system

Abstract

We provide the system. [Solution] A means of acquiring the reporter's voice, converting the voice information, and analyzing it, A method for evaluating emotions by acquiring video footage of the person being reported to and analyzing their facial expressions, A means for generating real-time advice for the reporter based on analyzed voice and facial expression information, A means of communication to convey advice to the reporter, A means of generating a review report based on the overall analysis results after the report is completed, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a new employee makes a work report, there is a problem that it is difficult to convey to the recipient. This is because the reaction of the recipient of the report cannot be immediately read, and appropriate measures cannot be taken on the spot. As a result, it is difficult to obtain feedback from the supervisor, which hinders the performance of the work. In addition, in a remote environment, face-to-face communication is restricted, so this problem becomes more prominent.

Means for Solving the Problems

[0005] This invention provides a system that acquires the reporter's voice, converts the voice information into text and analyzes it, and further acquires the video of the person being reported to and performs facial expression analysis to evaluate emotions. Based on the analyzed voice and facial expression information, it generates appropriate advice for the reporter in real time and transmits it through earphones, thereby immediately improving the content of the report. In addition, after the report is completed, a review report is generated based on the overall analysis results, enabling new employees to improve their reporting methods.

[0006] "Audio information" refers to audio data obtained from the reporter, and analyzing this data provides the foundation for understanding the content and context of the report.

[0007] "Video" refers to the visual information of the person being reported to, and this information is used to analyze facial expressions and evaluate emotions.

[0008] "Facial expression analysis" is a process that analyzes the facial expressions of the person being reported to from acquired video data and numerically evaluates their emotional state.

[0009] "A means of generating advice in real time" refers to a function that provides immediate and appropriate feedback to the reporter based on analyzed voice and facial expression information.

[0010] "Communication methods" refer to devices and protocols used to transmit generated advice to the reporter, including examples such as earphones and wireless communication.

[0011] A "reflection report" is a document created after the completion of a report, based on the overall analysis results, and is intended for new employees to use to improve their reporting. [Brief explanation of the drawing]

[0012] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the 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), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the 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, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system to support new employees when they submit work reports, and can be implemented in the manner described below. This system primarily functions around three main components: a terminal, a server, and a user.

[0034] 1. Data acquisition and processing

[0035] First, the device uses microphones and cameras placed around the user to acquire audio and video data. This records the progress of the conversation and the facial expressions of the person being reported to. The acquired data is unusable as is, so it needs to be sent to a server for data conversion.

[0036] 2. Audio and video analysis

[0037] The server uses a speech recognition engine to convert audio data into text and performs natural language processing. This analysis allows the user's utterances to be understood and the flow of the conversation to be grasped. Simultaneously, video data is analyzed by a facial expression analysis algorithm. This allows for a logical evaluation of the emotional state of the person being reported to.

[0038] 3. Advice generation and provision

[0039] Based on the analysis results, the server generates necessary advice for the user. This generation is supported by a machine learning model, which forms optimal feedback by comparing it with past data. This advice is delivered to the user via the device and through earphones. This allows the user to improve their reporting methods in real time, resulting in more effective communication.

[0040] 4. Report generation and delivery

[0041] Once the report is completed, the server automatically generates a review report based on the combined results of voice and facial expression analysis. This report includes areas for improvement and positive feedback. Ultimately, users can receive this report and use it to improve their reporting skills. Therefore, the introduction of this system will enable new employees to confidently and effectively submit work reports.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The device acquires the user's voice data via the microphone and simultaneously collects video data of the person being reported to via the camera. This data is then prepared to be transmitted to the server in real time.

[0045] Step 2:

[0046] The server converts the received audio data into text data using a speech recognition engine. This text is then analyzed using natural language processing techniques to understand the content and context of the conversation.

[0047] Step 3:

[0048] The server processes the video data using an expression recognition algorithm to evaluate the emotional state of the person being reported to. This allows the server to obtain numerical data on how the recipient of the report is reacting.

[0049] Step 4:

[0050] Based on the analysis results, the server uses machine learning models to generate optimal advice for the user. This advice is then compared with past reporting data, and the most effective advice is selected.

[0051] Step 5:

[0052] The device transmits the generated advice to the user. Since the advice is delivered in real-time via audio through earphones, the user can improve their report immediately.

[0053] Step 6:

[0054] Once the report is complete, the server automatically generates a review report based on all the data collected. This report includes suggestions for improvement and feedback based on the analysis results.

[0055] Step 7:

[0056] Users receive a retrospective report and consider ways to improve future reports. Through this process, they gain improved reporting skills and confidence in performing their tasks.

[0057] (Example 1)

[0058] 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."

[0059] There is a problem in that new employees have difficulty making effective work reports. In particular, there is a lack of real-time feedback on how to speak when reporting and how to interpret the reactions of those they are reporting to. Traditional methods are limited to feedback after the report has been made, making it difficult to make improvements on the spot.

[0060] 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.

[0061] In this invention, the server includes means for converting speech information into text data using a speech recognition engine, means for quantitatively evaluating emotions using a facial expression analysis algorithm, and means for generating advice in real time using a generative AI model. This enables the provision of immediate and effective feedback during reporting.

[0062] A "voice acquisition device" is a device used to capture the voice of the reporter in real time.

[0063] A "speech recognition engine" is a part of the software or hardware that converts captured speech data into text data.

[0064] A "video acquisition device" is a device such as a camera used to record the facial expressions and reactions of the person being reported to.

[0065] A "facial expression analysis algorithm" is an algorithm that analyzes the facial movements and expressions of the person being reported to from acquired video data and quantitatively evaluates their emotions.

[0066] A "generative AI model" is an artificial intelligence model that automatically generates optimal advice based on analyzed data.

[0067] A "communication device" is a device used to transmit generated advice to the reporter, and includes earphones, speakers, and other similar devices.

[0068] The "automatic reflection report generation method" is a method that automatically generates a report after the reporting is completed, based on the results of voice and facial expression analysis.

[0069] This invention is a system to support new employees when submitting work reports, and is implemented as follows: The main components, a terminal, a server, and a user, cooperate with each other to provide support for effective work reporting.

[0070] First, the terminal uses a voice acquisition device to collect the user's speech in real time. Simultaneously, it uses a video acquisition device to monitor the facial expressions of the person being reported to. The audio and video data acquired by these devices is transmitted from the terminal to the server.

[0071] The server converts the received audio data into text data using a speech recognition engine. This text data is then subjected to natural language processing to analyze the flow and context of the conversation. In addition, video data is processed using a facial expression analysis algorithm to quantitatively evaluate emotions based on facial movements.

[0072] Based on the analyzed data, the server utilizes a generative AI model to generate optimal advice for the user. This advice is delivered to the user in real time via a communication device, and the user can adjust the tone and content of their report as needed during the process.

[0073] As a concrete example, when a new employee is giving a presentation, the speech recognition engine transcribes what he is saying into text, uses facial expression analysis to determine which parts the audience is interested in, and based on that information generates advice such as "Your tone of voice was good" or "Let's try this next time."

[0074] This allows users to adjust their actions on the spot, enabling them to deliver more confident and effective presentations.

[0075] An example of a prompt when using a generative AI model is: "Please tell me how new employees can improve their work reports. Please generate real-time advice based on past data."

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The device collects user speech using a voice acquisition device. The input is the user's voice data. This voice data is recorded and temporarily stored by the device. Specifically, the microphone activates as soon as the user begins speaking, capturing the speech.

[0079] Step 2:

[0080] The terminal simultaneously uses a video acquisition device to obtain facial expression data from the person being reported to. The input is video data of the person being reported to. This video data is saved for later analysis. Specifically, the camera continuously captures the facial movements of the person being reported to.

[0081] Step 3:

[0082] The terminal sends the collected audio data to the server. The input is audio data, and the output is the state in which the audio data has been sent. Specifically, the operation involves transferring data to the server via an internet connection.

[0083] Step 4:

[0084] The server converts received audio data into text data using a speech recognition engine. The input is audio data, and the output is text data. Specifically, it analyzes the audio waveform and converts it into a string using a language model.

[0085] Step 5:

[0086] The server inputs video data into a facial expression analysis algorithm to evaluate emotions. The input is video data, and the output is data including emotional states. Specifically, it detects facial feature points and uses them to determine emotions.

[0087] Step 6:

[0088] The server uses a generative AI model to generate optimal advice from analyzed text and sentiment data. The input is text and sentiment data, and the output is the generated advice. Specifically, it references a database of past data and applies learning results from similar cases.

[0089] Step 7:

[0090] The terminal receives advice sent from the server and transmits it to the user via a communication device. The input is the advice content, and the output is the audio transmission to the user. Specifically, the advice is output as audio via earphones.

[0091] (Application Example 1)

[0092] 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."

[0093] In modern industrial facilities, operators are required to perform complex machine operations while simultaneously providing reports and communication, but improving efficiency and accuracy in this process remains a challenge. Furthermore, accurately understanding and responding to the emotional state of those being reported to is a crucial element for smooth work execution. However, current methods do not adequately provide real-time, appropriate guidance and feedback, raising concerns about operator stress and decreased work efficiency.

[0094] 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.

[0095] This invention includes a server that acquires verbal information from the reporter, converts and analyzes the audio data, acquires image data of the person being reported to, and evaluates emotions by analyzing their facial expressions, generates real-time guidance for the reporter based on the analyzed audio and facial information, and an assistant automated machine device for supporting the work of knowledge workers in an industrial environment. This enables operators to receive appropriate feedback during their work and achieve efficient and reliable communication.

[0096] "Oral information from the reporter" refers to information obtained through the voice of the person making the report, including audio data such as conversations and explanations.

[0097] "Methods for converting and analyzing audio data" refers to methods that convert acquired audio into text and then perform a process to analyze its content.

[0098] "Image data of the person being reported to" refers to video data that includes visual information of the person receiving the report, including information that captures facial expressions and movements.

[0099] "Methods for evaluating emotions by analyzing facial expressions" refers to methods for analyzing facial expressions from acquired video footage and quantifying or categorizing the emotional state of a person.

[0100] "A means of generating guidance in real time" refers to a method of immediately formulating appropriate advice and guidance based on audio and video data acquired on the spot and providing it to the reporter.

[0101] "Assistant automated machinery and equipment" refers to automated, functional devices or equipment that support the work of knowledge workers in an industrial environment, designed to simplify and streamline the operator's tasks.

[0102] The system for realizing this application primarily consists of an automated assistant machine that processes audio and video data and provides real-time guidance to the operator. A specific example is shown below.

[0103] The server uses a high-performance computer system to process audio and video data. Specifically, it uses a speech recognition API (such as Google® Cloud Speech-to-Text API) to convert audio data into text, and then performs natural language processing on the converted text. This allows for understanding what the reporter said and analyzing the context.

[0104] Furthermore, the server utilizes libraries such as OpenCV and dlib to process video data and analyzes the facial expressions of the person being reported to in real time. This allows the system to evaluate the other person's emotional state and determine an appropriate response.

[0105] The terminal employs a method of notifying operators of instructions from the server via voice through small earphones or wearable devices to provide immediate guidance. This notification allows operators to make real-time improvements while on duty.

[0106] For example, if an operator explains "how to deal with unstable machine operation" and the person they are reporting to shows signs of confusion, the system can analyze this information and advise the operator to "explain using specific examples."

[0107] An example of a prompt for the generating AI model would be: "Based on the contents of this work report, please tell me the specific improvement points that should be provided to the operator, and how to explain them in a way that is easy for the recipient to understand."

[0108] In this way, collaboration between servers, terminals, and users enables efficient communication support in factory environments.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The device uses its built-in microphone and camera to acquire the reporter's audio data and the other party's video data in real time. The audio data is captured as an analog signal and then converted to a digital signal. The video data is also digitized as video frames. This prepares the raw data that is input into the program.

[0112] Step 2:

[0113] The server converts the audio data received from the terminal into text data using the Google Cloud Speech-to-Text API. Noise filtering and speech segmentation are performed during this process. The audio data is processed as input, and the converted text data is output. This text data is then used in subsequent natural language processing steps.

[0114] Step 3:

[0115] The server analyzes the converted text data using a natural language processing engine (e.g., SpaCy or NLTK) to understand the context of the report. Key phrases are extracted and sentiment analysis is performed during this process. The input text data is analyzed, and contextual information is output. This forms the basis for feedback generation.

[0116] Step 4:

[0117] The server analyzes video data acquired using OpenCV and dlib to perform face recognition and facial expression analysis of the person being reported to. The input is video frames, and facial features are extracted from each frame. The output is a numerical value or label indicating emotion, which is used to evaluate the emotional state.

[0118] Step 5:

[0119] The server generates real-time instruction using a machine learning model (e.g., built with TENSORFLOW®) based on analyzed speech context information and facial expression data. The generating AI model selects the optimal feedback by comparing it with past data. The input to the model is context information and facial expression information, and the output is specific instruction content for the reporter.

[0120] Step 6:

[0121] The device provides voice feedback via small earphones or wearable devices to deliver generated instruction content to the user in real time. Bluetooth or Wi-Fi is used for communication. Users can receive this voice feedback and immediately act upon it.

[0122] Step 7:

[0123] After the report is completed, the server automatically generates an evaluation report by synthesizing the acquired voice and facial expression analysis results. The generated report contains detailed feedback and areas for improvement to help with the review. This report is provided to the end user and can be used to improve future reporting activities.

[0124] 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.

[0125] This invention is a system designed to support the reporting activities of new employees, aiming to provide comprehensive feedback that also takes into account the user's emotions. To achieve this, the system has a configuration primarily consisting of terminals and a server.

[0126] 1. Data acquisition and emotion recognition

[0127] First, the device uses a microphone to capture the user's voice data and a camera to capture video data of the person being reported to, collecting this data in real time. Furthermore, it uses sensors to acquire biometric data necessary for recognizing the user's emotions and transmits it to the emotion engine.

[0128] 2. Server-based analysis

[0129] The server converts received audio into text using speech recognition technology and analyzes the content using natural language processing. Additionally, a facial expression analysis algorithm evaluates the other party's emotional state using video data. Based on the data obtained through this process, an emotion engine recognizes the user's emotional state.

[0130] 3. Generating and providing advice

[0131] Based on the analysis and emotion recognition results, the server generates optimal advice. It utilizes machine learning models and combines them with real-time feedback based on past data and recent emotional states. This advice is delivered to the user via earphones through the device, enhancing responsiveness during reporting.

[0132] 4. Generating a retrospective report

[0133] After the report is submitted, the server comprehensively analyzes all data and automatically generates a review report. It also records the user's emotional fluctuations and presents this as analytical data to help improve the report. This allows the user to obtain specific improvement strategies for their next report.

[0134] This system enables users to submit effective reports and contribute to improving their skills. The introduction of an emotion engine allows the system to provide more human-like and flexible feedback, and also offers mental support to users.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The device captures the user's voice via a microphone and collects video of the person being reported to via a camera. Simultaneously, it acquires data such as heart rate and skin temperature using biosensors to capture the user's emotional state. This data is transmitted to the server in real time.

[0138] Step 2:

[0139] The server converts audio data into text data using a speech recognition engine and analyzes the content of the conversation using natural language processing capabilities. It extracts the context and key points of the conversation and tracks the progress of the report.

[0140] Step 3:

[0141] The server analyzes the video data using a facial recognition algorithm and numerically evaluates the emotional state of the person reporting to it. This helps identify areas where the person feels unclear or negative reactions.

[0142] Step 4:

[0143] The server uses data transmitted from biosensors to activate an emotion engine and evaluate the user's internal emotional state. It analyzes levels of tension and stress to understand the user's mental state.

[0144] Step 5:

[0145] The server integrates analyzed audio, video, and emotion data to generate optimal advice. It utilizes machine learning models to provide real-time feedback based on context and emotion.

[0146] Step 6:

[0147] The device transmits generated advice to the user in real time via earphones. This allows the user to take appropriate action while reporting.

[0148] Step 7:

[0149] After the report is completed, the server integrates the analyzed data and generates a retrospective report. This report includes analysis of factors such as tone of voice, word choice, and emotional fluctuations, helping users to develop improvement strategies for their next report.

[0150] Step 8:

[0151] Users receive a retrospective report and use the identified areas for improvement to prepare their next report. This allows users to improve their reporting skills and perform their tasks with confidence.

[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 will be referred to as the "terminal."

[0154] When new employees are involved in reporting activities, there is a challenge in that they often do not receive appropriate and real-time feedback, making it easy for them to miss opportunities for improving the quality of their reports and for self-improvement. Conventional systems have limitations in providing feedback using only partial data of voice and facial expressions, making it difficult to comprehensively evaluate the user's emotional state.

[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 converting and analyzing audio information, means for acquiring video and evaluating emotions, and means for acquiring biometric information and recognizing emotional states. This enables high-precision recognition of the user's diverse emotional states and provides more adaptive and practical feedback.

[0157] "Voice information" refers to information used to analyze the content and characteristics of voice data emitted by a user.

[0158] "Video" refers to visual data acquired using sensors such as cameras, and includes the facial expressions and movements of the person being reported to.

[0159] "Facial expression analysis" is a technology that analyzes the movements and characteristics of a person's face from acquired video data and evaluates their emotional state.

[0160] "Biometric information" refers to physiological data such as the user's heart rate and skin temperature, which is used to infer their emotional state.

[0161] "Emotional state" refers to the emotional state a user is currently experiencing, and can be of various types, such as tension, relief, or surprise.

[0162] "A means of generating advice in real time" refers to a method of generating adaptive feedback that is immediately provided to the user using conventional information and new emotion recognition technologies.

[0163] A "review report" is an analytical document compiled after the reporting period to comprehensively evaluate changes in user behavior and emotions, and to be used for future improvements.

[0164] The embodiment of this invention is designed as a system to support the reporting activities of new employees. This system mainly consists of terminals and a server.

[0165] First, the device plays a crucial role in acquiring audio and video. It uses a microphone to capture the user's speech and a camera to observe the facial expressions of the person being reported to. This allows for the collection of audio and video streams in real time. It also incorporates sensors to acquire biometric information, such as measuring heart rate and skin temperature to understand the user's emotional state. This hardware typically includes commercially available audio and video capture devices.

[0166] The server is the core component that processes this data. Audio data is transcribed into text using speech recognition software and analyzed using natural language processing techniques. Video data is evaluated by facial expression analysis algorithms, and simultaneously, an emotion engine recognizes the user's emotional state through biometric data. Commonly used AI models and analysis engines are employed in this process.

[0167] The server uses a generative AI model to create advice based on the analysis results. The generated advice takes into account past data and the user's emotional state at that time, providing responsive feedback. The feedback is transmitted to the earphones via the device, allowing the user to improve their reporting skills.

[0168] As a concrete example, consider a scenario in a "Weekly Project Progress Report" where the user requires emotional support. A suitable prompt for the AI ​​model would be something like, "The user is reporting on project progress. Please provide emotional support based on their statements and facial expressions." Based on this information, the system can provide human-like, flexible feedback, enabling it to offer emotional support to the user.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The device uses a microphone to capture the user's voice. The input is the user's speech, and the output is a digital audio stream. The audio capture device recognizes the voice and transmits it to the server in real time.

[0172] Step 2:

[0173] The terminal uses its camera to capture video of the person being reported to. The input is visual information of the person being reported to, and the output is a digital video stream. The video capture device records facial movements and sends that data to the server.

[0174] Step 3:

[0175] The device uses sensors to acquire the user's biometric information. Inputs are physiological data such as the user's heart rate and skin temperature, and outputs are biometric datasets. The sensor device collects the data and provides it to a server for emotion analysis.

[0176] Step 4:

[0177] The server uses speech recognition software to convert the received audio stream into text. The input is an audio stream, and the output is text data. The speech recognition engine analyzes the audio data and generates the transcribed speech.

[0178] Step 5:

[0179] The server uses natural language processing technology to analyze text data and extract the intent and key points of the report. The input is text data, and the output is the data structure of the analyzed content. This allows for the determination of the main topic and important elements of the report.

[0180] Step 6:

[0181] The server processes video data using a facial expression analysis algorithm to evaluate emotional states. The input is a video stream, and the output is emotional evaluation data based on facial expression information. The facial expression analysis module evaluates facial features and identifies the emotional state of the other person.

[0182] Step 7:

[0183] The server uses biometric data to recognize the user's emotional state with its emotion engine. The input is a biometric dataset, and the output is data on the user's emotional state. The emotion recognition module analyzes the physiological data to identify the user's psychological state.

[0184] Step 8:

[0185] The server uses a generative AI model to integrate all analysis results and create real-time advice. Inputs are analyzed audio, video, and emotion data, and output is adaptive feedback messages. An advice generation module combines each data point to generate feedback tailored to the user's situation.

[0186] Step 9:

[0187] The terminal transmits advice provided by the server to the user via earphones. The input is the generated feedback message, and the output is the user's auditory feedback. The audio output device plays the advice as audio and delivers it to the user.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0190] In modern manufacturing, there is a demand to improve the efficiency and accuracy of workers and robot operators. However, it is difficult to grasp workers' emotions and stress levels in real time and provide appropriate feedback based on that information. Furthermore, reviewing the results after the work is completed and using them to make improvements is also a challenge. Therefore, there is a need for a system that can improve the working environment and increase work efficiency.

[0191] 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.

[0192] In this invention, the server includes means for acquiring audio data, converting and analyzing the audio information, means for acquiring video data, and evaluating emotions by analyzing facial expressions, and means for providing the worker with execution instructions and improvement suggestions in real time based on the analyzed audio and facial expression information. This enables the provision of appropriate feedback in real time that takes into account the worker's emotional state, thereby improving work efficiency and reducing stress.

[0193] "Audio data" refers to sound information that records a speaker's speech, acquired through an input device such as a microphone.

[0194] "Audio information" refers to information about language and speech signals obtained by analyzing audio data.

[0195] "Video data" refers to visual information that records a visual scene, acquired through a visual device such as a camera.

[0196] "Facial expression analysis" is a process that uses video data to analyze the facial features of a subject and identify their emotions and mood at that moment.

[0197] "Evaluating emotions" refers to the act of determining an individual's internal emotional state based on facial expression analysis and biometric data.

[0198] "Worker" refers to an individual engaged in specific tasks in a manufacturing plant or office, or a person who performs a task, including a robot operator.

[0199] An "execution instruction" is a set of instructions that specify the concrete actions or operations that a worker should perform.

[0200] An "improvement proposal" is a suggested improvement to methods or procedures aimed at increasing the efficiency or quality of work.

[0201] A "means of communication" refers to a communication technology or device used to transmit generated information or instructions to a recipient.

[0202] "Review" is the process of re-analyzing the data and results recorded after the completion of a task to help improve it in the future.

[0203] The system implementing this invention is realized by integrating multiple hardware and software components. Specifically, it uses speech recognition and video analysis technologies to evaluate the worker's emotions and work status, and provides real-time feedback.

[0204] First, the robots and work stations, acting as terminals, are equipped with microphones and cameras, which are used to acquire voice and video data of the workers. The voice data is converted into text data by Microsoft's Azure Cognitive Services and analyzed through natural language processing algorithms.

[0205] Next, the server uses Amazon Rekognition to analyze facial expressions from video data and evaluate emotions. This process allows for the estimation of the worker's stress level and attentiveness based on the acquired data. The evaluated emotion information and voice analysis results are integrated, and a generative AI model using TensorFlow is used to create optimal execution instructions and improvement suggestions.

[0206] The generated instructions and suggestions are communicated to the worker via a terminal. These are output as voice instructions and visual information, provided in a way that is easy for the worker to understand in real time. Furthermore, after the work is completed, a review document based on all the data is generated on the server and can be discussed in reporting meetings. This is expected to improve work efficiency and safety.

[0207] For example, if a worker shows a high stress level, the system can provide real-time feedback such as, "We recommend you take a break." Also, if the production line speed is inappropriate, specific instructions such as, "Let's reduce the production speed by 20%," can be provided.

[0208] An example of a prompt for a generative AI model would be: "Based on past data, generate suggestions on what appropriate feedback settings should be used when the operator's stress level is high."

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] The terminal uses a microphone to acquire voice data from the worker. This voice data is then transmitted to a server via a communication network. The input is voice data, and the output is the transfer of voice data to the server.

[0212] Step 2:

[0213] The server converts the received audio data into text data using Microsoft's Azure Cognitive Services. This process uses speech recognition technology to convert the audio signal into a string of characters. The input is audio data, and the output is the converted text data.

[0214] Step 3:

[0215] The terminal uses a camera to acquire video data of the worker. This video data is transmitted to a server via a communication network. The input is video data, and the output is the transfer of video data to the server.

[0216] Step 4:

[0217] The server uses Amazon's Rekognition to analyze facial expressions from received video data. This allows it to evaluate the emotional state of the worker. The input is video data, and the output is the emotional evaluation result.

[0218] Step 5:

[0219] The server uses an AI model to generate optimal execution instructions and improvement suggestions for workers, based on the analyzed text data and sentiment evaluation results. This process takes past data and current emotional states into account when generating instructions. The input is text data and sentiment evaluation data, and the output is specific execution instructions and improvement suggestions.

[0220] Step 6:

[0221] The server sends the generated instructions and improvement suggestions to the terminal. The terminal provides this information to the worker using an audio or visual output device. The input is the generated instruction data, and the output is the information transmitted to the worker.

[0222] Step 7:

[0223] After the work is completed, the server integrates all the data and generates a retrospective report. This report includes analysis results regarding work efficiency and emotional fluctuations. The input is the complete record of the work data, and the output is the retrospective report.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] [Second Embodiment]

[0228] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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".

[0240] This invention is a system to support new employees when they submit work reports, and can be implemented in the manner described below. This system primarily functions around three main components: a terminal, a server, and a user.

[0241] 1. Data acquisition and processing

[0242] First, the device uses microphones and cameras placed around the user to acquire audio and video data. This records the progress of the conversation and the facial expressions of the person being reported to. The acquired data is unusable as is, so it needs to be sent to a server for data conversion.

[0243] 2. Audio and video analysis

[0244] The server uses a speech recognition engine to convert audio data into text and performs natural language processing. This analysis allows the user's utterances to be understood and the flow of the conversation to be grasped. Simultaneously, video data is analyzed by a facial expression analysis algorithm. This allows for a logical evaluation of the emotional state of the person being reported to.

[0245] 3. Advice generation and provision

[0246] Based on the analysis results, the server generates necessary advice for the user. This generation is supported by a machine learning model, which forms optimal feedback by comparing it with past data. This advice is delivered to the user via the device and through earphones. This allows the user to improve their reporting methods in real time, resulting in more effective communication.

[0247] 4. Report generation and delivery

[0248] Once the report is completed, the server automatically generates a review report based on the combined results of voice and facial expression analysis. This report includes areas for improvement and positive feedback. Ultimately, users can receive this report and use it to improve their reporting skills. Therefore, the introduction of this system will enable new employees to confidently and effectively submit work reports.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The device acquires the user's voice data via the microphone and simultaneously collects video data of the person being reported to via the camera. This data is then prepared to be transmitted to the server in real time.

[0252] Step 2:

[0253] The server converts the received audio data into text data using a speech recognition engine. This text is then analyzed using natural language processing techniques to understand the content and context of the conversation.

[0254] Step 3:

[0255] The server processes the video data using an expression recognition algorithm to evaluate the emotional state of the person being reported to. This allows the server to obtain numerical data on how the recipient of the report is reacting.

[0256] Step 4:

[0257] Based on the analysis results, the server uses machine learning models to generate optimal advice for the user. This advice is then compared with past reporting data, and the most effective advice is selected.

[0258] Step 5:

[0259] The device transmits the generated advice to the user. Since the advice is delivered in real-time via audio through earphones, the user can improve their report immediately.

[0260] Step 6:

[0261] Once the report is complete, the server automatically generates a review report based on all the data collected. This report includes suggestions for improvement and feedback based on the analysis results.

[0262] Step 7:

[0263] Users receive a retrospective report and consider ways to improve future reports. Through this process, they gain improved reporting skills and confidence in performing their tasks.

[0264] (Example 1)

[0265] 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."

[0266] There is a problem in that new employees have difficulty making effective work reports. In particular, there is a lack of real-time feedback on how to speak when reporting and how to interpret the reactions of those they are reporting to. Traditional methods are limited to feedback after the report has been made, making it difficult to make improvements on the spot.

[0267] 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.

[0268] In this invention, the server includes means for converting speech information into text data using a speech recognition engine, means for quantitatively evaluating emotions using a facial expression analysis algorithm, and means for generating advice in real time using a generative AI model. This enables the provision of immediate and effective feedback during reporting.

[0269] A "voice acquisition device" is a device used to capture the voice of the reporter in real time.

[0270] A "speech recognition engine" is a part of the software or hardware that converts captured speech data into text data.

[0271] A "video acquisition device" is a device such as a camera used to record the facial expressions and reactions of the person being reported to.

[0272] A "facial expression analysis algorithm" is an algorithm that analyzes the facial movements and expressions of the person being reported to from acquired video data and quantitatively evaluates their emotions.

[0273] A "generative AI model" is an artificial intelligence model that automatically generates optimal advice based on analyzed data.

[0274] A "communication device" is a device used to transmit generated advice to the reporter, and includes earphones, speakers, and other similar devices.

[0275] The "automatic reflection report generation method" is a method that automatically generates a report after the reporting is completed, based on the results of voice and facial expression analysis.

[0276] This invention is a system to support new employees when submitting work reports, and is implemented as follows: The main components, a terminal, a server, and a user, cooperate with each other to provide support for effective work reporting.

[0277] First, the terminal uses a voice acquisition device to collect the user's speech in real time. Simultaneously, it uses a video acquisition device to monitor the facial expressions of the person being reported to. The audio and video data acquired by these devices is transmitted from the terminal to the server.

[0278] The server converts the received audio data into text data using a speech recognition engine. This text data is then subjected to natural language processing to analyze the flow and context of the conversation. In addition, video data is processed using a facial expression analysis algorithm to quantitatively evaluate emotions based on facial movements.

[0279] Based on the analyzed data, the server utilizes a generative AI model to generate optimal advice for the user. This advice is delivered to the user in real time via a communication device, and the user can adjust the tone and content of their report as needed during the process.

[0280] As a concrete example, when a new employee is giving a presentation, the speech recognition engine transcribes what he is saying into text, uses facial expression analysis to determine which parts the audience is interested in, and based on that information generates advice such as "Your tone of voice was good" or "Let's try this next time."

[0281] This enables the user to modify their actions on the spot and conduct a more confident and effective presentation.

[0282] As an example of a prompt sentence when using a generative AI model, "Please tell me the areas for improvement when a new employee gives a work report. Please refer to past data and generate real-time advice." can be cited.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The terminal collects the user's speech using a voice acquisition device. The input is the user's voice data. This voice data is recorded by the terminal and temporarily stored. As a specific operation, the microphone is activated simultaneously when the user starts speaking, and the utterance is captured.

[0286] Step 2:

[0287] The terminal simultaneously acquires the facial expression data of the recipient of the report using a video acquisition device. The input is the video data of the recipient of the report. This video data is saved in preparation for later analysis. As a specific operation, the camera continuously captures the movements of the recipient's face.

[0288] Step 3:

[0289] The terminal sends the collected voice data to the server. The input is voice data, and the output is the state where the voice data has been sent. The specific operation is to transfer the data to the server via an Internet connection.

[0290] Step 4:

[0291] The server converts received audio data into text data using a speech recognition engine. The input is audio data, and the output is text data. Specifically, it analyzes the audio waveform and converts it into a string using a language model.

[0292] Step 5:

[0293] The server inputs video data into a facial expression analysis algorithm to evaluate emotions. The input is video data, and the output is data including emotional states. Specifically, it detects facial feature points and uses them to determine emotions.

[0294] Step 6:

[0295] The server uses a generative AI model to generate optimal advice from analyzed text and sentiment data. The input is text and sentiment data, and the output is the generated advice. Specifically, it references a database of past data and applies learning results from similar cases.

[0296] Step 7:

[0297] The terminal receives advice sent from the server and transmits it to the user via a communication device. The input is the advice content, and the output is the audio transmission to the user. Specifically, the advice is output as audio via earphones.

[0298] (Application Example 1)

[0299] 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."

[0300] In modern industrial facilities, operators are required to perform complex machine operations while simultaneously providing reports and communication, but improving efficiency and accuracy in this process remains a challenge. Furthermore, accurately understanding and responding to the emotional state of those being reported to is a crucial element for smooth work execution. However, current methods do not adequately provide real-time, appropriate guidance and feedback, raising concerns about operator stress and decreased work efficiency.

[0301] 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.

[0302] This invention includes a server that acquires verbal information from the reporter, converts and analyzes the audio data, acquires image data of the person being reported to, and evaluates emotions by analyzing their facial expressions, generates real-time guidance for the reporter based on the analyzed audio and facial information, and an assistant automated machine device for supporting the work of knowledge workers in an industrial environment. This enables operators to receive appropriate feedback during their work and achieve efficient and reliable communication.

[0303] "Oral information from the reporter" refers to information obtained through the voice of the person making the report, including audio data such as conversations and explanations.

[0304] "Methods for converting and analyzing audio data" refers to methods that convert acquired audio into text and then perform a process to analyze its content.

[0305] "Image data of the person being reported to" refers to video data that includes visual information of the person receiving the report, including information that captures facial expressions and movements.

[0306] "Methods for evaluating emotions by analyzing facial expressions" refers to methods for analyzing facial expressions from acquired video footage and quantifying or categorizing the emotional state of a person.

[0307] The "means for generating guidance in real time" is a method of immediately forming appropriate advice and guidance based on the voice and video data obtained on-site and providing it to the reporter.

[0308] The "assistant automated machine equipment" is a device or equipment with automated functions that supports the work of knowledge workers in an industrial environment and is designed to simplify and streamline the operations of operators.

[0309] The system for realizing this application example is mainly composed of assistant automated machine equipment that processes voice data and video data and provides guidance to the operator in real time. Specific implementation examples are shown below.

[0310] The server uses a high-performance computer system to process voice and video data. Specifically, a voice recognition API (such as Google Cloud Speech-to-Text API) is used to convert voice data into text, and natural language processing is performed on the converted text. This enables the understanding and context analysis of the content spoken by the reporter.

[0311] In addition, the server utilizes libraries such as OpenCV and dlib for processing video data to analyze the expression of the reporting partner in real time. This enables the system to evaluate the emotional state of the partner and determine appropriate responses.

[0312] The terminal adopts a method of notifying the operator of instructions from the server in voice through small earphones or wearable devices in order to immediately provide guidance to the operator. With this notification, the operator can make real-time improvements during work.

[0313] For example, if an operator explains "how to deal with unstable machine operation" and the person they are reporting to shows signs of confusion, the system can analyze this information and advise the operator to "explain using specific examples."

[0314] An example of a prompt for the generating AI model would be: "Based on the contents of this work report, please tell me the specific improvement points that should be provided to the operator, and how to explain them in a way that is easy for the recipient to understand."

[0315] In this way, collaboration between servers, terminals, and users enables efficient communication support in factory environments.

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] The device uses its built-in microphone and camera to acquire the reporter's audio data and the other party's video data in real time. The audio data is captured as an analog signal and then converted to a digital signal. The video data is also digitized as video frames. This prepares the raw data that is input into the program.

[0319] Step 2:

[0320] The server converts the audio data received from the terminal into text data using the Google Cloud Speech-to-Text API. Noise filtering and speech segmentation are performed during this process. The audio data is processed as input, and the converted text data is output. This text data is then used in subsequent natural language processing steps.

[0321] Step 3:

[0322] The server analyzes the converted text data using a natural language processing engine (e.g., SpaCy or NLTK) to understand the context of the report. Key phrases are extracted and sentiment analysis is performed during this process. The input text data is analyzed, and contextual information is output. This forms the basis for feedback generation.

[0323] Step 4:

[0324] The server analyzes video data acquired using OpenCV and dlib to perform face recognition and facial expression analysis of the person being reported to. The input is video frames, and facial features are extracted from each frame. The output is a numerical value or label indicating emotion, which is used to evaluate the emotional state.

[0325] Step 5:

[0326] The server generates real-time guidance using a machine learning model (e.g., built with TensorFlow) based on analyzed speech context information and facial expression data. The generating AI model selects the optimal feedback by comparing it with past data. The input to the model is context information and facial expression data, and the output is specific guidance content for the reporter.

[0327] Step 6:

[0328] The device provides voice feedback via small earphones or wearable devices to deliver generated instruction content to the user in real time. Bluetooth or Wi-Fi is used for communication. Users can receive this voice feedback and immediately act upon it.

[0329] Step 7:

[0330] After the report is completed, the server automatically generates an evaluation report by synthesizing the acquired voice and facial expression analysis results. The generated report contains detailed feedback and areas for improvement to help with the review. This report is provided to the end user and can be used to improve future reporting activities.

[0331] 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.

[0332] This invention is a system designed to support the reporting activities of new employees, aiming to provide comprehensive feedback that also takes into account the user's emotions. To achieve this, the system has a configuration primarily consisting of terminals and a server.

[0333] 1. Data acquisition and emotion recognition

[0334] First, the device uses a microphone to capture the user's voice data and a camera to capture video data of the person being reported to, collecting this data in real time. Furthermore, it uses sensors to acquire biometric data necessary for recognizing the user's emotions and transmits it to the emotion engine.

[0335] 2. Server-based analysis

[0336] The server converts received audio into text using speech recognition technology and analyzes the content using natural language processing. Additionally, a facial expression analysis algorithm evaluates the other party's emotional state using video data. Based on the data obtained through this process, an emotion engine recognizes the user's emotional state.

[0337] 3. Generating and providing advice

[0338] Based on the analysis and emotion recognition results, the server generates optimal advice. It utilizes machine learning models and combines them with real-time feedback based on past data and recent emotional states. This advice is delivered to the user via earphones through the device, enhancing responsiveness during reporting.

[0339] 4. Generating a retrospective report

[0340] After the report is submitted, the server comprehensively analyzes all data and automatically generates a review report. It also records the user's emotional fluctuations and presents this as analytical data to help improve the report. This allows the user to obtain specific improvement strategies for their next report.

[0341] This system enables users to submit effective reports and contribute to improving their skills. The introduction of an emotion engine allows the system to provide more human-like and flexible feedback, and also offers mental support to users.

[0342] The following describes the processing flow.

[0343] Step 1:

[0344] The device captures the user's voice via a microphone and collects video of the person being reported to via a camera. Simultaneously, it acquires data such as heart rate and skin temperature using biosensors to capture the user's emotional state. This data is transmitted to the server in real time.

[0345] Step 2:

[0346] The server converts audio data into text data using a speech recognition engine and analyzes the content of the conversation using natural language processing capabilities. It extracts the context and key points of the conversation and tracks the progress of the report.

[0347] Step 3:

[0348] The server analyzes the video data using a facial recognition algorithm and numerically evaluates the emotional state of the person reporting to it. This helps identify areas where the person feels unclear or negative reactions.

[0349] Step 4:

[0350] The server uses data transmitted from biosensors to activate an emotion engine and evaluate the user's internal emotional state. It analyzes levels of tension and stress to understand the user's mental state.

[0351] Step 5:

[0352] The server integrates analyzed audio, video, and emotion data to generate optimal advice. It utilizes machine learning models to provide real-time feedback based on context and emotion.

[0353] Step 6:

[0354] The device transmits generated advice to the user in real time via earphones. This allows the user to take appropriate action while reporting.

[0355] Step 7:

[0356] After the report is completed, the server integrates the analyzed data and generates a retrospective report. This report includes analysis of factors such as tone of voice, word choice, and emotional fluctuations, helping users to develop improvement strategies for their next report.

[0357] Step 8:

[0358] Users receive a retrospective report and use the identified areas for improvement to prepare their next report. This allows users to improve their reporting skills and perform their tasks with confidence.

[0359] (Example 2)

[0360] 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".

[0361] When new employees are involved in reporting activities, there is a challenge in that they often do not receive appropriate and real-time feedback, making it easy for them to miss opportunities for improving the quality of their reports and for self-improvement. Conventional systems have limitations in providing feedback using only partial data of voice and facial expressions, making it difficult to comprehensively evaluate the user's emotional state.

[0362] 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.

[0363] In this invention, the server includes means for converting and analyzing audio information, means for acquiring video and evaluating emotions, and means for acquiring biometric information and recognizing emotional states. This enables high-precision recognition of the user's diverse emotional states and provides more adaptive and practical feedback.

[0364] "Voice information" refers to information used to analyze the content and characteristics of voice data emitted by a user.

[0365] "Video" refers to visual data acquired using sensors such as cameras, and includes the facial expressions and movements of the person being reported to.

[0366] "Facial expression analysis" is a technology that analyzes the movements and characteristics of a person's face from acquired video data and evaluates their emotional state.

[0367] "Biometric information" refers to physiological data such as the user's heart rate and skin temperature, which is used to infer their emotional state.

[0368] "Emotional state" refers to the emotional state a user is currently experiencing, and can be of various types, such as tension, relief, or surprise.

[0369] "A means of generating advice in real time" refers to a method of generating adaptive feedback that is immediately provided to the user using conventional information and new emotion recognition technologies.

[0370] A "review report" is an analytical document compiled after the reporting period to comprehensively evaluate changes in user behavior and emotions, and to be used for future improvements.

[0371] The embodiment of this invention is designed as a system to support the reporting activities of new employees. This system mainly consists of terminals and a server.

[0372] First, the device plays a crucial role in acquiring audio and video. It uses a microphone to capture the user's speech and a camera to observe the facial expressions of the person being reported to. This allows for the collection of audio and video streams in real time. It also incorporates sensors to acquire biometric information, such as measuring heart rate and skin temperature to understand the user's emotional state. This hardware typically includes commercially available audio and video capture devices.

[0373] The server is the core component that processes this data. Audio data is transcribed into text using speech recognition software and analyzed using natural language processing techniques. Video data is evaluated by facial expression analysis algorithms, and simultaneously, an emotion engine recognizes the user's emotional state through biometric data. Commonly used AI models and analysis engines are employed in this process.

[0374] The server uses a generative AI model to create advice based on the analysis results. The generated advice takes into account past data and the user's emotional state at that time, providing responsive feedback. The feedback is transmitted to the earphones via the device, allowing the user to improve their reporting skills.

[0375] As a concrete example, consider a scenario in a "Weekly Project Progress Report" where the user requires emotional support. A suitable prompt for the AI ​​model would be something like, "The user is reporting on project progress. Please provide emotional support based on their statements and facial expressions." Based on this information, the system can provide human-like, flexible feedback, enabling it to offer emotional support to the user.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The device uses a microphone to capture the user's voice. The input is the user's speech, and the output is a digital audio stream. The audio capture device recognizes the voice and transmits it to the server in real time.

[0379] Step 2:

[0380] The terminal uses its camera to capture video of the person being reported to. The input is visual information of the person being reported to, and the output is a digital video stream. The video capture device records facial movements and sends that data to the server.

[0381] Step 3:

[0382] The device uses sensors to acquire the user's biometric information. Inputs are physiological data such as the user's heart rate and skin temperature, and outputs are biometric datasets. The sensor device collects the data and provides it to a server for emotion analysis.

[0383] Step 4:

[0384] The server uses speech recognition software to convert the received audio stream into text. The input is an audio stream, and the output is text data. The speech recognition engine analyzes the audio data and generates the transcribed speech.

[0385] Step 5:

[0386] The server uses natural language processing technology to analyze text data and extract the intent and key points of the report. The input is text data, and the output is the data structure of the analyzed content. This allows for the determination of the main topic and important elements of the report.

[0387] Step 6:

[0388] The server processes video data using a facial expression analysis algorithm to evaluate emotional states. The input is a video stream, and the output is emotional evaluation data based on facial expression information. The facial expression analysis module evaluates facial features and identifies the emotional state of the other person.

[0389] Step 7:

[0390] The server uses biometric data to recognize the user's emotional state with its emotion engine. The input is a biometric dataset, and the output is data on the user's emotional state. The emotion recognition module analyzes the physiological data to identify the user's psychological state.

[0391] Step 8:

[0392] The server uses a generative AI model to integrate all analysis results and create real-time advice. Inputs are analyzed audio, video, and emotion data, and output is adaptive feedback messages. An advice generation module combines each data point to generate feedback tailored to the user's situation.

[0393] Step 9:

[0394] The terminal transmits advice provided by the server to the user via earphones. The input is the generated feedback message, and the output is the user's auditory feedback. The audio output device plays the advice as audio and delivers it to the user.

[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 modern manufacturing, there is a demand to improve the efficiency and accuracy of workers and robot operators. However, it is difficult to grasp workers' emotions and stress levels in real time and provide appropriate feedback based on that information. Furthermore, reviewing the results after the work is completed and using them to make improvements is also a challenge. Therefore, there is a need for a system that can improve the working environment and increase work efficiency.

[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 acquiring audio data, converting and analyzing the audio information, means for acquiring video data, and evaluating emotions by analyzing facial expressions, and means for providing the worker with execution instructions and improvement suggestions in real time based on the analyzed audio and facial expression information. This enables the provision of appropriate feedback in real time that takes into account the worker's emotional state, thereby improving work efficiency and reducing stress.

[0400] "Audio data" refers to sound information that records a speaker's speech, acquired through an input device such as a microphone.

[0401] "Audio information" refers to information about language and speech signals obtained by analyzing audio data.

[0402] "Video data" refers to visual information that records a visual scene, acquired through a visual device such as a camera.

[0403] "Facial expression analysis" is a process that uses video data to analyze the facial features of a subject and identify their emotions and mood at that moment.

[0404] "Evaluating emotions" refers to the act of determining an individual's internal emotional state based on facial expression analysis and biometric data.

[0405] "Worker" refers to an individual engaged in specific tasks in a manufacturing plant or office, or a person who performs a task, including a robot operator.

[0406] An "execution instruction" is a set of instructions that specify the concrete actions or operations that a worker should perform.

[0407] An "improvement proposal" is a suggested improvement to methods or procedures aimed at increasing the efficiency or quality of work.

[0408] A "means of communication" refers to a communication technology or device used to transmit generated information or instructions to a recipient.

[0409] "Review" is the process of re-analyzing the data and results recorded after the completion of a task to help improve it in the future.

[0410] The system implementing this invention is realized by integrating multiple hardware and software components. Specifically, it uses speech recognition and video analysis technologies to evaluate the worker's emotions and work status, and provides real-time feedback.

[0411] First, the robots and work stations, acting as terminals, are equipped with microphones and cameras, which are used to acquire voice and video data of the workers. The voice data is converted into text data by Microsoft's Azure Cognitive Services and then analyzed through natural language processing algorithms.

[0412] Next, the server uses Amazon Rekognition to analyze facial expressions from video data and evaluate emotions. This process allows for the estimation of the worker's stress level and attentiveness based on the acquired data. The evaluated emotion information and voice analysis results are integrated, and a generative AI model using TensorFlow is used to create optimal execution instructions and improvement suggestions.

[0413] The generated instructions and suggestions are communicated to the worker via a terminal. These are output as voice instructions and visual information, provided in a way that is easy for the worker to understand in real time. Furthermore, after the work is completed, a review document based on all the data is generated on the server and can be discussed in reporting meetings. This is expected to improve work efficiency and safety.

[0414] For example, if a worker shows a high stress level, the system can provide real-time feedback such as, "We recommend you take a break." Also, if the production line speed is inappropriate, specific instructions such as, "Let's reduce the production speed by 20%," can be provided.

[0415] An example of a prompt for a generative AI model would be: "Based on past data, generate suggestions on what appropriate feedback settings should be used when the operator's stress level is high."

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] The terminal uses a microphone to acquire voice data from the worker. This voice data is then transmitted to a server via a communication network. The input is voice data, and the output is the transfer of voice data to the server.

[0419] Step 2:

[0420] The server converts the received audio data into text data using Microsoft's Azure Cognitive Services. This process uses speech recognition technology to convert the audio signal into a string of characters. The input is audio data, and the output is the converted text data.

[0421] Step 3:

[0422] The terminal uses a camera to acquire video data of the worker. This video data is transmitted to a server via a communication network. The input is video data, and the output is the transfer of video data to the server.

[0423] Step 4:

[0424] The server uses Amazon's Rekognition to analyze facial expressions from received video data. This allows it to evaluate the emotional state of the worker. The input is video data, and the output is the emotional evaluation result.

[0425] Step 5:

[0426] The server uses an AI model to generate optimal execution instructions and improvement suggestions for workers, based on the analyzed text data and sentiment evaluation results. This process takes past data and current emotional states into account when generating instructions. The input is text data and sentiment evaluation data, and the output is specific execution instructions and improvement suggestions.

[0427] Step 6:

[0428] The server sends the generated instructions and improvement suggestions to the terminal. The terminal provides this information to the worker using an audio or visual output device. The input is the generated instruction data, and the output is the information transmitted to the worker.

[0429] Step 7:

[0430] After the work is completed, the server integrates all the data and generates a retrospective report. This report includes analysis results regarding work efficiency and emotional fluctuations. The input is the complete record of the work data, and the output is the retrospective report.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] [Third Embodiment]

[0435] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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".

[0447] This invention is a system to support new employees when they submit work reports, and can be implemented in the manner described below. This system primarily functions around three main components: a terminal, a server, and a user.

[0448] 1. Data acquisition and processing

[0449] First, the device uses microphones and cameras placed around the user to acquire audio and video data. This records the progress of the conversation and the facial expressions of the person being reported to. The acquired data is unusable as is, so it needs to be sent to a server for data conversion.

[0450] 2. Audio and video analysis

[0451] The server uses a speech recognition engine to convert audio data into text and performs natural language processing. This analysis allows the user's utterances to be understood and the flow of the conversation to be grasped. Simultaneously, video data is analyzed by a facial expression analysis algorithm. This allows for a logical evaluation of the emotional state of the person being reported to.

[0452] 3. Advice generation and provision

[0453] Based on the analysis results, the server generates necessary advice for the user. This generation is supported by a machine learning model, which forms optimal feedback by comparing it with past data. This advice is delivered to the user via the device and through earphones. This allows the user to improve their reporting methods in real time, resulting in more effective communication.

[0454] 4. Report generation and delivery

[0455] Once the report is completed, the server automatically generates a review report based on the combined results of voice and facial expression analysis. This report includes areas for improvement and positive feedback. Ultimately, users can receive this report and use it to improve their reporting skills. Therefore, the introduction of this system will enable new employees to confidently and effectively submit work reports.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The device acquires the user's voice data via the microphone and simultaneously collects video data of the person being reported to via the camera. This data is then prepared to be transmitted to the server in real time.

[0459] Step 2:

[0460] The server converts the received audio data into text data using a speech recognition engine. This text is then analyzed using natural language processing techniques to understand the content and context of the conversation.

[0461] Step 3:

[0462] The server processes the video data using an expression recognition algorithm to evaluate the emotional state of the person being reported to. This allows the server to obtain numerical data on how the recipient of the report is reacting.

[0463] Step 4:

[0464] Based on the analysis results, the server uses machine learning models to generate optimal advice for the user. This advice is then compared with past reporting data, and the most effective advice is selected.

[0465] Step 5:

[0466] The device transmits the generated advice to the user. Since the advice is delivered in real-time via audio through earphones, the user can improve their report immediately.

[0467] Step 6:

[0468] Once the report is complete, the server automatically generates a review report based on all the data collected. This report includes suggestions for improvement and feedback based on the analysis results.

[0469] Step 7:

[0470] Users receive a retrospective report and consider ways to improve future reports. Through this process, they gain improved reporting skills and confidence in performing their tasks.

[0471] (Example 1)

[0472] 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."

[0473] There is a problem in that new employees have difficulty making effective work reports. In particular, there is a lack of real-time feedback on how to speak when reporting and how to interpret the reactions of those they are reporting to. Traditional methods are limited to feedback after the report has been made, making it difficult to make improvements on the spot.

[0474] 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.

[0475] In this invention, the server includes means for converting speech information into text data using a speech recognition engine, means for quantitatively evaluating emotions using a facial expression analysis algorithm, and means for generating advice in real time using a generative AI model. This enables the provision of immediate and effective feedback during reporting.

[0476] A "voice acquisition device" is a device used to capture the voice of the reporter in real time.

[0477] A "speech recognition engine" is a part of the software or hardware that converts captured speech data into text data.

[0478] A "video acquisition device" is a device such as a camera used to record the facial expressions and reactions of the person being reported to.

[0479] A "facial expression analysis algorithm" is an algorithm that analyzes the facial movements and expressions of the person being reported to from acquired video data and quantitatively evaluates their emotions.

[0480] A "generative AI model" is an artificial intelligence model that automatically generates optimal advice based on analyzed data.

[0481] A "communication device" is a device used to transmit generated advice to the reporter, and includes earphones, speakers, and other similar devices.

[0482] The "automatic reflection report generation method" is a method that automatically generates a report after the reporting is completed, based on the results of voice and facial expression analysis.

[0483] This invention is a system to support new employees when submitting work reports, and is implemented as follows: The main components, a terminal, a server, and a user, cooperate with each other to provide support for effective work reporting.

[0484] First, the terminal uses a voice acquisition device to collect the user's speech in real time. Simultaneously, it uses a video acquisition device to monitor the facial expressions of the person being reported to. The audio and video data acquired by these devices is transmitted from the terminal to the server.

[0485] The server converts the received audio data into text data using a speech recognition engine. This text data is then subjected to natural language processing to analyze the flow and context of the conversation. In addition, video data is processed using a facial expression analysis algorithm to quantitatively evaluate emotions based on facial movements.

[0486] Based on the analyzed data, the server utilizes a generative AI model to generate optimal advice for the user. This advice is delivered to the user in real time via a communication device, and the user can adjust the tone and content of their report as needed during the process.

[0487] As a concrete example, when a new employee is giving a presentation, the speech recognition engine transcribes what he is saying into text, uses facial expression analysis to determine which parts the audience is interested in, and based on that information generates advice such as "Your tone of voice was good" or "Let's try this next time."

[0488] This allows users to adjust their actions on the spot, enabling them to deliver more confident and effective presentations.

[0489] An example of a prompt when using a generative AI model is: "Please tell me how new employees can improve their work reports. Please generate real-time advice based on past data."

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1:

[0492] The device collects user speech using a voice acquisition device. The input is the user's voice data. This voice data is recorded and temporarily stored by the device. Specifically, the microphone activates as soon as the user begins speaking, capturing the speech.

[0493] Step 2:

[0494] The terminal simultaneously uses a video acquisition device to obtain facial expression data from the person being reported to. The input is video data of the person being reported to. This video data is saved for later analysis. Specifically, the camera continuously captures the facial movements of the person being reported to.

[0495] Step 3:

[0496] The terminal sends the collected audio data to the server. The input is audio data, and the output is the state in which the audio data has been sent. Specifically, the operation involves transferring data to the server via an internet connection.

[0497] Step 4:

[0498] The server converts received audio data into text data using a speech recognition engine. The input is audio data, and the output is text data. Specifically, it analyzes the audio waveform and converts it into a string using a language model.

[0499] Step 5:

[0500] The server inputs video data into a facial expression analysis algorithm to evaluate emotions. The input is video data, and the output is data including emotional states. Specifically, it detects facial feature points and uses them to determine emotions.

[0501] Step 6:

[0502] The server uses a generative AI model to generate optimal advice from analyzed text and sentiment data. The input is text and sentiment data, and the output is the generated advice. Specifically, it references a database of past data and applies learning results from similar cases.

[0503] Step 7:

[0504] The terminal receives advice sent from the server and transmits it to the user via a communication device. The input is the advice content, and the output is the audio transmission to the user. Specifically, the advice is output as audio via earphones.

[0505] (Application Example 1)

[0506] 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."

[0507] In modern industrial facilities, operators are required to perform complex machine operations while simultaneously providing reports and communication, but improving efficiency and accuracy in this process remains a challenge. Furthermore, accurately understanding and responding to the emotional state of those being reported to is a crucial element for smooth work execution. However, current methods do not adequately provide real-time, appropriate guidance and feedback, raising concerns about operator stress and decreased work efficiency.

[0508] 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.

[0509] This invention includes a server that acquires verbal information from the reporter, converts and analyzes the audio data, acquires image data of the person being reported to, and evaluates emotions by analyzing their facial expressions, generates real-time guidance for the reporter based on the analyzed audio and facial information, and an assistant automated machine device for supporting the work of knowledge workers in an industrial environment. This enables operators to receive appropriate feedback during their work and achieve efficient and reliable communication.

[0510] "Oral information from the reporter" refers to information obtained through the voice of the person making the report, including audio data such as conversations and explanations.

[0511] "Methods for converting and analyzing audio data" refers to methods that convert acquired audio into text and then perform a process to analyze its content.

[0512] "Image data of the person being reported to" refers to video data that includes visual information of the person receiving the report, including information that captures facial expressions and movements.

[0513] "Methods for evaluating emotions by analyzing facial expressions" refers to methods for analyzing facial expressions from acquired video footage and quantifying or categorizing the emotional state of a person.

[0514] "A means of generating guidance in real time" refers to a method of immediately formulating appropriate advice and guidance based on audio and video data acquired on the spot and providing it to the reporter.

[0515] "Assistant automated machinery and equipment" refers to automated, functional devices or equipment that support the work of knowledge workers in an industrial environment, designed to simplify and streamline the operator's tasks.

[0516] The system for realizing this application primarily consists of an automated assistant machine that processes audio and video data and provides real-time guidance to the operator. A specific example is shown below.

[0517] The server uses a high-performance computer system to process audio and video data. Specifically, it utilizes a speech recognition API (such as the Google Cloud Speech-to-Text API) to convert audio data into text, and then performs natural language processing on the converted text. This allows for understanding what the reporter said and analyzing the context.

[0518] Furthermore, the server utilizes libraries such as OpenCV and dlib to process video data and analyzes the facial expressions of the person being reported to in real time. This allows the system to evaluate the other person's emotional state and determine an appropriate response.

[0519] The terminal employs a method of notifying operators of instructions from the server via voice through small earphones or wearable devices to provide immediate guidance. This notification allows operators to make real-time improvements while on duty.

[0520] For example, if an operator explains "how to deal with unstable machine operation" and the person they are reporting to shows signs of confusion, the system can analyze this information and advise the operator to "explain using specific examples."

[0521] An example of a prompt for the generating AI model would be: "Based on the contents of this work report, please tell me the specific improvement points that should be provided to the operator, and how to explain them in a way that is easy for the recipient to understand."

[0522] In this way, collaboration between servers, terminals, and users enables efficient communication support in factory environments.

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The device uses its built-in microphone and camera to acquire the reporter's audio data and the other party's video data in real time. The audio data is captured as an analog signal and then converted to a digital signal. The video data is also digitized as video frames. This prepares the raw data that is input into the program.

[0526] Step 2:

[0527] The server converts the audio data received from the terminal into text data using the Google Cloud Speech-to-Text API. Noise filtering and speech segmentation are performed during this process. The audio data is processed as input, and the converted text data is output. This text data is then used in subsequent natural language processing steps.

[0528] Step 3:

[0529] The server analyzes the converted text data using a natural language processing engine (e.g., SpaCy or NLTK) to understand the context of the report. Key phrases are extracted and sentiment analysis is performed during this process. The input text data is analyzed, and contextual information is output. This forms the basis for feedback generation.

[0530] Step 4:

[0531] The server analyzes video data acquired using OpenCV and dlib to perform face recognition and facial expression analysis of the person being reported to. The input is video frames, and facial features are extracted from each frame. The output is a numerical value or label indicating emotion, which is used to evaluate the emotional state.

[0532] Step 5:

[0533] The server generates real-time guidance using a machine learning model (e.g., built with TensorFlow) based on analyzed speech context information and facial expression data. The generating AI model selects the optimal feedback by comparing it with past data. The input to the model is context information and facial expression data, and the output is specific guidance content for the reporter.

[0534] Step 6:

[0535] The device provides voice feedback via small earphones or wearable devices to deliver generated instruction content to the user in real time. Bluetooth or Wi-Fi is used for communication. Users can receive this voice feedback and immediately act upon it.

[0536] Step 7:

[0537] After the report is completed, the server automatically generates an evaluation report by synthesizing the acquired voice and facial expression analysis results. The generated report contains detailed feedback and areas for improvement to help with the review. This report is provided to the end user and can be used to improve future reporting activities.

[0538] 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.

[0539] This invention is a system designed to support the reporting activities of new employees, aiming to provide comprehensive feedback that also takes into account the user's emotions. To achieve this, the system has a configuration primarily consisting of terminals and a server.

[0540] 1. Data acquisition and emotion recognition

[0541] First, the device uses a microphone to capture the user's voice data and a camera to capture video data of the person being reported to, collecting this data in real time. Furthermore, it uses sensors to acquire biometric data necessary for recognizing the user's emotions and transmits it to the emotion engine.

[0542] 2. Server-based analysis

[0543] The server converts received audio into text using speech recognition technology and analyzes the content using natural language processing. Additionally, a facial expression analysis algorithm evaluates the other party's emotional state using video data. Based on the data obtained through this process, an emotion engine recognizes the user's emotional state.

[0544] 3. Generating and providing advice

[0545] Based on the analysis and emotion recognition results, the server generates optimal advice. It utilizes machine learning models and combines them with real-time feedback based on past data and recent emotional states. This advice is delivered to the user via earphones through the device, enhancing responsiveness during reporting.

[0546] 4. Generating a retrospective report

[0547] After the report is submitted, the server comprehensively analyzes all data and automatically generates a review report. It also records the user's emotional fluctuations and presents this as analytical data to help improve the report. This allows the user to obtain specific improvement strategies for their next report.

[0548] This system enables users to submit effective reports and contribute to improving their skills. The introduction of an emotion engine allows the system to provide more human-like and flexible feedback, and also offers mental support to users.

[0549] The following describes the processing flow.

[0550] Step 1:

[0551] The device captures the user's voice via a microphone and collects video of the person being reported to via a camera. Simultaneously, it acquires data such as heart rate and skin temperature using biosensors to capture the user's emotional state. This data is transmitted to the server in real time.

[0552] Step 2:

[0553] The server converts audio data into text data using a speech recognition engine and analyzes the content of the conversation using natural language processing capabilities. It extracts the context and key points of the conversation and tracks the progress of the report.

[0554] Step 3:

[0555] The server analyzes the video data using a facial recognition algorithm and numerically evaluates the emotional state of the person reporting to it. This helps identify areas where the person feels unclear or negative reactions.

[0556] Step 4:

[0557] The server uses data transmitted from biosensors to activate an emotion engine and evaluate the user's internal emotional state. It analyzes levels of tension and stress to understand the user's mental state.

[0558] Step 5:

[0559] The server integrates analyzed audio, video, and emotion data to generate optimal advice. It utilizes machine learning models to provide real-time feedback based on context and emotion.

[0560] Step 6:

[0561] The device transmits generated advice to the user in real time via earphones. This allows the user to take appropriate action while reporting.

[0562] Step 7:

[0563] After the report is completed, the server integrates the analyzed data and generates a retrospective report. This report includes analysis of factors such as tone of voice, word choice, and emotional fluctuations, helping users to develop improvement strategies for their next report.

[0564] Step 8:

[0565] Users receive a retrospective report and use the identified areas for improvement to prepare their next report. This allows users to improve their reporting skills and perform their tasks with confidence.

[0566] (Example 2)

[0567] 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."

[0568] When new employees are involved in reporting activities, there is a challenge in that they often do not receive appropriate and real-time feedback, making it easy for them to miss opportunities for improving the quality of their reports and for self-improvement. Conventional systems have limitations in providing feedback using only partial data of voice and facial expressions, making it difficult to comprehensively evaluate the user's emotional state.

[0569] 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.

[0570] In this invention, the server includes means for converting and analyzing audio information, means for acquiring video and evaluating emotions, and means for acquiring biometric information and recognizing emotional states. This enables high-precision recognition of the user's diverse emotional states and provides more adaptive and practical feedback.

[0571] "Voice information" refers to information used to analyze the content and characteristics of voice data emitted by a user.

[0572] "Video" refers to visual data acquired using sensors such as cameras, and includes the facial expressions and movements of the person being reported to.

[0573] "Facial expression analysis" is a technology that analyzes the movements and characteristics of a person's face from acquired video data and evaluates their emotional state.

[0574] "Biometric information" refers to physiological data such as the user's heart rate and skin temperature, which is used to infer their emotional state.

[0575] "Emotional state" refers to the emotional state a user is currently experiencing, and can be of various types, such as tension, relief, or surprise.

[0576] "A means of generating advice in real time" refers to a method of generating adaptive feedback that is immediately provided to the user using conventional information and new emotion recognition technologies.

[0577] A "review report" is an analytical document compiled after the reporting period to comprehensively evaluate changes in user behavior and emotions, and to be used for future improvements.

[0578] The embodiment of this invention is designed as a system to support the reporting activities of new employees. This system mainly consists of terminals and a server.

[0579] First, the device plays a crucial role in acquiring audio and video. It uses a microphone to capture the user's speech and a camera to observe the facial expressions of the person being reported to. This allows for the collection of audio and video streams in real time. It also incorporates sensors to acquire biometric information, such as measuring heart rate and skin temperature to understand the user's emotional state. This hardware typically includes commercially available audio and video capture devices.

[0580] The server is the core component that processes this data. Audio data is transcribed into text using speech recognition software and analyzed using natural language processing techniques. Video data is evaluated by facial expression analysis algorithms, and simultaneously, an emotion engine recognizes the user's emotional state through biometric data. Commonly used AI models and analysis engines are employed in this process.

[0581] The server uses a generative AI model to create advice based on the analysis results. The generated advice takes into account past data and the user's emotional state at that time, providing responsive feedback. The feedback is transmitted to the earphones via the device, allowing the user to improve their reporting skills.

[0582] As a concrete example, consider a scenario in a "Weekly Project Progress Report" where the user requires emotional support. A suitable prompt for the AI ​​model would be something like, "The user is reporting on project progress. Please provide emotional support based on their statements and facial expressions." Based on this information, the system can provide human-like, flexible feedback, enabling it to offer emotional support to the user.

[0583] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0584] Step 1:

[0585] The device uses a microphone to capture the user's voice. The input is the user's speech, and the output is a digital audio stream. The audio capture device recognizes the voice and transmits it to the server in real time.

[0586] Step 2:

[0587] The terminal uses its camera to capture video of the person being reported to. The input is visual information of the person being reported to, and the output is a digital video stream. The video capture device records facial movements and sends that data to the server.

[0588] Step 3:

[0589] The device uses sensors to acquire the user's biometric information. Inputs are physiological data such as the user's heart rate and skin temperature, and outputs are biometric datasets. The sensor device collects the data and provides it to a server for emotion analysis.

[0590] Step 4:

[0591] The server uses speech recognition software to convert the received audio stream into text. The input is an audio stream, and the output is text data. The speech recognition engine analyzes the audio data and generates the transcribed speech.

[0592] Step 5:

[0593] The server uses natural language processing technology to analyze text data and extract the intent and key points of the report. The input is text data, and the output is the data structure of the analyzed content. This allows for the determination of the main topic and important elements of the report.

[0594] Step 6:

[0595] The server processes video data using a facial expression analysis algorithm to evaluate emotional states. The input is a video stream, and the output is emotional evaluation data based on facial expression information. The facial expression analysis module evaluates facial features and identifies the emotional state of the other person.

[0596] Step 7:

[0597] The server uses biometric data to recognize the user's emotional state with its emotion engine. The input is a biometric dataset, and the output is data on the user's emotional state. The emotion recognition module analyzes the physiological data to identify the user's psychological state.

[0598] Step 8:

[0599] The server uses a generative AI model to integrate all analysis results and create real-time advice. Inputs are analyzed audio, video, and emotion data, and output is adaptive feedback messages. An advice generation module combines each data point to generate feedback tailored to the user's situation.

[0600] Step 9:

[0601] The terminal transmits advice provided by the server to the user via earphones. The input is the generated feedback message, and the output is the user's auditory feedback. The audio output device plays the advice as audio and delivers it to the user.

[0602] (Application Example 2)

[0603] 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."

[0604] In modern manufacturing, there is a demand to improve the efficiency and accuracy of workers and robot operators. However, it is difficult to grasp workers' emotions and stress levels in real time and provide appropriate feedback based on that information. Furthermore, reviewing the results after the work is completed and using them to make improvements is also a challenge. Therefore, there is a need for a system that can improve the working environment and increase work efficiency.

[0605] 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.

[0606] In this invention, the server includes means for acquiring audio data, converting and analyzing the audio information, means for acquiring video data, and evaluating emotions by analyzing facial expressions, and means for providing the worker with execution instructions and improvement suggestions in real time based on the analyzed audio and facial expression information. This enables the provision of appropriate feedback in real time that takes into account the worker's emotional state, thereby improving work efficiency and reducing stress.

[0607] "Audio data" refers to sound information that records a speaker's speech, acquired through an input device such as a microphone.

[0608] "Audio information" refers to information about language and speech signals obtained by analyzing audio data.

[0609] "Video data" refers to visual information that records a visual scene, acquired through a visual device such as a camera.

[0610] "Facial expression analysis" is a process that uses video data to analyze the facial features of a subject and identify their emotions and mood at that moment.

[0611] "Evaluating emotions" refers to the act of determining an individual's internal emotional state based on facial expression analysis and biometric data.

[0612] "Worker" refers to an individual engaged in specific tasks in a manufacturing plant or office, or a person who performs a task, including a robot operator.

[0613] An "execution instruction" is a set of instructions that specify the concrete actions or operations that a worker should perform.

[0614] An "improvement proposal" is a suggested improvement to methods or procedures aimed at increasing the efficiency or quality of work.

[0615] A "means of communication" refers to a communication technology or device used to transmit generated information or instructions to a recipient.

[0616] "Review" is the process of re-analyzing the data and results recorded after the completion of a task to help improve it in the future.

[0617] The system implementing this invention is realized by integrating multiple hardware and software components. Specifically, it uses speech recognition and video analysis technologies to evaluate the worker's emotions and work status, and provides real-time feedback.

[0618] First, the robots and work stations, acting as terminals, are equipped with microphones and cameras, which are used to acquire voice and video data of the workers. The voice data is converted into text data by Microsoft's Azure Cognitive Services and then analyzed through natural language processing algorithms.

[0619] Next, the server uses Amazon Rekognition to analyze facial expressions from video data and evaluate emotions. This process allows for the estimation of the worker's stress level and attentiveness based on the acquired data. The evaluated emotion information and voice analysis results are integrated, and a generative AI model using TensorFlow is used to create optimal execution instructions and improvement suggestions.

[0620] The generated instructions and suggestions are communicated to the worker via a terminal. These are output as voice instructions and visual information, provided in a way that is easy for the worker to understand in real time. Furthermore, after the work is completed, a review document based on all the data is generated on the server and can be discussed in reporting meetings. This is expected to improve work efficiency and safety.

[0621] For example, if a worker shows a high stress level, the system can provide real-time feedback such as, "We recommend you take a break." Also, if the production line speed is inappropriate, specific instructions such as, "Let's reduce the production speed by 20%," can be provided.

[0622] An example of a prompt for a generative AI model would be: "Based on past data, generate suggestions on what appropriate feedback settings should be used when the operator's stress level is high."

[0623] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0624] Step 1:

[0625] The terminal uses a microphone to acquire voice data from the worker. This voice data is then transmitted to a server via a communication network. The input is voice data, and the output is the transfer of voice data to the server.

[0626] Step 2:

[0627] The server converts the received audio data into text data using Microsoft's Azure Cognitive Services. This process uses speech recognition technology to convert the audio signal into a string of characters. The input is audio data, and the output is the converted text data.

[0628] Step 3:

[0629] The terminal uses a camera to acquire video data of the worker. This video data is transmitted to a server via a communication network. The input is video data, and the output is the transfer of video data to the server.

[0630] Step 4:

[0631] The server uses Amazon's Rekognition to analyze facial expressions from received video data. This allows it to evaluate the emotional state of the worker. The input is video data, and the output is the emotional evaluation result.

[0632] Step 5:

[0633] The server uses an AI model to generate optimal execution instructions and improvement suggestions for workers, based on the analyzed text data and sentiment evaluation results. This process takes past data and current emotional states into account when generating instructions. The input is text data and sentiment evaluation data, and the output is specific execution instructions and improvement suggestions.

[0634] Step 6:

[0635] The server sends the generated instructions and improvement suggestions to the terminal. The terminal provides this information to the worker using an audio or visual output device. The input is the generated instruction data, and the output is the information transmitted to the worker.

[0636] Step 7:

[0637] After the work is completed, the server integrates all the data and generates a retrospective report. This report includes analysis results regarding work efficiency and emotional fluctuations. The input is the complete record of the work data, and the output is the retrospective report.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] [Fourth Embodiment]

[0642] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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).

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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".

[0655] This invention is a system to support new employees when they submit work reports, and can be implemented in the manner described below. This system primarily functions around three main components: a terminal, a server, and a user.

[0656] 1. Data acquisition and processing

[0657] First, the device uses microphones and cameras placed around the user to acquire audio and video data. This records the progress of the conversation and the facial expressions of the person being reported to. The acquired data is unusable as is, so it needs to be sent to a server for data conversion.

[0658] 2. Audio and video analysis

[0659] The server uses a speech recognition engine to convert audio data into text and performs natural language processing. This analysis allows the user's utterances to be understood and the flow of the conversation to be grasped. Simultaneously, video data is analyzed by a facial expression analysis algorithm. This allows for a logical evaluation of the emotional state of the person being reported to.

[0660] 3. Advice generation and provision

[0661] Based on the analysis results, the server generates necessary advice for the user. This generation is supported by a machine learning model, which forms optimal feedback by comparing it with past data. This advice is delivered to the user via the device and through earphones. This allows the user to improve their reporting methods in real time, resulting in more effective communication.

[0662] 4. Report generation and delivery

[0663] Once the report is completed, the server automatically generates a review report based on the combined results of voice and facial expression analysis. This report includes areas for improvement and positive feedback. Ultimately, users can receive this report and use it to improve their reporting skills. Therefore, the introduction of this system will enable new employees to confidently and effectively submit work reports.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] The device acquires the user's voice data via the microphone and simultaneously collects video data of the person being reported to via the camera. This data is then prepared to be transmitted to the server in real time.

[0667] Step 2:

[0668] The server converts the received audio data into text data using a speech recognition engine. This text is then analyzed using natural language processing techniques to understand the content and context of the conversation.

[0669] Step 3:

[0670] The server processes the video data using an expression recognition algorithm to evaluate the emotional state of the person being reported to. This allows the server to obtain numerical data on how the recipient of the report is reacting.

[0671] Step 4:

[0672] Based on the analysis results, the server uses machine learning models to generate optimal advice for the user. This advice is then compared with past reporting data, and the most effective advice is selected.

[0673] Step 5:

[0674] The device transmits the generated advice to the user. Since the advice is delivered in real-time via audio through earphones, the user can improve their report immediately.

[0675] Step 6:

[0676] Once the report is complete, the server automatically generates a review report based on all the data collected. This report includes suggestions for improvement and feedback based on the analysis results.

[0677] Step 7:

[0678] Users receive a retrospective report and consider ways to improve future reports. Through this process, they gain improved reporting skills and confidence in performing their tasks.

[0679] (Example 1)

[0680] 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".

[0681] There is a problem in that new employees have difficulty making effective work reports. In particular, there is a lack of real-time feedback on how to speak when reporting and how to interpret the reactions of those they are reporting to. Traditional methods are limited to feedback after the report has been made, making it difficult to make improvements on the spot.

[0682] 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.

[0683] In this invention, the server includes means for converting speech information into text data using a speech recognition engine, means for quantitatively evaluating emotions using a facial expression analysis algorithm, and means for generating advice in real time using a generative AI model. This enables the provision of immediate and effective feedback during reporting.

[0684] A "voice acquisition device" is a device used to capture the voice of the reporter in real time.

[0685] A "speech recognition engine" is a part of the software or hardware that converts captured speech data into text data.

[0686] A "video acquisition device" is a device such as a camera used to record the facial expressions and reactions of the person being reported to.

[0687] A "facial expression analysis algorithm" is an algorithm that analyzes the facial movements and expressions of the person being reported to from acquired video data and quantitatively evaluates their emotions.

[0688] A "generative AI model" is an artificial intelligence model that automatically generates optimal advice based on analyzed data.

[0689] A "communication device" is a device used to transmit generated advice to the reporter, and includes earphones, speakers, and other similar devices.

[0690] The "automatic reflection report generation method" is a method that automatically generates a report after the reporting is completed, based on the results of voice and facial expression analysis.

[0691] This invention is a system to support new employees when submitting work reports, and is implemented as follows: The main components, a terminal, a server, and a user, cooperate with each other to provide support for effective work reporting.

[0692] First, the terminal uses a voice acquisition device to collect the user's speech in real time. Simultaneously, it uses a video acquisition device to monitor the facial expressions of the person being reported to. The audio and video data acquired by these devices is transmitted from the terminal to the server.

[0693] The server converts the received audio data into text data using a speech recognition engine. This text data is then subjected to natural language processing to analyze the flow and context of the conversation. In addition, video data is processed using a facial expression analysis algorithm to quantitatively evaluate emotions based on facial movements.

[0694] Based on the analyzed data, the server utilizes a generative AI model to generate optimal advice for the user. This advice is delivered to the user in real time via a communication device, and the user can adjust the tone and content of their report as needed during the process.

[0695] As a concrete example, when a new employee is giving a presentation, the speech recognition engine transcribes what he is saying into text, uses facial expression analysis to determine which parts the audience is interested in, and based on that information generates advice such as "Your tone of voice was good" or "Let's try this next time."

[0696] This allows users to adjust their actions on the spot, enabling them to deliver more confident and effective presentations.

[0697] An example of a prompt when using a generative AI model is: "Please tell me how new employees can improve their work reports. Please generate real-time advice based on past data."

[0698] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0699] Step 1:

[0700] The device collects user speech using a voice acquisition device. The input is the user's voice data. This voice data is recorded and temporarily stored by the device. Specifically, the microphone activates as soon as the user begins speaking, capturing the speech.

[0701] Step 2:

[0702] The terminal simultaneously uses a video acquisition device to obtain facial expression data from the person being reported to. The input is video data of the person being reported to. This video data is saved for later analysis. Specifically, the camera continuously captures the facial movements of the person being reported to.

[0703] Step 3:

[0704] The terminal sends the collected audio data to the server. The input is audio data, and the output is the state in which the audio data has been sent. Specifically, the operation involves transferring data to the server via an internet connection.

[0705] Step 4:

[0706] The server converts received audio data into text data using a speech recognition engine. The input is audio data, and the output is text data. Specifically, it analyzes the audio waveform and converts it into a string using a language model.

[0707] Step 5:

[0708] The server inputs video data into a facial expression analysis algorithm to evaluate emotions. The input is video data, and the output is data including emotional states. Specifically, it detects facial feature points and uses them to determine emotions.

[0709] Step 6:

[0710] The server uses a generative AI model to generate optimal advice from analyzed text and sentiment data. The input is text and sentiment data, and the output is the generated advice. Specifically, it references a database of past data and applies learning results from similar cases.

[0711] Step 7:

[0712] The terminal receives advice sent from the server and transmits it to the user via a communication device. The input is the advice content, and the output is the audio transmission to the user. Specifically, the advice is output as audio via earphones.

[0713] (Application Example 1)

[0714] 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".

[0715] In modern industrial facilities, operators are required to perform complex machine operations while simultaneously providing reports and communication, but improving efficiency and accuracy in this process remains a challenge. Furthermore, accurately understanding and responding to the emotional state of those being reported to is a crucial element for smooth work execution. However, current methods do not adequately provide real-time, appropriate guidance and feedback, raising concerns about operator stress and decreased work efficiency.

[0716] 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.

[0717] This invention includes a server that acquires verbal information from the reporter, converts and analyzes the audio data, acquires image data of the person being reported to, and evaluates emotions by analyzing their facial expressions, generates real-time guidance for the reporter based on the analyzed audio and facial information, and an assistant automated machine device for supporting the work of knowledge workers in an industrial environment. This enables operators to receive appropriate feedback during their work and achieve efficient and reliable communication.

[0718] "Oral information from the reporter" refers to information obtained through the voice of the person making the report, including audio data such as conversations and explanations.

[0719] "Methods for converting and analyzing audio data" refers to methods that convert acquired audio into text and then perform a process to analyze its content.

[0720] "Image data of the person being reported to" refers to video data that includes visual information of the person receiving the report, including information that captures facial expressions and movements.

[0721] "Methods for evaluating emotions by analyzing facial expressions" refers to methods for analyzing facial expressions from acquired video footage and quantifying or categorizing the emotional state of a person.

[0722] "A means of generating guidance in real time" refers to a method of immediately formulating appropriate advice and guidance based on audio and video data acquired on the spot and providing it to the reporter.

[0723] "Assistant automated machinery and equipment" refers to automated, functional devices or equipment that support the work of knowledge workers in an industrial environment, designed to simplify and streamline the operator's tasks.

[0724] The system for realizing this application primarily consists of an automated assistant machine that processes audio and video data and provides real-time guidance to the operator. A specific example is shown below.

[0725] The server uses a high-performance computer system to process audio and video data. Specifically, it utilizes a speech recognition API (such as the Google Cloud Speech-to-Text API) to convert audio data into text, and then performs natural language processing on the converted text. This allows for understanding what the reporter said and analyzing the context.

[0726] Furthermore, the server utilizes libraries such as OpenCV and dlib to process video data and analyzes the facial expressions of the person being reported to in real time. This allows the system to evaluate the other person's emotional state and determine an appropriate response.

[0727] The terminal employs a method of notifying operators of instructions from the server via voice through small earphones or wearable devices to provide immediate guidance. This notification allows operators to make real-time improvements while on duty.

[0728] For example, if an operator explains "how to deal with unstable machine operation" and the person they are reporting to shows signs of confusion, the system can analyze this information and advise the operator to "explain using specific examples."

[0729] An example of a prompt for the generating AI model would be: "Based on the contents of this work report, please tell me the specific improvement points that should be provided to the operator, and how to explain them in a way that is easy for the recipient to understand."

[0730] In this way, collaboration between servers, terminals, and users enables efficient communication support in factory environments.

[0731] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0732] Step 1:

[0733] The device uses its built-in microphone and camera to acquire the reporter's audio data and the other party's video data in real time. The audio data is captured as an analog signal and then converted to a digital signal. The video data is also digitized as video frames. This prepares the raw data that is input into the program.

[0734] Step 2:

[0735] The server converts the audio data received from the terminal into text data using the Google Cloud Speech-to-Text API. Noise filtering and speech segmentation are performed during this process. The audio data is processed as input, and the converted text data is output. This text data is then used in subsequent natural language processing steps.

[0736] Step 3:

[0737] The server analyzes the converted text data using a natural language processing engine (e.g., SpaCy or NLTK) to understand the context of the report. Key phrases are extracted and sentiment analysis is performed during this process. The input text data is analyzed, and contextual information is output. This forms the basis for feedback generation.

[0738] Step 4:

[0739] The server analyzes video data acquired using OpenCV and dlib to perform face recognition and facial expression analysis of the person being reported to. The input is video frames, and facial features are extracted from each frame. The output is a numerical value or label indicating emotion, which is used to evaluate the emotional state.

[0740] Step 5:

[0741] The server generates real-time guidance using a machine learning model (e.g., built with TensorFlow) based on analyzed speech context information and facial expression data. The generating AI model selects the optimal feedback by comparing it with past data. The input to the model is context information and facial expression data, and the output is specific guidance content for the reporter.

[0742] Step 6:

[0743] The device provides voice feedback via small earphones or wearable devices to deliver generated instruction content to the user in real time. Bluetooth or Wi-Fi is used for communication. Users can receive this voice feedback and immediately act upon it.

[0744] Step 7:

[0745] After the report is completed, the server automatically generates an evaluation report by synthesizing the acquired voice and facial expression analysis results. The generated report contains detailed feedback and areas for improvement to help with the review. This report is provided to the end user and can be used to improve future reporting activities.

[0746] 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.

[0747] This invention is a system designed to support the reporting activities of new employees, aiming to provide comprehensive feedback that also takes into account the user's emotions. To achieve this, the system has a configuration primarily consisting of terminals and a server.

[0748] 1. Data acquisition and emotion recognition

[0749] First, the device uses a microphone to capture the user's voice data and a camera to capture video data of the person being reported to, collecting this data in real time. Furthermore, it uses sensors to acquire biometric data necessary for recognizing the user's emotions and transmits it to the emotion engine.

[0750] 2. Server-based analysis

[0751] The server converts received audio into text using speech recognition technology and analyzes the content using natural language processing. Additionally, a facial expression analysis algorithm evaluates the other party's emotional state using video data. Based on the data obtained through this process, an emotion engine recognizes the user's emotional state.

[0752] 3. Generating and providing advice

[0753] Based on the analysis and emotion recognition results, the server generates optimal advice. It utilizes machine learning models and combines them with real-time feedback based on past data and recent emotional states. This advice is delivered to the user via earphones through the device, enhancing responsiveness during reporting.

[0754] 4. Generating a retrospective report

[0755] After the report is submitted, the server comprehensively analyzes all data and automatically generates a review report. It also records the user's emotional fluctuations and presents this as analytical data to help improve the report. This allows the user to obtain specific improvement strategies for their next report.

[0756] This system enables users to submit effective reports and contribute to improving their skills. The introduction of an emotion engine allows the system to provide more human-like and flexible feedback, and also offers mental support to users.

[0757] The following describes the processing flow.

[0758] Step 1:

[0759] The device captures the user's voice via a microphone and collects video of the person being reported to via a camera. Simultaneously, it acquires data such as heart rate and skin temperature using biosensors to capture the user's emotional state. This data is transmitted to the server in real time.

[0760] Step 2:

[0761] The server converts audio data into text data using a speech recognition engine and analyzes the content of the conversation using natural language processing capabilities. It extracts the context and key points of the conversation and tracks the progress of the report.

[0762] Step 3:

[0763] The server analyzes the video data using a facial recognition algorithm and numerically evaluates the emotional state of the person reporting to it. This helps identify areas where the person feels unclear or negative reactions.

[0764] Step 4:

[0765] The server uses data transmitted from biosensors to activate an emotion engine and evaluate the user's internal emotional state. It analyzes levels of tension and stress to understand the user's mental state.

[0766] Step 5:

[0767] The server integrates analyzed audio, video, and emotion data to generate optimal advice. It utilizes machine learning models to provide real-time feedback based on context and emotion.

[0768] Step 6:

[0769] The device transmits generated advice to the user in real time via earphones. This allows the user to take appropriate action while reporting.

[0770] Step 7:

[0771] After the report is completed, the server integrates the analyzed data and generates a retrospective report. This report includes analysis of factors such as tone of voice, word choice, and emotional fluctuations, helping users to develop improvement strategies for their next report.

[0772] Step 8:

[0773] Users receive a retrospective report and use the identified areas for improvement to prepare their next report. This allows users to improve their reporting skills and perform their tasks with confidence.

[0774] (Example 2)

[0775] 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".

[0776] When new employees are involved in reporting activities, there is a challenge in that they often do not receive appropriate and real-time feedback, making it easy for them to miss opportunities for improving the quality of their reports and for self-improvement. Conventional systems have limitations in providing feedback using only partial data of voice and facial expressions, making it difficult to comprehensively evaluate the user's emotional state.

[0777] 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.

[0778] In this invention, the server includes means for converting and analyzing audio information, means for acquiring video and evaluating emotions, and means for acquiring biometric information and recognizing emotional states. This enables high-precision recognition of the user's diverse emotional states and provides more adaptive and practical feedback.

[0779] "Voice information" refers to information used to analyze the content and characteristics of voice data emitted by a user.

[0780] "Video" refers to visual data acquired using sensors such as cameras, and includes the facial expressions and movements of the person being reported to.

[0781] "Facial expression analysis" is a technology that analyzes the movements and characteristics of a person's face from acquired video data and evaluates their emotional state.

[0782] "Biometric information" refers to physiological data such as the user's heart rate and skin temperature, which is used to infer their emotional state.

[0783] "Emotional state" refers to the emotional state a user is currently experiencing, and can be of various types, such as tension, relief, or surprise.

[0784] "A means of generating advice in real time" refers to a method of generating adaptive feedback that is immediately provided to the user using conventional information and new emotion recognition technologies.

[0785] A "review report" is an analytical document compiled after the reporting period to comprehensively evaluate changes in user behavior and emotions, and to be used for future improvements.

[0786] The embodiment of this invention is designed as a system to support the reporting activities of new employees. This system mainly consists of terminals and a server.

[0787] First, the device plays a crucial role in acquiring audio and video. It uses a microphone to capture the user's speech and a camera to observe the facial expressions of the person being reported to. This allows for the collection of audio and video streams in real time. It also incorporates sensors to acquire biometric information, such as measuring heart rate and skin temperature to understand the user's emotional state. This hardware typically includes commercially available audio and video capture devices.

[0788] The server is the core component that processes this data. Audio data is transcribed into text using speech recognition software and analyzed using natural language processing techniques. Video data is evaluated by facial expression analysis algorithms, and simultaneously, an emotion engine recognizes the user's emotional state through biometric data. Commonly used AI models and analysis engines are employed in this process.

[0789] The server uses a generative AI model to create advice based on the analysis results. The generated advice takes into account past data and the user's emotional state at that time, providing responsive feedback. The feedback is transmitted to the earphones via the device, allowing the user to improve their reporting skills.

[0790] As a concrete example, consider a scenario in a "Weekly Project Progress Report" where the user requires emotional support. A suitable prompt for the AI ​​model would be something like, "The user is reporting on project progress. Please provide emotional support based on their statements and facial expressions." Based on this information, the system can provide human-like, flexible feedback, enabling it to offer emotional support to the user.

[0791] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0792] Step 1:

[0793] The device uses a microphone to capture the user's voice. The input is the user's speech, and the output is a digital audio stream. The audio capture device recognizes the voice and transmits it to the server in real time.

[0794] Step 2:

[0795] The terminal uses its camera to capture video of the person being reported to. The input is visual information of the person being reported to, and the output is a digital video stream. The video capture device records facial movements and sends that data to the server.

[0796] Step 3:

[0797] The device uses sensors to acquire the user's biometric information. Inputs are physiological data such as the user's heart rate and skin temperature, and outputs are biometric datasets. The sensor device collects the data and provides it to a server for emotion analysis.

[0798] Step 4:

[0799] The server uses speech recognition software to convert the received audio stream into text. The input is an audio stream, and the output is text data. The speech recognition engine analyzes the audio data and generates the transcribed speech.

[0800] Step 5:

[0801] The server uses natural language processing technology to analyze text data and extract the intent and key points of the report. The input is text data, and the output is the data structure of the analyzed content. This allows for the determination of the main topic and important elements of the report.

[0802] Step 6:

[0803] The server processes video data using a facial expression analysis algorithm to evaluate emotional states. The input is a video stream, and the output is emotional evaluation data based on facial expression information. The facial expression analysis module evaluates facial features and identifies the emotional state of the other person.

[0804] Step 7:

[0805] The server uses biometric data to recognize the user's emotional state with its emotion engine. The input is a biometric dataset, and the output is data on the user's emotional state. The emotion recognition module analyzes the physiological data to identify the user's psychological state.

[0806] Step 8:

[0807] The server uses a generative AI model to integrate all analysis results and create real-time advice. Inputs are analyzed audio, video, and emotion data, and output is adaptive feedback messages. An advice generation module combines each data point to generate feedback tailored to the user's situation.

[0808] Step 9:

[0809] The terminal transmits advice provided by the server to the user via earphones. The input is the generated feedback message, and the output is the user's auditory feedback. The audio output device plays the advice as audio and delivers it to the user.

[0810] (Application Example 2)

[0811] 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".

[0812] In modern manufacturing, there is a demand to improve the efficiency and accuracy of workers and robot operators. However, it is difficult to grasp workers' emotions and stress levels in real time and provide appropriate feedback based on that information. Furthermore, reviewing the results after the work is completed and using them to make improvements is also a challenge. Therefore, there is a need for a system that can improve the working environment and increase work efficiency.

[0813] 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.

[0814] In this invention, the server includes means for acquiring audio data, converting and analyzing the audio information, means for acquiring video data, and evaluating emotions by analyzing facial expressions, and means for providing the worker with execution instructions and improvement suggestions in real time based on the analyzed audio and facial expression information. This enables the provision of appropriate feedback in real time that takes into account the worker's emotional state, thereby improving work efficiency and reducing stress.

[0815] "Audio data" refers to sound information that records a speaker's speech, acquired through an input device such as a microphone.

[0816] "Audio information" refers to information about language and speech signals obtained by analyzing audio data.

[0817] "Video data" refers to visual information that records a visual scene, acquired through a visual device such as a camera.

[0818] "Facial expression analysis" is a process that uses video data to analyze the facial features of a subject and identify their emotions and mood at that moment.

[0819] "Evaluating emotions" refers to the act of determining an individual's internal emotional state based on facial expression analysis and biometric data.

[0820] "Worker" refers to an individual engaged in specific tasks in a manufacturing plant or office, or a person who performs a task, including a robot operator.

[0821] An "execution instruction" is a set of instructions that specify the concrete actions or operations that a worker should perform.

[0822] An "improvement proposal" is a suggested improvement to methods or procedures aimed at increasing the efficiency or quality of work.

[0823] A "means of communication" refers to a communication technology or device used to transmit generated information or instructions to a recipient.

[0824] "Review" is the process of re-analyzing the data and results recorded after the completion of a task to help improve it in the future.

[0825] The system implementing this invention is realized by integrating multiple hardware and software components. Specifically, it uses speech recognition and video analysis technologies to evaluate the worker's emotions and work status, and provides real-time feedback.

[0826] First, the robots and work stations, acting as terminals, are equipped with microphones and cameras, which are used to acquire voice and video data of the workers. The voice data is converted into text data by Microsoft's Azure Cognitive Services and then analyzed through natural language processing algorithms.

[0827] Next, the server uses Amazon Rekognition to analyze facial expressions from video data and evaluate emotions. This process allows for the estimation of the worker's stress level and attentiveness based on the acquired data. The evaluated emotion information and voice analysis results are integrated, and a generative AI model using TensorFlow is used to create optimal execution instructions and improvement suggestions.

[0828] The generated instructions and suggestions are communicated to the worker via a terminal. These are output as voice instructions and visual information, provided in a way that is easy for the worker to understand in real time. Furthermore, after the work is completed, a review document based on all the data is generated on the server and can be discussed in reporting meetings. This is expected to improve work efficiency and safety.

[0829] For example, if a worker shows a high stress level, the system can provide real-time feedback such as, "We recommend you take a break." Also, if the production line speed is inappropriate, specific instructions such as, "Let's reduce the production speed by 20%," can be provided.

[0830] An example of a prompt for a generative AI model would be: "Based on past data, generate suggestions on what appropriate feedback settings should be used when the operator's stress level is high."

[0831] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0832] Step 1:

[0833] The terminal uses a microphone to acquire voice data from the worker. This voice data is then transmitted to a server via a communication network. The input is voice data, and the output is the transfer of voice data to the server.

[0834] Step 2:

[0835] The server converts the received audio data into text data using Microsoft's Azure Cognitive Services. This process uses speech recognition technology to convert the audio signal into a string of characters. The input is audio data, and the output is the converted text data.

[0836] Step 3:

[0837] The terminal uses a camera to acquire video data of the worker. This video data is transmitted to a server via a communication network. The input is video data, and the output is the transfer of video data to the server.

[0838] Step 4:

[0839] The server uses Amazon's Rekognition to analyze facial expressions from received video data. This allows it to evaluate the emotional state of the worker. The input is video data, and the output is the emotional evaluation result.

[0840] Step 5:

[0841] The server uses an AI model to generate optimal execution instructions and improvement suggestions for workers, based on the analyzed text data and sentiment evaluation results. This process takes past data and current emotional states into account when generating instructions. The input is text data and sentiment evaluation data, and the output is specific execution instructions and improvement suggestions.

[0842] Step 6:

[0843] The server sends the generated instructions and improvement suggestions to the terminal. The terminal provides this information to the worker using an audio or visual output device. The input is the generated instruction data, and the output is the information transmitted to the worker.

[0844] Step 7:

[0845] After the work is completed, the server integrates all the data and generates a retrospective report. This report includes analysis results regarding work efficiency and emotional fluctuations. The input is the complete record of the work data, and the output is the retrospective report.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] The following is further disclosed regarding the embodiments described above.

[0868] (Claim 1)

[0869] A means of acquiring the reporter's voice, converting the voice information, and analyzing it,

[0870] A method for evaluating emotions by acquiring video footage of the person being reported to and analyzing their facial expressions,

[0871] A means for generating real-time advice for the reporter based on analyzed voice and facial expression information,

[0872] A means of communication to convey advice to the reporter,

[0873] A means of generating a review report based on the overall analysis results after the report is completed,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, which identifies the context of a report from the analyzed audio information and selects the most appropriate advice.

[0877] (Claim 3)

[0878] The system according to claim 1, wherein the facial expression analysis means evaluates multiple emotional states and generates adaptive advice for the reporter accordingly.

[0879] "Example 1"

[0880] (Claim 1)

[0881] A means for acquiring the reporter's voice using a voice acquisition device and converting the voice information into text data using a speech recognition engine,

[0882] A means of acquiring video of the person being reported to using a video acquisition device and quantitatively evaluating their emotions using a facial expression analysis algorithm,

[0883] A means of generating advice for the reporter in real time using a generative AI model based on analyzed voice and facial expression information,

[0884] A means of communication that informs the reporter of advice via a communication device,

[0885] After the report is completed, a means to automatically generate a review report based on the analyzed information,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, which identifies the context of a report from transcribed audio information and selects the most appropriate advice based on that context.

[0889] (Claim 3)

[0890] The system according to claim 1, wherein the facial expression analysis means evaluates multiple emotional states and generates adaptive advice for the reporter accordingly.

[0891] "Application Example 1"

[0892] (Claim 1)

[0893] A means of obtaining the reporter's oral information, converting it into audio data, and analyzing it,

[0894] A method for evaluating emotions by acquiring image data of the person being reported to and analyzing their facial expressions,

[0895] A means for generating real-time instruction for the reporter based on analyzed voice and facial expression information,

[0896] A means of communication to convey instructions to the reporter,

[0897] A means of generating an evaluation report based on the overall analysis results after the report is completed,

[0898] Including assistant automated machinery and equipment to support the work of knowledge workers in industrial environments,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, which identifies the context of a report from the analyzed oral information and selects the most appropriate guidance.

[0902] (Claim 3)

[0903] The system according to claim 1, wherein the facial expression analysis means evaluates multiple emotional states and generates adaptive guidance for the reporter accordingly.

[0904] "Example 2 of combining an emotion engine"

[0905] (Claim 1)

[0906] A means of acquiring the reporter's voice, converting the voice information, and analyzing it,

[0907] A method for evaluating emotions by acquiring video footage of the person being reported to and analyzing their facial expressions,

[0908] A means of acquiring biometric information and recognizing the emotional state of the reporter,

[0909] A means for generating real-time advice for the reporter based on analyzed voice and facial expression information, and biometric information,

[0910] A means of communication to convey advice to the reporter,

[0911] A means of generating a review report based on the overall analysis results after the report is completed,

[0912] A system that includes this.

[0913] (Claim 2)

[0914] The system according to claim 1, which identifies the context of a report from the analyzed voice information and biometric information and selects the most appropriate advice.

[0915] (Claim 3)

[0916] The system according to claim 1, wherein the facial expression analysis means and the bio-information analysis means evaluate multiple emotional states and generate adaptive advice for the reporter accordingly.

[0917] "Application example 2 when combining with an emotional engine"

[0918] (Claim 1)

[0919] A means of acquiring audio data, converting the audio information, and analyzing it,

[0920] A method for evaluating emotions by acquiring video data and analyzing facial expressions,

[0921] A means of providing workers with real-time instructions and improvement suggestions based on analyzed voice and facial expression information,

[0922] A means of communication to notify workers of the provided instructions and improvement proposals,

[0923] A method for generating improvement suggestions based on the overall analysis results after the work is completed,

[0924] A system that includes this.

[0925] (Claim 2)

[0926] The system according to claim 1, which identifies the context of the work from the analyzed audio information and selects the optimal execution instructions or improvement proposals.

[0927] (Claim 3)

[0928] The system according to claim 1, wherein the facial expression analysis means evaluates multiple emotional states and generates corresponding instructions for the worker. [Explanation of symbols]

[0929] 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 of acquiring the reporter's voice, converting the voice information, and analyzing it, A method for evaluating emotions by acquiring video footage of the person being reported to and analyzing their facial expressions, A means for generating real-time advice for the reporter based on analyzed voice and facial expression information, A means of communication to convey advice to the reporter, A means of generating a review report based on the overall analysis results after the report is completed, A system that includes this.

2. The system according to claim 1, which identifies the context of a report from the analyzed audio information and selects the most appropriate advice.

3. The system according to claim 1, wherein the facial expression analysis means evaluates multiple emotional states and generates adaptive advice for the reporter accordingly.

Images