system

Abstract

We provide the system. [Solution] Information processing means that receives audio information and analyzes emotions based on said audio information, Information processing means that receives image information and analyzes emotions based on said image information, Information presentation means that integrates the analysis results obtained by the audio information processing means and the image information processing means and presents them visually to the user, A display means for adjusting dialogue or care methods based on analyzed emotional information for care workers or relatives, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , , ,

[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] In order to accurately grasp human emotions and support smooth communication, it is necessary to efficiently analyze information from voices and expressions, and appropriately visualize and provide it. However, existing technologies are insufficient in any of these processes, and there are problems in real-time analysis and display of emotion data. Therefore, it is necessary to establish a system that effectively processes voice and image data and visually provides emotion information to users.

Means for Solving the Problems

[0005] The present invention solves the above problems by using an audio processing means for analyzing emotions based on audio data, an image processing means for analyzing emotions based on image data, and a visualization means for integrating these analysis results and presenting them visually to the user. Specifically, it securely transmits data using encrypted communication while processing audio and image data, generates a chart showing the emotional state, and provides real-time emotional feedback to the user.

[0006] "Voice data" refers to information obtained from the user's voice, and is an audio signal used for emotion analysis.

[0007] "Image data" refers to visual information, including a user's face, and is a digital image used to analyze emotions from facial expressions.

[0008] "Voice processing means" refers to functions or devices for analyzing emotions based on voice data, and includes techniques for analyzing voice tone and patterns.

[0009] "Image processing means" refers to functions or devices for analyzing emotions based on image data, and includes technologies for determining emotions through facial recognition.

[0010] "Visualization means" refers to functions or devices that visually display analyzed emotional information to the user, such as graphs or charts that show the state of emotions.

[0011] "Encryption" refers to the technology that transforms information to ensure secure transmission of data and prevents unauthorized access.

[0012] A "chart" is a graphical display format of information generated by visualization means, and is a visual tool used to show the proportion or fluctuation of emotions.

[0013] A "user" is the individual who uses this system to receive the results of sentiment analysis and provides audio and image data through their device. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a method for analyzing emotions using audio and image data collected from a user through an emotion analysis system, and providing visual feedback. In the implementation of this system, a server processes the data using multiple AI modules and transmits the results to a terminal.

[0036] First, the user operates the device to begin collecting audio and images. The device uses the microphone to acquire audio data and the camera to collect image data. This data is encrypted for security purposes and transmitted to the server in real time.

[0037] The server performs emotion analysis based on the received audio data via audio processing. Specifically, it analyzes the tone, intonation, and speed of the voice and generates associated emotion labels. Similarly, it uses image processing to interpret facial feature points from image data and identify emotions based on facial expressions.

[0038] These analysis results are integrated within the server to perform a comprehensive sentiment assessment. This assessment is then formalized as graphs and infographics using visualization tools, and the generated visual information is immediately sent to the terminal.

[0039] The device receives this information and displays it visually to the user. This allows the user to intuitively understand the emotional state of the person they are communicating with and respond appropriately to the actual conversation.

[0040] One concrete example is its application in educational settings. When teachers interact with students, this system allows them to grasp changes in students' understanding and interests in real time. This enables teachers to quickly adjust teaching methods and content, thereby improving student learning effectiveness. In this way, the present invention contributes to improving emotion-based interactions in various fields.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user launches the application on their device and selects the sentiment analysis mode. The device then prepares to begin collecting audio and image data.

[0044] Step 2:

[0045] The device uses its built-in microphone to capture audio data in real time. Simultaneously, it uses its camera to capture the user's facial expressions and acquire image data.

[0046] Step 3:

[0047] The device encrypts the collected audio and image data for security purposes. This encrypted data is then securely transmitted to the server.

[0048] Step 4:

[0049] The server analyzes the received audio data using audio processing equipment. Specifically, it analyzes the tone, intonation, and speed of the sound and assigns emotion labels to them.

[0050] Step 5:

[0051] The server analyzes the received image data using image processing tools to extract facial feature points. Based on the facial expression information, it determines the emotion and assigns a label.

[0052] Step 6:

[0053] The server integrates the analysis results of both audio and image to perform an overall sentiment assessment. This allows individual emotional states to be consolidated into a single, comprehensive evaluation.

[0054] Step 7:

[0055] The server generates graphs and infographics to visualize the integrated sentiment data. The generated output is in a user-friendly format.

[0056] Step 8:

[0057] The server sends the generated visualization data to the terminal.

[0058] Step 9:

[0059] The device displays the received visualization information on the application's dashboard, allowing users to check their emotional state in real time.

[0060] (Example 1)

[0061] 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."

[0062] While many systems exist that analyze emotions using audio and image data and provide visual feedback to users, real-time processing and ensuring data security are challenging. Furthermore, there is a lack of means to integrate the obtained emotional information and make it intuitively understandable to users.

[0063] 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.

[0064] In this invention, the server includes a voice analysis means for receiving voice data and analyzing emotions, an image recognition means for receiving image data and analyzing emotions, and an evaluation means for integrating the analysis results and generating visual information. This makes it possible to analyze emotions in real time with high accuracy based on collected voice and image data and provide the user with visual and safe feedback.

[0065] A "voice analysis means" is a method for generating emotion labels by analyzing characteristics such as tone, intonation, and speed of voice based on received voice data, in order to identify emotions.

[0066] "Image recognition means" refers to a method for detecting facial feature points from received image data, analyzing facial expressions based on these points, and identifying emotions.

[0067] "Evaluation means" refers to a means of integrating the analysis results obtained by the speech analysis means and the image recognition means, performing an overall emotional evaluation, and generating it as visual information.

[0068] A "display means" is a means of presenting visual information transmitted from a server to the user, enabling them to intuitively understand their emotional state.

[0069] "Transmission means" refers to the means for securely encrypting the collected audio and image data and transmitting it to the server.

[0070] A "text conversion method" is a means of converting audio data into text data and providing basic data for sentiment analysis.

[0071] A "feature point analysis method" is a means of analyzing facial feature points obtained from image data in detail and estimating emotions from the resulting facial expressions.

[0072] This invention is a system that analyzes emotions using audio and image data and provides visual feedback to the user. The system utilizes terminals, servers, and various hardware and software components.

[0073] First, the user operates the device to begin collecting audio and image data. Specifically, the device uses a microphone and camera. For example, the user uses a smartphone to launch an application and perform operations to collect audio and facial expressions. As a result, the actual data is captured on the device.

[0074] The terminal encrypts the collected audio data using encryption technologies such as AES, and similarly encrypts image data to ensure the security of communications. This encrypted data is sent to the server via the SSL / TLS protocol.

[0075] On the server, a speech analysis tool converts the speech data into text and uses a machine learning model to generate emotion labels. A common speech recognition API can be used for this speech-to-text conversion. Specifically, AI technology that analyzes tone and intonation is employed.

[0076] Similarly, the image recognition system on the server uses libraries such as OpenCV and Dlib to analyze facial feature points from image data and re-evaluate emotions. For example, if a smile is detected in an image, the emotion "joy" is identified.

[0077] The results of speech analysis and image recognition are integrated by an evaluation tool and presented to the user as visual information. This visual information is generated using TENSORFLOW® or PyTorch as infographics showing sentiment scores and fluctuations.

[0078] One concrete example of its application is in educational settings. When teachers interact with students, they can use this system to grasp students' level of understanding and emotional changes in real time. By quickly adjusting teaching methods based on this information, they can improve students' learning effectiveness.

[0079] An example of a prompt might be, "Analyze the audio and image data from the students' statements to determine their level of understanding and interest in real time."

[0080] In this way, the present invention can support the improvement of emotion-based interactions in many fields and realize intuitive and effective communication.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The user operates the device to begin collecting audio and image data. Specifically, the user launches the application on the device, presses the record button, speaks into the microphone, and simultaneously uses the camera to capture their facial expressions. The input is the user's voice and facial expressions, and the output is audio and image data converted into digital format within the device.

[0084] Step 2:

[0085] The terminal encrypts the collected audio and image data using encryption technologies such as AES. To ensure data security, this process is performed on the terminal immediately after collection. The input is the audio and image data obtained in step 1, and the output is the encrypted data.

[0086] Step 3:

[0087] The terminal transmits encrypted audio and image data to the server in real time using the SSL / TLS protocol. This process ensures the security of data transmission. The input is the encrypted data obtained in step 2, and the output is the data that has safely reached the server.

[0088] Step 4:

[0089] The server decrypts the received encrypted data and analyzes the audio data using speech analysis tools. Specifically, it converts the audio to text and generates sentiment labels using a machine learning model. The input is the decrypted audio data, and the output is the sentiment labels.

[0090] Step 5:

[0091] The server analyzes image data using image recognition techniques. It detects facial feature points using a library and estimates emotions using a generative AI model. The input is decrypted image data, and the output is emotion labels.

[0092] Step 6:

[0093] The server integrates the analysis results obtained from audio and images and performs a comprehensive sentiment assessment using evaluation tools. In this step, sentiment scores and related infographics are generated. The input is the sentiment labels obtained in steps 4 and 5, and the output is the sentiment assessment as visual information.

[0094] Step 7:

[0095] The server sends the generated visual information to the terminal. The terminal receives this information and visualizes it on the user interface. The input is the visual information obtained in step 6, and the output is the emotional feedback presented to the user. The user can use this information to improve communication.

[0096] (Application Example 1)

[0097] 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."

[0098] In elderly care settings, a key challenge is to quickly and accurately understand the emotional state of elderly individuals and provide appropriate care and communication to improve their quality of life. In particular, it is essential to communicate changes in emotions to caregivers and family members in real time.

[0099] 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.

[0100] In this invention, the server includes an information processing means for receiving audio information and analyzing emotions based on the audio information; an information processing means for receiving image information and analyzing emotions based on the image information; an information presentation means for integrating the analysis results obtained by the audio information processing means and the image information processing means and presenting them visually to the user; and a display means for adjusting dialogue or care methods based on the analyzed emotional information for care workers or relatives. This makes it possible to accurately grasp the emotional state of the person receiving care and quickly adjust individual care policies.

[0101] "Audio information" refers to data analyzed based on the characteristics of received sounds, and it forms the basis for identifying emotions.

[0102] "Image information" refers to data extracted from received video footage, and it forms the basis for analyzing facial features and identifying emotions.

[0103] "Information processing means" refers to a program or device for analyzing emotions based on audio and image information.

[0104] An "information presentation means" is a program or device that visually processes analyzed emotional information and transmits it to the user.

[0105] "Display means" refers to a program or device for showing specific messages or policies to care workers or relatives based on analyzed emotional information.

[0106] This invention aims to build a system that analyzes the emotional state of elderly individuals in care settings and provides appropriate care plans. The user terminal is connected to a microphone for acquiring audio information and a camera for acquiring image information. The user uses these devices to collect audio and video data of the elderly individual in question.

[0107] The collected audio information is processed on the server using a TensorFlow speech analysis model. The server analyzes the tone, intonation, and speed of the sound to identify emotions. Additionally, OpenCV is used to detect facial feature points from image information and perform emotion analysis based on facial expressions.

[0108] These analysis results are integrated in real time using AWS Lambda and monitored by Amazon CloudWatch. The integrated emotional information is sent to the user's device via Amazon SNS. The device then presents visual feedback to caregivers and family members based on the analyzed emotional information. This allows for flexible adjustment of communication and care methods in caregiving.

[0109] For example, if an elderly person's facial expression during morning care is analyzed to indicate fatigue or stress, the system will send a notification to the caregiver suggesting a rest. This prompt allows the caregiver to suggest a rest to the elderly person and adjust the care program on the spot if necessary.

[0110] An example of a prompt message would be, "I need advice on how to proceed with a conversation when an elderly person is feeling anxious. Please tell me how to change the topic."

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The device uses a microphone and camera to acquire voice and image information from elderly individuals. Voice information includes tone, intonation, and speaking speed, while image information captures facial features. This data serves as input.

[0114] Step 2:

[0115] The terminal encrypts the collected audio and image information for security purposes and sends it to the server. Data encryption is performed to ensure the confidentiality of the information, and this is the output.

[0116] Step 3:

[0117] The server uses a TensorFlow speech analysis model to analyze the received audio information. This model processes the audio information as input and generates sentiment labels. The result is the output.

[0118] Step 4:

[0119] The server uses OpenCV to detect facial feature points and perform facial expression analysis to analyze image information. It takes image information as input and outputs the analyzed emotion information.

[0120] Step 5:

[0121] The server integrates the audio and image analysis results using AWS Lambda, aggregating emotional information in real time. This generates integrated emotional data, and the final emotional evaluation is output.

[0122] Step 6:

[0123] The server sends integrated emotion assessments to the device via Amazon SNS. This data serves as input and is presented to caregivers and family members as visual feedback on the device.

[0124] Step 7:

[0125] Users (caregivers and family members) flexibly adjust their interactions and care methods with the elderly based on the emotional information presented. This feedback becomes the final output, improving the quality of care in real time.

[0126] 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.

[0127] This invention relates to a system that more accurately recognizes a user's emotions and provides visual feedback of the analysis results. This system uses a combination of voice processing means, image processing means, and an emotion engine. This allows for high-precision evaluation of the user's emotional state from collected data and provides this information to the user in real time through visualization means.

[0128] The user first launches the application on their device and begins data acquisition. The device collects audio data using the microphone and image data using the camera. This data is encrypted and sent to the server in a secure state.

[0129] The server analyzes the audio data using audio processing equipment, analyzing tone, intonation, and rhythm to determine emotion. Similarly, image processing equipment analyzes the user's facial expressions using image data and infers emotions based on them. These results are then sent to the emotion engine for further advanced analysis. The emotion engine uses machine learning algorithms to recognize the unique emotional state of each user based on the analyzed data, improving the accuracy of the analysis results.

[0130] The analysis results are generated as graphs or infographics using visualization tools and transmitted to the terminal. The terminal receives these and displays them to the user in an intuitive format.

[0131] A concrete example of its application is in business meetings. When users utilize this system in a meeting, it displays the emotional state of participants in real time as they speak, allowing them to instantly perceive changes in the meeting's progress and atmosphere. This enables them to accurately grasp reactions to the agenda and respond as needed. As a result, better communication and more effective discussions can be achieved.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user launches a dedicated application on their device and starts an emotion analysis session. The device then prepares to acquire audio and image data.

[0135] Step 2:

[0136] The device uses a built-in microphone to capture the user's conversation as audio data in real time. Simultaneously, it uses a built-in camera to photograph the user's face and collect image data.

[0137] Step 3:

[0138] The device encrypts the collected audio and image data to protect privacy. This encrypted data is then sent to the server using a secure communication protocol.

[0139] Step 4:

[0140] The server passes the received audio data to an audio processing device, which analyzes the tone, intonation, speed, and other characteristics of the sound. The analysis results are output as emotion labels.

[0141] Step 5:

[0142] The server passes the received image data to an image processing device, which extracts feature points from the user's face and analyzes their facial expressions. This yields emotion labels associated with those expressions.

[0143] Step 6:

[0144] The server integrates the analyzed voice and facial emotion labels into the emotion engine. The emotion engine uses machine learning algorithms to perform more refined emotion analysis based on the user's past patterns and individual profile.

[0145] Step 7:

[0146] The server generates the results of an integrated evaluation using an emotion engine and formalizes them as graphs or infographics using visualization tools.

[0147] Step 8:

[0148] The server sends the generated visual data to the terminal, which then displays this data in an easy-to-understand format for the user. This allows the user to consider appropriate actions based on the situation.

[0149] Step 9:

[0150] By enabling real-time feedback, the system helps users make necessary decisions during meetings and discussions, thereby improving the quality of communication.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] Conventional emotion analysis technologies have suffered from low accuracy in analyzing emotions derived from audio and image information. Furthermore, it has been difficult to provide users with intuitively understandable analysis results, making it challenging for users to accurately understand their own emotional state. In addition, security issues arose due to insufficient protection of personal information in many cases.

[0154] 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.

[0155] In this invention, the server includes an acoustic analysis means for receiving audio information and analyzing emotions based on the audio information; an image analysis means for receiving image information and analyzing emotions based on the image information; and an emotion engine that integrates the analysis results obtained by the acoustic analysis means and the image analysis means and recognizes the user's unique emotional state using a machine learning algorithm. This enables highly accurate emotion analysis based on audio and image data, and by visually presenting the analysis results to the user, it becomes easier to understand the emotional state. Furthermore, by encrypting and transmitting the data, the protection of personal information can be enhanced and security can be ensured.

[0156] "Audio information" refers to digital or analog signals transmitted through sound, including data such as user speech and verbal expressions.

[0157] "Acoustic analysis means" refers to a device or system that analyzes audio information and uses its characteristics to evaluate emotional states.

[0158] "Image information" refers to visual data that records the user's face and facial expressions, and includes digital images acquired by cameras and other imaging devices.

[0159] "Image analysis means" refers to a device or system that analyzes image information and infers an emotional state based on its facial features.

[0160] The "emotion engine" is a system that integrates voice and image analysis results and uses machine learning algorithms to accurately recognize the user's unique emotional state.

[0161] A "visualization device" is a device for displaying analyzed emotion results in an intuitively understandable format, and can use graphs or infographics.

[0162] A "machine learning algorithm" is a computational method for learning from data and recognizing patterns, and is a mathematical model used to improve the accuracy of emotional states.

[0163] Encryption is a security technique that transforms data to protect its confidentiality and prevent unauthorized access.

[0164] This invention relates to an emotion analysis system that recognizes a user's emotions in real time with high accuracy and visualizes the results intuitively. This system is comprised of an acoustic analysis means, an image analysis means, an emotion engine, and a visualization device.

[0165] The user launches the application on the device and operates the system. The device collects audio information using the microphone and acquires image information using the camera. This information is encrypted within the device and transmitted to the server via secure communication. Standard security protocols are used for encryption to maintain the confidentiality of the information.

[0166] The server analyzes audio information using acoustic analysis tools. Specifically, it analyzes the tone, intonation, and rhythm of the audio signal to make a preliminary judgment about the user's emotions. This process can utilize general-purpose audio analysis platforms or open-source audio analysis libraries. Similarly, image analysis tools analyze image information and use facial recognition algorithms to infer emotions from the user's facial expressions. The server then sends these analysis results to the emotion engine.

[0167] The emotion engine uses machine learning algorithms to accurately recognize user-specific emotional states based on integrated analysis results. General datasets are used to train the machine learning model, and high-precision emotion recognition is achieved through the application of the algorithm.

[0168] The analyzed emotion results are generated in real time as graphs and infographics using a visualization device and transmitted to the terminal. The terminal displays this information, providing it to the user in an intuitively understandable format.

[0169] A concrete example of using this system is during a business meeting. When a user speaks during a meeting, the system instantly visualizes the emotional state of other participants, making it possible to accurately understand the impact of their comments and thus facilitate a more effective discussion.

[0170] An example of a prompt might be: "We are developing a system that uses user voice and image data to report emotional changes during a meeting in real time. Please suggest the most intuitive way to visualize the emotional analysis results."

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The user launches an application on the device. The device uses the microphone to acquire the user's voice and sensors and a camera to collect facial image information. The input here is real-time audio and image data, and audio and image files are generated as output. This operation prepares the necessary data within the device.

[0174] Step 2:

[0175] The device encrypts the acquired audio and image data. The encryption process uses an appropriate encryption algorithm to transform the data and protect it from unauthorized access. The input is the audio and image files obtained in step 1, and the output is encrypted data. This operation ensures the security of the data.

[0176] Step 3:

[0177] The terminal sends encrypted data to the server. A secure communication protocol is used for data transfer. The input consists of encrypted audio and image data, and this data reaches the server as output. This process ensures the reliable transmission of data for analysis.

[0178] Step 4:

[0179] The server decodes the received audio data and analyzes its tone, intonation, and rhythm using acoustic analysis tools. The input is decrypted audio data, and the output is information that provides a preliminary assessment of the user's emotions. This process generates audio-based emotion data.

[0180] Step 5:

[0181] The server decrypts the received image data and executes a face recognition algorithm using image analysis tools. The input is decrypted image data, and the output is the result of emotion inference based on facial expression analysis. This process generates image-based emotion data.

[0182] Step 6:

[0183] The server transmits the results obtained from acoustic and image analysis to the emotion engine, which uses machine learning algorithms to accurately recognize the user's unique emotional state. The input is the results of audio and image analysis, and the output is an integrated, advanced emotion analysis result. This operation provides a comprehensive understanding of the user's emotional state.

[0184] Step 7:

[0185] The server generates the emotion analysis results as graphs and infographics through a visualization device and sends them to the terminal. The input is the integrated emotion analysis results, and the output is delivered to the terminal as visualized information. This operation intuitively conveys the emotional state to the user.

[0186] Step 8:

[0187] The terminal displays visualization information sent from the server and provides the user with sentiment analysis results. The input is visualized sentiment data, and the output is the information displayed on the terminal's screen. This operation allows the user to easily understand their own emotional state.

[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 a "server" and the smart device 14 as a "terminal".

[0190] In today's living environment, it is difficult for individuals to accurately understand their emotions and receive appropriate support. In particular, effective coping mechanisms for stress and fatigue are needed in our busy daily lives. However, conventional technology has not adequately provided systems that can analyze emotions in real time and autonomously respond according to the user's state.

[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: an audio processing means for receiving audio information and analyzing the user's mental state based on the audio information; an image processing means for receiving image information and analyzing the user's mental state based on the image information; a visualization means for integrating the analysis results obtained by the audio processing means and the image processing means and presenting them visually to the user; and an action decision means for analyzing the user's emotional state and providing appropriate support according to that state. This enables real-time analysis of the user's emotional state and provides appropriate support.

[0193] "Audio information" refers to data obtained by converting sound waves into digital signals, and includes the user's speech content, voice tone, intonation, and other details.

[0194] "State of mind" refers to the emotions and psychological state that an individual is currently experiencing, and includes basic emotions such as joy, anger, sadness, and pleasure, as well as states such as stress and relaxation.

[0195] "Voice processing means" refers to technology for analyzing voice information to identify the user's mental state, and includes functions for voice recognition and emotion analysis.

[0196] "Image information" refers to visual data acquired by a visual sensor, including the user's facial expressions and movements.

[0197] "Image processing means" refers to technology that analyzes image data and infers the user's mental state, and includes functions such as facial expression recognition.

[0198] "Visualization means" refers to technologies for visually presenting the analyzed mental state to the user, and includes functions for displaying information in charts and graphs.

[0199] A "behavioral decision-making mechanism" is a system for determining and executing appropriate responses based on the user's analyzed mental state, and includes functions that utilize machine learning and generative AI models to determine proposed actions.

[0200] In the system realizing this invention, a terminal collects audio and image information. This information is acquired using a microphone and camera attached to the terminal. The acquired information is encrypted to protect security and sent to a server. The server uses speech recognition technology as an audio processing means, and analyzes the tone, intonation, rhythm, etc. of the audio data through machine learning algorithms to identify the state of mind.

[0201] Furthermore, the server uses open-source image processing libraries (e.g., OpenCV) as image processing tools and applies facial expression analysis technology to analyze image data. This allows it to infer the user's emotional state based on their facial expressions. The analysis results are further evaluated comprehensively through an emotion engine and presented as intuitive graphics by a visualization tool.

[0202] The server, using its decision-making mechanism, proposes appropriate support based on the analyzed mental state. In this process, it utilizes a generative AI model to deliver optimal action instructions to the user. This allows the system to autonomously respond appropriately to the user's stress and relaxation levels. For example, if a robot recognizes that the user is tired, it can automatically play relaxation music.

[0203] Users can interact with the system through their smart devices. Examples of specific prompts include "Tell me how to reduce fatigue today" or "Play some relaxing music." This allows users to experience services that take their emotional state into consideration.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The device collects audio and image information using a microphone and camera. The input data obtained from these sensors consists of raw audio waveforms and visual data. At this stage, no processing has been done yet, so it captures the user's speech and facial expressions as they are. This data is stored in temporary storage for later analysis.

[0207] Step 2:

[0208] The device encrypts the collected audio and image information and sends it to the server via a secure communication link. Raw data is the input, and encrypted data is the output. The encryption process is crucial for protecting data privacy and uses common encryption algorithms.

[0209] Step 3:

[0210] The server decrypts the received encrypted data and inputs the audio data into the voice processing system for analysis. The voice processing system uses machine learning algorithms to analyze tone, intonation, and rhythm to identify the user's emotional state (e.g., joy, anger, sadness). This process outputs the audio waveform as data converted into emotion labels.

[0211] Step 4:

[0212] The server passes image data to an image processing system for facial expression analysis. The input is visual data, and the output is the user's mental state inferred from their facial expressions. In image processing, features of facial expressions are extracted using libraries such as OpenCV, and the analysis results are generated.

[0213] Step 5:

[0214] The server integrates the analysis results obtained from the speech processing system and the image processing system and sends them to the emotion engine. The emotion engine combines these results and evaluates the overall mental state using a generating AI model. The output is a score or label indicating the mental state. This information is used in the next step.

[0215] Step 6:

[0216] The server generates results using visualization tools based on the overall mental state obtained. These visualization tools produce user-friendly graphs and infographics and transmit the data to the terminal. The output is visualized data displayed on the user interface.

[0217] Step 7:

[0218] Users can review the displayed visualization data and accept the server's suggested actions based on their mental state. Suggested actions based on prompts generated using a generative AI model (e.g., "Tell me how to reduce today's fatigue" or "Play some relaxing music") are displayed, allowing users to select the appropriate response.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] This invention relates to a method for analyzing emotions using audio and image data collected from a user through an emotion analysis system, and providing visual feedback. In the implementation of this system, a server processes the data using multiple AI modules and transmits the results to a terminal.

[0236] First, the user operates the device to begin collecting audio and images. The device uses the microphone to acquire audio data and the camera to collect image data. This data is encrypted for security purposes and transmitted to the server in real time.

[0237] The server performs emotion analysis based on the received audio data via audio processing. Specifically, it analyzes the tone, intonation, and speed of the voice and generates associated emotion labels. Similarly, it uses image processing to interpret facial feature points from image data and identify emotions based on facial expressions.

[0238] These analysis results are integrated within the server to perform a comprehensive sentiment assessment. This assessment is then formalized as graphs and infographics using visualization tools, and the generated visual information is immediately sent to the terminal.

[0239] The device receives this information and displays it visually to the user. This allows the user to intuitively understand the emotional state of the person they are communicating with and respond appropriately to the actual conversation.

[0240] One concrete example is its application in educational settings. When teachers interact with students, this system allows them to grasp changes in students' understanding and interests in real time. This enables teachers to quickly adjust teaching methods and content, thereby improving student learning effectiveness. In this way, the present invention contributes to improving emotion-based interactions in various fields.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The user launches the application on their device and selects the sentiment analysis mode. The device then prepares to begin collecting audio and image data.

[0244] Step 2:

[0245] The device uses its built-in microphone to capture audio data in real time. Simultaneously, it uses its camera to capture the user's facial expressions and acquire image data.

[0246] Step 3:

[0247] The device encrypts the collected audio and image data for security purposes. This encrypted data is then securely transmitted to the server.

[0248] Step 4:

[0249] The server analyzes the received audio data using audio processing equipment. Specifically, it analyzes the tone, intonation, and speed of the sound and assigns emotion labels to them.

[0250] Step 5:

[0251] The server analyzes the received image data using image processing tools to extract facial feature points. Based on the facial expression information, it determines the emotion and assigns a label.

[0252] Step 6:

[0253] The server integrates the analysis results of both audio and image to perform an overall sentiment assessment. This allows individual emotional states to be consolidated into a single, comprehensive evaluation.

[0254] Step 7:

[0255] The server generates graphs and infographics to visualize the integrated sentiment data. The generated output is in a user-friendly format.

[0256] Step 8:

[0257] The server sends the generated visualization data to the terminal.

[0258] Step 9:

[0259] The device displays the received visualization information on the application's dashboard, allowing users to check their emotional state in real time.

[0260] (Example 1)

[0261] 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."

[0262] While many systems exist that analyze emotions using audio and image data and provide visual feedback to users, real-time processing and ensuring data security are challenging. Furthermore, there is a lack of means to integrate the obtained emotional information and make it intuitively understandable to users.

[0263] 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.

[0264] In this invention, the server includes a voice analysis means for receiving voice data and analyzing emotions, an image recognition means for receiving image data and analyzing emotions, and an evaluation means for integrating the analysis results and generating visual information. This makes it possible to analyze emotions in real time with high accuracy based on collected voice and image data and provide the user with visual and safe feedback.

[0265] A "voice analysis means" is a method for generating emotion labels by analyzing characteristics such as tone, intonation, and speed of voice based on received voice data, in order to identify emotions.

[0266] "Image recognition means" refers to a method for detecting facial feature points from received image data, analyzing facial expressions based on these points, and identifying emotions.

[0267] "Evaluation means" refers to a means of integrating the analysis results obtained by the speech analysis means and the image recognition means, performing an overall emotional evaluation, and generating it as visual information.

[0268] A "display means" is a means of presenting visual information transmitted from a server to the user, enabling them to intuitively understand their emotional state.

[0269] "Transmission means" refers to the means for securely encrypting the collected audio and image data and transmitting it to the server.

[0270] A "text conversion method" is a means of converting audio data into text data and providing basic data for sentiment analysis.

[0271] A "feature point analysis method" is a means of analyzing facial feature points obtained from image data in detail and estimating emotions from the resulting facial expressions.

[0272] This invention is a system that analyzes emotions using audio and image data and provides visual feedback to the user. The system utilizes terminals, servers, and various hardware and software components.

[0273] First, the user operates the device to begin collecting audio and image data. Specifically, the device uses a microphone and camera. For example, the user uses a smartphone to launch an application and perform operations to collect audio and facial expressions. As a result, the actual data is captured on the device.

[0274] The terminal encrypts the collected audio data using encryption technologies such as AES, and similarly encrypts image data to ensure the security of communications. This encrypted data is sent to the server via the SSL / TLS protocol.

[0275] On the server, a speech analysis tool converts the speech data into text and uses a machine learning model to generate emotion labels. A common speech recognition API can be used for this speech-to-text conversion. Specifically, AI technology that analyzes tone and intonation is employed.

[0276] Similarly, the image recognition means on the server analyzes the facial feature points from the image data using libraries such as OpenCV and Dlib, and re-evaluates the emotion. For example, when a smiling face is detected from the image, the emotion of "joy" is identified.

[0277] The results of voice analysis and image recognition are integrated by the evaluation means and presented to the user as visual information. This visual information is generated as infographics showing emotion scores and fluctuations using TensorFlow or PyTorch.

[0278] As a specific example, application in the educational field can be considered. When a teacher interacts with a student, by using this system, it is possible to grasp the student's understanding level and emotional changes in real time. By quickly adjusting the teaching method based on this information, the learning effect of the student can be improved.

[0279] As an example of the prompt sentence, content such as "Analyze the voice and image data for real-time determination of the understanding level and interest from the student's speech." can be considered.

[0280] In this way, the present invention supports the improvement of emotion-based interactions in many fields and enables intuitive and effective communication.

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] [ Step 1:

[0283] The user operates the terminal to start collecting voice data and image data. Specifically, the user launches the application on the terminal, presses the recording button, speaks towards the microphone, and at the same time uses the camera to take a picture of the expression. The input is the user's voice and expression, and the output is the voice data and image data converted into digital format within the terminal.

[0284] Step 2: [

[0285] The terminal encrypts the collected voice data and image data using encryption technologies such as AES. To ensure data security, this process is performed on the terminal immediately after collection. The input is the voice data and image data obtained in Step 1, and the output is the encrypted data.

[0286] Step 3:

[0287] The terminal transmits the encrypted voice data and image data to the server in real time using the SSL / TLS protocol. In this process, the security of data transmission is ensured. The input is the encrypted data obtained in Step 2, and the output is the data that has safely reached the server.

[0288] Step 4:

[0289] The server decrypts the received encrypted data and analyzes the voice data using voice analysis means. Specifically, it converts the voice into text and generates an emotion label using a machine learning model. The input is the decrypted voice data, and the output is the emotion label.

[0290] Step 5:

[0291] The server analyzes the image data using image recognition means. It detects facial feature points using a library and estimates emotions using a generated AI model. The input is the decrypted image data, and the output is the emotion label.

[0292] Step 6:

[0293] The server integrates the analysis results obtained from voice and image, and performs a comprehensive emotion evaluation using evaluation means. In this step, an emotion score and related infographics are generated. The input is the emotion labels obtained in Step 4 and Step 5, and the output is the emotion evaluation as visual information.

[0294] Step 7:

[0295] The server sends the generated visual information to the terminal. The terminal receives this information and visualizes it on the user interface. The input is the visual information obtained in step 6, and the output is the emotional feedback presented to the user. The user can use this information to improve communication.

[0296] (Application Example 1)

[0297] 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."

[0298] In elderly care settings, a key challenge is to quickly and accurately understand the emotional state of elderly individuals and provide appropriate care and communication to improve their quality of life. In particular, it is essential to communicate changes in emotions to caregivers and family members in real time.

[0299] 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.

[0300] In this invention, the server includes an information processing means for receiving audio information and analyzing emotions based on the audio information; an information processing means for receiving image information and analyzing emotions based on the image information; an information presentation means for integrating the analysis results obtained by the audio information processing means and the image information processing means and presenting them visually to the user; and a display means for adjusting dialogue or care methods based on the analyzed emotional information for care workers or relatives. This makes it possible to accurately grasp the emotional state of the person receiving care and quickly adjust individual care policies.

[0301] "Audio information" refers to data analyzed based on the characteristics of received sounds, and it forms the basis for identifying emotions.

[0302] "Image information" refers to data extracted from received video footage, and it forms the basis for analyzing facial features and identifying emotions.

[0303] The "information processing means" is a program or device for analyzing emotions based on voice information and image information.

[0304] The "information presentation means" is a program or device for visually processing the analyzed emotion information and transmitting it to the user.

[0305] The "display means" is a program or device for indicating specific messages or guidelines to the caregiver or family members based on the analyzed emotion information.

[0306] The present invention aims to construct a system for analyzing the emotional state of the elderly at the care site and providing appropriate care guidelines. A microphone for acquiring voice information and a camera for acquiring image information are connected to the user terminal. The user uses these devices to collect the voice and video of the target elderly person.

[0307] The collected voice information is processed on the server using the TensorFlow voice analysis model. The server analyzes the tone, intonation, speed, etc. of the voice to identify the emotion. Also, the image information is used with OpenCV to detect the facial feature points and perform emotion analysis based on the expression.

[0308] These analysis results are integrated in real time using AWS Lambda and monitored by Amazon CloudWatch. The integrated emotion information is transmitted to the user terminal via Amazon SNS. The terminal presents visual feedback to the caregiver and family members based on the analyzed emotion information. Thereby, the methods of interaction and care in caregiving can be flexibly adjusted.

[0309] As a specific example, when the face of the elderly person is analyzed as showing an expression of fatigue or stress during the morning care time, the system sends a notification of "proposing rest" to the caregiver. With this prompt, the caregiver can propose rest to the elderly person and, if necessary, adjust the care program on the spot.

[0310] An example of a prompt message would be, "I need advice on how to proceed with a conversation when an elderly person is feeling anxious. Please tell me how to change the topic."

[0311] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0312] Step 1:

[0313] The device uses a microphone and camera to acquire voice and image information from elderly individuals. Voice information includes tone, intonation, and speaking speed, while image information captures facial features. This data serves as input.

[0314] Step 2:

[0315] The terminal encrypts the collected audio and image information for security purposes and sends it to the server. Data encryption is performed to ensure the confidentiality of the information, and this is the output.

[0316] Step 3:

[0317] The server uses a TensorFlow speech analysis model to analyze the received audio information. This model processes the audio information as input and generates sentiment labels. The result is the output.

[0318] Step 4:

[0319] The server uses OpenCV to detect facial feature points and perform facial expression analysis to analyze image information. It takes image information as input and outputs the analyzed emotion information.

[0320] Step 5:

[0321] The server integrates the audio and image analysis results using AWS Lambda, aggregating emotional information in real time. This generates integrated emotional data, and the final emotional evaluation is output.

[0322] Step 6:

[0323] The server sends integrated emotion assessments to the device via Amazon SNS. This data serves as input and is presented to caregivers and family members as visual feedback on the device.

[0324] Step 7:

[0325] Users (caregivers and family members) flexibly adjust their interactions and care methods with the elderly based on the emotional information presented. This feedback becomes the final output, improving the quality of care in real time.

[0326] 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.

[0327] This invention relates to a system that more accurately recognizes a user's emotions and provides visual feedback of the analysis results. This system uses a combination of voice processing means, image processing means, and an emotion engine. This allows for high-precision evaluation of the user's emotional state from collected data and provides this information to the user in real time through visualization means.

[0328] The user first launches the application on their device and begins data acquisition. The device collects audio data using the microphone and image data using the camera. This data is encrypted and sent to the server in a secure state.

[0329] The server analyzes the audio data using audio processing equipment, analyzing tone, intonation, and rhythm to determine emotion. Similarly, image processing equipment analyzes the user's facial expressions using image data and infers emotions based on them. These results are then sent to the emotion engine for further advanced analysis. The emotion engine uses machine learning algorithms to recognize the unique emotional state of each user based on the analyzed data, improving the accuracy of the analysis results.

[0330] The analysis results are generated as graphs or infographics using visualization tools and transmitted to the terminal. The terminal receives these and displays them to the user in an intuitive format.

[0331] A concrete example of its application is in business meetings. When users utilize this system in a meeting, it displays the emotional state of participants in real time as they speak, allowing them to instantly perceive changes in the meeting's progress and atmosphere. This enables them to accurately grasp reactions to the agenda and respond as needed. As a result, better communication and more effective discussions can be achieved.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The user launches a dedicated application on their device and starts an emotion analysis session. The device then prepares to acquire audio and image data.

[0335] Step 2:

[0336] The device uses a built-in microphone to capture the user's conversation as audio data in real time. Simultaneously, it uses a built-in camera to photograph the user's face and collect image data.

[0337] Step 3:

[0338] The device encrypts the collected audio and image data to protect privacy. This encrypted data is then sent to the server using a secure communication protocol.

[0339] Step 4:

[0340] The server passes the received audio data to an audio processing device, which analyzes the tone, intonation, speed, and other characteristics of the sound. The analysis results are output as emotion labels.

[0341] Step 5:

[0342] The server passes the received image data to an image processing device, which extracts feature points from the user's face and analyzes their facial expressions. This yields emotion labels associated with those expressions.

[0343] Step 6:

[0344] The server integrates the analyzed voice and facial emotion labels into the emotion engine. The emotion engine uses machine learning algorithms to perform more refined emotion analysis based on the user's past patterns and individual profile.

[0345] Step 7:

[0346] The server generates the results of an integrated evaluation using an emotion engine and formalizes them as graphs or infographics using visualization tools.

[0347] Step 8:

[0348] The server sends the generated visual data to the terminal, which then displays this data in an easy-to-understand format for the user. This allows the user to consider appropriate actions based on the situation.

[0349] Step 9:

[0350] By enabling real-time feedback, the system helps users make necessary decisions during meetings and discussions, thereby improving the quality of communication.

[0351] (Example 2)

[0352] 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".

[0353] Conventional emotion analysis technologies have suffered from low accuracy in analyzing emotions derived from audio and image information. Furthermore, it has been difficult to provide users with intuitively understandable analysis results, making it challenging for users to accurately understand their own emotional state. In addition, security issues arose due to insufficient protection of personal information in many cases.

[0354] 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.

[0355] In this invention, the server includes an acoustic analysis means for receiving audio information and analyzing emotions based on the audio information; an image analysis means for receiving image information and analyzing emotions based on the image information; and an emotion engine that integrates the analysis results obtained by the acoustic analysis means and the image analysis means and recognizes the user's unique emotional state using a machine learning algorithm. This enables highly accurate emotion analysis based on audio and image data, and by visually presenting the analysis results to the user, it becomes easier to understand the emotional state. Furthermore, by encrypting and transmitting the data, the protection of personal information can be enhanced and security can be ensured.

[0356] "Audio information" refers to digital or analog signals transmitted through sound, including data such as user speech and verbal expressions.

[0357] "Acoustic analysis means" refers to a device or system that analyzes audio information and uses its characteristics to evaluate emotional states.

[0358] "Image information" refers to visual data that records the user's face and facial expressions, and includes digital images acquired by cameras and other imaging devices.

[0359] "Image analysis means" refers to a device or system that analyzes image information and infers an emotional state based on its facial features.

[0360] The "emotion engine" is a system that integrates voice and image analysis results and uses machine learning algorithms to accurately recognize the user's unique emotional state.

[0361] A "visualization device" is a device for displaying analyzed emotion results in an intuitively understandable format, and can use graphs or infographics.

[0362] A "machine learning algorithm" is a computational method for learning from data and recognizing patterns, and is a mathematical model used to improve the accuracy of emotional states.

[0363] Encryption is a security technique that transforms data to protect its confidentiality and prevent unauthorized access.

[0364] This invention relates to an emotion analysis system that recognizes a user's emotions in real time with high accuracy and visualizes the results intuitively. This system is comprised of an acoustic analysis means, an image analysis means, an emotion engine, and a visualization device.

[0365] The user launches the application on the device and operates the system. The device collects audio information using the microphone and acquires image information using the camera. This information is encrypted within the device and transmitted to the server via secure communication. Standard security protocols are used for encryption to maintain the confidentiality of the information.

[0366] The server analyzes audio information using acoustic analysis tools. Specifically, it analyzes the tone, intonation, and rhythm of the audio signal to make a preliminary judgment about the user's emotions. This process can utilize general-purpose audio analysis platforms or open-source audio analysis libraries. Similarly, image analysis tools analyze image information and use facial recognition algorithms to infer emotions from the user's facial expressions. The server then sends these analysis results to the emotion engine.

[0367] The emotion engine uses machine learning algorithms to accurately recognize user-specific emotional states based on integrated analysis results. General datasets are used to train the machine learning model, and high-precision emotion recognition is achieved through the application of the algorithm.

[0368] The analyzed emotion results are generated in real time as graphs and infographics using a visualization device and transmitted to the terminal. The terminal displays this information, providing it to the user in an intuitively understandable format.

[0369] A concrete example of using this system is during a business meeting. When a user speaks during a meeting, the system instantly visualizes the emotional state of other participants, making it possible to accurately understand the impact of their comments and thus facilitate a more effective discussion.

[0370] An example of a prompt might be: "We are developing a system that uses user voice and image data to report emotional changes during a meeting in real time. Please suggest the most intuitive way to visualize the emotional analysis results."

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1:

[0373] The user launches an application on the device. The device uses the microphone to acquire the user's voice and sensors and a camera to collect facial image information. The input here is real-time audio and image data, and audio and image files are generated as output. This operation prepares the necessary data within the device.

[0374] Step 2:

[0375] The device encrypts the acquired audio and image data. The encryption process uses an appropriate encryption algorithm to transform the data and protect it from unauthorized access. The input is the audio and image files obtained in step 1, and the output is encrypted data. This operation ensures the security of the data.

[0376] Step 3:

[0377] The terminal sends encrypted data to the server. A secure communication protocol is used for data transfer. The input consists of encrypted audio and image data, and this data reaches the server as output. This process ensures the reliable transmission of data for analysis.

[0378] Step 4:

[0379] The server decodes the received audio data and analyzes its tone, intonation, and rhythm using acoustic analysis tools. The input is decrypted audio data, and the output is information that provides a preliminary assessment of the user's emotions. This process generates audio-based emotion data.

[0380] Step 5:

[0381] The server decrypts the received image data and executes a face recognition algorithm using image analysis tools. The input is decrypted image data, and the output is the result of emotion inference based on facial expression analysis. This process generates image-based emotion data.

[0382] Step 6:

[0383] The server transmits the results obtained from acoustic and image analysis to the emotion engine, which uses machine learning algorithms to accurately recognize the user's unique emotional state. The input is the results of audio and image analysis, and the output is an integrated, advanced emotion analysis result. This operation provides a comprehensive understanding of the user's emotional state.

[0384] Step 7:

[0385] The server generates the emotion analysis results as graphs and infographics through a visualization device and sends them to the terminal. The input is the integrated emotion analysis results, and the output is delivered to the terminal as visualized information. This operation intuitively conveys the emotional state to the user.

[0386] Step 8:

[0387] The terminal displays visualization information sent from the server and provides the user with sentiment analysis results. The input is visualized sentiment data, and the output is the information displayed on the terminal's screen. This operation allows the user to easily understand their own emotional state.

[0388] (Application Example 2)

[0389] 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."

[0390] In today's living environment, it is difficult for individuals to accurately understand their emotions and receive appropriate support. In particular, effective coping mechanisms for stress and fatigue are needed in our busy daily lives. However, conventional technology has not adequately provided systems that can analyze emotions in real time and autonomously respond according to the user's state.

[0391] 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.

[0392] In this invention, the server includes: an audio processing means for receiving audio information and analyzing the user's mental state based on the audio information; an image processing means for receiving image information and analyzing the user's mental state based on the image information; a visualization means for integrating the analysis results obtained by the audio processing means and the image processing means and presenting them visually to the user; and an action decision means for analyzing the user's emotional state and providing appropriate support according to that state. This enables real-time analysis of the user's emotional state and provides appropriate support.

[0393] "Audio information" refers to data obtained by converting sound waves into digital signals, and includes the user's speech content, voice tone, intonation, and other details.

[0394] "State of mind" refers to the emotions and psychological state that an individual is currently experiencing, and includes basic emotions such as joy, anger, sadness, and pleasure, as well as states such as stress and relaxation.

[0395] "Voice processing means" refers to technology for analyzing voice information to identify the user's mental state, and includes functions for voice recognition and emotion analysis.

[0396] "Image information" refers to visual data acquired by a visual sensor, including the user's facial expressions and movements.

[0397] "Image processing means" refers to technology that analyzes image data and infers the user's mental state, and includes functions such as facial expression recognition.

[0398] "Visualization means" refers to technologies for visually presenting the analyzed mental state to the user, and includes functions for displaying information in charts and graphs.

[0399] A "behavioral decision-making mechanism" is a system for determining and executing appropriate responses based on the user's analyzed mental state, and includes functions that utilize machine learning and generative AI models to determine proposed actions.

[0400] In the system realizing this invention, a terminal collects audio and image information. This information is acquired using a microphone and camera attached to the terminal. The acquired information is encrypted to protect security and sent to a server. The server uses speech recognition technology as an audio processing means, and analyzes the tone, intonation, rhythm, etc. of the audio data through machine learning algorithms to identify the state of mind.

[0401] Furthermore, the server uses open-source image processing libraries (e.g., OpenCV) as image processing tools and applies facial expression analysis technology to analyze image data. This allows it to infer the user's emotional state based on their facial expressions. The analysis results are further evaluated comprehensively through an emotion engine and presented as intuitive graphics by a visualization tool.

[0402] The server, using its decision-making mechanism, proposes appropriate support based on the analyzed mental state. In this process, it utilizes a generative AI model to deliver optimal action instructions to the user. This allows the system to autonomously respond appropriately to the user's stress and relaxation levels. For example, if a robot recognizes that the user is tired, it can automatically play relaxation music.

[0403] Users can interact with the system through their smart devices. Examples of specific prompts include "Tell me how to reduce fatigue today" or "Play some relaxing music." This allows users to experience services that take their emotional state into consideration.

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The device collects audio and image information using a microphone and camera. The input data obtained from these sensors consists of raw audio waveforms and visual data. At this stage, no processing has been done yet, so it captures the user's speech and facial expressions as they are. This data is stored in temporary storage for later analysis.

[0407] Step 2:

[0408] The device encrypts the collected audio and image information and sends it to the server via a secure communication link. Raw data is the input, and encrypted data is the output. The encryption process is crucial for protecting data privacy and uses common encryption algorithms.

[0409] Step 3:

[0410] The server decrypts the received encrypted data and inputs the audio data into the voice processing system for analysis. The voice processing system uses machine learning algorithms to analyze tone, intonation, and rhythm to identify the user's emotional state (e.g., joy, anger, sadness). This process outputs the audio waveform as data converted into emotion labels.

[0411] Step 4:

[0412] The server passes image data to an image processing system for facial expression analysis. The input is visual data, and the output is the user's mental state inferred from their facial expressions. In image processing, features of facial expressions are extracted using libraries such as OpenCV, and the analysis results are generated.

[0413] Step 5:

[0414] The server integrates the analysis results obtained from the speech processing system and the image processing system and sends them to the emotion engine. The emotion engine combines these results and evaluates the overall mental state using a generating AI model. The output is a score or label indicating the mental state. This information is used in the next step.

[0415] Step 6:

[0416] The server generates results using visualization tools based on the overall mental state obtained. These visualization tools produce user-friendly graphs and infographics and transmit the data to the terminal. The output is visualized data displayed on the user interface.

[0417] Step 7:

[0418] Users can review the displayed visualization data and accept the server's suggested actions based on their mental state. Suggested actions based on prompts generated using a generative AI model (e.g., "Tell me how to reduce today's fatigue" or "Play some relaxing music") are displayed, allowing users to select the appropriate response.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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".

[0435] This invention relates to a method for analyzing emotions using audio and image data collected from a user through an emotion analysis system, and providing visual feedback. In the implementation of this system, a server processes the data using multiple AI modules and transmits the results to a terminal.

[0436] First, the user operates the device to begin collecting audio and images. The device uses the microphone to acquire audio data and the camera to collect image data. This data is encrypted for security purposes and transmitted to the server in real time.

[0437] The server performs emotion analysis based on the received audio data via audio processing. Specifically, it analyzes the tone, intonation, and speed of the voice and generates associated emotion labels. Similarly, it uses image processing to interpret facial feature points from image data and identify emotions based on facial expressions.

[0438] These analysis results are integrated within the server to perform a comprehensive sentiment assessment. This assessment is then formalized as graphs and infographics using visualization tools, and the generated visual information is immediately sent to the terminal.

[0439] The device receives this information and displays it visually to the user. This allows the user to intuitively understand the emotional state of the person they are communicating with and respond appropriately to the actual conversation.

[0440] One concrete example is its application in educational settings. When teachers interact with students, this system allows them to grasp changes in students' understanding and interests in real time. This enables teachers to quickly adjust teaching methods and content, thereby improving student learning effectiveness. In this way, the present invention contributes to improving emotion-based interactions in various fields.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The user launches the application on their device and selects the sentiment analysis mode. The device then prepares to begin collecting audio and image data.

[0444] Step 2:

[0445] The device uses its built-in microphone to capture audio data in real time. Simultaneously, it uses its camera to capture the user's facial expressions and acquire image data.

[0446] Step 3:

[0447] The device encrypts the collected audio and image data for security purposes. This encrypted data is then securely transmitted to the server.

[0448] Step 4:

[0449] The server analyzes the received audio data using audio processing equipment. Specifically, it analyzes the tone, intonation, and speed of the sound and assigns emotion labels to them.

[0450] Step 5:

[0451] The server analyzes the received image data using image processing tools to extract facial feature points. Based on the facial expression information, it determines the emotion and assigns a label.

[0452] Step 6:

[0453] The server integrates the analysis results of both audio and image to perform an overall sentiment assessment. This allows individual emotional states to be consolidated into a single, comprehensive evaluation.

[0454] Step 7:

[0455] The server generates graphs and infographics to visualize the integrated sentiment data. The generated output is in a user-friendly format.

[0456] Step 8:

[0457] The server sends the generated visualization data to the terminal.

[0458] Step 9:

[0459] The device displays the received visualization information on the application's dashboard, allowing users to check their emotional state in real time.

[0460] (Example 1)

[0461] 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."

[0462] While many systems exist that analyze emotions using audio and image data and provide visual feedback to users, real-time processing and ensuring data security are challenging. Furthermore, there is a lack of means to integrate the obtained emotional information and make it intuitively understandable to users.

[0463] 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.

[0464] In this invention, the server includes a voice analysis means for receiving voice data and analyzing emotions, an image recognition means for receiving image data and analyzing emotions, and an evaluation means for integrating the analysis results and generating visual information. This makes it possible to analyze emotions in real time with high accuracy based on collected voice and image data and provide the user with visual and safe feedback.

[0465] A "voice analysis means" is a method for generating emotion labels by analyzing characteristics such as tone, intonation, and speed of voice based on received voice data, in order to identify emotions.

[0466] "Image recognition means" refers to a method for detecting facial feature points from received image data, analyzing facial expressions based on these points, and identifying emotions.

[0467] "Evaluation means" refers to a means of integrating the analysis results obtained by the speech analysis means and the image recognition means, performing an overall emotional evaluation, and generating it as visual information.

[0468] A "display means" is a means of presenting visual information transmitted from a server to the user, enabling them to intuitively understand their emotional state.

[0469] "Transmission means" refers to the means for securely encrypting the collected audio and image data and transmitting it to the server.

[0470] A "text conversion method" is a means of converting audio data into text data and providing basic data for sentiment analysis.

[0471] A "feature point analysis method" is a means of analyzing facial feature points obtained from image data in detail and estimating emotions from the resulting facial expressions.

[0472] This invention is a system that analyzes emotions using audio and image data and provides visual feedback to the user. The system utilizes terminals, servers, and various hardware and software components.

[0473] First, the user operates the device to begin collecting audio and image data. Specifically, the device uses a microphone and camera. For example, the user uses a smartphone to launch an application and perform operations to collect audio and facial expressions. As a result, the actual data is captured on the device.

[0474] The terminal encrypts the collected audio data using encryption technologies such as AES, and similarly encrypts image data to ensure the security of communications. This encrypted data is sent to the server via the SSL / TLS protocol.

[0475] On the server, a speech analysis tool converts the speech data into text and uses a machine learning model to generate emotion labels. A common speech recognition API can be used for this speech-to-text conversion. Specifically, AI technology that analyzes tone and intonation is employed.

[0476] Similarly, the image recognition system on the server uses libraries such as OpenCV and Dlib to analyze facial feature points from image data and re-evaluate emotions. For example, if a smile is detected in an image, the emotion "joy" is identified.

[0477] The results of speech analysis and image recognition are integrated by an evaluation tool and presented to the user as visual information. This visual information is generated using TensorFlow or PyTorch as infographics showing sentiment scores and fluctuations.

[0478] One concrete example of its application is in educational settings. When teachers interact with students, they can use this system to grasp students' level of understanding and emotional changes in real time. By quickly adjusting teaching methods based on this information, they can improve students' learning effectiveness.

[0479] An example of a prompt might be, "Analyze the audio and image data from the students' statements to determine their level of understanding and interest in real time."

[0480] In this way, the present invention can support the improvement of emotion-based interactions in many fields and realize intuitive and effective communication.

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] The user operates the device to begin collecting audio and image data. Specifically, the user launches the application on the device, presses the record button, speaks into the microphone, and simultaneously uses the camera to capture their facial expressions. The input is the user's voice and facial expressions, and the output is audio and image data converted into digital format within the device.

[0484] Step 2:

[0485] The terminal encrypts the collected audio and image data using encryption technologies such as AES. To ensure data security, this process is performed on the terminal immediately after collection. The input is the audio and image data obtained in step 1, and the output is the encrypted data.

[0486] Step 3:

[0487] The terminal transmits encrypted audio and image data to the server in real time using the SSL / TLS protocol. This process ensures the security of data transmission. The input is the encrypted data obtained in step 2, and the output is the data that has safely reached the server.

[0488] Step 4:

[0489] The server decrypts the received encrypted data and analyzes the audio data using speech analysis tools. Specifically, it converts the audio to text and generates sentiment labels using a machine learning model. The input is the decrypted audio data, and the output is the sentiment labels.

[0490] Step 5:

[0491] The server analyzes image data using image recognition techniques. It detects facial feature points using a library and estimates emotions using a generative AI model. The input is decrypted image data, and the output is emotion labels.

[0492] Step 6:

[0493] The server integrates the analysis results obtained from audio and images and performs a comprehensive sentiment assessment using evaluation tools. In this step, sentiment scores and related infographics are generated. The input is the sentiment labels obtained in steps 4 and 5, and the output is the sentiment assessment as visual information.

[0494] Step 7:

[0495] The server sends the generated visual information to the terminal. The terminal receives this information and visualizes it on the user interface. The input is the visual information obtained in step 6, and the output is the emotional feedback presented to the user. The user can use this information to improve communication.

[0496] (Application Example 1)

[0497] 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."

[0498] In elderly care settings, a key challenge is to quickly and accurately understand the emotional state of elderly individuals and provide appropriate care and communication to improve their quality of life. In particular, it is essential to communicate changes in emotions to caregivers and family members in real time.

[0499] 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.

[0500] In this invention, the server includes an information processing means for receiving audio information and analyzing emotions based on the audio information; an information processing means for receiving image information and analyzing emotions based on the image information; an information presentation means for integrating the analysis results obtained by the audio information processing means and the image information processing means and presenting them visually to the user; and a display means for adjusting dialogue or care methods based on the analyzed emotional information for care workers or relatives. This makes it possible to accurately grasp the emotional state of the person receiving care and quickly adjust individual care policies.

[0501] "Audio information" refers to data analyzed based on the characteristics of received sounds, and it forms the basis for identifying emotions.

[0502] "Image information" refers to data extracted from received video footage, and it forms the basis for analyzing facial features and identifying emotions.

[0503] "Information processing means" refers to a program or device for analyzing emotions based on audio and image information.

[0504] An "information presentation means" is a program or device that visually processes analyzed emotional information and transmits it to the user.

[0505] "Display means" refers to a program or device for showing specific messages or policies to care workers or relatives based on analyzed emotional information.

[0506] This invention aims to build a system that analyzes the emotional state of elderly individuals in care settings and provides appropriate care plans. The user terminal is connected to a microphone for acquiring audio information and a camera for acquiring image information. The user uses these devices to collect audio and video data of the elderly individual in question.

[0507] The collected audio information is processed on the server using a TensorFlow speech analysis model. The server analyzes the tone, intonation, and speed of the sound to identify emotions. Additionally, OpenCV is used to detect facial feature points from image information and perform emotion analysis based on facial expressions.

[0508] These analysis results are integrated in real time using AWS Lambda and monitored with Amazon CloudWatch. The integrated emotional information is sent to the user's device via Amazon SNS. The device then presents visual feedback to caregivers and family members based on the analyzed emotional information. This allows for flexible adjustment of communication and care methods in caregiving.

[0509] For example, if an elderly person's facial expression during morning care is analyzed to indicate fatigue or stress, the system will send a notification to the caregiver suggesting a rest. This prompt allows the caregiver to suggest a rest to the elderly person and adjust the care program on the spot if necessary.

[0510] An example of a prompt message would be, "I need advice on how to proceed with a conversation when an elderly person is feeling anxious. Please tell me how to change the topic."

[0511] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0512] Step 1:

[0513] The device uses a microphone and camera to acquire voice and image information from elderly individuals. Voice information includes tone, intonation, and speaking speed, while image information captures facial features. This data serves as input.

[0514] Step 2:

[0515] The terminal encrypts the collected audio and image information for security purposes and sends it to the server. Data encryption is performed to ensure the confidentiality of the information, and this is the output.

[0516] Step 3:

[0517] The server uses a TensorFlow speech analysis model to analyze the received audio information. This model processes the audio information as input and generates sentiment labels. The result is the output.

[0518] Step 4:

[0519] The server uses OpenCV to detect facial feature points and perform facial expression analysis to analyze image information. It takes image information as input and outputs the analyzed emotion information.

[0520] Step 5:

[0521] The server integrates the audio and image analysis results using AWS Lambda, aggregating emotional information in real time. This generates integrated emotional data, and the final emotional evaluation is output.

[0522] Step 6:

[0523] The server sends integrated emotion assessments to the device via Amazon SNS. This data serves as input and is presented to caregivers and family members as visual feedback on the device.

[0524] Step 7:

[0525] Users (caregivers and family members) flexibly adjust their interactions and care methods with the elderly based on the emotional information presented. This feedback becomes the final output, improving the quality of care in real time.

[0526] 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.

[0527] This invention relates to a system that more accurately recognizes a user's emotions and provides visual feedback of the analysis results. This system uses a combination of voice processing means, image processing means, and an emotion engine. This allows for high-precision evaluation of the user's emotional state from collected data and provides this information to the user in real time through visualization means.

[0528] The user first launches the application on their device and begins data acquisition. The device collects audio data using the microphone and image data using the camera. This data is encrypted and sent to the server in a secure state.

[0529] The server analyzes the audio data using audio processing equipment, analyzing tone, intonation, and rhythm to determine emotion. Similarly, image processing equipment analyzes the user's facial expressions using image data and infers emotions based on them. These results are then sent to the emotion engine for further advanced analysis. The emotion engine uses machine learning algorithms to recognize the unique emotional state of each user based on the analyzed data, improving the accuracy of the analysis results.

[0530] The analysis results are generated as graphs or infographics using visualization tools and transmitted to the terminal. The terminal receives these and displays them to the user in an intuitive format.

[0531] A concrete example of its application is in business meetings. When users utilize this system in a meeting, it displays the emotional state of participants in real time as they speak, allowing them to instantly perceive changes in the meeting's progress and atmosphere. This enables them to accurately grasp reactions to the agenda and respond as needed. As a result, better communication and more effective discussions can be achieved.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The user launches a dedicated application on their device and starts an emotion analysis session. The device then prepares to acquire audio and image data.

[0535] Step 2:

[0536] The device uses a built-in microphone to capture the user's conversation as audio data in real time. Simultaneously, it uses a built-in camera to photograph the user's face and collect image data.

[0537] Step 3:

[0538] The device encrypts the collected audio and image data to protect privacy. This encrypted data is then sent to the server using a secure communication protocol.

[0539] Step 4:

[0540] The server passes the received audio data to an audio processing device, which analyzes the tone, intonation, speed, and other characteristics of the sound. The analysis results are output as emotion labels.

[0541] Step 5:

[0542] The server passes the received image data to an image processing device, which extracts feature points from the user's face and analyzes their facial expressions. This yields emotion labels associated with those expressions.

[0543] Step 6:

[0544] The server integrates the analyzed voice and facial emotion labels into the emotion engine. The emotion engine uses machine learning algorithms to perform more refined emotion analysis based on the user's past patterns and individual profile.

[0545] Step 7:

[0546] The server generates the results of an integrated evaluation using an emotion engine and formalizes them as graphs or infographics using visualization tools.

[0547] Step 8:

[0548] The server sends the generated visual data to the terminal, which then displays this data in an easy-to-understand format for the user. This allows the user to consider appropriate actions based on the situation.

[0549] Step 9:

[0550] By enabling real-time feedback, the system helps users make necessary decisions during meetings and discussions, thereby improving the quality of communication.

[0551] (Example 2)

[0552] 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."

[0553] Conventional emotion analysis technologies have suffered from low accuracy in analyzing emotions derived from audio and image information. Furthermore, it has been difficult to provide users with intuitively understandable analysis results, making it challenging for users to accurately understand their own emotional state. In addition, security issues arose due to insufficient protection of personal information in many cases.

[0554] 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.

[0555] In this invention, the server includes an acoustic analysis means for receiving audio information and analyzing emotions based on the audio information; an image analysis means for receiving image information and analyzing emotions based on the image information; and an emotion engine that integrates the analysis results obtained by the acoustic analysis means and the image analysis means and recognizes the user's unique emotional state using a machine learning algorithm. This enables highly accurate emotion analysis based on audio and image data, and by visually presenting the analysis results to the user, it becomes easier to understand the emotional state. Furthermore, by encrypting and transmitting the data, the protection of personal information can be enhanced and security can be ensured.

[0556] "Audio information" refers to digital or analog signals transmitted through sound, including data such as user speech and verbal expressions.

[0557] "Acoustic analysis means" refers to a device or system that analyzes audio information and uses its characteristics to evaluate emotional states.

[0558] "Image information" refers to visual data that records the user's face and facial expressions, and includes digital images acquired by cameras and other imaging devices.

[0559] "Image analysis means" refers to a device or system that analyzes image information and infers an emotional state based on its facial features.

[0560] The "emotion engine" is a system that integrates voice and image analysis results and uses machine learning algorithms to accurately recognize the user's unique emotional state.

[0561] A "visualization device" is a device for displaying analyzed emotion results in an intuitively understandable format, and can use graphs or infographics.

[0562] A "machine learning algorithm" is a computational method for learning from data and recognizing patterns, and is a mathematical model used to improve the accuracy of emotional states.

[0563] Encryption is a security technique that transforms data to protect its confidentiality and prevent unauthorized access.

[0564] This invention relates to an emotion analysis system that recognizes a user's emotions in real time with high accuracy and visualizes the results intuitively. This system is comprised of an acoustic analysis means, an image analysis means, an emotion engine, and a visualization device.

[0565] The user launches the application on the device and operates the system. The device collects audio information using the microphone and acquires image information using the camera. This information is encrypted within the device and transmitted to the server via secure communication. Standard security protocols are used for encryption to maintain the confidentiality of the information.

[0566] The server analyzes audio information using acoustic analysis tools. Specifically, it analyzes the tone, intonation, and rhythm of the audio signal to make a preliminary judgment about the user's emotions. This process can utilize general-purpose audio analysis platforms or open-source audio analysis libraries. Similarly, image analysis tools analyze image information and use facial recognition algorithms to infer emotions from the user's facial expressions. The server then sends these analysis results to the emotion engine.

[0567] The emotion engine uses machine learning algorithms to accurately recognize user-specific emotional states based on integrated analysis results. General datasets are used to train the machine learning model, and high-precision emotion recognition is achieved through the application of the algorithm.

[0568] The analyzed emotion results are generated in real time as graphs and infographics using a visualization device and transmitted to the terminal. The terminal displays this information, providing it to the user in an intuitively understandable format.

[0569] A concrete example of using this system is during a business meeting. When a user speaks during a meeting, the system instantly visualizes the emotional state of other participants, making it possible to accurately understand the impact of their comments and thus facilitate a more effective discussion.

[0570] An example of a prompt might be: "We are developing a system that uses user voice and image data to report emotional changes during a meeting in real time. Please suggest the most intuitive way to visualize the emotional analysis results."

[0571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0572] Step 1:

[0573] The user launches an application on the device. The device uses the microphone to acquire the user's voice and sensors and a camera to collect facial image information. The input here is real-time audio and image data, and audio and image files are generated as output. This operation prepares the necessary data within the device.

[0574] Step 2:

[0575] The device encrypts the acquired audio and image data. The encryption process uses an appropriate encryption algorithm to transform the data and protect it from unauthorized access. The input is the audio and image files obtained in step 1, and the output is encrypted data. This operation ensures the security of the data.

[0576] Step 3:

[0577] The terminal sends encrypted data to the server. A secure communication protocol is used for data transfer. The input consists of encrypted audio and image data, and this data reaches the server as output. This process ensures the reliable transmission of data for analysis.

[0578] Step 4:

[0579] The server decodes the received audio data and analyzes its tone, intonation, and rhythm using acoustic analysis tools. The input is decrypted audio data, and the output is information that provides a preliminary assessment of the user's emotions. This process generates audio-based emotion data.

[0580] Step 5:

[0581] The server decrypts the received image data and executes a face recognition algorithm using image analysis tools. The input is decrypted image data, and the output is the result of emotion inference based on facial expression analysis. This process generates image-based emotion data.

[0582] Step 6:

[0583] The server transmits the results obtained from acoustic and image analysis to the emotion engine, which uses machine learning algorithms to accurately recognize the user's unique emotional state. The input is the results of audio and image analysis, and the output is an integrated, advanced emotion analysis result. This operation provides a comprehensive understanding of the user's emotional state.

[0584] Step 7:

[0585] The server generates the emotion analysis results as graphs and infographics through a visualization device and sends them to the terminal. The input is the integrated emotion analysis results, and the output is delivered to the terminal as visualized information. This operation intuitively conveys the emotional state to the user.

[0586] Step 8:

[0587] The terminal displays visualization information sent from the server and provides the user with sentiment analysis results. The input is visualized sentiment data, and the output is the information displayed on the terminal's screen. This operation allows the user to easily understand their own emotional state.

[0588] (Application Example 2)

[0589] 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."

[0590] In today's living environment, it is difficult for individuals to accurately understand their emotions and receive appropriate support. In particular, effective coping mechanisms for stress and fatigue are needed in our busy daily lives. However, conventional technology has not adequately provided systems that can analyze emotions in real time and autonomously respond according to the user's state.

[0591] 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.

[0592] In this invention, the server includes: an audio processing means for receiving audio information and analyzing the user's mental state based on the audio information; an image processing means for receiving image information and analyzing the user's mental state based on the image information; a visualization means for integrating the analysis results obtained by the audio processing means and the image processing means and presenting them visually to the user; and an action decision means for analyzing the user's emotional state and providing appropriate support according to that state. This enables real-time analysis of the user's emotional state and provides appropriate support.

[0593] "Audio information" refers to data obtained by converting sound waves into digital signals, and includes the user's speech content, voice tone, intonation, and other details.

[0594] "State of mind" refers to the emotions and psychological state that an individual is currently experiencing, and includes basic emotions such as joy, anger, sadness, and pleasure, as well as states such as stress and relaxation.

[0595] "Voice processing means" refers to technology for analyzing voice information to identify the user's mental state, and includes functions for voice recognition and emotion analysis.

[0596] "Image information" refers to visual data acquired by a visual sensor, including the user's facial expressions and movements.

[0597] "Image processing means" refers to technology that analyzes image data and infers the user's mental state, and includes functions such as facial expression recognition.

[0598] "Visualization means" refers to technologies for visually presenting the analyzed mental state to the user, and includes functions for displaying information in charts and graphs.

[0599] A "behavioral decision-making mechanism" is a system for determining and executing appropriate responses based on the user's analyzed mental state, and includes functions that utilize machine learning and generative AI models to determine proposed actions.

[0600] In the system realizing this invention, a terminal collects audio and image information. This information is acquired using a microphone and camera attached to the terminal. The acquired information is encrypted to protect security and sent to a server. The server uses speech recognition technology as an audio processing means, and analyzes the tone, intonation, rhythm, etc. of the audio data through machine learning algorithms to identify the state of mind.

[0601] Furthermore, the server uses open-source image processing libraries (e.g., OpenCV) as image processing tools and applies facial expression analysis technology to analyze image data. This allows it to infer the user's emotional state based on their facial expressions. The analysis results are further evaluated comprehensively through an emotion engine and presented as intuitive graphics by a visualization tool.

[0602] The server, using its decision-making mechanism, proposes appropriate support based on the analyzed mental state. In this process, it utilizes a generative AI model to deliver optimal action instructions to the user. This allows the system to autonomously respond appropriately to the user's stress and relaxation levels. For example, if a robot recognizes that the user is tired, it can automatically play relaxation music.

[0603] Users can interact with the system through their smart devices. Examples of specific prompts include "Tell me how to reduce fatigue today" or "Play some relaxing music." This allows users to experience services that take their emotional state into consideration.

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The device collects audio and image information using a microphone and camera. The input data obtained from these sensors consists of raw audio waveforms and visual data. At this stage, no processing has been done yet, so it captures the user's speech and facial expressions as they are. This data is stored in temporary storage for later analysis.

[0607] Step 2:

[0608] The device encrypts the collected audio and image information and sends it to the server via a secure communication link. Raw data is the input, and encrypted data is the output. The encryption process is crucial for protecting data privacy and uses common encryption algorithms.

[0609] Step 3:

[0610] The server decrypts the received encrypted data and inputs the audio data into the voice processing system for analysis. The voice processing system uses machine learning algorithms to analyze tone, intonation, and rhythm to identify the user's emotional state (e.g., joy, anger, sadness). This process outputs the audio waveform as data converted into emotion labels.

[0611] Step 4:

[0612] The server passes image data to an image processing system for facial expression analysis. The input is visual data, and the output is the user's mental state inferred from their facial expressions. In image processing, features of facial expressions are extracted using libraries such as OpenCV, and the analysis results are generated.

[0613] Step 5:

[0614] The server integrates the analysis results obtained from the speech processing system and the image processing system and sends them to the emotion engine. The emotion engine combines these results and evaluates the overall mental state using a generating AI model. The output is a score or label indicating the mental state. This information is used in the next step.

[0615] Step 6:

[0616] The server generates results using visualization tools based on the overall mental state obtained. These visualization tools produce user-friendly graphs and infographics and transmit the data to the terminal. The output is visualized data displayed on the user interface.

[0617] Step 7:

[0618] Users can review the displayed visualization data and accept the server's suggested actions based on their mental state. Suggested actions based on prompts generated using a generative AI model (e.g., "Tell me how to reduce today's fatigue" or "Play some relaxing music") are displayed, allowing users to select the appropriate response.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] [Fourth Embodiment]

[0623] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0624] 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.

[0625] 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).

[0626] 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.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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".

[0636] This invention relates to a method for analyzing emotions using audio and image data collected from a user through an emotion analysis system, and providing visual feedback. In the implementation of this system, a server processes the data using multiple AI modules and transmits the results to a terminal.

[0637] First, the user operates the device to begin collecting audio and images. The device uses the microphone to acquire audio data and the camera to collect image data. This data is encrypted for security purposes and transmitted to the server in real time.

[0638] The server performs emotion analysis based on the received audio data via audio processing. Specifically, it analyzes the tone, intonation, and speed of the voice and generates associated emotion labels. Similarly, it uses image processing to interpret facial feature points from image data and identify emotions based on facial expressions.

[0639] These analysis results are integrated within the server to perform a comprehensive sentiment assessment. This assessment is then formalized as graphs and infographics using visualization tools, and the generated visual information is immediately sent to the terminal.

[0640] The device receives this information and displays it visually to the user. This allows the user to intuitively understand the emotional state of the person they are communicating with and respond appropriately to the actual conversation.

[0641] One concrete example is its application in educational settings. When teachers interact with students, this system allows them to grasp changes in students' understanding and interests in real time. This enables teachers to quickly adjust teaching methods and content, thereby improving student learning effectiveness. In this way, the present invention contributes to improving emotion-based interactions in various fields.

[0642] The following describes the processing flow.

[0643] Step 1:

[0644] The user launches the application on their device and selects the sentiment analysis mode. The device then prepares to begin collecting audio and image data.

[0645] Step 2:

[0646] The device uses its built-in microphone to capture audio data in real time. Simultaneously, it uses its camera to capture the user's facial expressions and acquire image data.

[0647] Step 3:

[0648] The device encrypts the collected audio and image data for security purposes. This encrypted data is then securely transmitted to the server.

[0649] Step 4:

[0650] The server analyzes the received audio data using audio processing equipment. Specifically, it analyzes the tone, intonation, and speed of the sound and assigns emotion labels to them.

[0651] Step 5:

[0652] The server analyzes the received image data using image processing tools to extract facial feature points. Based on the facial expression information, it determines the emotion and assigns a label.

[0653] Step 6:

[0654] The server integrates the analysis results of both audio and image to perform an overall sentiment assessment. This allows individual emotional states to be consolidated into a single, comprehensive evaluation.

[0655] Step 7:

[0656] The server generates graphs and infographics to visualize the integrated sentiment data. The generated output is in a user-friendly format.

[0657] Step 8:

[0658] The server sends the generated visualization data to the terminal.

[0659] Step 9:

[0660] The device displays the received visualization information on the application's dashboard, allowing users to check their emotional state in real time.

[0661] (Example 1)

[0662] 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".

[0663] While many systems exist that analyze emotions using audio and image data and provide visual feedback to users, real-time processing and ensuring data security are challenging. Furthermore, there is a lack of means to integrate the obtained emotional information and make it intuitively understandable to users.

[0664] 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.

[0665] In this invention, the server includes a voice analysis means for receiving voice data and analyzing emotions, an image recognition means for receiving image data and analyzing emotions, and an evaluation means for integrating the analysis results and generating visual information. This makes it possible to analyze emotions in real time with high accuracy based on collected voice and image data and provide the user with visual and safe feedback.

[0666] A "voice analysis means" is a method for generating emotion labels by analyzing characteristics such as tone, intonation, and speed of voice based on received voice data, in order to identify emotions.

[0667] "Image recognition means" refers to a method for detecting facial feature points from received image data, analyzing facial expressions based on these points, and identifying emotions.

[0668] "Evaluation means" refers to a means of integrating the analysis results obtained by the speech analysis means and the image recognition means, performing an overall emotional evaluation, and generating it as visual information.

[0669] A "display means" is a means of presenting visual information transmitted from a server to the user, enabling them to intuitively understand their emotional state.

[0670] "Transmission means" refers to the means for securely encrypting the collected audio and image data and transmitting it to the server.

[0671] A "text conversion method" is a means of converting audio data into text data and providing basic data for sentiment analysis.

[0672] A "feature point analysis method" is a means of analyzing facial feature points obtained from image data in detail and estimating emotions from the resulting facial expressions.

[0673] This invention is a system that analyzes emotions using audio and image data and provides visual feedback to the user. The system utilizes terminals, servers, and various hardware and software components.

[0674] First, the user operates the device to begin collecting audio and image data. Specifically, the device uses a microphone and camera. For example, the user uses a smartphone to launch an application and perform operations to collect audio and facial expressions. As a result, the actual data is captured on the device.

[0675] The terminal encrypts the collected audio data using encryption technologies such as AES, and similarly encrypts image data to ensure the security of communications. This encrypted data is sent to the server via the SSL / TLS protocol.

[0676] On the server, a speech analysis tool converts the speech data into text and uses a machine learning model to generate emotion labels. A common speech recognition API can be used for this speech-to-text conversion. Specifically, AI technology that analyzes tone and intonation is employed.

[0677] Similarly, the image recognition system on the server uses libraries such as OpenCV and Dlib to analyze facial feature points from image data and re-evaluate emotions. For example, if a smile is detected in an image, the emotion "joy" is identified.

[0678] The results of speech analysis and image recognition are integrated by an evaluation tool and presented to the user as visual information. This visual information is generated using TensorFlow or PyTorch as infographics showing sentiment scores and fluctuations.

[0679] One concrete example of its application is in educational settings. When teachers interact with students, they can use this system to grasp students' level of understanding and emotional changes in real time. By quickly adjusting teaching methods based on this information, they can improve students' learning effectiveness.

[0680] An example of a prompt might be, "Analyze the audio and image data from the students' statements to determine their level of understanding and interest in real time."

[0681] In this way, the present invention can support the improvement of emotion-based interactions in many fields and realize intuitive and effective communication.

[0682] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0683] Step 1:

[0684] The user operates the device to begin collecting audio and image data. Specifically, the user launches the application on the device, presses the record button, speaks into the microphone, and simultaneously uses the camera to capture their facial expressions. The input is the user's voice and facial expressions, and the output is audio and image data converted into digital format within the device.

[0685] Step 2:

[0686] The terminal encrypts the collected audio and image data using encryption technologies such as AES. To ensure data security, this process is performed on the terminal immediately after collection. The input is the audio and image data obtained in step 1, and the output is the encrypted data.

[0687] Step 3:

[0688] The terminal transmits encrypted audio and image data to the server in real time using the SSL / TLS protocol. This process ensures the security of data transmission. The input is the encrypted data obtained in step 2, and the output is the data that has safely reached the server.

[0689] Step 4:

[0690] The server decrypts the received encrypted data and analyzes the audio data using speech analysis tools. Specifically, it converts the audio to text and generates sentiment labels using a machine learning model. The input is the decrypted audio data, and the output is the sentiment labels.

[0691] Step 5:

[0692] The server analyzes image data using image recognition techniques. It detects facial feature points using a library and estimates emotions using a generative AI model. The input is decrypted image data, and the output is emotion labels.

[0693] Step 6:

[0694] The server integrates the analysis results obtained from audio and images and performs a comprehensive sentiment assessment using evaluation tools. In this step, sentiment scores and related infographics are generated. The input is the sentiment labels obtained in steps 4 and 5, and the output is the sentiment assessment as visual information.

[0695] Step 7:

[0696] The server sends the generated visual information to the terminal. The terminal receives this information and visualizes it on the user interface. The input is the visual information obtained in step 6, and the output is the emotional feedback presented to the user. The user can use this information to improve communication.

[0697] (Application Example 1)

[0698] 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".

[0699] In elderly care settings, a key challenge is to quickly and accurately understand the emotional state of elderly individuals and provide appropriate care and communication to improve their quality of life. In particular, it is essential to communicate changes in emotions to caregivers and family members in real time.

[0700] 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.

[0701] In this invention, the server includes an information processing means for receiving audio information and analyzing emotions based on the audio information; an information processing means for receiving image information and analyzing emotions based on the image information; an information presentation means for integrating the analysis results obtained by the audio information processing means and the image information processing means and presenting them visually to the user; and a display means for adjusting dialogue or care methods based on the analyzed emotional information for care workers or relatives. This makes it possible to accurately grasp the emotional state of the person receiving care and quickly adjust individual care policies.

[0702] "Audio information" refers to data analyzed based on the characteristics of received sounds, and it forms the basis for identifying emotions.

[0703] "Image information" refers to data extracted from received video footage, and it forms the basis for analyzing facial features and identifying emotions.

[0704] "Information processing means" refers to a program or device for analyzing emotions based on audio and image information.

[0705] An "information presentation means" is a program or device that visually processes analyzed emotional information and transmits it to the user.

[0706] "Display means" refers to a program or device for showing specific messages or policies to care workers or relatives based on analyzed emotional information.

[0707] This invention aims to build a system that analyzes the emotional state of elderly individuals in care settings and provides appropriate care plans. The user terminal is connected to a microphone for acquiring audio information and a camera for acquiring image information. The user uses these devices to collect audio and video data of the elderly individual in question.

[0708] The collected audio information is processed on the server using a TensorFlow speech analysis model. The server analyzes the tone, intonation, and speed of the sound to identify emotions. Additionally, OpenCV is used to detect facial feature points from image information and perform emotion analysis based on facial expressions.

[0709] These analysis results are integrated in real time using AWS Lambda and monitored with Amazon CloudWatch. The integrated emotional information is sent to the user's device via Amazon SNS. The device then presents visual feedback to caregivers and family members based on the analyzed emotional information. This allows for flexible adjustment of communication and care methods in caregiving.

[0710] For example, if an elderly person's facial expression during morning care is analyzed to indicate fatigue or stress, the system will send a notification to the caregiver suggesting a rest. This prompt allows the caregiver to suggest a rest to the elderly person and adjust the care program on the spot if necessary.

[0711] An example of a prompt message would be, "I need advice on how to proceed with a conversation when an elderly person is feeling anxious. Please tell me how to change the topic."

[0712] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0713] Step 1:

[0714] The device uses a microphone and camera to acquire voice and image information from elderly individuals. Voice information includes tone, intonation, and speaking speed, while image information captures facial features. This data serves as input.

[0715] Step 2:

[0716] The terminal encrypts the collected audio and image information for security purposes and sends it to the server. Data encryption is performed to ensure the confidentiality of the information, and this is the output.

[0717] Step 3:

[0718] The server uses a TensorFlow speech analysis model to analyze the received audio information. This model processes the audio information as input and generates sentiment labels. The result is the output.

[0719] Step 4:

[0720] The server uses OpenCV to detect facial feature points and perform facial expression analysis to analyze image information. It takes image information as input and outputs the analyzed emotion information.

[0721] Step 5:

[0722] The server integrates the audio and image analysis results using AWS Lambda, aggregating emotional information in real time. This generates integrated emotional data, and the final emotional evaluation is output.

[0723] Step 6:

[0724] The server sends integrated emotion assessments to the device via Amazon SNS. This data serves as input and is presented to caregivers and family members as visual feedback on the device.

[0725] Step 7:

[0726] Users (caregivers and family members) flexibly adjust their interactions and care methods with the elderly based on the emotional information presented. This feedback becomes the final output, improving the quality of care in real time.

[0727] 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.

[0728] This invention relates to a system that more accurately recognizes a user's emotions and provides visual feedback of the analysis results. This system uses a combination of voice processing means, image processing means, and an emotion engine. This allows for high-precision evaluation of the user's emotional state from collected data and provides this information to the user in real time through visualization means.

[0729] The user first launches the application on their device and begins data acquisition. The device collects audio data using the microphone and image data using the camera. This data is encrypted and sent to the server in a secure state.

[0730] The server analyzes the audio data using audio processing equipment, analyzing tone, intonation, and rhythm to determine emotion. Similarly, image processing equipment analyzes the user's facial expressions using image data and infers emotions based on them. These results are then sent to the emotion engine for further advanced analysis. The emotion engine uses machine learning algorithms to recognize the unique emotional state of each user based on the analyzed data, improving the accuracy of the analysis results.

[0731] The analysis results are generated as graphs or infographics using visualization tools and transmitted to the terminal. The terminal receives these and displays them to the user in an intuitive format.

[0732] A concrete example of its application is in business meetings. When users utilize this system in a meeting, it displays the emotional state of participants in real time as they speak, allowing them to instantly perceive changes in the meeting's progress and atmosphere. This enables them to accurately grasp reactions to the agenda and respond as needed. As a result, better communication and more effective discussions can be achieved.

[0733] The following describes the processing flow.

[0734] Step 1:

[0735] The user launches a dedicated application on their device and starts an emotion analysis session. The device then prepares to acquire audio and image data.

[0736] Step 2:

[0737] The device uses a built-in microphone to capture the user's conversation as audio data in real time. Simultaneously, it uses a built-in camera to photograph the user's face and collect image data.

[0738] Step 3:

[0739] The device encrypts the collected audio and image data to protect privacy. This encrypted data is then sent to the server using a secure communication protocol.

[0740] Step 4:

[0741] The server passes the received audio data to an audio processing device, which analyzes the tone, intonation, speed, and other characteristics of the sound. The analysis results are output as emotion labels.

[0742] Step 5:

[0743] The server passes the received image data to an image processing device, which extracts feature points from the user's face and analyzes their facial expressions. This yields emotion labels associated with those expressions.

[0744] Step 6:

[0745] The server integrates the analyzed voice and facial emotion labels into the emotion engine. The emotion engine uses machine learning algorithms to perform more refined emotion analysis based on the user's past patterns and individual profile.

[0746] Step 7:

[0747] The server generates the results of an integrated evaluation using an emotion engine and formalizes them as graphs or infographics using visualization tools.

[0748] Step 8:

[0749] The server sends the generated visual data to the terminal, which then displays this data in an easy-to-understand format for the user. This allows the user to consider appropriate actions based on the situation.

[0750] Step 9:

[0751] By enabling real-time feedback, the system helps users make necessary decisions during meetings and discussions, thereby improving the quality of communication.

[0752] (Example 2)

[0753] 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".

[0754] Conventional emotion analysis technologies have suffered from low accuracy in analyzing emotions derived from audio and image information. Furthermore, it has been difficult to provide users with intuitively understandable analysis results, making it challenging for users to accurately understand their own emotional state. In addition, security issues arose due to insufficient protection of personal information in many cases.

[0755] 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.

[0756] In this invention, the server includes an acoustic analysis means for receiving audio information and analyzing emotions based on the audio information; an image analysis means for receiving image information and analyzing emotions based on the image information; and an emotion engine that integrates the analysis results obtained by the acoustic analysis means and the image analysis means and recognizes the user's unique emotional state using a machine learning algorithm. This enables highly accurate emotion analysis based on audio and image data, and by visually presenting the analysis results to the user, it becomes easier to understand the emotional state. Furthermore, by encrypting and transmitting the data, the protection of personal information can be enhanced and security can be ensured.

[0757] "Audio information" refers to digital or analog signals transmitted through sound, including data such as user speech and verbal expressions.

[0758] "Acoustic analysis means" refers to a device or system that analyzes audio information and uses its characteristics to evaluate emotional states.

[0759] "Image information" refers to visual data that records the user's face and facial expressions, and includes digital images acquired by cameras and other imaging devices.

[0760] "Image analysis means" refers to a device or system that analyzes image information and infers an emotional state based on its facial features.

[0761] The "emotion engine" is a system that integrates voice and image analysis results and uses machine learning algorithms to accurately recognize the user's unique emotional state.

[0762] A "visualization device" is a device for displaying analyzed emotion results in an intuitively understandable format, and can use graphs or infographics.

[0763] A "machine learning algorithm" is a computational method for learning from data and recognizing patterns, and is a mathematical model used to improve the accuracy of emotional states.

[0764] Encryption is a security technique that transforms data to protect its confidentiality and prevent unauthorized access.

[0765] This invention relates to an emotion analysis system that recognizes a user's emotions in real time with high accuracy and visualizes the results intuitively. This system is comprised of an acoustic analysis means, an image analysis means, an emotion engine, and a visualization device.

[0766] The user launches the application on the device and operates the system. The device collects audio information using the microphone and acquires image information using the camera. This information is encrypted within the device and transmitted to the server via secure communication. Standard security protocols are used for encryption to maintain the confidentiality of the information.

[0767] The server analyzes audio information using acoustic analysis tools. Specifically, it analyzes the tone, intonation, and rhythm of the audio signal to make a preliminary judgment about the user's emotions. This process can utilize general-purpose audio analysis platforms or open-source audio analysis libraries. Similarly, image analysis tools analyze image information and use facial recognition algorithms to infer emotions from the user's facial expressions. The server then sends these analysis results to the emotion engine.

[0768] The emotion engine uses machine learning algorithms to accurately recognize user-specific emotional states based on integrated analysis results. General datasets are used to train the machine learning model, and high-precision emotion recognition is achieved through the application of the algorithm.

[0769] The analyzed emotion results are generated in real time as graphs and infographics using a visualization device and transmitted to the terminal. The terminal displays this information, providing it to the user in an intuitively understandable format.

[0770] A concrete example of using this system is during a business meeting. When a user speaks during a meeting, the system instantly visualizes the emotional state of other participants, making it possible to accurately understand the impact of their comments and thus facilitate a more effective discussion.

[0771] An example of a prompt might be: "We are developing a system that uses user voice and image data to report emotional changes during a meeting in real time. Please suggest the most intuitive way to visualize the emotional analysis results."

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] The user launches an application on the device. The device uses the microphone to acquire the user's voice and sensors and a camera to collect facial image information. The input here is real-time audio and image data, and audio and image files are generated as output. This operation prepares the necessary data within the device.

[0775] Step 2:

[0776] The device encrypts the acquired audio and image data. The encryption process uses an appropriate encryption algorithm to transform the data and protect it from unauthorized access. The input is the audio and image files obtained in step 1, and the output is encrypted data. This operation ensures the security of the data.

[0777] Step 3:

[0778] The terminal sends encrypted data to the server. A secure communication protocol is used for data transfer. The input consists of encrypted audio and image data, and this data reaches the server as output. This process ensures the reliable transmission of data for analysis.

[0779] Step 4:

[0780] The server decodes the received audio data and analyzes its tone, intonation, and rhythm using acoustic analysis tools. The input is decrypted audio data, and the output is information that provides a preliminary assessment of the user's emotions. This process generates audio-based emotion data.

[0781] Step 5:

[0782] The server decrypts the received image data and executes a face recognition algorithm using image analysis tools. The input is decrypted image data, and the output is the result of emotion inference based on facial expression analysis. This process generates image-based emotion data.

[0783] Step 6:

[0784] The server transmits the results obtained from acoustic and image analysis to the emotion engine, which uses machine learning algorithms to accurately recognize the user's unique emotional state. The input is the results of audio and image analysis, and the output is an integrated, advanced emotion analysis result. This operation provides a comprehensive understanding of the user's emotional state.

[0785] Step 7:

[0786] The server generates the emotion analysis results as graphs and infographics through a visualization device and sends them to the terminal. The input is the integrated emotion analysis results, and the output is delivered to the terminal as visualized information. This operation intuitively conveys the emotional state to the user.

[0787] Step 8:

[0788] The terminal displays visualization information sent from the server and provides the user with sentiment analysis results. The input is visualized sentiment data, and the output is the information displayed on the terminal's screen. This operation allows the user to easily understand their own emotional state.

[0789] (Application Example 2)

[0790] 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".

[0791] In today's living environment, it is difficult for individuals to accurately understand their emotions and receive appropriate support. In particular, effective coping mechanisms for stress and fatigue are needed in our busy daily lives. However, conventional technology has not adequately provided systems that can analyze emotions in real time and autonomously respond according to the user's state.

[0792] 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.

[0793] In this invention, the server includes: an audio processing means for receiving audio information and analyzing the user's mental state based on the audio information; an image processing means for receiving image information and analyzing the user's mental state based on the image information; a visualization means for integrating the analysis results obtained by the audio processing means and the image processing means and presenting them visually to the user; and an action decision means for analyzing the user's emotional state and providing appropriate support according to that state. This enables real-time analysis of the user's emotional state and provides appropriate support.

[0794] "Audio information" refers to data obtained by converting sound waves into digital signals, and includes the user's speech content, voice tone, intonation, and other details.

[0795] "State of mind" refers to the emotions and psychological state that an individual is currently experiencing, and includes basic emotions such as joy, anger, sadness, and pleasure, as well as states such as stress and relaxation.

[0796] "Voice processing means" refers to technology for analyzing voice information to identify the user's mental state, and includes functions for voice recognition and emotion analysis.

[0797] "Image information" refers to visual data acquired by a visual sensor, including the user's facial expressions and movements.

[0798] "Image processing means" refers to technology that analyzes image data and infers the user's mental state, and includes functions such as facial expression recognition.

[0799] "Visualization means" refers to technologies for visually presenting the analyzed mental state to the user, and includes functions for displaying information in charts and graphs.

[0800] A "behavioral decision-making mechanism" is a system for determining and executing appropriate responses based on the user's analyzed mental state, and includes functions that utilize machine learning and generative AI models to determine proposed actions.

[0801] In the system realizing this invention, a terminal collects audio and image information. This information is acquired using a microphone and camera attached to the terminal. The acquired information is encrypted to protect security and sent to a server. The server uses speech recognition technology as an audio processing means, and analyzes the tone, intonation, rhythm, etc. of the audio data through machine learning algorithms to identify the state of mind.

[0802] Furthermore, the server uses open-source image processing libraries (e.g., OpenCV) as image processing tools and applies facial expression analysis technology to analyze image data. This allows it to infer the user's emotional state based on their facial expressions. The analysis results are further evaluated comprehensively through an emotion engine and presented as intuitive graphics by a visualization tool.

[0803] The server, using its decision-making mechanism, proposes appropriate support based on the analyzed mental state. In this process, it utilizes a generative AI model to deliver optimal action instructions to the user. This allows the system to autonomously respond appropriately to the user's stress and relaxation levels. For example, if a robot recognizes that the user is tired, it can automatically play relaxation music.

[0804] Users can interact with the system through their smart devices. Examples of specific prompts include "Tell me how to reduce fatigue today" or "Play some relaxing music." This allows users to experience services that take their emotional state into consideration.

[0805] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0806] Step 1:

[0807] The device collects audio and image information using a microphone and camera. The input data obtained from these sensors consists of raw audio waveforms and visual data. At this stage, no processing has been done yet, so it captures the user's speech and facial expressions as they are. This data is stored in temporary storage for later analysis.

[0808] Step 2:

[0809] The device encrypts the collected audio and image information and sends it to the server via a secure communication link. Raw data is the input, and encrypted data is the output. The encryption process is crucial for protecting data privacy and uses common encryption algorithms.

[0810] Step 3:

[0811] The server decrypts the received encrypted data and inputs the audio data into the voice processing system for analysis. The voice processing system uses machine learning algorithms to analyze tone, intonation, and rhythm to identify the user's emotional state (e.g., joy, anger, sadness). This process outputs the audio waveform as data converted into emotion labels.

[0812] Step 4:

[0813] The server passes image data to an image processing system for facial expression analysis. The input is visual data, and the output is the user's mental state inferred from their facial expressions. In image processing, features of facial expressions are extracted using libraries such as OpenCV, and the analysis results are generated.

[0814] Step 5:

[0815] The server integrates the analysis results obtained from the speech processing system and the image processing system and sends them to the emotion engine. The emotion engine combines these results and evaluates the overall mental state using a generating AI model. The output is a score or label indicating the mental state. This information is used in the next step.

[0816] Step 6:

[0817] The server generates results using visualization tools based on the overall mental state obtained. These visualization tools produce user-friendly graphs and infographics and transmit the data to the terminal. The output is visualized data displayed on the user interface.

[0818] Step 7:

[0819] Users can review the displayed visualization data and accept the server's suggested actions based on their mental state. Suggested actions based on prompts generated using a generative AI model (e.g., "Tell me how to reduce today's fatigue" or "Play some relaxing music") are displayed, allowing users to select the appropriate response.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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."

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0841] The following is further disclosed regarding the embodiments described above.

[0842] (Claim 1)

[0843] A voice processing means that receives voice data and analyzes emotions based on said voice data,

[0844] Image processing means that receives image data and analyzes emotions based on said image data,

[0845] A visualization means that integrates the analysis results obtained by the audio processing means and the image processing means and presents them visually to the user,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, wherein the visualization means has means for generating a chart showing the proportion of emotions and for displaying the chart to a user.

[0849] (Claim 3)

[0850] The system according to claim 1, further comprising means for encrypting and transmitting audio data and image data.

[0851] "Example 1"

[0852] (Claim 1)

[0853] A voice analysis means that receives voice data and analyzes emotions based on said voice data,

[0854] Image recognition means that receives image data and analyzes emotions based on said image data,

[0855] An evaluation means that integrates the analysis results obtained by the speech analysis means and the image recognition means to generate visual information,

[0856] A display means for presenting generated visual information to the user,

[0857] A transmission means for encrypting and transmitting audio data and image data,

[0858] A system including a text conversion means for converting speech to text.

[0859] (Claim 2)

[0860] The system according to claim 1, comprising means for generating a diagram showing the proportion of emotions from visual information and displaying the diagram to a user.

[0861] (Claim 3)

[0862] The system according to claim 1, further comprising a feature point analysis means for detecting facial feature points and estimating emotions based on facial expressions.

[0863] "Application Example 1"

[0864] (Claim 1)

[0865] Information processing means that receives audio information and analyzes emotions based on said audio information,

[0866] Information processing means that receives image information and analyzes emotions based on said image information,

[0867] Information presentation means that integrates the analysis results obtained by the audio information processing means and the image information processing means and presents them visually to the user,

[0868] A display means for adjusting dialogue or care methods based on analyzed emotional information for care workers or relatives,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, wherein the visualization means generates a chart showing the proportion of emotions and has means for displaying the chart to a user in a care setting.

[0872] (Claim 3)

[0873] The system according to claim 1, further comprising means for encrypting and transmitting audio information and image information.

[0874] "Example 2 of combining an emotion engine"

[0875] (Claim 1)

[0876] An acoustic analysis means that receives audio information and analyzes emotions based on said audio information,

[0877] Image analysis means that receives image information and analyzes emotions based on said image information,

[0878] An emotion engine that integrates the analysis results obtained by the acoustic analysis means and the image analysis means and recognizes the user's unique emotional state using a machine learning algorithm,

[0879] A visualization device that visually presents the results analyzed by the emotion engine,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, comprising a visualization device for generating a chart showing the proportion or change of emotions and for displaying the chart to a user.

[0883] (Claim 3)

[0884] The system according to claim 1, further comprising a device for encrypting and transmitting audio information and image information.

[0885] "Application example 2 when combining with an emotional engine"

[0886] (Claim 1)

[0887] A voice processing means that receives voice information and analyzes the state of mind based on said voice information,

[0888] Image processing means that receives image information and analyzes the state of mind based on said image information,

[0889] A visualization means that integrates the analysis results obtained by the audio processing means and the image processing means and presents them visually to the user,

[0890] A decision-making mechanism that analyzes the user's emotional state and provides appropriate support according to that state of mind,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, wherein the visualization means generates a diagram showing the proportion of mental states and has means for displaying the diagram to the user, and the action decision means makes suggestions based on the generated AI.

[0894] (Claim 3)

[0895] The system according to claim 1, further comprising means for encrypting and transmitting audio information and image information. [Explanation of Symbols]

[0896] 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. Information processing means that receives audio information and analyzes emotions based on said audio information, Information processing means that receives image information and analyzes emotions based on said image information, Information presentation means that integrates the analysis results obtained by the audio information processing means and the image information processing means and presents them visually to the user, A display means for adjusting dialogue or care methods based on analyzed emotional information for care workers or relatives, A system that includes this.

2. The system according to claim 1, wherein the visualization means generates a chart showing the proportion of emotions and has means for displaying the chart to a user in a care setting.

3. The system according to claim 1, further comprising means for encrypting and transmitting audio information and image information.

Images