically generate a message of praise. For example, a message such as "User A's suggestion made the project more efficient" might be created.

[0455] Step 5:

[0456] The server applies sentiment analysis technology to analyze the emotional state of members from text data. This determines emotional categories such as positive, negative, and neutral.

[0457] Step 6:

[0458] The terminal receives analysis results and praise messages sent from the server and displays them visually on the dashboard. Each member's contribution and emotional state are represented using radar charts and bar graphs.

[0459] Step 7:

[0460] Users see the praise message notified on their device and understand that their contributions have been recognized. This increases user motivation and encourages them to engage in further work.

[0461] (Example 1)

[0462] 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."

[0463] In remote work environments, smooth communication among team members is often hindered, making it difficult to accurately grasp members' contributions and emotional states. Furthermore, there is a lack of mechanisms to properly evaluate members' contributions and thereby improve motivation. As a result, the efficiency of remote work decreases, and productivity is less likely to improve.

[0464] 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.

[0465] In this invention, the server includes means for collecting voice information and work progress information via a communication network, voice recognition means for converting the collected voice information into text information, and means for analyzing the text information and work progress information using natural language processing. This enables accurate evaluation of members' contributions, generation and notification of praise messages, thereby facilitating communication within the team and improving the productivity of remote work.

[0466] A "communication network" is the infrastructure used to send and receive information between electronic devices.

[0467] "Audio information" refers to information that records or transmits human speech as acoustic signals.

[0468] "Work progress information" refers to data that shows the progress of a project or task.

[0469] "Speech recognition means" refers to a technology or device that analyzes speech signals and converts them into corresponding textual information.

[0470] "Textual information" refers to data expressed in characters in a format usable by humans or machines.

[0471] "Natural language processing" is a technology that uses computers to understand, interpret, and generate human language.

[0472] "Sentiment analysis methods" refer to technologies or devices that estimate an individual's emotions and psychological state from text or audio.

[0473] "Display means" refers to a technology or device that presents data or information to humans visually.

[0474] A "praise message" is a written or spoken message that evaluates and positively communicates a specific action or achievement.

[0475] "Communication means" refers to the technology or equipment used to send and receive information.

[0476] The system for implementing this invention includes a server and terminals and is designed to streamline team communication in a remote work environment.

[0477] First, the server collects audio and work progress information from conferencing systems and project management tools via the communication network. The audio information is converted into text information using general speech recognition technology. Specifically, a "speech recognition API" is used as the speech recognition software. At this stage, the server temporarily stores the audio files and retrieves the corresponding text information using the API.

[0478] Next, the server uses natural language processing technology to analyze textual information and work progress information. For this, the "Text Analysis API" is used as the natural language processing library. Based on the analysis results, the server evaluates each member's contribution based on their statements and automatically generates praise messages based on prompts. Sentiment analysis technology is also used to evaluate the participants' psychological state from their statements. This allows the server to understand the members' motivation and stress levels.

[0479] The analysis results are transmitted to the terminal and visualized as a dashboard on the display device. Users can view the visualized data in real time through the terminal. Specifically, the dashboard is displayed in the form of radar charts and bar graphs using a "data visualization tool," allowing users to see at a glance the contributions and emotional trends of team members.

[0480] Finally, the server notifies each member's device of the generated praise message. This allows users to confirm that their contributions are being recognized, which can boost their motivation.

[0481] As a concrete example, suppose a member proposes an efficient way to manage a new project during a remote meeting. This member's contribution is evaluated by the system, and a message of praise is generated using a prompt, such as, "We look forward to hearing your ideas at the next meeting!"

[0482] Examples of prompts for a generative AI model:

[0483] "Analyze the key statements made during the meeting and create commendation messages for members who made excellent suggestions."

[0484] Through this configuration, the system aims to visualize members' contributions and emotions, and to facilitate communication in a remote work environment.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] The server retrieves audio information from the conferencing system and work progress information from the project management tool via the communication network. Inputs include audio files and task lists for each participant, while outputs include raw audio data and progress data. Specifically, the server calls an API to download audio data and retrieve work progress information.

[0488] Step 2:

[0489] The server uses speech recognition technology to convert the acquired audio data into text data. The input is the audio data obtained in step 1, and the output is the corresponding text data. This conversion utilizes a speech recognition API, and the audio file is uploaded to obtain the text information.

[0490] Step 3:

[0491] The server analyzes text data and work progress information using natural language processing technology. The input for the analysis is text data and progress information, and the output is the analysis results. Specifically, the server uses a natural language processing library to extract important keywords and phrases contained in the text and evaluate the content of members' statements and their level of task completion.

[0492] Step 4:

[0493] The server uses sentiment analysis technology to analyze the psychological state of members from their statements. The input is the text data converted in step 2, and the output is the sentiment analysis result. Using the sentiment analysis API, the text is analyzed to determine the type and intensity of emotion.

[0494] Step 5:

[0495] The terminal receives analysis results sent from the server and visualizes them as a dashboard. Here, the input is the analysis result data, and the output is the visualized data. The terminal uses data visualization tools to generate radar charts and bar graphs, allowing users to review their evaluations.

[0496] Step 6:

[0497] The server uses a generative AI model to generate praise messages for high-contributing members. The input is the contribution evaluation score from the analysis results, and the output is the generated praise message. A prompt is given to the generative AI model, instructing it to "create a message that evaluates this emphasis point," and the message is generated.

[0498] Step 7:

[0499] The server notifies each member's device of the generated praise message. The input here is the praise message, and the output is a notification displayed on each member's device. A message sending API is used to send messages to users' devices in real time, facilitating smooth communication among members.

[0500] (Application Example 1)

[0501] 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."

[0502] In remote work environments and manufacturing sites, it is necessary to appropriately evaluate the contributions and emotions of team members and workers, thereby improving motivation and promoting efficient work execution. In particular, in collaborative work between robots and humans, it is essential to improve the quality of communication and coordination between both parties. The challenge lies in improving work efficiency, reducing worker stress, and facilitating smooth team communication.

[0503] 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.

[0504] In this invention, the server includes means for collecting voice information and work management information using communication means, acoustic recognition means for converting voice information into text information, and means for analyzing text information and work management information using natural language processing. This makes it possible to enhance work efficiency, evaluate the contributions of workers and team members, and notify them with appropriate recognition information. In addition, by using emotion analysis means, the emotional state of workers can be analyzed, appropriate support can be provided, and the quality of collaborative work between robots and humans can be improved. Furthermore, the analysis results can be visualized using display means, promoting cooperation in the work process.

[0505] "Communication means" refers to a technological device that transmits and receives information data via a network.

[0506] "Audio information" refers to data of language or sound waves recorded as sound.

[0507] "Project management information" refers to data that includes information on the progress and tasks related to project and work execution.

[0508] "Acoustic recognition means" refers to a device that converts audio data into text data.

[0509] "Character information" refers to data that is represented as a string of characters.

[0510] "Natural language processing" is a computer technology that analyzes text data and makes it understandable to humans.

[0511] A "generation means" is a technological device that generates new information based on the analysis results.

[0512] "Award information" refers to data that represents praise and commendation for the contributions of workers and team members.

[0513] A "sentiment analysis tool" is a technological device that extracts and evaluates the emotions of workers from data.

[0514] A "visual display device" is a technological device used to display data as graphs or diagrams on a monitor or other display.

[0515] A "terminal device" is an electronic device that receives, displays, or processes data.

[0516] "Means of promoting collaboration" refer to technological devices that support smooth cooperation between different equipment and workers.

[0517] The system implementing this invention aims to improve the efficiency of teamwork and enhance worker motivation in remote environments and manufacturing sites. Specifically, the system consists of a server that collects voice information and work management information via communication means. Next, the server converts the voice information into text information using acoustic recognition means. The Google Speech Recognition API is often used in this process.

[0518] The converted text information and business management information are analyzed on the server using natural language processing. The Hugging Face Transformers library is used for text analysis. Then, the contributions of team members are analyzed using a generation method, and recognition information is generated. For example, if a worker demonstrates outstanding performance, their contribution is analyzed, and recognition information is generated at the appropriate time.

[0519] Furthermore, the server evaluates the emotional state of workers and team members through sentiment analysis tools. This makes it possible to provide support for reducing work-related stress and creating a positive work environment. The analysis results are displayed on the terminal as dashboards and graphs via a visual display device, allowing users to immediately grasp the situation.

[0520] Ultimately, the generated award information is notified to the terminal device, allowing workers to feel that their contributions have been recognized. This improves the efficiency and quality of work. As a concrete example, if a worker on a manufacturing line makes a suggestion to optimize a work process, and as a result, efficiency improves, this will be evaluated and recognized in real time.

[0521] Furthermore, an example of a prompt based on a generative AI model is, "Please explain how to analyze audio and text data to evaluate each member's contribution and generate a message of appreciation." Using this example, it is possible to obtain more detailed analysis and responses.

[0522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0523] Step 1:

[0524] The server collects voice information and business management information using communication methods. It receives data as input from online meeting systems and business management tools, and stores this data. The output is data in a format that can be processed by acoustic recognition means.

[0525] Step 2:

[0526] The server converts audio information collected using acoustic recognition into text information. Here, the Google Speech Recognition API is utilized to convert audio data into text data. The input is an audio file, and the output is data in the corresponding text format.

[0527] Step 3:

[0528] The server analyzes textual and business management information using natural language processing. The Hugging Face Transformers library is used for natural language processing, evaluating the text content and recognizing specific keywords and phrases. The input is the text data created in the previous stage, and the output is the analyzed data.

[0529] Step 4:

[0530] The server uses a generation mechanism to evaluate the worker's contribution based on the analysis results and generates commendation information. At this stage, it automatically recognizes particularly high-contributing actions and generates commendation messages based on them. The input is the analyzed data, and the output is the generated commendation message.

[0531] Step 5:

[0532] The server analyzes the worker's emotional state using sentiment analysis tools. Sentiment analysis employs techniques that evaluate emotional status based on text data. Input is the result of natural language processing and award information, while output is data indicating the worker's emotional state.

[0533] Step 6:

[0534] The terminal displays analysis results from the server on a visual display device. Analysis results, award information, and emotional states are visualized in dashboard and graph formats. This allows users to intuitively understand important information. Input is visualized data from the server, and output is the visual display on the terminal.

[0535] Step 7:

[0536] Users receive commendation information addressed to them through a terminal device. The server delivers a generated commendation message, and the worker feels that their contribution has been recognized. The input is the commendation information data, and the output is the message that the user confirms.

[0537] 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.

[0538] The system for implementing this invention collects and analyzes voice data, text data, and project management data via a server and terminals incorporating an emotion engine. The aim is to recognize user emotions and improve communication within the team.

[0539] First, the server acquires audio and project management data from the conference system and project management tools via the communication network. The server converts this audio data into text data using speech recognition technology, and then analyzes the results using natural language processing technology. This analysis identifies members' contributions and important statements.

[0540] Next, the emotion engine is applied to the text and audio data to recognize the user's emotional state in real time. For example, emotions such as "joy," "anxiety," and "calmness" are detected from the user's statements. This information optimizes the praise messages generated by the server, customizing them to match the user's emotions.

[0541] Furthermore, the analysis results and emotional states are sent to the device and displayed as a dashboard that visualizes each member's strengths, contributions, and emotional state. This display deepens mutual understanding among members and strengthens team collaboration.

[0542] The terminal also notifies the user of praise messages sent from the server. Receiving these messages lets the user know their contributions are recognized, resulting in increased motivation. This system is expected to promote communication and respect among users, even in remote work environments, and improve overall workplace efficiency.

[0543] The following describes the processing flow.

[0544] Step 1:

[0545] The server accesses the conference system and project management tools via the communication network to collect audio and project management data. At this stage, the audio data is captured in a streaming format and transferred to the server in real time.

[0546] Step 2:

[0547] The server uses speech recognition technology to instantly convert the streamed audio data into text data. The converted text data is stored in a format that accurately records the content of the meeting.

[0548] Step 3:

[0549] The server utilizes natural language processing technology to analyze text data and project management data. This analysis extracts key phrases and important issues from discussions, and quantifies members' contributions.

[0550] Step 4:

[0551] Based on the generated analysis data, the server applies an emotion engine. This identifies the emotional state from the user's conversation and makes evaluations such as "User A is positive" or "User B is feeling anxious."

[0552] Step 5:

[0553] Taking into account the analyzed contribution and emotional state, the server automatically generates a message of praise. Here, the message is customized for each member, providing content tailored to their individual emotional state.

[0554] Step 6:

[0555] The device receives analysis results and praise messages sent from the server and visualizes them as a dashboard. Users can view each member's contribution level and emotional state as radar charts and timelines.

[0556] Step 7:

[0557] Users can review the praise messages notified on their devices and understand how their contributions and feelings were appreciated. This fosters cognitive and emotional engagement among users, improving motivation and efficiency in the workplace.

[0558] (Example 2)

[0559] 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."

[0560] In today's work environment, remote work and non-face-to-face communication are increasing. In this situation, it is difficult to accurately grasp the emotions and contributions of team members and to provide appropriate feedback, making team collaboration and motivation improvement challenges.

[0561] 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.

[0562] In this invention, the server includes means for acquiring voice information and business management information via a communication network, voice conversion means for converting the acquired voice information into text information, and means for interpreting the text information and business management information by language processing. This enables efficient analysis of team members' emotions and contributions even in a remote environment, and allows for the generation of evaluation messages and visualization of emotions.

[0563] A "communication network" refers to the network infrastructure used for sending and receiving digital data, and is a means of efficiently handling voice information and business management information.

[0564] "Audio information" refers to data that is recorded or transmitted in audio format and forms the basis for electronically processing human speech.

[0565] "Business management information" refers to data that records the progress of work and project details within an organization, and is used for efficient business operations.

[0566] "Speech conversion means" refers to technology that converts speech information into text information, and is a device or program that uses speech recognition technology to convert human speech into text format.

[0567] "Textual information" refers to text data recorded in digital format, which can be used for language processing, searching, and storage.

[0568] "Language processing" refers to the techniques used to analyze human language and mechanically understand its structure and meaning, and is also known as natural language processing.

[0569] "Interpretation methods" refer to techniques or processes for analyzing acquired data and understanding its meaning and trends.

[0570] "Emotional interpretation methods" refer to technologies that analyze a user's emotional state from data and evaluate it quantitatively or qualitatively.

[0571] A "display panel" refers to a digital interface for visually displaying interpretation results, providing the analyzed information in the form of graphs and charts.

[0572] "Means of transmission" refers to the technology or system used to send generated messages or information to the terminal of a designated recipient.

[0573] The system for implementing this invention aims to improve team communication by efficiently collecting voice information and business management information using a digital network, and by processing and analyzing it. The embodiments are described in detail below.

[0574] Server operation

[0575] The server acquires audio information from conferencing systems and task management systems via the communication network. During this process, it captures the audio information using a common API and converts it into text using a speech recognition service such as Google Cloud Speech-to-Text. The converted text is then analyzed using a natural language processing engine (e.g., spaCy). This natural language processing performs keyword extraction from the utterances, determines the speaker's level of involvement, and automatically recognizes important statements.

[0576] Emotional interpretation and generation

[0577] The server uses an emotion interpretation engine to analyze the user's emotional state from acquired text and audio information. During this process, it uses an emotion analysis API (e.g., IBM Watson) to identify emotions such as "joy," "anxiety," and "calmness" in real time. Based on this, the server generates appropriately tailored evaluation messages for the user, providing feedback that aligns with the member's emotions.

[0578] Terminal processing

[0579] The terminal displays analysis results sent from the server as a dashboard, visually representing the team's dynamics. Here, each user's contribution and emotional state are visualized in chart format, facilitating mutual understanding among team members. The terminal also notifies users of evaluation messages generated by the server, ensuring that their individual contributions are appropriately recognized.

[0580] Specific example

[0581] User A participates in a remote meeting, and the audio information of that meeting is collected by a server. The audio is converted into text information via a speech-to-text converter and analyzed by a language processing device. The analysis determines that User A actively participated in the meeting and made useful contributions. Furthermore, because User A's emotional state is analyzed as "joyful," a message of praise such as "Thank you for your creative suggestions" is sent to the device.

[0582] Example of a prompt

[0583] "Design a program to estimate team members' emotions based on user conversations and evaluate their project contributions. It needs to provide specific emotion labels (e.g., joy, anxiety, calmness) and personalized praise messages based on those labels."

[0584] Thus, the present invention provides a means to improve teamwork through effective information analysis and emotion recognition.

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] The server retrieves audio and project management information from conference systems and task management systems via the communication network. Audio files from meetings and project management data are provided as input. Audio information is typically retrieved using an API, automatically fetching data from the system. The output consists of raw audio data stored on the server and project-related management data.

[0588] Step 2:

[0589] The server converts the acquired audio information into text information using a speech-to-text conversion method. This process utilizes services such as Google Cloud Speech-to-Text. The input is raw audio data, which is then converted into text format. Specifically, the audio file is sent to the cloud service, and the returned text data is retrieved. The output is text information.

[0590] Step 3:

[0591] The server performs language processing using textual information and business management information. A natural language processing engine, such as spaCy, is used to analyze specific keywords, contributions, and roles. The input consists of textual information and business management information obtained in step 2. Based on this information, data tagging and statistical analysis are performed. The output consists of syntactic analysis results and contribution data for each member.

[0592] Step 4:

[0593] The server uses an emotion interpretation engine to identify the user's emotional state from the text information. The input includes the text information generated in step 3. Emotion analysis APIs such as IBM Watson are utilized for emotion interpretation. Specifically, it calculates positive, negative, and neutral emotion scores for the text. The output is quantitative data on the user's emotional state.

[0594] Step 5:

[0595] The server generates an evaluation message based on the analysis results. The analysis results, as input, include emotional state and contribution level. A generative AI model is used to create individually tailored messages. The output is a customized evaluation message.

[0596] Step 6:

[0597] The terminal receives analysis results and evaluation messages sent from the server and visualizes them in a dashboard format. Inputs include evaluation messages generated in step 5 and contribution data from step 3. Specifically, it displays information using graphs and charts and notifies the user. Outputs include a dashboard display and message notifications that the user can visually confirm.

[0598] (Application Example 2)

[0599] 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."

[0600] In remote work environments and at home, smooth communication is often difficult, posing a challenge in accurately evaluating and appreciating team members' collaboration and contributions. There is a need for methods to improve the quality of communication in remote work and home environments by providing appropriate responses and encouragement through emotional recognition within the home.

[0601] 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.

[0602] In this invention, the server includes means for collecting voice data and management data via a communication network, voice recognition means for converting the collected voice data into text data, and means for analyzing the text data and management data by language processing. This makes it possible to facilitate smooth communication in a home environment, accurately evaluate members' contributions, and provide appropriate emotional responses.

[0603] A "communication network" is a digital information transfer route for collecting and transmitting voice data and management data.

[0604] "Audio data" refers to data that records human speech and ambient sounds in digital format.

[0605] "Management data" refers to data that includes information related to a project or task.

[0606] "Character data" refers to discrete text information converted by speech recognition.

[0607] "Speech recognition means" refers to technology that analyzes speech data and converts it into text data.

[0608] "Language processing" is the technology used to analyze natural language and understand its meaning and emotions.

[0609] A "member" is an individual who participates as a member of a specific group or team.

[0610] "Contribution" refers to the support and results achieved for a group or project.

[0611] "Emotional response" refers to appropriate actions and messages generated in accordance with the user's emotional state.

[0612] "Home environment" refers to the circumstances surrounding an individual's daily life in the place where they live.

[0613] To implement this invention, it is necessary to build a system centered on a server and terminals. The server collects voice data and management data using a communication network. Voice data is acquired via a terminal equipped with a microphone and transmitted to the server. The server converts the voice data into text data using speech recognition technology and then performs analysis using a language processing engine.

[0614] The information obtained through analysis is used to evaluate members' contributions and emotional states. To analyze emotional states, an emotion analysis engine is used to identify characteristic emotions from the user's voice and text. For example, if a text contains many positive words, it will be processed as "joyful."

[0615] This system generates emotional responses from home automated devices and delivers them to the user at the appropriate time. For example, if the system detects that the user is feeling stressed, the robot will immediately provide an encouraging message. This response is optimized for the user's specific situation and is generated based on emotional analysis and historical data.

[0616] An example of a prompt message would be, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement." This message is sent to a generative AI model and used as a guide for generating appropriate messages. This enables smoother communication within the family environment and increases the contribution of family members.

[0617] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0618] Step 1:

[0619] The terminal collects voice data through its microphone and sends that data to the server. Real-time voice data is the input, and the audio data, converted to a digital format, is sent to the server as output. Specifically, the microphone captures the user's speech and sends it to the server via a data communication protocol.

[0620] Step 2:

[0621] The server converts received audio data into text data using speech recognition technology. It receives digital audio data as input and generates corresponding text data as output. Specifically, the speech recognition engine performs phoneme-to-text conversion, checks for errors, and generates consistent text data.

[0622] Step 3:

[0623] The server analyzes the generated character data using a language processing engine. The input is character data, and the output is the result of the analysis of emotion and meaning. The specific analysis operation involves detecting the emotions used from the content of the text; for example, it calculates the frequency of positive words to extract emotions such as "joy."

[0624] Step 4:

[0625] The server generates a response message based on the sentiment analysis results and sends it to the home automated device. The input is the sentiment analysis results, and the output is a response message suitable for the automated device. Specifically, it uses a generative AI model to create the message best suited to the sentiment data and optimizes it according to the prompt statement, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement."

[0626] Step 5:

[0627] Home automated devices present received response messages to the user with appropriate voice and actions. The input is the generated response message, and the output is the message content as perceived by the user. Specifically, the action involves a speech synthesis engine uttering the message and performing related actions (e.g., displaying it on a screen or turning on a light).

[0628] 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.

[0629] 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.

[0630] 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.

[0631] [Fourth Embodiment]

[0632] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0633] 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.

[0634] 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).

[0635] 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.

[0636] 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.

[0637] 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).

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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".

[0645] A system for carrying out this invention consists of a server and terminals that include multiple modules for acquiring voice data and project management data via a communication network, and for analyzing and visualizing them.

[0646] First, the server collects audio and project management data from the meeting system and project management tools. The server then converts the audio data into text using speech recognition technology. This allows users to later review the meeting content in text format.

[0647] The server then uses natural language processing techniques to analyze text data and project management data. The purpose of the analysis is to evaluate the contributions of individual members and generate messages of appreciation. For example, if a member proposes an effective idea in a meeting, that contribution will be identified and a message of appreciation will be generated.

[0648] Furthermore, the server uses sentiment analysis technology to analyze members' emotional states from their statements and reactions. This allows for an understanding of stress levels and trends in positive emotions within the team. The results of this analysis are visually displayed on the terminal as a dashboard. The dashboard uses radar charts and bar graphs to show members' contributions and emotional states at a glance.

[0649] Finally, the generated praise message is sent from the server to each member's terminal. Upon receiving this notification, users feel their contributions are recognized, leading to increased motivation. This system promotes respect and communication among members, even in a remote work environment, contributing to improved work productivity.

[0650] The following describes the processing flow.

[0651] Step 1:

[0652] The server communicates with the conferencing system and project management tools, collecting audio and project data in real time. Audio data is streamed directly, while project data is retrieved via an API.

[0653] Step 2:

[0654] The server converts the acquired audio data into text data using speech recognition technology. This process saves the meeting content as text information, which can then be used for later analysis.

[0655] Step 3:

[0656] The server utilizes natural language processing technology to analyze text data and project management data. This involves extracting key keywords and performing contextual analysis to identify member contributions and important statements.

[0657] Step 4:

[0658] Based on the analysis results, the server uses a generation AI to automatically generate a message of praise. For example, a message such as "User A's suggestion made the project more efficient" might be created.

[0659] Step 5:

[0660] The server applies sentiment analysis technology to analyze the emotional state of members from text data. This determines emotional categories such as positive, negative, and neutral.

[0661] Step 6:

[0662] The terminal receives analysis results and praise messages sent from the server and displays them visually on the dashboard. Each member's contribution and emotional state are represented using radar charts and bar graphs.

[0663] Step 7:

[0664] Users see the praise message notified on their device and understand that their contributions have been recognized. This increases user motivation and encourages them to engage in further work.

[0665] (Example 1)

[0666] 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".

[0667] In remote work environments, smooth communication among team members is often hindered, making it difficult to accurately grasp members' contributions and emotional states. Furthermore, there is a lack of mechanisms to properly evaluate members' contributions and thereby improve motivation. As a result, the efficiency of remote work decreases, and productivity is less likely to improve.

[0668] 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.

[0669] In this invention, the server includes means for collecting voice information and work progress information via a communication network, voice recognition means for converting the collected voice information into text information, and means for analyzing the text information and work progress information using natural language processing. This enables accurate evaluation of members' contributions, generation and notification of praise messages, thereby facilitating communication within the team and improving the productivity of remote work.

[0670] A "communication network" is the infrastructure used to send and receive information between electronic devices.

[0671] "Audio information" refers to information that records or transmits human speech as acoustic signals.

[0672] "Work progress information" refers to data that shows the progress of a project or task.

[0673] "Speech recognition means" refers to a technology or device that analyzes speech signals and converts them into corresponding textual information.

[0674] "Textual information" refers to data expressed in characters in a format usable by humans or machines.

[0675] "Natural language processing" is a technology that uses computers to understand, interpret, and generate human language.

[0676] "Sentiment analysis methods" refer to technologies or devices that estimate an individual's emotions and psychological state from text or audio.

[0677] "Display means" refers to a technology or device that presents data or information to humans visually.

[0678] A "praise message" is a written or spoken message that evaluates and positively communicates a specific action or achievement.

[0679] "Communication means" refers to the technology or equipment used to send and receive information.

[0680] The system for implementing this invention includes a server and terminals and is designed to streamline team communication in a remote work environment.

[0681] First, the server collects audio and work progress information from conferencing systems and project management tools via the communication network. The audio information is converted into text information using general speech recognition technology. Specifically, a "speech recognition API" is used as the speech recognition software. At this stage, the server temporarily stores the audio files and retrieves the corresponding text information using the API.

[0682] Next, the server uses natural language processing technology to analyze textual information and work progress information. For this, the "Text Analysis API" is used as the natural language processing library. Based on the analysis results, the server evaluates each member's contribution based on their statements and automatically generates praise messages based on prompts. Sentiment analysis technology is also used to evaluate the participants' psychological state from their statements. This allows the server to understand the members' motivation and stress levels.

[0683] The analysis results are transmitted to the terminal and visualized as a dashboard on the display device. Users can view the visualized data in real time through the terminal. Specifically, the dashboard is displayed in the form of radar charts and bar graphs using a "data visualization tool," allowing users to see at a glance the contributions and emotional trends of team members.

[0684] Finally, the server notifies each member's device of the generated praise message. This allows users to confirm that their contributions are being recognized, which can boost their motivation.

[0685] As a concrete example, suppose a member proposes an efficient way to manage a new project during a remote meeting. This member's contribution is evaluated by the system, and a message of praise is generated using a prompt, such as, "We look forward to hearing your ideas at the next meeting!"

[0686] Examples of prompts for a generative AI model:

[0687] "Analyze the key statements made during the meeting and create commendation messages for members who made excellent suggestions."

[0688] Through this configuration, the system aims to visualize members' contributions and emotions, and to facilitate communication in a remote work environment.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] The server retrieves audio information from the conferencing system and work progress information from the project management tool via the communication network. Inputs include audio files and task lists for each participant, while outputs include raw audio data and progress data. Specifically, the server calls an API to download audio data and retrieve work progress information.

[0692] Step 2:

[0693] The server uses speech recognition technology to convert the acquired audio data into text data. The input is the audio data obtained in step 1, and the output is the corresponding text data. This conversion utilizes a speech recognition API, and the audio file is uploaded to obtain the text information.

[0694] Step 3:

[0695] The server analyzes text data and work progress information using natural language processing technology. The input for the analysis is text data and progress information, and the output is the analysis results. Specifically, the server uses a natural language processing library to extract important keywords and phrases contained in the text and evaluate the content of members' statements and their level of task completion.

[0696] Step 4:

[0697] The server uses sentiment analysis technology to analyze the psychological state of members from their statements. The input is the text data converted in step 2, and the output is the sentiment analysis result. Using the sentiment analysis API, the text is analyzed to determine the type and intensity of emotion.

[0698] Step 5:

[0699] The terminal receives analysis results sent from the server and visualizes them as a dashboard. Here, the input is the analysis result data, and the output is the visualized data. The terminal uses data visualization tools to generate radar charts and bar graphs, allowing users to review their evaluations.

[0700] Step 6:

[0701] The server uses a generative AI model to generate praise messages for high-contributing members. The input is the contribution evaluation score from the analysis results, and the output is the generated praise message. A prompt is given to the generative AI model, instructing it to "create a message that evaluates this emphasis point," and the message is generated.

[0702] Step 7:

[0703] The server notifies each member's device of the generated praise message. The input here is the praise message, and the output is a notification displayed on each member's device. A message sending API is used to send messages to users' devices in real time, facilitating smooth communication among members.

[0704] (Application Example 1)

[0705] 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".

[0706] In remote work environments and manufacturing sites, it is necessary to appropriately evaluate the contributions and emotions of team members and workers, thereby improving motivation and promoting efficient work execution. In particular, in collaborative work between robots and humans, it is essential to improve the quality of communication and coordination between both parties. The challenge lies in improving work efficiency, reducing worker stress, and facilitating smooth team communication.

[0707] 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.

[0708] In this invention, the server includes means for collecting voice information and work management information using communication means, acoustic recognition means for converting voice information into text information, and means for analyzing text information and work management information using natural language processing. This makes it possible to enhance work efficiency, evaluate the contributions of workers and team members, and notify them with appropriate recognition information. In addition, by using emotion analysis means, the emotional state of workers can be analyzed, appropriate support can be provided, and the quality of collaborative work between robots and humans can be improved. Furthermore, the analysis results can be visualized using display means, promoting cooperation in the work process.

[0709] "Communication means" refers to a technological device that transmits and receives information data via a network.

[0710] "Audio information" refers to data of language or sound waves recorded as sound.

[0711] "Project management information" refers to data that includes information on the progress and tasks related to project and work execution.

[0712] "Acoustic recognition means" refers to a device that converts audio data into text data.

[0713] "Character information" refers to data that is represented as a string of characters.

[0714] "Natural language processing" is a computer technology that analyzes text data and makes it understandable to humans.

[0715] A "generation means" is a technological device that generates new information based on the analysis results.

[0716] "Award information" refers to data that represents praise and commendation for the contributions of workers and team members.

[0717] A "sentiment analysis tool" is a technological device that extracts and evaluates the emotions of workers from data.

[0718] A "visual display device" is a technological device used to display data as graphs or diagrams on a monitor or other display.

[0719] A "terminal device" is an electronic device that receives, displays, or processes data.

[0720] "Means of promoting collaboration" refer to technological devices that support smooth cooperation between different equipment and workers.

[0721] The system implementing this invention aims to improve the efficiency of teamwork and enhance worker motivation in remote environments and manufacturing sites. Specifically, the system consists of a server that collects voice information and work management information via communication means. Next, the server converts the voice information into text information using acoustic recognition means. The Google Speech Recognition API is often used in this process.

[0722] The converted text information and business management information are analyzed on the server using natural language processing. The Hugging Face Transformers library is used for text analysis. Then, the contributions of team members are analyzed using a generation method, and recognition information is generated. For example, if a worker demonstrates outstanding performance, their contribution is analyzed, and recognition information is generated at the appropriate time.

[0723] Furthermore, the server evaluates the emotional state of workers and team members through sentiment analysis tools. This makes it possible to provide support for reducing work-related stress and creating a positive work environment. The analysis results are displayed on the terminal as dashboards and graphs via a visual display device, allowing users to immediately grasp the situation.

[0724] Ultimately, the generated award information is notified to the terminal device, allowing workers to feel that their contributions have been recognized. This improves the efficiency and quality of work. As a concrete example, if a worker on a manufacturing line makes a suggestion to optimize a work process, and as a result, efficiency improves, this will be evaluated and recognized in real time.

[0725] Furthermore, an example of a prompt based on a generative AI model is, "Please explain how to analyze audio and text data to evaluate each member's contribution and generate a message of appreciation." Using this example, it is possible to obtain more detailed analysis and responses.

[0726] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0727] Step 1:

[0728] The server collects voice information and business management information using communication methods. It receives data as input from online meeting systems and business management tools, and stores this data. The output is data in a format that can be processed by acoustic recognition means.

[0729] Step 2:

[0730] The server converts audio information collected using acoustic recognition into text information. Here, the Google Speech Recognition API is utilized to convert audio data into text data. The input is an audio file, and the output is data in the corresponding text format.

[0731] Step 3:

[0732] The server analyzes textual and business management information using natural language processing. The Hugging Face Transformers library is used for natural language processing, evaluating the text content and recognizing specific keywords and phrases. The input is the text data created in the previous stage, and the output is the analyzed data.

[0733] Step 4:

[0734] The server uses a generation mechanism to evaluate the worker's contribution based on the analysis results and generates commendation information. At this stage, it automatically recognizes particularly high-contributing actions and generates commendation messages based on them. The input is the analyzed data, and the output is the generated commendation message.

[0735] Step 5:

[0736] The server analyzes the worker's emotional state using sentiment analysis tools. Sentiment analysis employs techniques that evaluate emotional status based on text data. Input is the result of natural language processing and award information, while output is data indicating the worker's emotional state.

[0737] Step 6:

[0738] The terminal displays analysis results from the server on a visual display device. Analysis results, award information, and emotional states are visualized in dashboard and graph formats. This allows users to intuitively understand important information. Input is visualized data from the server, and output is the visual display on the terminal.

[0739] Step 7:

[0740] Users receive commendation information addressed to them through a terminal device. The server delivers a generated commendation message, and the worker feels that their contribution has been recognized. The input is the commendation information data, and the output is the message that the user confirms.

[0741] 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.

[0742] The system for implementing this invention collects and analyzes voice data, text data, and project management data via a server and terminals incorporating an emotion engine. The aim is to recognize user emotions and improve communication within the team.

[0743] First, the server acquires audio and project management data from the conference system and project management tools via the communication network. The server converts this audio data into text data using speech recognition technology, and then analyzes the results using natural language processing technology. This analysis identifies members' contributions and important statements.

[0744] Next, the emotion engine is applied to the text and audio data to recognize the user's emotional state in real time. For example, emotions such as "joy," "anxiety," and "calmness" are detected from the user's statements. This information optimizes the praise messages generated by the server, customizing them to match the user's emotions.

[0745] Furthermore, the analysis results and emotional states are sent to the device and displayed as a dashboard that visualizes each member's strengths, contributions, and emotional state. This display deepens mutual understanding among members and strengthens team collaboration.

[0746] The terminal also notifies the user of praise messages sent from the server. Receiving these messages lets the user know their contributions are recognized, resulting in increased motivation. This system is expected to promote communication and respect among users, even in remote work environments, and improve overall workplace efficiency.

[0747] The following describes the processing flow.

[0748] Step 1:

[0749] The server accesses the conference system and project management tools via the communication network to collect audio and project management data. At this stage, the audio data is captured in a streaming format and transferred to the server in real time.

[0750] Step 2:

[0751] The server uses speech recognition technology to instantly convert the streamed audio data into text data. The converted text data is stored in a format that accurately records the content of the meeting.

[0752] Step 3:

[0753] The server utilizes natural language processing technology to analyze text data and project management data. This analysis extracts key phrases and important issues from discussions, and quantifies members' contributions.

[0754] Step 4:

[0755] Based on the generated analysis data, the server applies an emotion engine. This identifies the emotional state from the user's conversation and makes evaluations such as "User A is positive" or "User B is feeling anxious."

[0756] Step 5:

[0757] Taking into account the analyzed contribution and emotional state, the server automatically generates a message of praise. Here, the message is customized for each member, providing content tailored to their individual emotional state.

[0758] Step 6:

[0759] The device receives analysis results and praise messages sent from the server and visualizes them as a dashboard. Users can view each member's contribution level and emotional state as radar charts and timelines.

[0760] Step 7:

[0761] Users can review the praise messages notified on their devices and understand how their contributions and feelings were appreciated. This fosters cognitive and emotional engagement among users, improving motivation and efficiency in the workplace.

[0762] (Example 2)

[0763] 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".

[0764] In today's work environment, remote work and non-face-to-face communication are increasing. In this situation, it is difficult to accurately grasp the emotions and contributions of team members and to provide appropriate feedback, making team collaboration and motivation improvement challenges.

[0765] 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.

[0766] In this invention, the server includes means for acquiring voice information and business management information via a communication network, voice conversion means for converting the acquired voice information into text information, and means for interpreting the text information and business management information by language processing. This enables efficient analysis of team members' emotions and contributions even in a remote environment, and allows for the generation of evaluation messages and visualization of emotions.

[0767] A "communication network" refers to the network infrastructure used for sending and receiving digital data, and is a means of efficiently handling voice information and business management information.

[0768] "Audio information" refers to data that is recorded or transmitted in audio format and forms the basis for electronically processing human speech.

[0769] "Business management information" refers to data that records the progress of work and project details within an organization, and is used for efficient business operations.

[0770] "Speech conversion means" refers to technology that converts speech information into text information, and is a device or program that uses speech recognition technology to convert human speech into text format.

[0771] "Textual information" refers to text data recorded in digital format, which can be used for language processing, searching, and storage.

[0772] "Language processing" refers to the techniques used to analyze human language and mechanically understand its structure and meaning, and is also known as natural language processing.

[0773] "Interpretation methods" refer to techniques or processes for analyzing acquired data and understanding its meaning and trends.

[0774] "Emotional interpretation methods" refer to technologies that analyze a user's emotional state from data and evaluate it quantitatively or qualitatively.

[0775] A "display panel" refers to a digital interface for visually displaying interpretation results, providing the analyzed information in the form of graphs and charts.

[0776] "Means of transmission" refers to the technology or system used to send generated messages or information to the terminal of a designated recipient.

[0777] The system for implementing this invention aims to improve team communication by efficiently collecting voice information and business management information using a digital network, and by processing and analyzing it. The embodiments are described in detail below.

[0778] Server operation

[0779] The server acquires audio information from conferencing systems and task management systems via the communication network. During this process, it captures the audio information using a common API and converts it into text using a speech recognition service such as Google Cloud Speech-to-Text. The converted text is then analyzed using a natural language processing engine (e.g., spaCy). This natural language processing performs keyword extraction from the utterances, determines the speaker's level of involvement, and automatically recognizes important statements.

[0780] Emotional interpretation and generation

[0781] The server uses an emotion interpretation engine to analyze the user's emotional state from acquired text and audio information. During this process, it uses an emotion analysis API (e.g., IBM Watson) to identify emotions such as "joy," "anxiety," and "calmness" in real time. Based on this, the server generates appropriately tailored evaluation messages for the user, providing feedback that aligns with the member's emotions.

[0782] Terminal processing

[0783] The terminal displays analysis results sent from the server as a dashboard, visually representing the team's dynamics. Here, each user's contribution and emotional state are visualized in chart format, facilitating mutual understanding among team members. The terminal also notifies users of evaluation messages generated by the server, ensuring that their individual contributions are appropriately recognized.

[0784] Specific example

[0785] User A participates in a remote meeting, and the audio information of that meeting is collected by a server. The audio is converted into text information via a speech-to-text converter and analyzed by a language processing device. The analysis determines that User A actively participated in the meeting and made useful contributions. Furthermore, because User A's emotional state is analyzed as "joyful," a message of praise such as "Thank you for your creative suggestions" is sent to the device.

[0786] Example of a prompt

[0787] "Design a program to estimate team members' emotions based on user conversations and evaluate their project contributions. It needs to provide specific emotion labels (e.g., joy, anxiety, calmness) and personalized praise messages based on those labels."

[0788] Thus, the present invention provides a means to improve teamwork through effective information analysis and emotion recognition.

[0789] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0790] Step 1:

[0791] The server retrieves audio and project management information from conference systems and task management systems via the communication network. Audio files from meetings and project management data are provided as input. Audio information is typically retrieved using an API, automatically fetching data from the system. The output consists of raw audio data stored on the server and project-related management data.

[0792] Step 2:

[0793] The server converts the acquired audio information into text information using a speech-to-text conversion method. This process utilizes services such as Google Cloud Speech-to-Text. The input is raw audio data, which is then converted into text format. Specifically, the audio file is sent to the cloud service, and the returned text data is retrieved. The output is text information.

[0794] Step 3:

[0795] The server performs language processing using textual information and business management information. A natural language processing engine, such as spaCy, is used to analyze specific keywords, contributions, and roles. The input consists of textual information and business management information obtained in step 2. Based on this information, data tagging and statistical analysis are performed. The output consists of syntactic analysis results and contribution data for each member.

[0796] Step 4:

[0797] The server uses an emotion interpretation engine to identify the user's emotional state from the text information. The input includes the text information generated in step 3. Emotion analysis APIs such as IBM Watson are utilized for emotion interpretation. Specifically, it calculates positive, negative, and neutral emotion scores for the text. The output is quantitative data on the user's emotional state.

[0798] Step 5:

[0799] The server generates an evaluation message based on the analysis results. The analysis results, as input, include emotional state and contribution level. A generative AI model is used to create individually tailored messages. The output is a customized evaluation message.

[0800] Step 6:

[0801] The terminal receives analysis results and evaluation messages sent from the server and visualizes them in a dashboard format. Inputs include evaluation messages generated in step 5 and contribution data from step 3. Specifically, it displays information using graphs and charts and notifies the user. Outputs include a dashboard display and message notifications that the user can visually confirm.

[0802] (Application Example 2)

[0803] 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".

[0804] In remote work environments and at home, smooth communication is often difficult, posing a challenge in accurately evaluating and appreciating team members' collaboration and contributions. There is a need for methods to improve the quality of communication in remote work and home environments by providing appropriate responses and encouragement through emotional recognition within the home.

[0805] 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.

[0806] In this invention, the server includes means for collecting voice data and management data via a communication network, voice recognition means for converting the collected voice data into text data, and means for analyzing the text data and management data by language processing. This makes it possible to facilitate smooth communication in a home environment, accurately evaluate members' contributions, and provide appropriate emotional responses.

[0807] A "communication network" is a digital information transfer route for collecting and transmitting voice data and management data.

[0808] "Audio data" refers to data that records human speech and ambient sounds in digital format.

[0809] "Management data" refers to data that includes information related to a project or task.

[0810] "Character data" refers to discrete text information converted by speech recognition.

[0811] "Speech recognition means" refers to technology that analyzes speech data and converts it into text data.

[0812] "Language processing" is the technology used to analyze natural language and understand its meaning and emotions.

[0813] A "member" is an individual who participates as a member of a specific group or team.

[0814] "Contribution" refers to the support and results achieved for a group or project.

[0815] "Emotional response" refers to appropriate actions and messages generated in accordance with the user's emotional state.

[0816] "Home environment" refers to the circumstances surrounding an individual's daily life in the place where they live.

[0817] To implement this invention, it is necessary to build a system centered on a server and terminals. The server collects voice data and management data using a communication network. Voice data is acquired via a terminal equipped with a microphone and transmitted to the server. The server converts the voice data into text data using speech recognition technology and then performs analysis using a language processing engine.

[0818] The information obtained through analysis is used to evaluate members' contributions and emotional states. To analyze emotional states, an emotion analysis engine is used to identify characteristic emotions from the user's voice and text. For example, if a text contains many positive words, it will be processed as "joyful."

[0819] This system generates emotional responses from home automated devices and delivers them to the user at the appropriate time. For example, if the system detects that the user is feeling stressed, the robot will immediately provide an encouraging message. This response is optimized for the user's specific situation and is generated based on emotional analysis and historical data.

[0820] An example of a prompt message would be, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement." This message is sent to a generative AI model and used as a guide for generating appropriate messages. This enables smoother communication within the family environment and increases the contribution of family members.

[0821] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0822] Step 1:

[0823] The terminal collects voice data through its microphone and sends that data to the server. Real-time voice data is the input, and the audio data, converted to a digital format, is sent to the server as output. Specifically, the microphone captures the user's speech and sends it to the server via a data communication protocol.

[0824] Step 2:

[0825] The server converts received audio data into text data using speech recognition technology. It receives digital audio data as input and generates corresponding text data as output. Specifically, the speech recognition engine performs phoneme-to-text conversion, checks for errors, and generates consistent text data.

[0826] Step 3:

[0827] The server analyzes the generated character data using a language processing engine. The input is character data, and the output is the result of the analysis of emotion and meaning. The specific analysis operation involves detecting the emotions used from the content of the text; for example, it calculates the frequency of positive words to extract emotions such as "joy."

[0828] Step 4:

[0829] The server generates a response message based on the sentiment analysis results and sends it to the home automated device. The input is the sentiment analysis results, and the output is a response message suitable for the automated device. Specifically, it uses a generative AI model to create the message best suited to the sentiment data and optimizes it according to the prompt statement, "Recognize emotions from conversations within the family and generate an appropriate message of encouragement."

[0830] Step 5:

[0831] Home automated devices present received response messages to the user with appropriate voice and actions. The input is the generated response message, and the output is the message content as perceived by the user. Specifically, the action involves a speech synthesis engine uttering the message and performing related actions (e.g., displaying it on a screen or turning on a light).

[0832] 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.

[0833] 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.

[0834] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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."

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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 to be incorporated by reference.

[0853] The following is further disclosed regarding the embodiments described above.

[0854] (Claim 1)

[0855] A means for collecting voice data and project management data via a communication network,

[0856] A speech recognition means that converts collected audio data into text data,

[0857] A means for analyzing text data and project management data using natural language processing,

[0858] A generation means that evaluates the contributions of team members based on the analysis results and generates a message of praise,

[0859] A sentiment analysis tool for analyzing the emotional state of team members,

[0860] A display method for visualizing the analysis results as a dashboard,

[0861] A means of notifying team members of praise messages on their devices,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, further comprising means for customizing the generated praise message according to the member's contribution.

[0865] (Claim 3)

[0866] The system according to claim 1, further comprising means of communication for promoting expressions of gratitude among members.

[0867] "Example 1"

[0868] (Claim 1)

[0869] Means for collecting voice information and work progress information via a communication network,

[0870] A speech recognition means that converts collected audio information into text information,

[0871] A means for analyzing textual information and work progress information using natural language processing,

[0872] A generation means that evaluates the contributions of the work participants based on the analysis results and generates a message of praise,

[0873] A means of emotional analysis to analyze the psychological state of the work participants,

[0874] A display means for displaying the analysis results as visualized information,

[0875] A means of notifying the devices of the work participants of praise messages,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, further comprising means for personalizing the generated praise messages according to the participant's contribution.

[0879] (Claim 3)

[0880] The system according to claim 1, further comprising means for facilitating expressions of gratitude among participants.

[0881] "Application Example 1"

[0882] (Claim 1)

[0883] A means for collecting voice information and business management information using communication means,

[0884] Acoustic recognition means for converting collected audio information into text information,

[0885] A means for analyzing textual information and business management information using natural language processing,

[0886] A generation means that evaluates the worker's contribution based on the analysis results and generates award information,

[0887] A means of analyzing the emotional state of workers,

[0888] A display means for visualizing the analysis results as a visual display device,

[0889] A means of notifying workers of award information via their terminal devices,

[0890] In the work process, means to promote collaboration between robots and humans in order to enhance operational efficiency,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, further comprising means for individualizing the generated award information according to the worker's contribution.

[0894] (Claim 3)

[0895] The system according to claim 1, further comprising means for communication to promote appreciation among workers and improve work efficiency.

[0896] "Example 2 of combining an emotion engine"

[0897] (Claim 1)

[0898] Means for acquiring voice information and business management information via a communication network,

[0899] A speech conversion means that converts acquired speech information into text information,

[0900] A means for interpreting textual information and business management information through language processing,

[0901] A generation means that evaluates the contributions of team members based on the interpretation results and generates an evaluation message,

[0902] A means of interpreting emotions to analyze the emotional state of team members,

[0903] A display means for visualizing the interpretation results as a display panel,

[0904] A means of transmitting evaluation messages to the devices of team members,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, further comprising means for adjusting the generated evaluation message according to the contribution of the members.

[0908] (Claim 3)

[0909] The system according to claim 1, further comprising means of communication for promoting appreciation among members.

[0910] "Application example 2 when combining with an emotional engine"

[0911] (Claim 1)

[0912] Means for collecting voice data and management data via a communication network,

[0913] A speech recognition means that converts collected audio data into text data,

[0914] A means for analyzing character data and management data using language processing,

[0915] A generation means that evaluates the contributions of members based on the analysis results and generates a message of praise,

[0916] A state analysis method for analyzing the emotional state of members,

[0917] A display means for visualizing the analysis results,

[0918] A means of notifying members' devices of praise messages,

[0919] A means for generating and implementing a response suitable for household automated equipment,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, further comprising means for customizing the generated praise message according to the user's contribution and emotional state.

[0923] (Claim 3)

[0924] The system according to claim 1, further comprising means for communication to promote awareness and gratitude among users. [Explanation of Symbols]

[0925] 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 means for collecting voice information and business management information using communication means, Acoustic recognition means for converting collected audio information into text information, A means for analyzing textual information and business management information using natural language processing, A generation means that evaluates the worker's contribution based on the analysis results and generates award information, A means of analyzing the emotional state of workers, A display means for visualizing the analysis results as a visual display device, A means of notifying workers of award information via their terminal devices, In the work process, means to promote collaboration between robots and humans in order to enhance operational efficiency, A system that includes this.

2. The system according to claim 1, further comprising means for individualizing the generated award information according to the worker's contribution.

3. The system according to claim 1, further comprising means for communication to promote appreciation among workers and improve work efficiency.

Images