System

Abstract

A system is provided.SOLUTION: A system comprising: means for capturing a user's voice and facial expressions in real-time and transmitting these data to a server; means for analyzing the data and inferring the user's emotional state at the server; means for suggesting stress management tips and actions to the user based on the analysis; means for feeding back the suggestions and analysis to the user; means for storing and tracking the user's daily emotional state data and analyzing trends and patterns; and means for generating and providing customized advice to the user based on these analyses.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, it is recognized that stress and emotional instability have a significant impact on health. However, systems that can properly recognize these emotional states and provide support tailored to individual users have not yet been fully established. Furthermore, efficient methods for tracking daily emotional states and long-term health management are lacking. Therefore, there is a growing need for a system that can recognize a user's emotional state in real time, make appropriate suggestions based on that information, and provide health support by tracking that information over the long term. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system that provides means for capturing a user's voice and facial expressions in real time and transmitting this data to a server. It then provides means for analyzing the data in the server and inferring the user's emotional state. It also provides means for suggesting stress management tips and actions to the user based on the analysis results. It also provides means for providing feedback on these suggestions and the analysis results to the user. It also includes means for storing and tracking the user's daily emotional state data and analyzing trends and patterns. Finally, it provides means for generating and providing customized advice to the user based on the analysis results.

[0006] "Capture" is the act of acquiring specific data (e.g., audio or video) in real time and storing or processing it in digital form.

[0007] A "server" is a computer system that receives requests from multiple clients over a network and processes data and provides information.

[0008] "Analysis" is the process of breaking down and analyzing collected data based on certain criteria in order to understand and evaluate it.

[0009] "Emotional state" refers to the user's psychological and physiological responses, including feelings such as stress, joy, and sadness.

[0010] "Stress management" is the act or process of providing users with methods and means to appropriately recognize stress and reduce or cope with it.

[0011] "Tracking" refers to the continuous tracking and recording of specific data or behavior over time.

[0012] "Suggestion" means providing the user with actionable actions or advice.

[0013] "Analysis results" refers to the information and conclusions obtained through the data analysis process.

[0014] A "pattern" refers to a trend or regularity shown in a set of data.

[0015] "Advice" refers to instructions or suggestions that recommend appropriate actions or measures based on the user's situation and needs. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[0038] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0039] The server then analyzes the received data using machine learning algorithms, extracting tone and rhythm from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data, allowing the server to infer the user's emotional state.

[0040] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and adds referral information to specialists (e.g., hospitals or counseling services) if necessary. These suggestions and analysis results are sent from the server to the device.

[0041] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[0042] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0043] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management. By clarifying the specific flow of operations, the quality of support provided to the user can be improved, and appropriate health management can be achieved.

[0044] The processing flow will be explained below.

[0045] Step 1:

[0046] The user launches the app and allows it to use the camera and microphone.

[0047] The device captures the user's voice and facial expressions in real time.

[0048] Step 2:

[0049] The device temporarily stores the captured audio and video data.

[0050] The device converts the stored data into the appropriate format (e.g., JSON, XML).

[0051] Step 3:

[0052] The terminal transmits formatted audio and video data to the server.

[0053] Step 4:

[0054] The server sends the received audio and video data to an analysis algorithm.

[0055] The server uses machine learning models to analyze the data and infer the user's emotional state.

[0056] Step 5:

[0057] The server determines the user's emotional state based on the analysis results (e.g., "I feel stressed").

[0058] The server organizes the analysis results and generates response data.

[0059] Step 6:

[0060] The server transmits the generated response data to the terminal.

[0061] Step 7:

[0062] The terminal receives the response data from the server.

[0063] The device displays the analysis results and suggestions to the user (e.g., "Try taking deep breaths to relax").

[0064] Step 8:

[0065] The server stores the user's daily emotional state data in a database.

[0066] The server organizes each day's data with a timestamp.

[0067] Step 9:

[0068] The server aggregates and analyzes the stored data at regular intervals (e.g., once a month).

[0069] The server identifies trends and patterns in the data.

[0070] Step 10:

[0071] The server generates customized advice based on the analysis results.

[0072] The server transmits response data including the customized advice content to the terminal.

[0073] Step 11:

[0074] The terminal receives the advice content from the server.

[0075] The device will display customized advice to the user (e.g., "You seem to be feeling particularly stressed over the weekend. Let's make some relaxing plans").

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] In modern society, many people experience stress on a daily basis, and proper management of stress is an important issue. However, conventional stress management methods have difficulty understanding a user's emotional state in real time and providing individually tailored advice. In particular, there is a need for long-term tracking of a user's state and providing customized advice.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data using a machine learning algorithm and inferring the user's emotional state in the server, means for creating stress management tips and suggested actions for the user based on the analysis results, means for providing the suggestions and analysis results as feedback to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, and means for generating and providing customized advice to the user based on the analysis results. This makes it possible to grasp the user's emotional state in real time, provide individually tailored advice, and realize long-term health management.

[0081] "User's voice" refers to the sound waves generated when the user speaks, and is data that can be collected and analyzed to infer the user's emotional state.

[0082] "Facial expressions" are changes in the movement and placement of facial muscles that indicate the user's emotions and reactions, and are data that can be analyzed to determine the user's emotional state.

[0083] "Real-time capture" refers to a method of instantly collecting and processing a user's voice and facial expressions, meaning that data is obtained without delay.

[0084] "Server" refers to a remote computer system used over a network to analyze and store data and provide feedback to users.

[0085] "Transmitting means" refers to the technical methods and devices for transferring collected user voice and facial expression data from the terminal to the server.

[0086] A "machine learning algorithm" refers to a computational method that trains a model based on large amounts of data and makes appropriate predictions and judgments even for unknown data.

[0087] "Emotional state" refers to the emotional state a user is feeling at a particular moment, including joy, anger, sadness, stress, etc.

[0088] "Stress management tips and action suggestions" means specific advice or recommended actions to help users reduce stress.

[0089] "Storage and Tracking" refers to the process of recording a user's daily emotional state data over time and tracking changes and trends.

[0090] "Customized Advice" refers to suggestions or instructions that are tailored to a specific user based on that user's data.

[0091] "Feedback means" refers to technical methods or devices for directly notifying users of analysis results and suggestions.

[0092] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[0093] First, the user launches the application and allows the use of the camera and microphone. The device uses the built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0094] Specifically, the device's built-in microphone and audio recording software can be used to capture and transmit voice data, and the device's built-in camera and image processing software can be used to capture facial expression data. For example, a smartphone's default camera app and audio recording app can be used.

[0095] The server then analyzes the received data using machine learning algorithms, specifically extracting tone and rate from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data. This analysis can be performed using machine learning libraries such as TensorFlow or PyTorch. This allows the server to infer the user's emotional state.

[0096] Once the analysis results are obtained, the server will suggest appropriate stress management tips and actions based on the results. For example, it can generate messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" The server will then provide the user with the option to accept or decline the suggestion. The suggestion and analysis results are then sent from the server to the device.

[0097] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., one month), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0098] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management.

[0099] Specific examples

[0100] Hardware and software used

[0101] Camera and microphone: Built-in or connected to the device (smartphone or PC)

[0102] Machine learning libraries: TensorFlow, PyTorch

[0103] Specific scenarios

[0104] 1. The user launches the app on their smartphone and allows it to use the camera and microphone.

[0105] Prompt example

[0106] "Do you want to allow use of your camera and microphone?"

[0107] Tap "OK" to ask for permission.

[0108] 2. The device captures the user's facial expressions and voice.

[0109] Prompt example

[0110] Facial expressions are being recognized and audio is being recorded.

[0111] 3. The server analyzes the data and infers the user's emotional state.

[0112] Prompt example

[0113] The user's voice tone is calm, but their facial expression shows signs of stress.

[0114] 4. Generate appropriate stress management recommendations and send them to the device, including expert referral information.

[0115] Prompt example

[0116] "Try taking slower breaths" "Why not try using a counselling service near you?"

[0117] 5. The device displays the analysis results and suggestions to the user, who then makes a selection.

[0118] Prompt example

[0119] Select a suggestion:

[0120] Regulate your breathing

[0121] Find counseling services

[0122] 6. The server provides long-term tracking and customized advice.

[0123] Prompt example

[0124] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[0125]

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1:

[0128] User starts and authorizes the system

[0129] The user launches the app and allows it to use the camera and microphone. When the user taps the app icon on their smartphone, the app launches and a pop-up appears requesting permission to access the camera and microphone. The user approves the access by tapping the "Allow" button.

[0130] Input: User actions (launching an app, approving permissions)

[0131] Output: Camera and microphone permissions are set

[0132] Specific behavior:

[0133] "Do you want to allow use of your camera and microphone?"

[0134] Tap "OK" to ask for permission.

[0135] Step 2:

[0136] Data capture and transmission

[0137] The device uses a built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. When the user faces the camera and speaks into the microphone, the device collects audio and video data. The data is temporarily stored on the device and then sent to a server.

[0138] Input: Camera and microphone data (audio, video)

[0139] Output: Temporarily stored audio and video data, data sent to the server

[0140] Specific behavior:

[0141] Facial expressions are being recognized and audio is being recorded.

[0142] Step 3:

[0143] Data analysis by server

[0144] The server uses machine learning algorithms to analyze the received voice and facial expression data. Specifically, it extracts features such as tone, pitch, and speed from the voice data, and analyzes facial muscle movements and changes from the facial expression data. The server then integrates these features and inputs them into a model that infers the user's emotional state.

[0145] Input: Audio and video data sent to the server

[0146] Output: Analysis results (inferred emotional state)

[0147] Specific behavior:

[0148] The user's voice tone is calm, but their facial expression shows signs of stress.

[0149] Step 4:

[0150] Generate and submit stress management suggestions

[0151] The server generates appropriate stress management recommendations based on the analysis results, including referral information for experts if necessary. The generated recommendations and analysis results are sent from the server to the device. The recommendations include specific behavioral advice and expert contact information.

[0152] Input: Analysis results

[0153] Output: Stress management suggestions, expert referrals

[0154] Specific behavior:

[0155] "Try taking slower breaths" "Why not try using a counselling service near you?"

[0156] Step 5:

[0157] Displaying results to the user and making selections

[0158] The device displays the received analysis results and suggestions to the user, who taps a button to choose whether to accept the suggestions or not. The device then executes an action according to the user's choice.

[0159] Input: Analysis results and suggestions sent from the server

[0160] Output: User's choice

[0161] Specific behavior:

[0162] Select a suggestion:

[0163] Regulate your breathing

[0164] Find counseling services

[0165] Step 6:

[0166] Long-term tracking and personalized advice

[0167] The server stores daily emotional state data and tracks it over the long term. Every certain period (e.g., one month), the accumulated data is analyzed to identify trends and patterns. The server generates customized advice based on the results of this long-term data analysis and sends it back to the device.

[0168] Input: Daily emotional state data

[0169] Output: Customized advice

[0170] Specific behavior:

[0171] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[0172] (Application example 1)

[0173] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0174] Conventional emotion analysis systems have been designed primarily for the purpose of personal stress management and health support, and have not been used to improve customer service in brick-and-mortar stores. As a result, there has been a lack of systems that can provide real-time customer service advice based on the customer's emotional state. Furthermore, there are limited ways for customer service staff in brick-and-mortar stores to properly grasp the customer's emotional state, making it difficult to provide personalized service based on that information.

[0175] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0176] In this invention, the server includes means for capturing the user's voice and facial expression in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, and means for suggesting stress management tips and actions to the user based on the analysis results. This makes it possible to use a device that captures the user's facial expression and voice in a physical store and provide customer service advice in real time based on the analysis results.

[0177] A "user" is a subject who uses the system and whose voice and facial expressions are captured.

[0178] "Voice" refers to data of the voice uttered by the user, and is an information source for inferring the emotional state by analyzing this data.

[0179] "Facial expressions" refer to the movements and changes of the user's facial muscles, and are visual data used to infer emotional states.

[0180] "Real-time capture" refers to a means of obtaining voice and facial expression data instantly, without delay.

[0181] A "server" is a computer system that receives and analyzes the captured data.

[0182] "Analysis" refers to the process of processing voice and facial expression data using machine learning algorithms to infer emotional states.

[0183] "Emotional state" refers to the emotions and psychological state that a user is feeling at that moment.

[0184] "Suggestions" refers to advice or action plans provided to users based on the results of sentiment analysis.

[0185] "Stress management" is the process of suggesting methods and actions to reduce the stress a user feels.

[0186] "Feedback" refers to the act of communicating analysis results and suggestions to users.

[0187] "Preservation" refers to the long-term storage of captured data and analysis results.

[0188] "Tracking" is the process of continuously tracking a user's daily emotional state data and recording patterns and trends.

[0189] "Customized advice" refers to recommendations that are individually optimized based on user-specific data.

[0190] "Brick and Mortar Store" means a business establishment that offers goods and services at a physical location.

[0191] "Device" generally refers to the hardware used to capture voice and facial expressions.

[0192] "Customer service advice" refers to advice on how to deal with customers that is provided to customer service staff based on the analysis results.

[0193] This invention configures a system that captures a user's voice and facial expressions in real time and analyzes their emotional state, with the aim of utilizing this system to improve customer service in brick-and-mortar stores.

[0194] 1. System Program Overview

[0195] Server program

[0196] Capture and data transmission (terminal):

[0197] The device (e.g., smart glasses) captures the user's voice and facial expressions in real time, temporarily stores them locally, and then transmits them to the server using a network request library.

[0198] Data analysis (server):

[0199] The server then analyzes the received data using machine learning algorithms, converting the voice data into text using the Google Speech-to-Text API and analyzing the facial expression data using OpenCV and TensorFlow, thereby inferring the user's emotional state.

[0200] Proposal generation (server):

[0201] Generate stress management tips and customer service advice based on emotional state, including advice on how to reduce stress and how to respond appropriately.

[0202] Real-time display (terminal):

[0203] The analysis results and suggestions are then fed back to the device via the network and displayed on the smart glasses screen.

[0204] Data Storage and Tracking (Server):

[0205] It continuously stores data on the user's daily emotional state and analyzes long-term trends and patterns to generate and deliver customized advice to the user.

[0206] 2. Hardware and software used

[0207] Hardware:

[0208] Smart glasses (e.g., Google Glass, Vuzix Blade)

[0209] Server (e.g. AWS EC2, Google Cloud Platform)

[0210] software:

[0211] Image capture library (e.g. OpenCV)

[0212] Speech recognition library (e.g. Google Speech-to-Text)

[0213] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0214] Network request libraries (e.g., Requests)

[0215] 3. Data processing and calculation

[0216] Processing the captured data:

[0217] Voice and facial expression data captured on the device is first temporarily stored and then sent to a server using the Requests library, where it is fed into a machine learning model to analyze voice tones and extract facial features to infer emotional states.

[0218] Proposal generation of analysis results:

[0219] Based on the analysis results, the system generates specific stress management tips for users and real-time advice for customer service staff, such as "The customer is smiling, so try to be friendly" or "The customer looks a little tired, so it would be good to speak to them in a calm tone."

[0220] Specific examples

[0221] When a customer service staff member wears the smart glasses in a brick-and-mortar store, the customer's facial expressions and voice are instantly captured and sent to a server. The server analyzes the data in real time and infers the customer's emotional state. As a result, the smart glasses display will say, "The customer appears interested. Let me explain the product in more detail."

[0222] Prompt Sentence Examples

[0223] "Please tell me about building a system that can infer emotions from a customer's facial expression and advise them on the best way to serve them."

[0224] In this way, by linking users, devices, and servers, it is possible to achieve daily stress management, long-term health management, and even improved customer service in physical stores.

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] The device (smart glasses) captures the user's voice and facial expressions in real time. Specifically, it uses a camera to capture facial expression data and a microphone to collect audio data. The input data are raw facial expression images and audio files. These data are stored in the device's temporary memory.

[0228] Step 2:

[0229] The device sends the captured data to the server using a network request library (e.g., Requests). The input facial expression images and audio files are converted into data packets that are sent to the server over the network. The output is an HTTP request containing these data.

[0230] Step 3:

[0231] The server analyzes the received data. First, it uses the Google Speech-to-Text API to convert the audio data into text. The input is an audio file, and the output is text data. Next, it uses OpenCV and TensorFlow to extract facial features from the facial expression image and input them into a machine learning model. The input is facial expression data, and the output is numerical data representing the emotional state.

[0232] Step 4:

[0233] The server generates stress management tips and customer service advice based on the analysis results. A machine learning algorithm analyzes the numerical emotional state data and derives optimal advice. The input is the numerical analysis results, and the output is a specific advice message.

[0234] Step 5:

[0235] The server generates an advice message and sends it to the terminal using the network request library. The input is the advice message, and the output is the HTTP response. The terminal receives this HTTP response and analyzes the data.

[0236] Step 6:

[0237] The device displays the analysis results and advice messages in real time on the smart glasses' display. The input is the advice message obtained from the HTTP response, and the output is the text displayed in the user's field of view. Specifically, a message such as "It appears the customer is interested. Let's explain the product in more detail" is displayed on the display.

[0238] Step 7:

[0239] The server stores daily emotional state data and performs long-term tracking. The input is historical analysis data, and the output is the analysis of long-term trends and patterns. Based on this, customized advice is generated and provided to the user.

[0240] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0241] This system combines an emotion engine that recognizes the user's emotions, captures the user's voice and facial expressions in real time, and sends the data to a server for analysis to estimate the user's emotional state and propose appropriate stress management. It is also possible to track daily emotional state data and provide long-term health support.

[0242] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0243] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. Specifically, the emotion engine extracts tone and rhythm from the voice data and analyzes facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data to infer the user's emotional state.

[0244] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and if necessary, adds referral information to specialists (e.g., hospitals or counseling services). These suggestions and analysis results are sent from the server to the device.

[0245] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[0246] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0247] This system recognizes and supports the user's emotional state through collaboration between the user, device, server, and emotion engine. This allows for effective daily stress management and long-term health management. By clarifying the specific operational flow, the quality of support provided to the user is improved, and appropriate health management is achieved.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] The user launches the app and allows it to use the camera and microphone. The device captures the user's facial expressions and voice in real time.

[0251] Step 2:

[0252] The device temporarily stores the captured audio and video data, which is then converted into a format (e.g., JSON, XML) for transmission to the emotion engine.

[0253] Step 3:

[0254] The terminal transmits formatted audio and video data to the server.

[0255] Step 4:

[0256] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. For example, it extracts tone and rhythm from the voice data and identifies facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[0257] Step 5:

[0258] The server receives the analysis results from the emotion engine and identifies the user's emotional state (e.g., "I feel stressed"). The server then organizes the analysis results and generates appropriate stress management tips and actions for the user.

[0259] Step 6:

[0260] The server collects referral information for professionals (e.g., hospitals or counseling services) as needed and adds it to the recommendations.

[0261] Step 7:

[0262] The server transmits the generated proposal content and analysis results to the terminal.

[0263] Step 8:

[0264] The device receives the suggestions and analysis results from the server and displays them to the user, such as messages like "Try breathing slowly" or "Why not try using a nearby counseling service?"

[0265] Step 9:

[0266] The system tracks users' daily emotional state data and stores it on a server, which then organizes the data for each day along with a timestamp and stores it in a database.

[0267] Step 10:

[0268] At regular intervals (e.g., monthly), the server aggregates and analyzes the stored emotional state data. The server identifies trends and patterns in the data.

[0269] Step 11:

[0270] The server generates customized advice based on the analysis results, such as "You seem to be feeling particularly stressed over the weekend, so make some plans to relax."

[0271] Step 12:

[0272] The server transmits the generated customization advice to the terminal.

[0273] Step 13:

[0274] The device receives customized advice from the server and displays it to the user, such as "We recommend you try some ways to relax on the weekend."

[0275] In this way, the user, the terminal, the server, and the emotion engine can work together to recognize the user's emotional state in real time and provide health support through appropriate suggestions and long-term analysis.

[0276] Example 2

[0277] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0278] In modern society, users often experience a lot of stress in their daily lives, but they have few opportunities to receive appropriate stress management techniques or expert support. Furthermore, there is a lack of systems that can accurately recognize a user's emotional state and provide specific advice based on that recognition. To address this issue, a system is needed that can capture and analyze a user's emotional state in real time and provide appropriate suggestions.

[0279] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, means for suggesting stress management tips and actions to the user based on the analysis results, means for feeding back the suggestions and analysis results to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, means for generating customized advice based on these analysis results and providing it to the user, means for temporarily saving the captured data in the terminal, and means for the user to select whether to accept the suggestions. This allows the user's emotional state to be accurately recognized, enabling appropriate stress management and expert support.

[0280] "Voice" refers to the user's speaking voice, which is captured as data for analyzing emotional state.

[0281] "Facial expressions" refer to the movements that show emotions on a user's face, and are data that are captured in real time to infer emotional states.

[0282] "Real-time" refers to processing and analysis being carried out in response to ongoing events or phenomena at the exact moment they occur.

[0283] "Capture" refers to taking in data such as audio and video, and is a means of obtaining the input information necessary to recognize the user's emotional state.

[0284] "Server" refers to a central processing unit that receives data sent by users and performs analysis and proposal generation.

[0285] "Analysis" refers to the process of examining acquired data in detail to find specific information or patterns.

[0286] "Emotional state" refers to the emotions a user feels at a particular moment, and analyzing this can help understand their stress level or happiness.

[0287] "Inference" means to make a deduction about an event or situation based on information obtained.

[0288] "Stress management tips and actions" refers to specific advice and suggested actions to help users reduce stress and maintain a better mental state.

[0289] "Feedback" refers to informing the user of the analysis results and suggestions, and serves as information to improve the user's behavior.

[0290] "Tracking" refers to the process of continuously monitoring and recording a user's emotional state.

[0291] "Customized advice" refers to suggestions or advice that are tailored to a particular user based on that individual user's emotional state data.

[0292] "Temporary storage" refers to the process of holding data on a device for a short period of time in order to send it to a server at a later time.

[0293] "Selection" refers to the action of a user deciding "yes" or "no" to a presented option or suggestion.

[0294] This invention is a system for recognizing a user's emotions and suggesting stress management. This system is mainly composed of a user, a terminal, and a server.

[0295] First, the user launches the application and allows the use of the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. Specifically, the device's camera (e.g., the front camera of a smartphone) and microphone are used. This video and audio data is temporarily stored on the device and then sent to the server. Appropriate encryption technology (e.g., SSL) is used for transmission.

[0296] The server sends the received data to the emotion engine, which then analyzes it using a voice recognition algorithm (e.g., a general voice recognition API) and a facial expression analysis algorithm (e.g., a general facial expression analysis API). Specifically, it extracts tone and rhythm from the voice data and facial features (e.g., smile, sadness, anger) from the facial expression data. Based on the analysis results, it infers the user's emotional state.

[0297] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. Specific examples include suggestions such as "Take a deep breath" or "Consult a specialist." Referral information for specialists may also be added. These suggestions and analysis results are sent from the server to the device.

[0298] The device displays the received suggestions and analysis results to the user. If the user's emotional state indicates stress, messages such as "Take slow, deep breaths" or "Why not seek out a nearby counseling service?" are displayed. The user can choose whether to accept the suggestions.

[0299] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. This data can be analyzed periodically to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend that you make plans to relax."

[0300] An example of a prompt sentence might be, "If the user is feeling anxious about tomorrow's presentation, please suggest an appropriate way for them to relax."

[0301] This system supports daily health management by recognizing the user's emotions in real time and providing appropriate stress management and expert support. By clarifying the specific flow of operations, the quality of support provided to users can be improved and appropriate health management can be achieved.

[0302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0303] Step 1:

[0304] The user launches the app.

[0305] Input: A user taps an app icon on their smartphone or tablet.

[0306] Action: The application starts and the initial screen is displayed.

[0307] Output: A dialog will appear requesting permission to use the camera and microphone.

[0308] Step 2:

[0309] The user allows use of the camera and microphone.

[0310] Input: The user taps the "Allow" button in the dialog.

[0311] What it does: The device gets access to the camera and microphone.

[0312] Output: Camera and microphone are allowed and ready for real-time capture.

[0313] Step 3:

[0314] The device captures the user's facial expressions and voice in real time.

[0315] Input: Video and audio data from authorized cameras and microphones.

[0316] What it does: Periodically captures video frames using the device's camera and audio samples using the device's microphone.

[0317] Output: The captured video and audio data is temporarily saved.

[0318] Step 4:

[0319] Temporarily saves audio and video data captured by the device.

[0320] Input: Real-time captured video and audio data.

[0321] What it does: Stores data in the device's temporary memory.

[0322] Output: Stored video and audio data.

[0323] Step 5:

[0324] The device sends the saved data to the server.

[0325] Input: Video and audio data stored in temporary memory.

[0326] How it works: Data is sent over the internet to a server and encrypted (e.g. SSL) technology is used to ensure secure communication.

[0327] Output: The data sent to the server.

[0328] Step 6:

[0329] The server receives the data and sends it to the emotion engine.

[0330] Input: Video and audio data sent from the device.

[0331] How it works: The server receives the data and converts the data format to pass it to the emotion engine.

[0332] Output: The emotion engine receives the data for analysis.

[0333] Step 7:

[0334] The emotion engine analyzes voice and facial expression data.

[0335] Input: Audio and video data received from the server.

[0336] How it works: Speech recognition algorithms extract tone and rhythm, and facial expression analysis algorithms analyze facial features (e.g., smiling, sad, angry).

[0337] Output: Analysis results showing the user's emotional state.

[0338] Step 8:

[0339] The server generates stress management suggestions based on the analysis results.

[0340] Input: Analysis results from the emotion engine.

[0341] How it works: Based on the analysis, it determines appropriate stress management tips and actions, and adds expert referrals as needed.

[0342] Output: The specific recommendations generated.

[0343] Step 9:

[0344] The server sends the proposals and analysis results to the device.

[0345] Input: Server-generated suggestions and analysis results.

[0346] What it does: Sends data to a device. The transmission is encrypted.

[0347] Output: Suggestions and analysis results sent to your device.

[0348] Step 10:

[0349] The device displays the suggestions and analysis results to the user.

[0350] Input: Proposal content and analysis results received from the server.

[0351] What it does: Analyzes the data and displays it in a user-friendly format, such as a message like "Take slow, deep breaths."

[0352] Output: Suggestions and analysis results displayed to the user.

[0353] Step 11:

[0354] The user chooses whether to accept the suggestion.

[0355] Input: The suggestions presented on the terminal.

[0356] Action: The user responds to a suggestion with a "yes" or "no" response.

[0357] Output: The user's selection.

[0358] Step 12:

[0359] The server stores the emotional state data in a database for long-term tracking.

[0360] Input: Daily emotional state data and user selection results.

[0361] How it works: The server stores the data in a database and manages it for long-term tracking.

[0362] Output: Saved emotional state data.

[0363] Step 13:

[0364] The server analyzes the data at regular intervals and generates customized advice.

[0365] Input: Long-term stored emotional state data.

[0366] How it works: Analyzes data to identify trends and patterns, and then generates personalized recommendations based on those trends.

[0367] Output: The generated customized advice.

[0368] (Application example 2)

[0369] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0370] Conventional stress management systems have the problem that they cannot provide feedback or suggestions based on the user's unique emotional state, and their long-term health management is limited in scope. Furthermore, they lack a means to obtain immediate and useful instructions for action in real-time face-to-face communication, making it difficult to improve the quality of customer service in hospitality and service industries.

[0371] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expression in real time and analyzing this data, means for suggesting stress management tips and actions to the user based on the analysis results, and means for presenting real-time behavioral instructions to the user who is face-to-face with others using a wearable device that displays feedback based on the real-time emotion analysis results. This allows the user to accurately understand their own emotional state and perform appropriate stress management, and further improves the quality of customer service in physical stores, etc.

[0372] "Means for capturing a user's voice and facial expressions in real time" refers to devices and software for acquiring and recording voice data and facial expression data emitted by a user in real time.

[0373] "Means for transmitting data to a server" refers to a communication device or protocol for transmitting the captured voice data and facial expression data to a server via a communication network such as the Internet.

[0374] "Means for analyzing data and inferring the user's emotional state" refers to software or algorithms that analyze received voice and facial expression data and use machine learning algorithms to infer the user's emotional state.

[0375] "Means for suggesting stress management tips and actions" refers to a system for generating messages and notifications that suggest appropriate stress management methods and actions to users based on the analysis results.

[0376] A "wearable device that displays feedback" is a device that displays the results of emotion analysis and suggested responses, and refers to a display device that can be worn by the user, such as smart glasses.

[0377] "Means for storing and tracking a user's daily emotional state data and analyzing trends and patterns" refers to a system that stores a user's emotional data over a long period of time and analyzes it to identify changes and patterns in emotions.

[0378] "Means for generating and providing customized advice to a user" refers to a system that generates advice tailored to a user's specific needs based on tracking data and analysis results and transmits that information to the user.

[0379] "Means for presenting real-time behavioral instructions to a user who is face-to-face with another person" refers to a system that instantly suggests actions and responses that are tailored to the person the user is face-to-face with based on the results of real-time emotion analysis.

[0380] In order to implement the present invention, it is necessary to configure the system as follows.

[0381] Capturing the user's voice and facial expressions

[0382] The user uses a wearable device such as smart glasses. This device is equipped with a camera and a microphone to capture the user's facial expressions and voice in real time. For example, rather than a specific brand name device, a device equipped with a general "high-resolution camera" and "high-sensitivity microphone" is used. This data is temporarily stored in the user's device and then sent to a server.

[0383] Sending data to the server for analysis

[0384] The voice and facial expression data captured by the device is sent to a server via the Internet. The server is a standard server equipped with a high-performance processor and large memory capacity. The received data is then processed by a specialized analysis engine, known as an "emotion engine," to infer the user's emotional state. This emotion engine uses machine learning algorithms to extract tone and rhythm from the voice data and analyze facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[0385] Stress management suggestions and feedback

[0386] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. These suggestions might be, for example, "Try breathing slowly" or "Why not consult a specialist?" The generated suggestions are sent to the wearable device and displayed to the user. Real-time action instructions may also be displayed depending on the person the user is facing. For example, a store clerk who is dealing with customers might be instructed to "Smile when serving customers."

[0387] Long-term emotional tracking and personalized advice

[0388] The server stores daily emotional state data in a database and tracks it over the long term. It periodically analyzes this data to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to users. For example, specific advice might be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0389] Hardware and software used

[0390] Wearable devices: Smart glasses equipped with a high-resolution camera, microphone, and display.

[0391] Server: A typical server device equipped with a high-performance processor and large memory capacity.

[0392] Software: OpenCV (camera image capture and processing), Dlib (face recognition and facial feature point acquisition), requests (emotion data transmission to server), gTTS (text-to-speech conversion), playsound (audio playback).

[0393] Specific examples

[0394] For example, in a customer service scenario in a brick-and-mortar store, if a customer enters the store and looks a little unhappy, the store clerk's smart glasses will display a message saying, "The customer seems a little nervous. Please try to greet them with a smile." The system will also track the user's daily emotional data and provide customized advice, such as, "You tend to feel stressed during the week, so we recommend you spend more time on your hobbies on the weekends."

[0395] Prompt Sentence Examples

[0396] "The customer is a little grumpy. Try to smile."

[0397] This system configuration makes it possible to accurately grasp the user's emotional state and provide appropriate stress management and face-to-face support.

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] Facial expression and voice capture

[0401] The device (smart glasses) captures the user's facial expressions and voice in real time. Specifically, the device's built-in camera captures facial expression data, and a high-sensitivity microphone captures voice data. These data are temporarily stored in the device.

[0402] Input: Trigger to start capture (e.g., app launch)

[0403] Data processing: Camera footage is captured in real time, facial recognition is performed, and facial expression data is extracted. Audio data is also captured in real time and noise is removed.

[0404] Output: A set of facial expression and speech data

[0405] For example, when a user puts on glasses and points their face towards the camera, facial recognition takes place.

[0406] Step 2:

[0407] Sending data to the server

[0408] The device transmits the temporarily stored facial expression data and voice data to a server via the Internet using a predetermined protocol (e.g., HTTPS).

[0409] Input: A set of facial expression and speech data

[0410] Data processing: Convert facial expression data and voice data into JSON format

[0411] Output: Send data to the server

[0412] Example: The device sends data collected in real time to the server.

[0413] Step 3:

[0414] Emotion analysis

[0415] The server analyzes the received data and infers the user's emotional state. Specifically, the emotion engine uses machine learning algorithms to analyze voice tone, facial feature points, etc.

[0416] Input: Facial expression data and voice data sent to the server

[0417] Data processing: Extracting tone and rhythm from voice data, analyzing emotional features (e.g., smile, anger) from facial data

[0418] Output: Estimated user emotional state (e.g., happy, angry, sad)

[0419] Example: The server analyzes voice tone and facial expressions to guess whether the user is "happy" or "angry."

[0420] Step 4:

[0421] Stress management suggestions and feedback

[0422] The server generates appropriate stress management tips and actions based on the user's emotional state, and the generated suggestions are sent to the wearable device and displayed to the user, along with real-time behavioral instructions based on the person the user is facing.

[0423] Input: User's emotional state

[0424] Data processing: Generate stress management tips and actions (e.g., "Take a deep breath" or "Consult a professional")

[0425] Output: Suggestions and real-time action instructions displayed on a wearable device

[0426] For example, if the user is feeling stressed, the message "Try breathing slowly" will be displayed. When serving customers face-to-face, the message "Try to smile when serving customers" will be displayed.

[0427] Step 5:

[0428] Long-term sentiment tracking and customized advice

[0429] The server stores daily emotional state data in a database and analyzes it. Based on the analysis results, it identifies long-term trends and patterns and generates customized advice, which is then provided to the user at regular intervals.

[0430] Input: Daily emotional state data

[0431] Data processing: analyzing trends and patterns and generating customized advice

[0432] Output: Providing regular, customized advice to users

[0433] Example: A user who tends to get stressed on weekends is given the advice, "We recommend that you make plans to relax on the weekend."

[0434] Through these steps, the user's emotional state is grasped in real time, providing appropriate feedback and long-term stress management.

[0435] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0436] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0437] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0438] [Second embodiment]

[0439] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0440] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0441] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0442] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0443] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0444] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0445] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0446] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0447] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0448] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0449] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0450] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0451] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[0452] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0453] The server then analyzes the received data using machine learning algorithms, extracting tone and rhythm from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data, allowing the server to infer the user's emotional state.

[0454] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and adds referral information to specialists (e.g., hospitals or counseling services) if necessary. These suggestions and analysis results are sent from the server to the device.

[0455] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[0456] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0457] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management. By clarifying the specific flow of operations, the quality of support provided to the user can be improved, and appropriate health management can be achieved.

[0458] The processing flow will be explained below.

[0459] Step 1:

[0460] The user launches the app and allows it to use the camera and microphone.

[0461] The device captures the user's voice and facial expressions in real time.

[0462] Step 2:

[0463] The device temporarily stores the captured audio and video data.

[0464] The device converts the stored data into the appropriate format (e.g., JSON, XML).

[0465] Step 3:

[0466] The terminal transmits formatted audio and video data to the server.

[0467] Step 4:

[0468] The server sends the received audio and video data to an analysis algorithm.

[0469] The server uses machine learning models to analyze the data and infer the user's emotional state.

[0470] Step 5:

[0471] The server determines the user's emotional state based on the analysis results (e.g., "I feel stressed").

[0472] The server organizes the analysis results and generates response data.

[0473] Step 6:

[0474] The server transmits the generated response data to the terminal.

[0475] Step 7:

[0476] The terminal receives the response data from the server.

[0477] The device displays the analysis results and suggestions to the user (e.g., "Try taking deep breaths to relax").

[0478] Step 8:

[0479] The server stores the user's daily emotional state data in a database.

[0480] The server organizes each day's data with a timestamp.

[0481] Step 9:

[0482] The server aggregates and analyzes the stored data at regular intervals (e.g., once a month).

[0483] The server identifies trends and patterns in the data.

[0484] Step 10:

[0485] The server generates customized advice based on the analysis results.

[0486] The server transmits response data including the customized advice content to the terminal.

[0487] Step 11:

[0488] The terminal receives the advice content from the server.

[0489] The device will display customized advice to the user (e.g., "You seem to be feeling particularly stressed over the weekend. Let's make some relaxing plans").

[0490] Example 1

[0491] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0492] In modern society, many people experience stress on a daily basis, and proper management of stress is an important issue. However, conventional stress management methods have difficulty understanding a user's emotional state in real time and providing individually tailored advice. In particular, there is a need for long-term tracking of a user's state and providing customized advice.

[0493] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0494] In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data using a machine learning algorithm and inferring the user's emotional state in the server, means for creating stress management tips and suggested actions for the user based on the analysis results, means for providing the suggestions and analysis results as feedback to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, and means for generating and providing customized advice to the user based on the analysis results. This makes it possible to grasp the user's emotional state in real time, provide individually tailored advice, and realize long-term health management.

[0495] "User's voice" refers to the sound waves generated when the user speaks, and is data that can be collected and analyzed to infer the user's emotional state.

[0496] "Facial expressions" are changes in the movement and placement of facial muscles that indicate the user's emotions and reactions, and are data that can be analyzed to determine the user's emotional state.

[0497] "Real-time capture" refers to a method of instantly collecting and processing a user's voice and facial expressions, meaning that data is obtained without delay.

[0498] "Server" refers to a remote computer system used over a network to analyze and store data and provide feedback to users.

[0499] "Transmitting means" refers to the technical methods and devices for transferring collected user voice and facial expression data from the terminal to the server.

[0500] A "machine learning algorithm" refers to a computational method that trains a model based on large amounts of data and makes appropriate predictions and judgments even for unknown data.

[0501] "Emotional state" refers to the emotional state a user is feeling at a particular moment, including joy, anger, sadness, stress, etc.

[0502] "Stress management tips and action suggestions" means specific advice or recommended actions to help users reduce stress.

[0503] "Storage and Tracking" refers to the process of recording a user's daily emotional state data over time and tracking changes and trends.

[0504] "Customized Advice" refers to suggestions or instructions that are tailored to a specific user based on that user's data.

[0505] "Feedback means" refers to technical methods or devices for directly notifying users of analysis results and suggestions.

[0506] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[0507] First, the user launches the application and allows the use of the camera and microphone. The device uses the built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0508] Specifically, the device's built-in microphone and audio recording software can be used to capture and transmit voice data, and the device's built-in camera and image processing software can be used to capture facial expression data. For example, a smartphone's default camera app and audio recording app can be used.

[0509] The server then analyzes the received data using machine learning algorithms, specifically extracting tone and rate from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data. This analysis can be performed using machine learning libraries such as TensorFlow or PyTorch. This allows the server to infer the user's emotional state.

[0510] Once the analysis results are obtained, the server will suggest appropriate stress management tips and actions based on the results. For example, it can generate messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" The server will then provide the user with the option to accept or decline the suggestion. The suggestion and analysis results are then sent from the server to the device.

[0511] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., one month), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0512] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management.

[0513] Specific examples

[0514] Hardware and software used

[0515] Camera and microphone: Built-in or connected to the device (smartphone or PC)

[0516] Machine learning libraries: TensorFlow, PyTorch

[0517] Specific scenarios

[0518] 1. The user launches the app on their smartphone and allows it to use the camera and microphone.

[0519] Prompt example

[0520] "Do you want to allow use of your camera and microphone?"

[0521] Tap "OK" to ask for permission.

[0522] 2. The device captures the user's facial expressions and voice.

[0523] Prompt example

[0524] Facial expressions are being recognized and audio is being recorded.

[0525] 3. The server analyzes the data and infers the user's emotional state.

[0526] Prompt example

[0527] The user's voice tone is calm, but their facial expression shows signs of stress.

[0528] 4. Generate appropriate stress management recommendations and send them to the device, including expert referral information.

[0529] Prompt example

[0530] "Try taking slower breaths" "Why not try using a counselling service near you?"

[0531] 5. The device displays the analysis results and suggestions to the user, who then makes a selection.

[0532] Prompt example

[0533] Select a suggestion:

[0534] Regulate your breathing

[0535] Find counseling services

[0536] 6. The server provides long-term tracking and customized advice.

[0537] Prompt example

[0538] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[0539]

[0540] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0541] Step 1:

[0542] User starts and authorizes the system

[0543] The user launches the app and allows it to use the camera and microphone. When the user taps the app icon on their smartphone, the app launches and a pop-up appears requesting permission to access the camera and microphone. The user approves the access by tapping the "Allow" button.

[0544] Input: User actions (launching an app, approving permissions)

[0545] Output: Camera and microphone permissions are set

[0546] Specific behavior:

[0547] "Do you want to allow use of your camera and microphone?"

[0548] Tap "OK" to ask for permission.

[0549] Step 2:

[0550] Data capture and transmission

[0551] The device uses a built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. When the user faces the camera and speaks into the microphone, the device collects audio and video data. The data is temporarily stored on the device and then sent to a server.

[0552] Input: Camera and microphone data (audio, video)

[0553] Output: Temporarily stored audio and video data, data sent to the server

[0554] Specific behavior:

[0555] Facial expressions are being recognized and audio is being recorded.

[0556] Step 3:

[0557] Data analysis by server

[0558] The server uses machine learning algorithms to analyze the received voice and facial expression data. Specifically, it extracts features such as tone, pitch, and speed from the voice data, and analyzes facial muscle movements and changes from the facial expression data. The server then integrates these features and inputs them into a model that infers the user's emotional state.

[0559] Input: Audio and video data sent to the server

[0560] Output: Analysis results (inferred emotional state)

[0561] Specific behavior:

[0562] The user's voice tone is calm, but their facial expression shows signs of stress.

[0563] Step 4:

[0564] Generate and submit stress management suggestions

[0565] The server generates appropriate stress management recommendations based on the analysis results, including referral information for experts if necessary. The generated recommendations and analysis results are sent from the server to the device. The recommendations include specific behavioral advice and expert contact information.

[0566] Input: Analysis results

[0567] Output: Stress management suggestions, expert referrals

[0568] Specific behavior:

[0569] "Try taking slower breaths" "Why not try using a counselling service near you?"

[0570] Step 5:

[0571] Displaying results to the user and making selections

[0572] The device displays the received analysis results and suggestions to the user, who taps a button to choose whether to accept the suggestions or not. The device then executes an action according to the user's choice.

[0573] Input: Analysis results and suggestions sent from the server

[0574] Output: User's choice

[0575] Specific behavior:

[0576] Select a suggestion:

[0577] Regulate your breathing

[0578] Find counseling services

[0579] Step 6:

[0580] Long-term tracking and personalized advice

[0581] The server stores daily emotional state data and tracks it over the long term. Every certain period (e.g., one month), the accumulated data is analyzed to identify trends and patterns. The server generates customized advice based on the results of this long-term data analysis and sends it back to the device.

[0582] Input: Daily emotional state data

[0583] Output: Customized advice

[0584] Specific behavior:

[0585] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[0586] (Application example 1)

[0587] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0588] Conventional emotion analysis systems have been designed primarily for the purpose of personal stress management and health support, and have not been used to improve customer service in brick-and-mortar stores. As a result, there has been a lack of systems that can provide real-time customer service advice based on the customer's emotional state. Furthermore, there are limited ways for customer service staff in brick-and-mortar stores to properly grasp the customer's emotional state, making it difficult to provide personalized service based on that information.

[0589] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0590] In this invention, the server includes means for capturing the user's voice and facial expression in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, and means for suggesting stress management tips and actions to the user based on the analysis results. This makes it possible to use a device that captures the user's facial expression and voice in a physical store and provide customer service advice in real time based on the analysis results.

[0591] A "user" is a subject who uses the system and whose voice and facial expressions are captured.

[0592] "Voice" refers to data of the voice uttered by the user, and is an information source for inferring the emotional state by analyzing this data.

[0593] "Facial expressions" refer to the movements and changes of the user's facial muscles, and are visual data used to infer emotional states.

[0594] "Real-time capture" refers to a means of obtaining voice and facial expression data instantly, without delay.

[0595] A "server" is a computer system that receives and analyzes the captured data.

[0596] "Analysis" refers to the process of processing voice and facial expression data using machine learning algorithms to infer emotional states.

[0597] "Emotional state" refers to the emotions and psychological state that a user is feeling at that moment.

[0598] "Suggestions" refers to advice or action plans provided to users based on the results of sentiment analysis.

[0599] "Stress management" is the process of suggesting methods and actions to reduce the stress a user feels.

[0600] "Feedback" refers to the act of communicating analysis results and suggestions to users.

[0601] "Preservation" refers to the long-term storage of captured data and analysis results.

[0602] "Tracking" is the process of continuously tracking a user's daily emotional state data and recording patterns and trends.

[0603] "Customized advice" refers to recommendations that are individually optimized based on user-specific data.

[0604] "Brick and Mortar Store" means a business establishment that offers goods and services at a physical location.

[0605] "Device" generally refers to the hardware used to capture voice and facial expressions.

[0606] "Customer service advice" refers to advice on how to deal with customers that is provided to customer service staff based on the analysis results.

[0607] This invention configures a system that captures a user's voice and facial expressions in real time and analyzes their emotional state, with the aim of utilizing this system to improve customer service in brick-and-mortar stores.

[0608] 1. System Program Overview

[0609] Server program

[0610] Capture and data transmission (terminal):

[0611] The device (e.g., smart glasses) captures the user's voice and facial expressions in real time, temporarily stores them locally, and then transmits them to the server using a network request library.

[0612] Data analysis (server):

[0613] The server then analyzes the received data using machine learning algorithms, converting the voice data into text using the Google Speech-to-Text API and analyzing the facial expression data using OpenCV and TensorFlow, thereby inferring the user's emotional state.

[0614] Proposal generation (server):

[0615] Generate stress management tips and customer service advice based on emotional state, including advice on how to reduce stress and how to respond appropriately.

[0616] Real-time display (terminal):

[0617] The analysis results and suggestions are then fed back to the device via the network and displayed on the smart glasses screen.

[0618] Data Storage and Tracking (Server):

[0619] It continuously stores data on the user's daily emotional state and analyzes long-term trends and patterns to generate and deliver customized advice to the user.

[0620] 2. Hardware and software used

[0621] Hardware:

[0622] Smart glasses (e.g., Google Glass, Vuzix Blade)

[0623] Server (e.g. AWS EC2, Google Cloud Platform)

[0624] software:

[0625] Image capture library (e.g. OpenCV)

[0626] Speech recognition library (e.g. Google Speech-to-Text)

[0627] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0628] Network request libraries (e.g., Requests)

[0629] 3. Data processing and calculation

[0630] Processing the captured data:

[0631] Voice and facial expression data captured on the device is first temporarily stored and then sent to a server using the Requests library, where it is fed into a machine learning model to analyze voice tones and extract facial features to infer emotional states.

[0632] Proposal generation of analysis results:

[0633] Based on the analysis results, the system generates specific stress management tips for users and real-time advice for customer service staff, such as "The customer is smiling, so try to be friendly" or "The customer looks a little tired, so it would be good to speak to them in a calm tone."

[0634] Specific examples

[0635] When a customer service staff member wears the smart glasses in a brick-and-mortar store, the customer's facial expressions and voice are instantly captured and sent to a server. The server analyzes the data in real time and infers the customer's emotional state. As a result, the smart glasses display will say, "The customer appears interested. Let me explain the product in more detail."

[0636] Prompt Sentence Examples

[0637] "Please tell me about building a system that can infer emotions from a customer's facial expression and advise them on the best way to serve them."

[0638] In this way, by linking users, devices, and servers, it is possible to achieve daily stress management, long-term health management, and even improved customer service in physical stores.

[0639] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0640] Step 1:

[0641] The device (smart glasses) captures the user's voice and facial expressions in real time. Specifically, it uses a camera to capture facial expression data and a microphone to collect audio data. The input data are raw facial expression images and audio files. These data are stored in the device's temporary memory.

[0642] Step 2:

[0643] The device sends the captured data to the server using a network request library (e.g., Requests). The input facial expression images and audio files are converted into data packets that are sent to the server over the network. The output is an HTTP request containing these data.

[0644] Step 3:

[0645] The server analyzes the received data. First, it uses the Google Speech-to-Text API to convert the audio data into text. The input is an audio file, and the output is text data. Next, it uses OpenCV and TensorFlow to extract facial features from the facial expression image and input them into a machine learning model. The input is facial expression data, and the output is numerical data representing the emotional state.

[0646] Step 4:

[0647] The server generates stress management tips and customer service advice based on the analysis results. A machine learning algorithm analyzes the numerical emotional state data and derives optimal advice. The input is the numerical analysis results, and the output is a specific advice message.

[0648] Step 5:

[0649] The server generates an advice message and sends it to the terminal using the network request library. The input is the advice message, and the output is the HTTP response. The terminal receives this HTTP response and analyzes the data.

[0650] Step 6:

[0651] The device displays the analysis results and advice messages in real time on the smart glasses' display. The input is the advice message obtained from the HTTP response, and the output is the text displayed in the user's field of view. Specifically, a message such as "It appears the customer is interested. Let's explain the product in more detail" is displayed on the display.

[0652] Step 7:

[0653] The server stores daily emotional state data and performs long-term tracking. The input is historical analysis data, and the output is the analysis of long-term trends and patterns. Based on this, customized advice is generated and provided to the user.

[0654] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0655] This system combines an emotion engine that recognizes the user's emotions, captures the user's voice and facial expressions in real time, and sends the data to a server for analysis to estimate the user's emotional state and propose appropriate stress management. It is also possible to track daily emotional state data and provide long-term health support.

[0656] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0657] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. Specifically, the emotion engine extracts tone and rhythm from the voice data and analyzes facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data to infer the user's emotional state.

[0658] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and if necessary, adds referral information to specialists (e.g., hospitals or counseling services). These suggestions and analysis results are sent from the server to the device.

[0659] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[0660] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0661] This system recognizes and supports the user's emotional state through collaboration between the user, device, server, and emotion engine. This allows for effective daily stress management and long-term health management. By clarifying the specific operational flow, the quality of support provided to the user is improved, and appropriate health management is achieved.

[0662] The processing flow will be explained below.

[0663] Step 1:

[0664] The user launches the app and allows it to use the camera and microphone. The device captures the user's facial expressions and voice in real time.

[0665] Step 2:

[0666] The device temporarily stores the captured audio and video data, which is then converted into a format (e.g., JSON, XML) for transmission to the emotion engine.

[0667] Step 3:

[0668] The terminal transmits formatted audio and video data to the server.

[0669] Step 4:

[0670] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. For example, it extracts tone and rhythm from the voice data and identifies facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[0671] Step 5:

[0672] The server receives the analysis results from the emotion engine and identifies the user's emotional state (e.g., "I feel stressed"). The server then organizes the analysis results and generates appropriate stress management tips and actions for the user.

[0673] Step 6:

[0674] The server collects referral information for professionals (e.g., hospitals or counseling services) as needed and adds it to the recommendations.

[0675] Step 7:

[0676] The server transmits the generated proposal content and analysis results to the terminal.

[0677] Step 8:

[0678] The device receives the suggestions and analysis results from the server and displays them to the user, such as messages like "Try breathing slowly" or "Why not try using a nearby counseling service?"

[0679] Step 9:

[0680] The system tracks users' daily emotional state data and stores it on a server, which then organizes the data for each day along with a timestamp and stores it in a database.

[0681] Step 10:

[0682] At regular intervals (e.g., monthly), the server aggregates and analyzes the stored emotional state data. The server identifies trends and patterns in the data.

[0683] Step 11:

[0684] The server generates customized advice based on the analysis results, such as "You seem to be feeling particularly stressed over the weekend, so make some plans to relax."

[0685] Step 12:

[0686] The server transmits the generated customization advice to the terminal.

[0687] Step 13:

[0688] The device receives customized advice from the server and displays it to the user, such as "We recommend you try some ways to relax on the weekend."

[0689] In this way, the user, the terminal, the server, and the emotion engine can work together to recognize the user's emotional state in real time and provide health support through appropriate suggestions and long-term analysis.

[0690] Example 2

[0691] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0692] In modern society, users often experience a lot of stress in their daily lives, but they have few opportunities to receive appropriate stress management techniques or expert support. Furthermore, there is a lack of systems that can accurately recognize a user's emotional state and provide specific advice based on that recognition. To address this issue, a system is needed that can capture and analyze a user's emotional state in real time and provide appropriate suggestions.

[0693] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, means for suggesting stress management tips and actions to the user based on the analysis results, means for feeding back the suggestions and analysis results to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, means for generating customized advice based on these analysis results and providing it to the user, means for temporarily saving the captured data in the terminal, and means for the user to select whether to accept the suggestions. This allows the user's emotional state to be accurately recognized, enabling appropriate stress management and expert support.

[0694] "Voice" refers to the user's speaking voice, which is captured as data for analyzing emotional state.

[0695] "Facial expressions" refer to the movements that show emotions on a user's face, and are data that are captured in real time to infer emotional states.

[0696] "Real-time" refers to processing and analysis being carried out in response to ongoing events or phenomena at the exact moment they occur.

[0697] "Capture" refers to taking in data such as audio and video, and is a means of obtaining the input information necessary to recognize the user's emotional state.

[0698] "Server" refers to a central processing unit that receives data sent by users and performs analysis and proposal generation.

[0699] "Analysis" refers to the process of examining acquired data in detail to find specific information or patterns.

[0700] "Emotional state" refers to the emotions a user feels at a particular moment, and analyzing this can help understand their stress level or happiness.

[0701] "Inference" means to make a deduction about an event or situation based on information obtained.

[0702] "Stress management tips and actions" refers to specific advice and suggested actions to help users reduce stress and maintain a better mental state.

[0703] "Feedback" refers to informing the user of the analysis results and suggestions, and serves as information to improve the user's behavior.

[0704] "Tracking" refers to the process of continuously monitoring and recording a user's emotional state.

[0705] "Customized advice" refers to suggestions or advice that are tailored to a particular user based on that individual user's emotional state data.

[0706] "Temporary storage" refers to the process of holding data on a device for a short period of time in order to send it to a server at a later time.

[0707] "Selection" refers to the action of a user deciding "yes" or "no" to a presented option or suggestion.

[0708] This invention is a system for recognizing a user's emotions and suggesting stress management. This system is mainly composed of a user, a terminal, and a server.

[0709] First, the user launches the application and allows the use of the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. Specifically, the device's camera (e.g., the front camera of a smartphone) and microphone are used. This video and audio data is temporarily stored on the device and then sent to the server. Appropriate encryption technology (e.g., SSL) is used for transmission.

[0710] The server sends the received data to the emotion engine, which then analyzes it using a voice recognition algorithm (e.g., a general voice recognition API) and a facial expression analysis algorithm (e.g., a general facial expression analysis API). Specifically, it extracts tone and rhythm from the voice data and facial features (e.g., smile, sadness, anger) from the facial expression data. Based on the analysis results, it infers the user's emotional state.

[0711] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. Specific examples include suggestions such as "Take a deep breath" or "Consult a specialist." Referral information for specialists may also be added. These suggestions and analysis results are sent from the server to the device.

[0712] The device displays the received suggestions and analysis results to the user. If the user's emotional state indicates stress, messages such as "Take slow, deep breaths" or "Why not seek out a nearby counseling service?" are displayed. The user can choose whether to accept the suggestions.

[0713] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. This data can be analyzed periodically to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend that you make plans to relax."

[0714] An example of a prompt sentence might be, "If the user is feeling anxious about tomorrow's presentation, please suggest an appropriate way for them to relax."

[0715] This system supports daily health management by recognizing the user's emotions in real time and providing appropriate stress management and expert support. By clarifying the specific flow of operations, the quality of support provided to users can be improved and appropriate health management can be achieved.

[0716] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0717] Step 1:

[0718] The user launches the app.

[0719] Input: A user taps an app icon on their smartphone or tablet.

[0720] Action: The application starts and the initial screen is displayed.

[0721] Output: A dialog will appear requesting permission to use the camera and microphone.

[0722] Step 2:

[0723] The user allows use of the camera and microphone.

[0724] Input: The user taps the "Allow" button in the dialog.

[0725] What it does: The device gets access to the camera and microphone.

[0726] Output: Camera and microphone are allowed and ready for real-time capture.

[0727] Step 3:

[0728] The device captures the user's facial expressions and voice in real time.

[0729] Input: Video and audio data from authorized cameras and microphones.

[0730] What it does: Periodically captures video frames using the device's camera and audio samples using the device's microphone.

[0731] Output: The captured video and audio data is temporarily saved.

[0732] Step 4:

[0733] Temporarily saves audio and video data captured by the device.

[0734] Input: Real-time captured video and audio data.

[0735] What it does: Stores data in the device's temporary memory.

[0736] Output: Stored video and audio data.

[0737] Step 5:

[0738] The device sends the saved data to the server.

[0739] Input: Video and audio data stored in temporary memory.

[0740] How it works: Data is sent over the internet to a server and encrypted (e.g. SSL) technology is used to ensure secure communication.

[0741] Output: The data sent to the server.

[0742] Step 6:

[0743] The server receives the data and sends it to the emotion engine.

[0744] Input: Video and audio data sent from the device.

[0745] How it works: The server receives the data and converts the data format to pass it to the emotion engine.

[0746] Output: The emotion engine receives the data for analysis.

[0747] Step 7:

[0748] The emotion engine analyzes voice and facial expression data.

[0749] Input: Audio and video data received from the server.

[0750] How it works: Speech recognition algorithms extract tone and rhythm, and facial expression analysis algorithms analyze facial features (e.g., smiling, sad, angry).

[0751] Output: Analysis results showing the user's emotional state.

[0752] Step 8:

[0753] The server generates stress management suggestions based on the analysis results.

[0754] Input: Analysis results from the emotion engine.

[0755] How it works: Based on the analysis, it determines appropriate stress management tips and actions, and adds expert referrals as needed.

[0756] Output: The specific recommendations generated.

[0757] Step 9:

[0758] The server sends the proposals and analysis results to the device.

[0759] Input: Server-generated suggestions and analysis results.

[0760] What it does: Sends data to a device. The transmission is encrypted.

[0761] Output: Suggestions and analysis results sent to your device.

[0762] Step 10:

[0763] The device displays the suggestions and analysis results to the user.

[0764] Input: Proposal content and analysis results received from the server.

[0765] What it does: Analyzes the data and displays it in a user-friendly format, such as a message like "Take slow, deep breaths."

[0766] Output: Suggestions and analysis results displayed to the user.

[0767] Step 11:

[0768] The user chooses whether to accept the suggestion.

[0769] Input: The suggestions presented on the terminal.

[0770] Action: The user responds to a suggestion with a "yes" or "no" response.

[0771] Output: The user's selection.

[0772] Step 12:

[0773] The server stores the emotional state data in a database for long-term tracking.

[0774] Input: Daily emotional state data and user selection results.

[0775] How it works: The server stores the data in a database and manages it for long-term tracking.

[0776] Output: Saved emotional state data.

[0777] Step 13:

[0778] The server analyzes the data at regular intervals and generates customized advice.

[0779] Input: Long-term stored emotional state data.

[0780] How it works: Analyzes data to identify trends and patterns, and then generates personalized recommendations based on those trends.

[0781] Output: The generated customized advice.

[0782] (Application example 2)

[0783] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0784] Conventional stress management systems have the problem that they cannot provide feedback or suggestions based on the user's unique emotional state, and their long-term health management is limited in scope. Furthermore, they lack a means to obtain immediate and useful instructions for action in real-time face-to-face communication, making it difficult to improve the quality of customer service in hospitality and service industries.

[0785] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expression in real time and analyzing this data, means for suggesting stress management tips and actions to the user based on the analysis results, and means for presenting real-time behavioral instructions to the user who is face-to-face with others using a wearable device that displays feedback based on the real-time emotion analysis results. This allows the user to accurately understand their own emotional state and perform appropriate stress management, and further improves the quality of customer service in physical stores, etc.

[0786] "Means for capturing a user's voice and facial expressions in real time" refers to devices and software for acquiring and recording voice data and facial expression data emitted by a user in real time.

[0787] "Means for transmitting data to a server" refers to a communication device or protocol for transmitting the captured voice data and facial expression data to a server via a communication network such as the Internet.

[0788] "Means for analyzing data and inferring the user's emotional state" refers to software or algorithms that analyze received voice and facial expression data and use machine learning algorithms to infer the user's emotional state.

[0789] "Means for suggesting stress management tips and actions" refers to a system for generating messages and notifications that suggest appropriate stress management methods and actions to users based on the analysis results.

[0790] A "wearable device that displays feedback" is a device that displays the results of emotion analysis and suggested responses, and refers to a display device that can be worn by the user, such as smart glasses.

[0791] "Means for storing and tracking a user's daily emotional state data and analyzing trends and patterns" refers to a system that stores a user's emotional data over a long period of time and analyzes it to identify changes and patterns in emotions.

[0792] "Means for generating and providing customized advice to a user" refers to a system that generates advice tailored to a user's specific needs based on tracking data and analysis results and transmits that information to the user.

[0793] "Means for presenting real-time behavioral instructions to a user who is face-to-face with another person" refers to a system that instantly suggests actions and responses that are tailored to the person the user is face-to-face with based on the results of real-time emotion analysis.

[0794] In order to implement the present invention, it is necessary to configure the system as follows.

[0795] Capturing the user's voice and facial expressions

[0796] The user uses a wearable device such as smart glasses. This device is equipped with a camera and a microphone to capture the user's facial expressions and voice in real time. For example, rather than a specific brand name device, a device equipped with a general "high-resolution camera" and "high-sensitivity microphone" is used. This data is temporarily stored in the user's device and then sent to a server.

[0797] Sending data to the server for analysis

[0798] The voice and facial expression data captured by the device is sent to a server via the Internet. The server is a standard server equipped with a high-performance processor and large memory capacity. The received data is then processed by a specialized analysis engine, known as an "emotion engine," to infer the user's emotional state. This emotion engine uses machine learning algorithms to extract tone and rhythm from the voice data and analyze facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[0799] Stress management suggestions and feedback

[0800] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. These suggestions might be, for example, "Try breathing slowly" or "Why not consult a specialist?" The generated suggestions are sent to the wearable device and displayed to the user. Real-time action instructions may also be displayed depending on the person the user is facing. For example, a store clerk who is dealing with customers might be instructed to "Smile when serving customers."

[0801] Long-term emotional tracking and personalized advice

[0802] The server stores daily emotional state data in a database and tracks it over the long term. It periodically analyzes this data to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to users. For example, specific advice might be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0803] Hardware and software used

[0804] Wearable devices: Smart glasses equipped with a high-resolution camera, microphone, and display.

[0805] Server: A typical server device equipped with a high-performance processor and large memory capacity.

[0806] Software: OpenCV (camera image capture and processing), Dlib (face recognition and facial feature point acquisition), requests (emotion data transmission to server), gTTS (text-to-speech conversion), playsound (audio playback).

[0807] Specific examples

[0808] For example, in a customer service scenario in a brick-and-mortar store, if a customer enters the store and looks a little unhappy, the store clerk's smart glasses will display a message saying, "The customer seems a little nervous. Please try to greet them with a smile." The system will also track the user's daily emotional data and provide customized advice, such as, "You tend to feel stressed during the week, so we recommend you spend more time on your hobbies on the weekends."

[0809] Prompt Sentence Examples

[0810] "The customer is a little grumpy. Try to smile."

[0811] This system configuration makes it possible to accurately grasp the user's emotional state and provide appropriate stress management and face-to-face support.

[0812] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0813] Step 1:

[0814] Facial expression and voice capture

[0815] The device (smart glasses) captures the user's facial expressions and voice in real time. Specifically, the device's built-in camera captures facial expression data, and a high-sensitivity microphone captures voice data. These data are temporarily stored in the device.

[0816] Input: Trigger to start capture (e.g., app launch)

[0817] Data processing: Camera footage is captured in real time, facial recognition is performed, and facial expression data is extracted. Audio data is also captured in real time and noise is removed.

[0818] Output: A set of facial expression and speech data

[0819] For example, when a user puts on glasses and points their face towards the camera, facial recognition takes place.

[0820] Step 2:

[0821] Sending data to the server

[0822] The device transmits the temporarily stored facial expression data and voice data to a server via the Internet using a predetermined protocol (e.g., HTTPS).

[0823] Input: A set of facial expression and speech data

[0824] Data processing: Convert facial expression data and voice data into JSON format

[0825] Output: Send data to the server

[0826] Example: The device sends data collected in real time to the server.

[0827] Step 3:

[0828] Emotion analysis

[0829] The server analyzes the received data and infers the user's emotional state. Specifically, the emotion engine uses machine learning algorithms to analyze voice tone, facial feature points, etc.

[0830] Input: Facial expression data and voice data sent to the server

[0831] Data processing: Extracting tone and rhythm from voice data, analyzing emotional features (e.g., smile, anger) from facial data

[0832] Output: Estimated user emotional state (e.g., happy, angry, sad)

[0833] Example: The server analyzes voice tone and facial expressions to guess whether the user is "happy" or "angry."

[0834] Step 4:

[0835] Stress management suggestions and feedback

[0836] The server generates appropriate stress management tips and actions based on the user's emotional state, and the generated suggestions are sent to the wearable device and displayed to the user, along with real-time behavioral instructions based on the person the user is facing.

[0837] Input: User's emotional state

[0838] Data processing: Generate stress management tips and actions (e.g., "Take a deep breath" or "Consult a professional")

[0839] Output: Suggestions and real-time action instructions displayed on a wearable device

[0840] For example, if the user is feeling stressed, the message "Try breathing slowly" will be displayed. When serving customers face-to-face, the message "Try to smile when serving customers" will be displayed.

[0841] Step 5:

[0842] Long-term sentiment tracking and customized advice

[0843] The server stores daily emotional state data in a database and analyzes it. Based on the analysis results, it identifies long-term trends and patterns and generates customized advice, which is then provided to the user at regular intervals.

[0844] Input: Daily emotional state data

[0845] Data processing: analyzing trends and patterns and generating customized advice

[0846] Output: Providing regular, customized advice to users

[0847] Example: A user who tends to get stressed on weekends is given the advice, "We recommend that you make plans to relax on the weekend."

[0848] Through these steps, the user's emotional state is grasped in real time, providing appropriate feedback and long-term stress management.

[0849] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0850] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0851] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0852] [Third embodiment]

[0853] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0854] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0855] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0856] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0857] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0858] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0859] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0860] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0861] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0862] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0863] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0864] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0865] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[0866] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0867] The server then analyzes the received data using machine learning algorithms, extracting tone and rhythm from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data, allowing the server to infer the user's emotional state.

[0868] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and adds referral information to specialists (e.g., hospitals or counseling services) if necessary. These suggestions and analysis results are sent from the server to the device.

[0869] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[0870] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0871] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management. By clarifying the specific flow of operations, the quality of support provided to the user can be improved, and appropriate health management can be achieved.

[0872] The processing flow will be explained below.

[0873] Step 1:

[0874] The user launches the app and allows it to use the camera and microphone.

[0875] The device captures the user's voice and facial expressions in real time.

[0876] Step 2:

[0877] The device temporarily stores the captured audio and video data.

[0878] The device converts the stored data into the appropriate format (e.g., JSON, XML).

[0879] Step 3:

[0880] The terminal transmits formatted audio and video data to the server.

[0881] Step 4:

[0882] The server sends the received audio and video data to an analysis algorithm.

[0883] The server uses machine learning models to analyze the data and infer the user's emotional state.

[0884] Step 5:

[0885] The server determines the user's emotional state based on the analysis results (e.g., "I feel stressed").

[0886] The server organizes the analysis results and generates response data.

[0887] Step 6:

[0888] The server transmits the generated response data to the terminal.

[0889] Step 7:

[0890] The terminal receives the response data from the server.

[0891] The device displays the analysis results and suggestions to the user (e.g., "Try taking deep breaths to relax").

[0892] Step 8:

[0893] The server stores the user's daily emotional state data in a database.

[0894] The server organizes each day's data with a timestamp.

[0895] Step 9:

[0896] The server aggregates and analyzes the stored data at regular intervals (e.g., once a month).

[0897] The server identifies trends and patterns in the data.

[0898] Step 10:

[0899] The server generates customized advice based on the analysis results.

[0900] The server transmits response data including the customized advice content to the terminal.

[0901] Step 11:

[0902] The terminal receives the advice content from the server.

[0903] The device will display customized advice to the user (e.g., "You seem to be feeling particularly stressed over the weekend. Let's make some relaxing plans").

[0904] Example 1

[0905] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0906] In modern society, many people experience stress on a daily basis, and proper management of stress is an important issue. However, conventional stress management methods have difficulty understanding a user's emotional state in real time and providing individually tailored advice. In particular, there is a need for long-term tracking of a user's state and providing customized advice.

[0907] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0908] In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data using a machine learning algorithm and inferring the user's emotional state in the server, means for creating stress management tips and suggested actions for the user based on the analysis results, means for providing the suggestions and analysis results as feedback to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, and means for generating and providing customized advice to the user based on the analysis results. This makes it possible to grasp the user's emotional state in real time, provide individually tailored advice, and realize long-term health management.

[0909] "User's voice" refers to the sound waves generated when the user speaks, and is data that can be collected and analyzed to infer the user's emotional state.

[0910] "Facial expressions" are changes in the movement and placement of facial muscles that indicate the user's emotions and reactions, and are data that can be analyzed to determine the user's emotional state.

[0911] "Real-time capture" refers to a method of instantly collecting and processing a user's voice and facial expressions, meaning that data is obtained without delay.

[0912] "Server" refers to a remote computer system used over a network to analyze and store data and provide feedback to users.

[0913] "Transmitting means" refers to the technical methods and devices for transferring collected user voice and facial expression data from the terminal to the server.

[0914] A "machine learning algorithm" refers to a computational method that trains a model based on large amounts of data and makes appropriate predictions and judgments even for unknown data.

[0915] "Emotional state" refers to the emotional state a user is feeling at a particular moment, including joy, anger, sadness, stress, etc.

[0916] "Stress management tips and action suggestions" means specific advice or recommended actions to help users reduce stress.

[0917] "Storage and Tracking" refers to the process of recording a user's daily emotional state data over time and tracking changes and trends.

[0918] "Customized Advice" refers to suggestions or instructions that are tailored to a specific user based on that user's data.

[0919] "Feedback means" refers to technical methods or devices for directly notifying users of analysis results and suggestions.

[0920] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[0921] First, the user launches the application and allows the use of the camera and microphone. The device uses the built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[0922] Specifically, the device's built-in microphone and audio recording software can be used to capture and transmit voice data, and the device's built-in camera and image processing software can be used to capture facial expression data. For example, a smartphone's default camera app and audio recording app can be used.

[0923] The server then analyzes the received data using machine learning algorithms, specifically extracting tone and rate from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data. This analysis can be performed using machine learning libraries such as TensorFlow or PyTorch. This allows the server to infer the user's emotional state.

[0924] Once the analysis results are obtained, the server will suggest appropriate stress management tips and actions based on the results. For example, it can generate messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" The server will then provide the user with the option to accept or decline the suggestion. The suggestion and analysis results are then sent from the server to the device.

[0925] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., one month), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[0926] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management.

[0927] Specific examples

[0928] Hardware and software used

[0929] Camera and microphone: Built-in or connected to the device (smartphone or PC)

[0930] Machine learning libraries: TensorFlow, PyTorch

[0931] Specific scenarios

[0932] 1. The user launches the app on their smartphone and allows it to use the camera and microphone.

[0933] Prompt example

[0934] "Do you want to allow use of your camera and microphone?"

[0935] Tap "OK" to ask for permission.

[0936] 2. The device captures the user's facial expressions and voice.

[0937] Prompt example

[0938] Facial expressions are being recognized and audio is being recorded.

[0939] 3. The server analyzes the data and infers the user's emotional state.

[0940] Prompt example

[0941] The user's voice tone is calm, but their facial expression shows signs of stress.

[0942] 4. Generate appropriate stress management recommendations and send them to the device, including expert referral information.

[0943] Prompt example

[0944] "Try taking slower breaths" "Why not try using a counselling service near you?"

[0945] 5. The device displays the analysis results and suggestions to the user, who then makes a selection.

[0946] Prompt example

[0947] Select a suggestion:

[0948] Regulate your breathing

[0949] Find counseling services

[0950] 6. The server provides long-term tracking and customized advice.

[0951] Prompt example

[0952] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[0953]

[0954] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0955] Step 1:

[0956] User starts and authorizes the system

[0957] The user launches the app and allows it to use the camera and microphone. When the user taps the app icon on their smartphone, the app launches and a pop-up appears requesting permission to access the camera and microphone. The user approves the access by tapping the "Allow" button.

[0958] Input: User actions (launching an app, approving permissions)

[0959] Output: Camera and microphone permissions are set

[0960] Specific behavior:

[0961] "Do you want to allow use of your camera and microphone?"

[0962] Tap "OK" to ask for permission.

[0963] Step 2:

[0964] Data capture and transmission

[0965] The device uses a built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. When the user faces the camera and speaks into the microphone, the device collects audio and video data. The data is temporarily stored on the device and then sent to a server.

[0966] Input: Camera and microphone data (audio, video)

[0967] Output: Temporarily stored audio and video data, data sent to the server

[0968] Specific behavior:

[0969] Facial expressions are being recognized and audio is being recorded.

[0970] Step 3:

[0971] Data analysis by server

[0972] The server uses machine learning algorithms to analyze the received voice and facial expression data. Specifically, it extracts features such as tone, pitch, and speed from the voice data, and analyzes facial muscle movements and changes from the facial expression data. The server then integrates these features and inputs them into a model that infers the user's emotional state.

[0973] Input: Audio and video data sent to the server

[0974] Output: Analysis results (inferred emotional state)

[0975] Specific behavior:

[0976] The user's voice tone is calm, but their facial expression shows signs of stress.

[0977] Step 4:

[0978] Generate and submit stress management suggestions

[0979] The server generates appropriate stress management recommendations based on the analysis results, including referral information for experts if necessary. The generated recommendations and analysis results are sent from the server to the device. The recommendations include specific behavioral advice and expert contact information.

[0980] Input: Analysis results

[0981] Output: Stress management suggestions, expert referrals

[0982] Specific behavior:

[0983] "Try taking slower breaths" "Why not try using a counselling service near you?"

[0984] Step 5:

[0985] Displaying results to the user and making selections

[0986] The device displays the received analysis results and suggestions to the user, who taps a button to choose whether to accept the suggestions or not. The device then executes an action according to the user's choice.

[0987] Input: Analysis results and suggestions sent from the server

[0988] Output: User's choice

[0989] Specific behavior:

[0990] Select a suggestion:

[0991] Regulate your breathing

[0992] Find counseling services

[0993] Step 6:

[0994] Long-term tracking and personalized advice

[0995] The server stores daily emotional state data and tracks it over the long term. Every certain period (e.g., one month), the accumulated data is analyzed to identify trends and patterns. The server generates customized advice based on the results of this long-term data analysis and sends it back to the device.

[0996] Input: Daily emotional state data

[0997] Output: Customized advice

[0998] Specific behavior:

[0999] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[1000] (Application example 1)

[1001] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1002] Conventional emotion analysis systems have been designed primarily for the purpose of personal stress management and health support, and have not been used to improve customer service in brick-and-mortar stores. As a result, there has been a lack of systems that can provide real-time customer service advice based on the customer's emotional state. Furthermore, there are limited ways for customer service staff in brick-and-mortar stores to properly grasp the customer's emotional state, making it difficult to provide personalized service based on that information.

[1003] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1004] In this invention, the server includes means for capturing the user's voice and facial expression in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, and means for suggesting stress management tips and actions to the user based on the analysis results. This makes it possible to use a device that captures the user's facial expression and voice in a physical store and provide customer service advice in real time based on the analysis results.

[1005] A "user" is a subject who uses the system and whose voice and facial expressions are captured.

[1006] "Voice" refers to data of the voice uttered by the user, and is an information source for inferring the emotional state by analyzing this data.

[1007] "Facial expressions" refer to the movements and changes of the user's facial muscles, and are visual data used to infer emotional states.

[1008] "Real-time capture" refers to a means of obtaining voice and facial expression data instantly, without delay.

[1009] A "server" is a computer system that receives and analyzes the captured data.

[1010] "Analysis" refers to the process of processing voice and facial expression data using machine learning algorithms to infer emotional states.

[1011] "Emotional state" refers to the emotions and psychological state that a user is feeling at that moment.

[1012] "Suggestions" refers to advice or action plans provided to users based on the results of sentiment analysis.

[1013] "Stress management" is the process of suggesting methods and actions to reduce the stress a user feels.

[1014] "Feedback" refers to the act of communicating analysis results and suggestions to users.

[1015] "Preservation" refers to the long-term storage of captured data and analysis results.

[1016] "Tracking" is the process of continuously tracking a user's daily emotional state data and recording patterns and trends.

[1017] "Customized advice" refers to recommendations that are individually optimized based on user-specific data.

[1018] "Brick and Mortar Store" means a business establishment that offers goods and services at a physical location.

[1019] "Device" generally refers to the hardware used to capture voice and facial expressions.

[1020] "Customer service advice" refers to advice on how to deal with customers that is provided to customer service staff based on the analysis results.

[1021] This invention configures a system that captures a user's voice and facial expressions in real time and analyzes their emotional state, with the aim of utilizing this system to improve customer service in brick-and-mortar stores.

[1022] 1. System Program Overview

[1023] Server program

[1024] Capture and data transmission (terminal):

[1025] The device (e.g., smart glasses) captures the user's voice and facial expressions in real time, temporarily stores them locally, and then transmits them to the server using a network request library.

[1026] Data analysis (server):

[1027] The server then analyzes the received data using machine learning algorithms, converting the voice data into text using the Google Speech-to-Text API and analyzing the facial expression data using OpenCV and TensorFlow, thereby inferring the user's emotional state.

[1028] Proposal generation (server):

[1029] Generate stress management tips and customer service advice based on emotional state, including advice on how to reduce stress and how to respond appropriately.

[1030] Real-time display (terminal):

[1031] The analysis results and suggestions are then fed back to the device via the network and displayed on the smart glasses screen.

[1032] Data Storage and Tracking (Server):

[1033] It continuously stores data on the user's daily emotional state and analyzes long-term trends and patterns to generate and deliver customized advice to the user.

[1034] 2. Hardware and software used

[1035] Hardware:

[1036] Smart glasses (e.g., Google Glass, Vuzix Blade)

[1037] Server (e.g. AWS EC2, Google Cloud Platform)

[1038] software:

[1039] Image capture library (e.g. OpenCV)

[1040] Speech recognition library (e.g. Google Speech-to-Text)

[1041] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1042] Network request libraries (e.g., Requests)

[1043] 3. Data processing and calculation

[1044] Processing the captured data:

[1045] Voice and facial expression data captured on the device is first temporarily stored and then sent to a server using the Requests library, where it is fed into a machine learning model to analyze voice tones and extract facial features to infer emotional states.

[1046] Proposal generation of analysis results:

[1047] Based on the analysis results, the system generates specific stress management tips for users and real-time advice for customer service staff, such as "The customer is smiling, so try to be friendly" or "The customer looks a little tired, so it would be good to speak to them in a calm tone."

[1048] Specific examples

[1049] When a customer service staff member wears the smart glasses in a brick-and-mortar store, the customer's facial expressions and voice are instantly captured and sent to a server. The server analyzes the data in real time and infers the customer's emotional state. As a result, the smart glasses display will say, "The customer appears interested. Let me explain the product in more detail."

[1050] Prompt Sentence Examples

[1051] "Please tell me about building a system that can infer emotions from a customer's facial expression and advise them on the best way to serve them."

[1052] In this way, by linking users, devices, and servers, it is possible to achieve daily stress management, long-term health management, and even improved customer service in physical stores.

[1053] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1054] Step 1:

[1055] The device (smart glasses) captures the user's voice and facial expressions in real time. Specifically, it uses a camera to capture facial expression data and a microphone to collect audio data. The input data are raw facial expression images and audio files. These data are stored in the device's temporary memory.

[1056] Step 2:

[1057] The device sends the captured data to the server using a network request library (e.g., Requests). The input facial expression images and audio files are converted into data packets that are sent to the server over the network. The output is an HTTP request containing these data.

[1058] Step 3:

[1059] The server analyzes the received data. First, it uses the Google Speech-to-Text API to convert the audio data into text. The input is an audio file, and the output is text data. Next, it uses OpenCV and TensorFlow to extract facial features from the facial expression image and input them into a machine learning model. The input is facial expression data, and the output is numerical data representing the emotional state.

[1060] Step 4:

[1061] The server generates stress management tips and customer service advice based on the analysis results. A machine learning algorithm analyzes the numerical emotional state data and derives optimal advice. The input is the numerical analysis results, and the output is a specific advice message.

[1062] Step 5:

[1063] The server generates an advice message and sends it to the terminal using the network request library. The input is the advice message, and the output is the HTTP response. The terminal receives this HTTP response and analyzes the data.

[1064] Step 6:

[1065] The device displays the analysis results and advice messages in real time on the smart glasses' display. The input is the advice message obtained from the HTTP response, and the output is the text displayed in the user's field of view. Specifically, a message such as "It appears the customer is interested. Let's explain the product in more detail" is displayed on the display.

[1066] Step 7:

[1067] The server stores daily emotional state data and performs long-term tracking. The input is historical analysis data, and the output is the analysis of long-term trends and patterns. Based on this, customized advice is generated and provided to the user.

[1068] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1069] This system combines an emotion engine that recognizes the user's emotions, captures the user's voice and facial expressions in real time, and sends the data to a server for analysis to estimate the user's emotional state and propose appropriate stress management. It is also possible to track daily emotional state data and provide long-term health support.

[1070] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[1071] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. Specifically, the emotion engine extracts tone and rhythm from the voice data and analyzes facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data to infer the user's emotional state.

[1072] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and if necessary, adds referral information to specialists (e.g., hospitals or counseling services). These suggestions and analysis results are sent from the server to the device.

[1073] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[1074] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[1075] This system recognizes and supports the user's emotional state through collaboration between the user, device, server, and emotion engine. This allows for effective daily stress management and long-term health management. By clarifying the specific operational flow, the quality of support provided to the user is improved, and appropriate health management is achieved.

[1076] The processing flow will be explained below.

[1077] Step 1:

[1078] The user launches the app and allows it to use the camera and microphone. The device captures the user's facial expressions and voice in real time.

[1079] Step 2:

[1080] The device temporarily stores the captured audio and video data, which is then converted into a format (e.g., JSON, XML) for transmission to the emotion engine.

[1081] Step 3:

[1082] The terminal transmits formatted audio and video data to the server.

[1083] Step 4:

[1084] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. For example, it extracts tone and rhythm from the voice data and identifies facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[1085] Step 5:

[1086] The server receives the analysis results from the emotion engine and identifies the user's emotional state (e.g., "I feel stressed"). The server then organizes the analysis results and generates appropriate stress management tips and actions for the user.

[1087] Step 6:

[1088] The server collects referral information for professionals (e.g., hospitals or counseling services) as needed and adds it to the recommendations.

[1089] Step 7:

[1090] The server transmits the generated proposal content and analysis results to the terminal.

[1091] Step 8:

[1092] The device receives the suggestions and analysis results from the server and displays them to the user, such as messages like "Try breathing slowly" or "Why not try using a nearby counseling service?"

[1093] Step 9:

[1094] The system tracks users' daily emotional state data and stores it on a server, which then organizes the data for each day along with a timestamp and stores it in a database.

[1095] Step 10:

[1096] At regular intervals (e.g., monthly), the server aggregates and analyzes the stored emotional state data. The server identifies trends and patterns in the data.

[1097] Step 11:

[1098] The server generates customized advice based on the analysis results, such as "You seem to be feeling particularly stressed over the weekend, so make some plans to relax."

[1099] Step 12:

[1100] The server transmits the generated customization advice to the terminal.

[1101] Step 13:

[1102] The device receives customized advice from the server and displays it to the user, such as "We recommend you try some ways to relax on the weekend."

[1103] In this way, the user, the terminal, the server, and the emotion engine can work together to recognize the user's emotional state in real time and provide health support through appropriate suggestions and long-term analysis.

[1104] Example 2

[1105] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1106] In modern society, users often experience a lot of stress in their daily lives, but they have few opportunities to receive appropriate stress management techniques or expert support. Furthermore, there is a lack of systems that can accurately recognize a user's emotional state and provide specific advice based on that recognition. To address this issue, a system is needed that can capture and analyze a user's emotional state in real time and provide appropriate suggestions.

[1107] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, means for suggesting stress management tips and actions to the user based on the analysis results, means for feeding back the suggestions and analysis results to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, means for generating customized advice based on these analysis results and providing it to the user, means for temporarily saving the captured data in the terminal, and means for the user to select whether to accept the suggestions. This allows the user's emotional state to be accurately recognized, enabling appropriate stress management and expert support.

[1108] "Voice" refers to the user's speaking voice, which is captured as data for analyzing emotional state.

[1109] "Facial expressions" refer to the movements that show emotions on a user's face, and are data that are captured in real time to infer emotional states.

[1110] "Real-time" refers to processing and analysis being carried out in response to ongoing events or phenomena at the exact moment they occur.

[1111] "Capture" refers to taking in data such as audio and video, and is a means of obtaining the input information necessary to recognize the user's emotional state.

[1112] "Server" refers to a central processing unit that receives data sent by users and performs analysis and proposal generation.

[1113] "Analysis" refers to the process of examining acquired data in detail to find specific information or patterns.

[1114] "Emotional state" refers to the emotions a user feels at a particular moment, and analyzing this can help understand their stress level or happiness.

[1115] "Inference" means to make a deduction about an event or situation based on information obtained.

[1116] "Stress management tips and actions" refers to specific advice and suggested actions to help users reduce stress and maintain a better mental state.

[1117] "Feedback" refers to informing the user of the analysis results and suggestions, and serves as information to improve the user's behavior.

[1118] "Tracking" refers to the process of continuously monitoring and recording a user's emotional state.

[1119] "Customized advice" refers to suggestions or advice that are tailored to a particular user based on that individual user's emotional state data.

[1120] "Temporary storage" refers to the process of holding data on a device for a short period of time in order to send it to a server at a later time.

[1121] "Selection" refers to the action of a user deciding "yes" or "no" to a presented option or suggestion.

[1122] This invention is a system for recognizing a user's emotions and suggesting stress management. This system is mainly composed of a user, a terminal, and a server.

[1123] First, the user launches the application and allows the use of the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. Specifically, the device's camera (e.g., the front camera of a smartphone) and microphone are used. This video and audio data is temporarily stored on the device and then sent to the server. Appropriate encryption technology (e.g., SSL) is used for transmission.

[1124] The server sends the received data to the emotion engine, which then analyzes it using a voice recognition algorithm (e.g., a general voice recognition API) and a facial expression analysis algorithm (e.g., a general facial expression analysis API). Specifically, it extracts tone and rhythm from the voice data and facial features (e.g., smile, sadness, anger) from the facial expression data. Based on the analysis results, it infers the user's emotional state.

[1125] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. Specific examples include suggestions such as "Take a deep breath" or "Consult a specialist." Referral information for specialists may also be added. These suggestions and analysis results are sent from the server to the device.

[1126] The device displays the received suggestions and analysis results to the user. If the user's emotional state indicates stress, messages such as "Take slow, deep breaths" or "Why not seek out a nearby counseling service?" are displayed. The user can choose whether to accept the suggestions.

[1127] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. This data can be analyzed periodically to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend that you make plans to relax."

[1128] An example of a prompt sentence might be, "If the user is feeling anxious about tomorrow's presentation, please suggest an appropriate way for them to relax."

[1129] This system supports daily health management by recognizing the user's emotions in real time and providing appropriate stress management and expert support. By clarifying the specific flow of operations, the quality of support provided to users can be improved and appropriate health management can be achieved.

[1130] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1131] Step 1:

[1132] The user launches the app.

[1133] Input: A user taps an app icon on their smartphone or tablet.

[1134] Action: The application starts and the initial screen is displayed.

[1135] Output: A dialog will appear requesting permission to use the camera and microphone.

[1136] Step 2:

[1137] The user allows use of the camera and microphone.

[1138] Input: The user taps the "Allow" button in the dialog.

[1139] What it does: The device gets access to the camera and microphone.

[1140] Output: Camera and microphone are allowed and ready for real-time capture.

[1141] Step 3:

[1142] The device captures the user's facial expressions and voice in real time.

[1143] Input: Video and audio data from authorized cameras and microphones.

[1144] What it does: Periodically captures video frames using the device's camera and audio samples using the device's microphone.

[1145] Output: The captured video and audio data is temporarily saved.

[1146] Step 4:

[1147] Temporarily saves audio and video data captured by the device.

[1148] Input: Real-time captured video and audio data.

[1149] What it does: Stores data in the device's temporary memory.

[1150] Output: Stored video and audio data.

[1151] Step 5:

[1152] The device sends the saved data to the server.

[1153] Input: Video and audio data stored in temporary memory.

[1154] How it works: Data is sent over the internet to a server and encrypted (e.g. SSL) technology is used to ensure secure communication.

[1155] Output: The data sent to the server.

[1156] Step 6:

[1157] The server receives the data and sends it to the emotion engine.

[1158] Input: Video and audio data sent from the device.

[1159] How it works: The server receives the data and converts the data format to pass it to the emotion engine.

[1160] Output: The emotion engine receives the data for analysis.

[1161] Step 7:

[1162] The emotion engine analyzes voice and facial expression data.

[1163] Input: Audio and video data received from the server.

[1164] How it works: Speech recognition algorithms extract tone and rhythm, and facial expression analysis algorithms analyze facial features (e.g., smiling, sad, angry).

[1165] Output: Analysis results showing the user's emotional state.

[1166] Step 8:

[1167] The server generates stress management suggestions based on the analysis results.

[1168] Input: Analysis results from the emotion engine.

[1169] How it works: Based on the analysis, it determines appropriate stress management tips and actions, and adds expert referrals as needed.

[1170] Output: The specific recommendations generated.

[1171] Step 9:

[1172] The server sends the proposals and analysis results to the device.

[1173] Input: Server-generated suggestions and analysis results.

[1174] What it does: Sends data to a device. The transmission is encrypted.

[1175] Output: Suggestions and analysis results sent to your device.

[1176] Step 10:

[1177] The device displays the suggestions and analysis results to the user.

[1178] Input: Proposal content and analysis results received from the server.

[1179] What it does: Analyzes the data and displays it in a user-friendly format, such as a message like "Take slow, deep breaths."

[1180] Output: Suggestions and analysis results displayed to the user.

[1181] Step 11:

[1182] The user chooses whether to accept the suggestion.

[1183] Input: The suggestions presented on the terminal.

[1184] Action: The user responds to a suggestion with a "yes" or "no" response.

[1185] Output: The user's selection.

[1186] Step 12:

[1187] The server stores the emotional state data in a database for long-term tracking.

[1188] Input: Daily emotional state data and user selection results.

[1189] How it works: The server stores the data in a database and manages it for long-term tracking.

[1190] Output: Saved emotional state data.

[1191] Step 13:

[1192] The server analyzes the data at regular intervals and generates customized advice.

[1193] Input: Long-term stored emotional state data.

[1194] How it works: Analyzes data to identify trends and patterns, and then generates personalized recommendations based on those trends.

[1195] Output: The generated customized advice.

[1196] (Application example 2)

[1197] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1198] Conventional stress management systems have the problem that they cannot provide feedback or suggestions based on the user's unique emotional state, and their long-term health management is limited in scope. Furthermore, they lack a means to obtain immediate and useful instructions for action in real-time face-to-face communication, making it difficult to improve the quality of customer service in hospitality and service industries.

[1199] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expression in real time and analyzing this data, means for suggesting stress management tips and actions to the user based on the analysis results, and means for presenting real-time behavioral instructions to the user who is face-to-face with others using a wearable device that displays feedback based on the real-time emotion analysis results. This allows the user to accurately understand their own emotional state and perform appropriate stress management, and further improves the quality of customer service in physical stores, etc.

[1200] "Means for capturing a user's voice and facial expressions in real time" refers to devices and software for acquiring and recording voice data and facial expression data emitted by a user in real time.

[1201] "Means for transmitting data to a server" refers to a communication device or protocol for transmitting the captured voice data and facial expression data to a server via a communication network such as the Internet.

[1202] "Means for analyzing data and inferring the user's emotional state" refers to software or algorithms that analyze received voice and facial expression data and use machine learning algorithms to infer the user's emotional state.

[1203] "Means for suggesting stress management tips and actions" refers to a system for generating messages and notifications that suggest appropriate stress management methods and actions to users based on the analysis results.

[1204] A "wearable device that displays feedback" is a device that displays the results of emotion analysis and suggested responses, and refers to a display device that can be worn by the user, such as smart glasses.

[1205] "Means for storing and tracking a user's daily emotional state data and analyzing trends and patterns" refers to a system that stores a user's emotional data over a long period of time and analyzes it to identify changes and patterns in emotions.

[1206] "Means for generating and providing customized advice to a user" refers to a system that generates advice tailored to a user's specific needs based on tracking data and analysis results and transmits that information to the user.

[1207] "Means for presenting real-time behavioral instructions to a user who is face-to-face with another person" refers to a system that instantly suggests actions and responses that are tailored to the person the user is face-to-face with based on the results of real-time emotion analysis.

[1208] In order to implement the present invention, it is necessary to configure the system as follows.

[1209] Capturing the user's voice and facial expressions

[1210] The user uses a wearable device such as smart glasses. This device is equipped with a camera and a microphone to capture the user's facial expressions and voice in real time. For example, rather than a specific brand name device, a device equipped with a general "high-resolution camera" and "high-sensitivity microphone" is used. This data is temporarily stored in the user's device and then sent to a server.

[1211] Sending data to the server for analysis

[1212] The voice and facial expression data captured by the device is sent to a server via the Internet. The server is a standard server equipped with a high-performance processor and large memory capacity. The received data is then processed by a specialized analysis engine, known as an "emotion engine," to infer the user's emotional state. This emotion engine uses machine learning algorithms to extract tone and rhythm from the voice data and analyze facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[1213] Stress management suggestions and feedback

[1214] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. These suggestions might be, for example, "Try breathing slowly" or "Why not consult a specialist?" The generated suggestions are sent to the wearable device and displayed to the user. Real-time action instructions may also be displayed depending on the person the user is facing. For example, a store clerk who is dealing with customers might be instructed to "Smile when serving customers."

[1215] Long-term emotional tracking and personalized advice

[1216] The server stores daily emotional state data in a database and tracks it over the long term. It periodically analyzes this data to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to users. For example, specific advice might be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[1217] Hardware and software used

[1218] Wearable devices: Smart glasses equipped with a high-resolution camera, microphone, and display.

[1219] Server: A typical server device equipped with a high-performance processor and large memory capacity.

[1220] Software: OpenCV (camera image capture and processing), Dlib (face recognition and facial feature point acquisition), requests (emotion data transmission to server), gTTS (text-to-speech conversion), playsound (audio playback).

[1221] Specific examples

[1222] For example, in a customer service scenario in a brick-and-mortar store, if a customer enters the store and looks a little unhappy, the store clerk's smart glasses will display a message saying, "The customer seems a little nervous. Please try to greet them with a smile." The system will also track the user's daily emotional data and provide customized advice, such as, "You tend to feel stressed during the week, so we recommend you spend more time on your hobbies on the weekends."

[1223] Prompt Sentence Examples

[1224] "The customer is a little grumpy. Try to smile."

[1225] This system configuration makes it possible to accurately grasp the user's emotional state and provide appropriate stress management and face-to-face support.

[1226] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1227] Step 1:

[1228] Facial expression and voice capture

[1229] The device (smart glasses) captures the user's facial expressions and voice in real time. Specifically, the device's built-in camera captures facial expression data, and a high-sensitivity microphone captures voice data. These data are temporarily stored in the device.

[1230] Input: Trigger to start capture (e.g., app launch)

[1231] Data processing: Camera footage is captured in real time, facial recognition is performed, and facial expression data is extracted. Audio data is also captured in real time and noise is removed.

[1232] Output: A set of facial expression and speech data

[1233] For example, when a user puts on glasses and points their face towards the camera, facial recognition takes place.

[1234] Step 2:

[1235] Sending data to the server

[1236] The device transmits the temporarily stored facial expression data and voice data to a server via the Internet using a predetermined protocol (e.g., HTTPS).

[1237] Input: A set of facial expression and speech data

[1238] Data processing: Convert facial expression data and voice data into JSON format

[1239] Output: Send data to the server

[1240] Example: The device sends data collected in real time to the server.

[1241] Step 3:

[1242] Emotion analysis

[1243] The server analyzes the received data and infers the user's emotional state. Specifically, the emotion engine uses machine learning algorithms to analyze voice tone, facial feature points, etc.

[1244] Input: Facial expression data and voice data sent to the server

[1245] Data processing: Extracting tone and rhythm from voice data, analyzing emotional features (e.g., smile, anger) from facial data

[1246] Output: Estimated user emotional state (e.g., happy, angry, sad)

[1247] Example: The server analyzes voice tone and facial expressions to guess whether the user is "happy" or "angry."

[1248] Step 4:

[1249] Stress management suggestions and feedback

[1250] The server generates appropriate stress management tips and actions based on the user's emotional state, and the generated suggestions are sent to the wearable device and displayed to the user, along with real-time behavioral instructions based on the person the user is facing.

[1251] Input: User's emotional state

[1252] Data processing: Generate stress management tips and actions (e.g., "Take a deep breath" or "Consult a professional")

[1253] Output: Suggestions and real-time action instructions displayed on a wearable device

[1254] For example, if the user is feeling stressed, the message "Try breathing slowly" will be displayed. When serving customers face-to-face, the message "Try to smile when serving customers" will be displayed.

[1255] Step 5:

[1256] Long-term sentiment tracking and customized advice

[1257] The server stores daily emotional state data in a database and analyzes it. Based on the analysis results, it identifies long-term trends and patterns and generates customized advice, which is then provided to the user at regular intervals.

[1258] Input: Daily emotional state data

[1259] Data processing: analyzing trends and patterns and generating customized advice

[1260] Output: Providing regular, customized advice to users

[1261] Example: A user who tends to get stressed on weekends is given the advice, "We recommend that you make plans to relax on the weekend."

[1262] Through these steps, the user's emotional state is grasped in real time, providing appropriate feedback and long-term stress management.

[1263] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1264] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1265] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1266] [Fourth embodiment]

[1267] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1268] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1269] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1270] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1271] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1272] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1273] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1274] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1275] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1276] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1277] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1278] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1279] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1280] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[1281] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[1282] The server then analyzes the received data using machine learning algorithms, extracting tone and rhythm from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data, allowing the server to infer the user's emotional state.

[1283] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and adds referral information to specialists (e.g., hospitals or counseling services) if necessary. These suggestions and analysis results are sent from the server to the device.

[1284] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[1285] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[1286] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management. By clarifying the specific flow of operations, the quality of support provided to the user can be improved, and appropriate health management can be achieved.

[1287] The processing flow will be explained below.

[1288] Step 1:

[1289] The user launches the app and allows it to use the camera and microphone.

[1290] The device captures the user's voice and facial expressions in real time.

[1291] Step 2:

[1292] The device temporarily stores the captured audio and video data.

[1293] The device converts the stored data into the appropriate format (e.g., JSON, XML).

[1294] Step 3:

[1295] The terminal transmits formatted audio and video data to the server.

[1296] Step 4:

[1297] The server sends the received audio and video data to an analysis algorithm.

[1298] The server uses machine learning models to analyze the data and infer the user's emotional state.

[1299] Step 5:

[1300] The server determines the user's emotional state based on the analysis results (e.g., "I feel stressed").

[1301] The server organizes the analysis results and generates response data.

[1302] Step 6:

[1303] The server transmits the generated response data to the terminal.

[1304] Step 7:

[1305] The terminal receives the response data from the server.

[1306] The device displays the analysis results and suggestions to the user (e.g., "Try taking deep breaths to relax").

[1307] Step 8:

[1308] The server stores the user's daily emotional state data in a database.

[1309] The server organizes each day's data with a timestamp.

[1310] Step 9:

[1311] The server aggregates and analyzes the stored data at regular intervals (e.g., once a month).

[1312] The server identifies trends and patterns in the data.

[1313] Step 10:

[1314] The server generates customized advice based on the analysis results.

[1315] The server transmits response data including the customized advice content to the terminal.

[1316] Step 11:

[1317] The terminal receives the advice content from the server.

[1318] The device will display customized advice to the user (e.g., "You seem to be feeling particularly stressed over the weekend. Let's make some relaxing plans").

[1319] Example 1

[1320] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1321] In modern society, many people experience stress on a daily basis, and proper management of stress is an important issue. However, conventional stress management methods have difficulty understanding a user's emotional state in real time and providing individually tailored advice. In particular, there is a need for long-term tracking of a user's state and providing customized advice.

[1322] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1323] In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data using a machine learning algorithm and inferring the user's emotional state in the server, means for creating stress management tips and suggested actions for the user based on the analysis results, means for providing the suggestions and analysis results as feedback to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, and means for generating and providing customized advice to the user based on the analysis results. This makes it possible to grasp the user's emotional state in real time, provide individually tailored advice, and realize long-term health management.

[1324] "User's voice" refers to the sound waves generated when the user speaks, and is data that can be collected and analyzed to infer the user's emotional state.

[1325] "Facial expressions" are changes in the movement and placement of facial muscles that indicate the user's emotions and reactions, and are data that can be analyzed to determine the user's emotional state.

[1326] "Real-time capture" refers to a method of instantly collecting and processing a user's voice and facial expressions, meaning that data is obtained without delay.

[1327] "Server" refers to a remote computer system used over a network to analyze and store data and provide feedback to users.

[1328] "Transmitting means" refers to the technical methods and devices for transferring collected user voice and facial expression data from the terminal to the server.

[1329] A "machine learning algorithm" refers to a computational method that trains a model based on large amounts of data and makes appropriate predictions and judgments even for unknown data.

[1330] "Emotional state" refers to the emotional state a user is feeling at a particular moment, including joy, anger, sadness, stress, etc.

[1331] "Stress management tips and action suggestions" means specific advice or recommended actions to help users reduce stress.

[1332] "Storage and Tracking" refers to the process of recording a user's daily emotional state data over time and tracking changes and trends.

[1333] "Customized Advice" refers to suggestions or instructions that are tailored to a specific user based on that user's data.

[1334] "Feedback means" refers to technical methods or devices for directly notifying users of analysis results and suggestions.

[1335] This invention is a system that captures a user's voice and facial expressions in real time, sends the data to a server for analysis, and infers the user's emotional state. Furthermore, based on the analysis results, it suggests appropriate stress management and provides long-term health support by tracking the user's daily emotional state data.

[1336] First, the user launches the application and allows the use of the camera and microphone. The device uses the built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[1337] Specifically, the device's built-in microphone and audio recording software can be used to capture and transmit voice data, and the device's built-in camera and image processing software can be used to capture facial expression data. For example, a smartphone's default camera app and audio recording app can be used.

[1338] The server then analyzes the received data using machine learning algorithms, specifically extracting tone and rate from the voice data and analyzing facial features (e.g., laughter, anger, sadness, etc.) from the expression data. This analysis can be performed using machine learning libraries such as TensorFlow or PyTorch. This allows the server to infer the user's emotional state.

[1339] Once the analysis results are obtained, the server will suggest appropriate stress management tips and actions based on the results. For example, it can generate messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" The server will then provide the user with the option to accept or decline the suggestion. The suggestion and analysis results are then sent from the server to the device.

[1340] Furthermore, the server stores daily emotional state data and tracks it over the long term. At regular intervals (e.g., one month), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[1341] This system works in cooperation with the user, device, and server to recognize and support the user's emotional state, thereby enabling effective daily stress management and long-term health management.

[1342] Specific examples

[1343] Hardware and software used

[1344] Camera and microphone: Built-in or connected to the device (smartphone or PC)

[1345] Machine learning libraries: TensorFlow, PyTorch

[1346] Specific scenarios

[1347] 1. The user launches the app on their smartphone and allows it to use the camera and microphone.

[1348] Example prompts

[1349] "Do you want to allow use of your camera and microphone?"

[1350] Tap "OK" to ask for permission.

[1351] 2. The device captures the user's facial expressions and voice.

[1352] Prompt example

[1353] Facial expressions are being recognized and audio is being recorded.

[1354] 3. The server analyzes the data and infers the user's emotional state.

[1355] Prompt example

[1356] The user's voice tone is calm, but their facial expression shows signs of stress.

[1357] 4. Generate appropriate stress management recommendations and send them to the device, including expert referral information.

[1358] Prompt example

[1359] "Try taking slower breaths" "Why not try using a counselling service near you?"

[1360] 5. The device displays the analysis results and suggestions to the user, who then makes a selection.

[1361] Prompt example

[1362] Select a suggestion:

[1363] Regulate your breathing

[1364] Find counseling services

[1365] 6. The server provides long-term tracking and customized advice.

[1366] Prompt example

[1367] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[1368]

[1369] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1370] Step 1:

[1371] User starts and authorizes the system

[1372] The user launches the app and allows it to use the camera and microphone. When the user taps the app icon on their smartphone, the app launches and a pop-up appears requesting permission to access the camera and microphone. The user approves the access by tapping the "Allow" button.

[1373] Input: User actions (launching an app, approving permissions)

[1374] Output: Camera and microphone permissions are set

[1375] Specific behavior:

[1376] "Do you want to allow use of your camera and microphone?"

[1377] Tap "OK" to ask for permission.

[1378] Step 2:

[1379] Data capture and transmission

[1380] The device uses a built-in or connected camera and microphone to capture the user's facial expressions and voice in real time. When the user faces the camera and speaks into the microphone, the device collects audio and video data. The data is temporarily stored on the device and then sent to a server.

[1381] Input: Camera and microphone data (audio, video)

[1382] Output: Temporarily stored audio and video data, data sent to the server

[1383] Specific behavior:

[1384] Facial expressions are being recognized and audio is being recorded.

[1385] Step 3:

[1386] Data analysis by server

[1387] The server uses machine learning algorithms to analyze the received voice and facial expression data. Specifically, it extracts features such as tone, pitch, and speed from the voice data, and analyzes facial muscle movements and changes from the facial expression data. The server then integrates these features and inputs them into a model that infers the user's emotional state.

[1388] Input: Audio and video data sent to the server

[1389] Output: Analysis results (inferred emotional state)

[1390] Specific behavior:

[1391] The user's voice tone is calm, but their facial expression shows signs of stress.

[1392] Step 4:

[1393] Generate and submit stress management suggestions

[1394] The server generates appropriate stress management recommendations based on the analysis results, including referral information for experts if necessary. The generated recommendations and analysis results are sent from the server to the device. The recommendations include specific behavioral advice and expert contact information.

[1395] Input: Analysis results

[1396] Output: Stress management suggestions, expert referrals

[1397] Specific behavior:

[1398] "Try taking slower breaths" "Why not try using a counselling service near you?"

[1399] Step 5:

[1400] Displaying results to the user and making selections

[1401] The device displays the received analysis results and suggestions to the user, who taps a button to choose whether to accept the suggestions or not. The device then executes an action according to the user's choice.

[1402] Input: Analysis results and suggestions sent from the server

[1403] Output: User's choice

[1404] Specific behavior:

[1405] Select a suggestion:

[1406] Regulate your breathing

[1407] Find counseling services

[1408] Step 6:

[1409] Long-term tracking and personalized advice

[1410] The server stores daily emotional state data and tracks it over the long term. Every certain period (e.g., one month), the accumulated data is analyzed to identify trends and patterns. The server generates customized advice based on the results of this long-term data analysis and sends it back to the device.

[1411] Input: Daily emotional state data

[1412] Output: Customized advice

[1413] Specific behavior:

[1414] "It's easy to get stressed on the weekends, so I recommend making plans to relax."

[1415] (Application example 1)

[1416] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1417] Conventional emotion analysis systems have been designed primarily for the purpose of personal stress management and health support, and have not been used to improve customer service in brick-and-mortar stores. As a result, there has been a lack of systems that can provide real-time customer service advice based on the customer's emotional state. Furthermore, there are limited ways for customer service staff in brick-and-mortar stores to properly grasp the customer's emotional state, making it difficult to provide personalized service based on that information.

[1418] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1419] In this invention, the server includes means for capturing the user's voice and facial expression in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, and means for suggesting stress management tips and actions to the user based on the analysis results. This makes it possible to use a device that captures the user's facial expression and voice in a physical store and provide customer service advice in real time based on the analysis results.

[1420] A "user" is a subject who uses the system and whose voice and facial expressions are captured.

[1421] "Voice" refers to data of the voice uttered by the user, and is an information source for inferring the emotional state by analyzing this data.

[1422] "Facial expressions" refer to the movements and changes of the user's facial muscles, and are visual data used to infer emotional states.

[1423] "Real-time capture" refers to a means of obtaining voice and facial expression data instantly, without delay.

[1424] A "server" is a computer system that receives and analyzes the captured data.

[1425] "Analysis" refers to the process of processing voice and facial expression data using machine learning algorithms to infer emotional states.

[1426] "Emotional state" refers to the emotions and psychological state that a user is feeling at that moment.

[1427] "Suggestions" refers to advice or action plans provided to users based on the results of sentiment analysis.

[1428] "Stress management" is the process of suggesting methods and actions to reduce the stress a user feels.

[1429] "Feedback" refers to the act of communicating analysis results and suggestions to users.

[1430] "Preservation" refers to the long-term storage of captured data and analysis results.

[1431] "Tracking" is the process of continuously tracking a user's daily emotional state data and recording patterns and trends.

[1432] "Customized advice" refers to recommendations that are individually optimized based on user-specific data.

[1433] "Brick and Mortar Store" means a business establishment that offers goods and services at a physical location.

[1434] "Device" generally refers to the hardware used to capture voice and facial expressions.

[1435] "Customer service advice" refers to advice on how to deal with customers that is provided to customer service staff based on the analysis results.

[1436] This invention configures a system that captures a user's voice and facial expressions in real time and analyzes their emotional state, with the aim of utilizing this system to improve customer service in brick-and-mortar stores.

[1437] 1. System Program Overview

[1438] Server program

[1439] Capture and data transmission (terminal):

[1440] The device (e.g., smart glasses) captures the user's voice and facial expressions in real time, temporarily stores them locally, and then transmits them to the server using a network request library.

[1441] Data analysis (server):

[1442] The server then analyzes the received data using machine learning algorithms, converting the voice data into text using the Google Speech-to-Text API and analyzing the facial expression data using OpenCV and TensorFlow, thereby inferring the user's emotional state.

[1443] Proposal generation (server):

[1444] Generate stress management tips and customer service advice based on emotional state, including advice on how to reduce stress and how to respond appropriately.

[1445] Real-time display (terminal):

[1446] The analysis results and suggestions are then fed back to the device via the network and displayed on the smart glasses screen.

[1447] Data Storage and Tracking (Server):

[1448] It continuously stores data on the user's daily emotional state and analyzes long-term trends and patterns to generate and deliver customized advice to the user.

[1449] 2. Hardware and software used

[1450] Hardware:

[1451] Smart glasses (e.g., Google Glass, Vuzix Blade)

[1452] Server (e.g. AWS EC2, Google Cloud Platform)

[1453] software:

[1454] Image capture library (e.g. OpenCV)

[1455] Speech recognition library (e.g. Google Speech-to-Text)

[1456] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1457] Network request libraries (e.g., Requests)

[1458] 3. Data processing and calculation

[1459] Processing the captured data:

[1460] Voice and facial expression data captured on the device is first temporarily stored and then sent to a server using the Requests library, where it is fed into a machine learning model to analyze voice tones and extract facial features to infer emotional states.

[1461] Proposal generation of analysis results:

[1462] Based on the analysis results, the system generates specific stress management tips for users and real-time advice for customer service staff, such as "The customer is smiling, so try to be friendly" or "The customer looks a little tired, so it would be good to speak to them in a calm tone."

[1463] Specific examples

[1464] When a customer service staff member wears the smart glasses in a brick-and-mortar store, the customer's facial expressions and voice are instantly captured and sent to a server. The server analyzes the data in real time and infers the customer's emotional state. As a result, the smart glasses display will say, "The customer appears interested. Let me explain the product in more detail."

[1465] Prompt Sentence Examples

[1466] "Please tell me about building a system that can infer emotions from a customer's facial expression and advise them on the best way to serve them."

[1467] In this way, by linking users, devices, and servers, it is possible to achieve daily stress management, long-term health management, and even improved customer service in physical stores.

[1468] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1469] Step 1:

[1470] The device (smart glasses) captures the user's voice and facial expressions in real time. Specifically, it uses a camera to capture facial expression data and a microphone to collect audio data. The input data are raw facial expression images and audio files. These data are stored in the device's temporary memory.

[1471] Step 2:

[1472] The device sends the captured data to the server using a network request library (e.g., Requests). The input facial expression images and audio files are converted into data packets that are sent to the server over the network. The output is an HTTP request containing these data.

[1473] Step 3:

[1474] The server analyzes the received data. First, it uses the Google Speech-to-Text API to convert the audio data into text. The input is an audio file, and the output is text data. Next, it uses OpenCV and TensorFlow to extract facial features from the facial expression image and input them into a machine learning model. The input is facial expression data, and the output is numerical data representing the emotional state.

[1475] Step 4:

[1476] The server generates stress management tips and customer service advice based on the analysis results. A machine learning algorithm analyzes the numerical emotional state data and derives optimal advice. The input is the numerical analysis results, and the output is a specific advice message.

[1477] Step 5:

[1478] The server generates an advice message and sends it to the terminal using the network request library. The input is the advice message, and the output is the HTTP response. The terminal receives this HTTP response and analyzes the data.

[1479] Step 6:

[1480] The device displays the analysis results and advice messages in real time on the smart glasses' display. The input is the advice message obtained from the HTTP response, and the output is the text displayed in the user's field of view. Specifically, a message such as "It appears the customer is interested. Let's explain the product in more detail" is displayed on the display.

[1481] Step 7:

[1482] The server stores daily emotional state data and performs long-term tracking. The input is historical analysis data, and the output is the analysis of long-term trends and patterns. Based on this, customized advice is generated and provided to the user.

[1483] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1484] This system combines an emotion engine that recognizes the user's emotions, captures the user's voice and facial expressions in real time, and sends the data to a server for analysis to estimate the user's emotional state and propose appropriate stress management. It is also possible to track daily emotional state data and provide long-term health support.

[1485] First, the user launches the app and allows it to use the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. This audio and video data is temporarily stored on the device and then sent to the server.

[1486] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. Specifically, the emotion engine extracts tone and rhythm from the voice data and analyzes facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data to infer the user's emotional state.

[1487] Once the analysis results are obtained, the server generates appropriate stress management tips and actions based on the results, and if necessary, adds referral information to specialists (e.g., hospitals or counseling services). These suggestions and analysis results are sent from the server to the device.

[1488] The device displays the analysis results and suggestions to the user. For example, if the user feels stressed, messages such as "Try breathing slowly" or "Why not seek out a nearby counseling service?" are displayed. The user can then choose whether to accept the suggestions.

[1489] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. At regular intervals (e.g., monthly), the data is analyzed to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[1490] This system recognizes and supports the user's emotional state through collaboration between the user, device, server, and emotion engine. This allows for effective daily stress management and long-term health management. By clarifying the specific operational flow, the quality of support provided to the user is improved, and appropriate health management is achieved.

[1491] The processing flow will be explained below.

[1492] Step 1:

[1493] The user launches the app and allows it to use the camera and microphone. The device captures the user's facial expressions and voice in real time.

[1494] Step 2:

[1495] The device temporarily stores the captured audio and video data, which is then converted into a format (e.g., JSON, XML) for transmission to the emotion engine.

[1496] Step 3:

[1497] The terminal transmits formatted audio and video data to the server.

[1498] Step 4:

[1499] The server then sends the received data to the emotion engine, which uses machine learning algorithms to analyze the voice and facial expression data to recognize the user's emotional state in real time. For example, it extracts tone and rhythm from the voice data and identifies facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[1500] Step 5:

[1501] The server receives the analysis results from the emotion engine and identifies the user's emotional state (e.g., "I feel stressed"). The server then organizes the analysis results and generates appropriate stress management tips and actions for the user.

[1502] Step 6:

[1503] The server collects referral information for professionals (e.g., hospitals or counseling services) as needed and adds it to the recommendations.

[1504] Step 7:

[1505] The server transmits the generated proposal content and analysis results to the terminal.

[1506] Step 8:

[1507] The device receives the suggestions and analysis results from the server and displays them to the user, such as messages like "Try breathing slowly" or "Why not try using a nearby counseling service?"

[1508] Step 9:

[1509] The system tracks users' daily emotional state data and stores it on a server, which then organizes the data for each day along with a timestamp and stores it in a database.

[1510] Step 10:

[1511] At regular intervals (e.g., monthly), the server aggregates and analyzes the stored emotional state data. The server identifies trends and patterns in the data.

[1512] Step 11:

[1513] The server generates customized advice based on the analysis results, such as "You seem to be feeling particularly stressed over the weekend, so make some plans to relax."

[1514] Step 12:

[1515] The server transmits the generated customization advice to the terminal.

[1516] Step 13:

[1517] The device receives customized advice from the server and displays it to the user, such as "We recommend you try some ways to relax on the weekend."

[1518] In this way, the user, the terminal, the server, and the emotion engine can work together to recognize the user's emotional state in real time and provide health support through appropriate suggestions and long-term analysis.

[1519] Example 2

[1520] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1521] In modern society, users often experience a lot of stress in their daily lives, but they have few opportunities to receive appropriate stress management techniques or expert support. Furthermore, there is a lack of systems that can accurately recognize a user's emotional state and provide specific advice based on that recognition. To address this issue, a system is needed that can capture and analyze a user's emotional state in real time and provide appropriate suggestions.

[1522] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expressions in real time and transmitting this data to the server, means for analyzing the data and inferring the user's emotional state in the server, means for suggesting stress management tips and actions to the user based on the analysis results, means for feeding back the suggestions and analysis results to the user, means for saving and tracking the user's daily emotional state data and analyzing trends and patterns, means for generating customized advice based on these analysis results and providing it to the user, means for temporarily saving the captured data in the terminal, and means for the user to select whether to accept the suggestions. This allows the user's emotional state to be accurately recognized, enabling appropriate stress management and expert support.

[1523] "Voice" refers to the user's speaking voice, which is captured as data for analyzing emotional state.

[1524] "Facial expressions" refer to the movements that show emotions on a user's face, and are data that are captured in real time to infer emotional states.

[1525] "Real-time" refers to processing and analysis being carried out in response to ongoing events or phenomena at the exact moment they occur.

[1526] "Capture" refers to taking in data such as audio and video, and is a means of obtaining the input information necessary to recognize the user's emotional state.

[1527] "Server" refers to a central processing unit that receives data sent by users and performs analysis and proposal generation.

[1528] "Analysis" refers to the process of examining acquired data in detail to find specific information or patterns.

[1529] "Emotional state" refers to the emotions a user feels at a particular moment, and analyzing this can help understand their stress level or happiness.

[1530] "Inference" means to make a deduction about an event or situation based on information obtained.

[1531] "Stress management tips and actions" refers to specific advice and suggested actions to help users reduce stress and maintain a better mental state.

[1532] "Feedback" refers to informing the user of the analysis results and suggestions, and serves as information to improve the user's behavior.

[1533] "Tracking" refers to the process of continuously monitoring and recording a user's emotional state.

[1534] "Customized advice" refers to suggestions or advice that are tailored to a particular user based on that individual user's emotional state data.

[1535] "Temporary storage" refers to the process of holding data on a device for a short period of time in order to send it to a server at a later time.

[1536] "Selection" refers to the action of a user deciding "yes" or "no" to a presented option or suggestion.

[1537] This invention is a system for recognizing a user's emotions and suggesting stress management. This system is mainly composed of a user, a terminal, and a server.

[1538] First, the user launches the application and allows the use of the camera and microphone. The device uses the camera and microphone to capture the user's facial expressions and voice in real time. Specifically, the device's camera (e.g., the front camera of a smartphone) and microphone are used. This video and audio data is temporarily stored on the device and then sent to the server. Appropriate encryption technology (e.g., SSL) is used for transmission.

[1539] The server sends the received data to the emotion engine, which then analyzes it using a voice recognition algorithm (e.g., a general voice recognition API) and a facial expression analysis algorithm (e.g., a general facial expression analysis API). Specifically, it extracts tone and rhythm from the voice data and facial features (e.g., smile, sadness, anger) from the facial expression data. Based on the analysis results, it infers the user's emotional state.

[1540] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. Specific examples include suggestions such as "Take a deep breath" or "Consult a specialist." Referral information for specialists may also be added. These suggestions and analysis results are sent from the server to the device.

[1541] The device displays the received suggestions and analysis results to the user. If the user's emotional state indicates stress, messages such as "Take slow, deep breaths" or "Why not seek out a nearby counseling service?" are displayed. The user can choose whether to accept the suggestions.

[1542] Furthermore, the server stores daily emotional state data in a database and tracks it over the long term. This data can be analyzed periodically to identify trends and patterns. Based on the results of this long-term data analysis, the server generates customized advice and provides it to the user. For example, specific advice may be displayed such as, "You tend to feel stressed on the weekends, so we recommend that you make plans to relax."

[1543] An example of a prompt sentence might be, "If the user is feeling anxious about tomorrow's presentation, please suggest an appropriate way for them to relax."

[1544] This system supports daily health management by recognizing the user's emotions in real time and providing appropriate stress management and expert support. By clarifying the specific flow of operations, the quality of support provided to users can be improved and appropriate health management can be achieved.

[1545] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1546] Step 1:

[1547] The user launches the app.

[1548] Input: A user taps an app icon on their smartphone or tablet.

[1549] Action: The application starts and the initial screen is displayed.

[1550] Output: A dialog will appear requesting permission to use the camera and microphone.

[1551] Step 2:

[1552] The user allows use of the camera and microphone.

[1553] Input: The user taps the "Allow" button in the dialog.

[1554] What it does: The device gets access to the camera and microphone.

[1555] Output: Camera and microphone are allowed and ready for real-time capture.

[1556] Step 3:

[1557] The device captures the user's facial expressions and voice in real time.

[1558] Input: Video and audio data from authorized cameras and microphones.

[1559] What it does: Periodically captures video frames using the device's camera and audio samples using the device's microphone.

[1560] Output: The captured video and audio data is temporarily saved.

[1561] Step 4:

[1562] Temporarily saves audio and video data captured by the device.

[1563] Input: Real-time captured video and audio data.

[1564] What it does: Stores data in the device's temporary memory.

[1565] Output: Stored video and audio data.

[1566] Step 5:

[1567] The device sends the saved data to the server.

[1568] Input: Video and audio data stored in temporary memory.

[1569] How it works: Data is sent over the internet to a server and encrypted (e.g. SSL) technology is used to ensure secure communication.

[1570] Output: The data sent to the server.

[1571] Step 6:

[1572] The server receives the data and sends it to the emotion engine.

[1573] Input: Video and audio data sent from the device.

[1574] How it works: The server receives the data and converts the data format to pass it to the emotion engine.

[1575] Output: The emotion engine receives the data for analysis.

[1576] Step 7:

[1577] The emotion engine analyzes voice and facial expression data.

[1578] Input: Audio and video data received from the server.

[1579] How it works: Speech recognition algorithms extract tone and rhythm, and facial expression analysis algorithms analyze facial features (e.g., smiling, sad, angry).

[1580] Output: Analysis results showing the user's emotional state.

[1581] Step 8:

[1582] The server generates stress management suggestions based on the analysis results.

[1583] Input: Analysis results from the emotion engine.

[1584] How it works: Based on the analysis, it determines appropriate stress management tips and actions, and adds expert referrals as needed.

[1585] Output: The specific recommendations generated.

[1586] Step 9:

[1587] The server sends the proposals and analysis results to the device.

[1588] Input: Server-generated suggestions and analysis results.

[1589] What it does: Sends data to a device. The transmission is encrypted.

[1590] Output: Suggestions and analysis results sent to your device.

[1591] Step 10:

[1592] The device displays the suggestions and analysis results to the user.

[1593] Input: Proposal content and analysis results received from the server.

[1594] What it does: Analyzes the data and displays it in a user-friendly format, such as a message like "Take slow, deep breaths."

[1595] Output: Suggestions and analysis results displayed to the user.

[1596] Step 11:

[1597] The user chooses whether to accept the suggestion.

[1598] Input: The suggestions presented on the terminal.

[1599] Action: The user responds to a suggestion with a "yes" or "no" response.

[1600] Output: The user's selection.

[1601] Step 12:

[1602] The server stores the emotional state data in a database for long-term tracking.

[1603] Input: Daily emotional state data and user selection results.

[1604] How it works: The server stores the data in a database and manages it for long-term tracking.

[1605] Output: Saved emotional state data.

[1606] Step 13:

[1607] The server analyzes the data at regular intervals and generates customized advice.

[1608] Input: Long-term stored emotional state data.

[1609] How it works: Analyzes data to identify trends and patterns, and then generates personalized recommendations based on those trends.

[1610] Output: The generated customized advice.

[1611] (Application example 2)

[1612] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1613] Conventional stress management systems have the problem that they cannot provide feedback or suggestions based on the user's unique emotional state, and their long-term health management is limited in scope. Furthermore, they lack a means to obtain immediate and useful instructions for action in real-time face-to-face communication, making it difficult to improve the quality of customer service in hospitality and service industries.

[1614] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the user's voice and facial expression in real time and analyzing this data, means for suggesting stress management tips and actions to the user based on the analysis results, and means for presenting real-time behavioral instructions to the user who is face-to-face with others using a wearable device that displays feedback based on the real-time emotion analysis results. This allows the user to accurately understand their own emotional state and perform appropriate stress management, and further improves the quality of customer service in physical stores, etc.

[1615] "Means for capturing a user's voice and facial expressions in real time" refers to devices and software for acquiring and recording voice data and facial expression data emitted by a user in real time.

[1616] "Means for transmitting data to a server" refers to a communication device or protocol for transmitting the captured voice data and facial expression data to a server via a communication network such as the Internet.

[1617] "Means for analyzing data and inferring the user's emotional state" refers to software or algorithms that analyze received voice and facial expression data and use machine learning algorithms to infer the user's emotional state.

[1618] "Means for suggesting stress management tips and actions" refers to a system for generating messages and notifications that suggest appropriate stress management methods and actions to users based on the analysis results.

[1619] A "wearable device that displays feedback" is a device that displays the results of emotion analysis and suggested responses, and refers to a display device that can be worn by the user, such as smart glasses.

[1620] "Means for storing and tracking a user's daily emotional state data and analyzing trends and patterns" refers to a system that stores a user's emotional data over a long period of time and analyzes it to identify changes and patterns in emotions.

[1621] "Means for generating and providing customized advice to a user" refers to a system that generates advice tailored to a user's specific needs based on tracking data and analysis results and transmits that information to the user.

[1622] "Means for presenting real-time behavioral instructions to a user who is face-to-face with another person" refers to a system that instantly suggests actions and responses that are tailored to the person the user is face-to-face with based on the results of real-time emotion analysis.

[1623] In order to implement the present invention, it is necessary to configure the system as follows.

[1624] Capturing the user's voice and facial expressions

[1625] The user uses a wearable device such as smart glasses. This device is equipped with a camera and a microphone to capture the user's facial expressions and voice in real time. For example, rather than a specific brand name device, a device equipped with a general "high-resolution camera" and "high-sensitivity microphone" is used. This data is temporarily stored in the user's device and then sent to a server.

[1626] Sending data to the server for analysis

[1627] The voice and facial expression data captured by the device is sent to a server via the Internet. The server is a standard server equipped with a high-performance processor and large memory capacity. The received data is then processed by a specialized analysis engine, known as an "emotion engine," to infer the user's emotional state. This emotion engine uses machine learning algorithms to extract tone and rhythm from the voice data and analyze facial features (e.g., laughter, anger, sadness, etc.) from the facial expression data.

[1628] Stress management suggestions and feedback

[1629] Once the analysis results are obtained, the server generates appropriate stress management tips and actions for the user based on the results. These suggestions might be, for example, "Try breathing slowly" or "Why not consult a specialist?" The generated suggestions are sent to the wearable device and displayed to the user. Real-time action instructions may also be displayed depending on the person the user is facing. For example, a store clerk who is dealing with customers might be instructed to "Smile when serving customers."

[1630] Long-term emotional tracking and personalized advice

[1631] The server stores daily emotional state data in a database and tracks it over the long term. It periodically analyzes this data to identify trends and patterns. Based on the results of this long-term data analysis, the server generates and provides customized advice to users. For example, specific advice might be displayed, such as, "You tend to feel stressed on the weekends, so we recommend you make plans to relax."

[1632] Hardware and software used

[1633] Wearable devices: Smart glasses equipped with a high-resolution camera, microphone, and display.

[1634] Server: A typical server device equipped with a high-performance processor and large memory capacity.

[1635] Software: OpenCV (camera image capture and processing), Dlib (face recognition and facial feature point acquisition), requests (emotion data transmission to server), gTTS (text-to-speech conversion), playsound (audio playback).

[1636] Specific examples

[1637] For example, in a customer service scenario in a brick-and-mortar store, if a customer enters the store and looks a little unhappy, the store clerk's smart glasses will display a message saying, "The customer seems a little nervous. Please try to greet them with a smile." The system will also track the user's daily emotional data and provide customized advice, such as, "You tend to feel stressed during the week, so we recommend you spend more time on your hobbies on the weekends."

[1638] Prompt Sentence Examples

[1639] "The customer is a little grumpy. Try to smile."

[1640] This system configuration makes it possible to accurately grasp the user's emotional state and provide appropriate stress management and face-to-face support.

[1641] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1642] Step 1:

[1643] Facial expression and voice capture

[1644] The device (smart glasses) captures the user's facial expressions and voice in real time. Specifically, the device's built-in camera captures facial expression data, and a high-sensitivity microphone captures voice data. These data are temporarily stored in the device.

[1645] Input: Trigger to start capture (e.g., app launch)

[1646] Data processing: Camera footage is captured in real time, facial recognition is performed, and facial expression data is extracted. Audio data is also captured in real time and noise is removed.

[1647] Output: A set of facial expression and speech data

[1648] For example, when a user puts on glasses and points their face towards the camera, facial recognition takes place.

[1649] Step 2:

[1650] Sending data to the server

[1651] The device transmits the temporarily stored facial expression data and voice data to a server via the Internet using a predetermined protocol (e.g., HTTPS).

[1652] Input: A set of facial expression and speech data

[1653] Data processing: Convert facial expression data and voice data into JSON format

[1654] Output: Send data to the server

[1655] Example: The device sends data collected in real time to the server.

[1656] Step 3:

[1657] Emotion analysis

[1658] The server analyzes the received data and infers the user's emotional state. Specifically, the emotion engine uses machine learning algorithms to analyze voice tone, facial feature points, etc.

[1659] Input: Facial expression data and voice data sent to the server

[1660] Data processing: Extracting tone and rhythm from voice data, analyzing emotional features (e.g., smile, anger) from facial data

[1661] Output: Estimated user emotional state (e.g., happy, angry, sad)

[1662] Example: The server analyzes voice tone and facial expressions to guess whether the user is "happy" or "angry."

[1663] Step 4:

[1664] Stress management suggestions and feedback

[1665] The server generates appropriate stress management tips and actions based on the user's emotional state, and the generated suggestions are sent to the wearable device and displayed to the user, along with real-time behavioral instructions based on the person the user is facing.

[1666] Input: User's emotional state

[1667] Data processing: Generate stress management tips and actions (e.g., "Take a deep breath" or "Consult a professional")

[1668] Output: Suggestions and real-time action instructions displayed on a wearable device

[1669] For example, if the user is feeling stressed, the message "Try breathing slowly" will be displayed. When serving customers face-to-face, the message "Try to smile when serving customers" will be displayed.

[1670] Step 5:

[1671] Long-term sentiment tracking and customized advice

[1672] The server stores daily emotional state data in a database and analyzes it. Based on the analysis results, it identifies long-term trends and patterns and generates customized advice, which is then provided to the user at regular intervals.

[1673] Input: Daily emotional state data

[1674] Data processing: analyzing trends and patterns and generating customized advice

[1675] Output: Providing regular, customized advice to users

[1676] Example: A user who tends to get stressed on weekends is given the advice, "We recommend that you make plans to relax on the weekend."

[1677] Through these steps, the user's emotional state is grasped in real time, providing appropriate feedback and long-term stress management.

[1678] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1679] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1680] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1681] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1682] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1683] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1684] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1685] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1686] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1687] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1688] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1689] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1690] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1691] 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.

[1692] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1693] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1694] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1695] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1696] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1697] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1698] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1699] The following is further disclosed regarding the above embodiment.

[1700] (Claim 1)

[1701] means for capturing the user's voice and facial expressions in real time and transmitting said data to a server;

[1702] means for analyzing the data and inferring the user's emotional state in the server;

[1703] A means for suggesting stress management tips and actions to the user based on the analysis results;

[1704] a means for feeding back the proposal content and analysis results to a user;

[1705] means for storing and tracking the user's daily emotional state data and analyzing trends and patterns;

[1706] The system includes a means for generating and providing customized advice to the user based on the results of these analyses.

[1707] (Claim 2)

[1708] 10. The system of claim 1, wherein inferring the user's emotional state comprises analyzing speech and facial expression data with machine learning algorithms.

[1709] (Claim 3)

[1710] 2. The system according to claim 1, further comprising means for including information on experts in the stress management suggestions to the user.

[1711] "Example 1"

[1712] (Claim 1)

[1713] means for capturing the user's voice and facial expressions in real time and transmitting said data to a server;

[1714] a means for analyzing the data using a machine learning algorithm in the server and inferring the user's emotional state;

[1715] A means for generating stress management tips and action suggestions for the user based on the analysis results;

[1716] a means for feeding back the proposal content and analysis results to a user;

[1717] means for storing and tracking the user's daily emotional state data and analyzing trends and patterns;

[1718] The system includes a means for generating and providing customized advice to the user based on the results of these analyses.

[1719] (Claim 2)

[1720] 10. The system of claim 1, wherein inferring the user's emotional state comprises analyzing speech and facial expression data with machine learning algorithms.

[1721] (Claim 3)

[1722] 2. The system according to claim 1, further comprising means for including information on experts in the stress management suggestions to the user.

[1723] "Application Example 1"

[1724] (Claim 1)

[1725] means for capturing the user's voice and facial expressions in real time and transmitting said data to a server;

[1726] means for analyzing the data and inferring the user's emotional state in the server;

[1727] A means for suggesting stress management tips and actions to the user based on the analysis results;

[1728] a means for feeding back the proposal content and analysis results to a user;

[1729] means for storing and tracking the user's daily emotional state data and analyzing trends and patterns;

[1730] means for generating and providing customized advice to the user based on the results of these analyses;

[1731] A system that uses a device to capture a user's facial expressions and voice in a physical store and includes a means for providing customer service advice in real time based on the analysis results.

[1732] (Claim 2)

[1733] 10. The system of claim 1, wherein inferring the user's emotional state comprises analyzing speech and facial expression data with machine learning algorithms.

[1734] (Claim 3)

[1735] 2. The system according to claim 1, further comprising means for including information on experts in the stress management suggestions to the user.

[1736] "Example 2: Combining Emotion Engines"

[1737] (Claim 1)

[1738] means for capturing the user's voice and facial expressions in real time and transmitting said data to a server;

[1739] means for analyzing the data and inferring the user's emotional state in the server;

[1740] A means for suggesting stress management tips and actions to the user based on the analysis results;

[1741] a means for feeding back the proposal content and analysis results to a user;

[1742] means for storing and tracking the user's daily emotional state data and analyzing trends and patterns;

[1743] means for generating and providing customized advice to the user based on the results of these analyses;

[1744] A means for temporarily storing the captured data on the device;

[1745] The system includes a means for the user to choose whether to accept the offer.

[1746] (Claim 2)

[1747] 10. The system of claim 1, wherein inferring the user's emotional state comprises analyzing speech and facial expression data with machine learning algorithms.

[1748] (Claim 3)

[1749] 2. The system according to claim 1, further comprising means for including information on experts in the stress management suggestions to the user.

[1750] "Application example 2 when combining emotion engines"

[1751] (Claim 1)

[1752] means for capturing the user's voice and facial expressions in real time and transmitting said data to a server;

[1753] means for analyzing the data and inferring the user's emotional state in the server;

[1754] A means for suggesting stress management tips and actions to the user based on the analysis results;

[1755] a means for feeding back the proposal content and analysis results to a user;

[1756] means for storing and tracking the user's daily emotional state data and analyzing trends and patterns;

[1757] means for generating and providing customized advice to the user based on the results of these analyses;

[1758] A means for providing real-time behavioral instructions to a user who is face-to-face with another person using a wearable device that displays feedback based on real-time emotion analysis results;

[1759] A system including:

[1760] (Claim 2)

[1761] 10. The system of claim 1, wherein inferring the user's emotional state comprises analyzing speech and facial expression data with machine learning algorithms.

[1762] (Claim 3)

[1763] 2. The system according to claim 1, further comprising means for including information on experts in the stress management suggestions to the user. [Explanation of symbols]

[1764] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing the user's voice and facial expressions in real time and transmitting said data to a server; means for analyzing the data and inferring the user's emotional state in the server; A means for suggesting stress management tips and actions to the user based on the analysis results; a means for feeding back the proposal content and analysis results to a user; means for storing and tracking the user's daily emotional state data and analyzing trends and patterns; The system includes a means for generating and providing customized advice to the user based on the results of these analyses.

2. 10. The system of claim 1, wherein inferring the user's emotional state comprises analyzing speech and facial expression data with machine learning algorithms.

3. 2. The system according to claim 1, further comprising means for including information on experts in the stress management suggestions for the user.

Images