System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting voice or text data from a user; means for analyzing the collected data with a natural language processing engine to detect signs of dementia; means for performing a risk assessment based on the analysis; and means for notifying a medical professional and the user of the assessment results.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] Dementia presents a challenge in its early stages, as even minor changes or anomalies in daily life are easily overlooked, making early detection difficult. Early diagnosis and intervention are crucial to slowing the progression of dementia, but self-diagnosis is difficult, and in many cases, a diagnosis takes time. Furthermore, prejudice and fear of dementia on the part of family members and individuals themselves can prevent them from seeking medical treatment at the appropriate time. This invention aims to solve these challenges and provide a system that supports the early detection and prevention of dementia. [Means for solving the problem]

[0005] The present invention is a system that includes a means for collecting voice or text data from a user and analyzing it with a natural language processing engine. The collected data is analyzed to detect signs of dementia, and a risk assessment is performed based on the results. The assessment results are notified to a medical professional and the user. The system further includes a means for periodically collecting new data from the user and comparing it with past data to analyze changes in the user's condition. The continuously updated risk assessment results are also notified to the medical professional and the user. The system also includes a means for providing the user with preventive measures and advice based on the analysis results, and a function for displaying reminders to apply to the user's daily life. In this way, the system supports the early detection and prevention of dementia.

[0006] "User" refers to a person who utilizes the system of the present invention to monitor their own health status and cognitive function.

[0007] "Voice or text data" refers to information about a health condition that is input by a user as spoken words or written text.

[0008] A "natural language processing engine" is a computer program that analyzes collected voice or text data and has the ability to identify specific patterns and keywords.

[0009] "Signs of dementia" refer to characteristic symptoms that appear in the early stages of dementia, such as a decline in memory, impaired thinking ability, and impaired judgment.

[0010] "Risk assessment" refers to the process of quantifying or qualitatively assessing a user's likelihood of developing dementia and the degree of progression based on analyzed data.

[0011] "Medical professional" refers to a professional with specialized knowledge about the user's health condition, such as a doctor, nurse, or psychologist.

[0012] "Notification" refers to the act or message from the system informing a user or medical professional of assessment results or advice.

[0013] "Periodic" refers to something that is repeated at a predetermined frequency, and in this case, it means that user data is collected periodically.

[0014] "Preventive measures" refer to behavioral, habit, and lifestyle changes recommended to users to slow the progression of dementia and reduce symptoms.

[0015] A "reminder" is a notification or alarm that reminds a user to take a specific action. [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] System Overview

[0038] The patented system is designed to detect early dementia risk in users and notify medical professionals and the users themselves. The system primarily consists of the following components:

[0039] 1. User Device

[0040] 2. Server

[0041] 3. Speech Recognition Engine

[0042] 4. Natural Language Processing (NLP) Engine

[0043] 5. Risk Assessment Module

[0044] 6. Notification Module

[0045] System Operation Details

[0046] Data collection

[0047] 1. Users

[0048] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0049] For example, a user may say, "I often forget where I put my keys these days."

[0050] 2. Terminal

[0051] The device collects the user's voice and stores it as audio data, or stores the text input as is.

[0052] The voice data is converted into text by the device's voice recognition engine.

[0053] Data transmission and analysis

[0054] 1. Terminal

[0055] The stored text data and the user's profile data (e.g., age, medical history) are sent to a server.

[0056] 2. Server

[0057] The server passes the received data to a natural language processing engine for analysis.

[0058] The NLP engine extracts specific keywords and phrases (e.g., "forget" and "recent") from text data and understands what the user is saying.

[0059] 3. Server

[0060] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[0061] Based on this score, an appropriate risk level (high risk, medium risk, low risk) is set.

[0062] Results report

[0063] 1. Server

[0064] A report summarizing the risk assessment results is generated.

[0065] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[0066] 2. Notification Module

[0067] The report is sent to the medical professional's device using a secure communication protocol.

[0068] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0069] 3. Terminal

[0070] The user's device will display a specific message such as, "You are showing signs of forgetfulness. We recommend that you see a specialist."

[0071] Continuous monitoring

[0072] 1. Terminal

[0073] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[0074] The user enters the answer by voice or text.

[0075] 2. Server

[0076] New data is continually collected and compared with past data.

[0077] If a change in status is detected, the risk assessment is updated.

[0078] 3. Notification Module

[0079] The updated risk assessment results are again communicated to medical professionals and users.

[0080] Additional precautions and advice will be provided where necessary.

[0081] Specific example explanation

[0082] 1. Entering the user's health status

[0083] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[0084] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[0085] 2. Specific examples of data analysis

[0086] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[0087] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[0088] 3. Specific examples of results reporting

[0089] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[0090] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[0091] 4. Specific examples of continuous monitoring

[0092] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[0093] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[0094] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[0095] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[0096] The system will support early detection and prevention of dementia through continuous data collection and risk assessment.

[0097] The processing flow will be explained below.

[0098] Step 1:

[0099] User

[0100] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0101] For example, a user may say, "I often forget where I put my keys these days."

[0102] Step 2:

[0103] Terminal

[0104] The device collects the user's voice and stores it as voice data.

[0105] When the user inputs text, the text data is saved as is.

[0106] The voice data is converted into text by the device's voice recognition engine.

[0107] Step 3:

[0108] Terminal

[0109] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[0110] Step 4:

[0111] server

[0112] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[0113] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[0114] Step 5:

[0115] server

[0116] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[0117] Based on this score, the system assigns an appropriate risk level (high risk, medium risk, low risk).

[0118] Step 6:

[0119] server

[0120] Generate a report summarizing the risk assessment results.

[0121] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[0122] Step 7:

[0123] server

[0124] The notification module sends the report to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[0125] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0126] Step 8:

[0127] Terminal

[0128] A specific message such as "You are showing signs of forgetfulness. We recommend that you see a specialist" will be displayed on the user's device.

[0129] Step 9:

[0130] Terminal

[0131] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[0132] Step 10:

[0133] User

[0134] The user responds to the reminder by entering new information about their health condition via voice or text.

[0135] For example, the user may respond, "I often forget where I put my keys."

[0136] Step 11:

[0137] Terminal

[0138] Collect new voice data and convert it into text using a speech recognition engine.

[0139] The converted text data or the directly input text data is sent to the server.

[0140] Step 12:

[0141] server

[0142] The server receives the new data and re-analyzes it to compare it with the previous data.

[0143] If a change in state is detected, the risk assessment module updates the risk score.

[0144] Step 13:

[0145] server

[0146] Generate a new report with the updated risk assessment results.

[0147] This report will again be communicated to medical professionals and users.

[0148] Step 14:

[0149] server

[0150] If necessary, include additional precautions or advice in your report.

[0151] Step 15:

[0152] Terminal

[0153] The updated assessment results and recommended actions are displayed on the user's device.

[0154] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[0155] This series of processes enables early detection of a user's dementia risk and supports intervention at the appropriate time.

[0156] Example 1

[0157] 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."

[0158] Currently, early detection and prevention of dementia requires a great deal of effort and specialized knowledge, and many people are unable to see a specialist or take the necessary measures at the appropriate time. For this reason, there is a need for a system that can detect users' dementia risk early and provide appropriate advice.

[0159] 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.

[0160] In this invention, the server includes means for collecting voice or text data from a user, means for converting the collected data into text using a voice recognition engine, means for analyzing the converted text data using a natural language processing engine to detect signs of dementia, means for conducting a risk assessment based on the analysis results, means for generating a report of the assessment results, and means for notifying a medical professional and the user of the generated report. This makes it possible to detect a user's risk of dementia early and provide appropriate advice or encourage the user to see a specialist.

[0161] "Voice or text data" refers to information input by the user in voice or text format about their health condition or daily life.

[0162] A "voice recognition engine" is a software or hardware technology for converting voice data into text data.

[0163] A "natural language processing engine" is a technology that extracts specific keywords and phrases from text data and understands the context.

[0164] "Signs of dementia" are characteristics or patterns that are revealed in a user's statements or behavior that may indicate a risk of dementia.

[0165] "Risk assessment" is the analytical process of quantifying or categorizing a user's dementia risk based on collected data.

[0166] A "report" is a document that summarizes the results of a risk assessment and includes the user's current risk level and recommended actions.

[0167] "Notification" is the act of communicating generated reports or important information to a user or medical professional.

[0168] "Preventive measures" are advice that indicates specific actions or efforts that the user should take to prevent the progression of dementia.

[0169] A "reminder" is a notification or message that is displayed periodically to prompt the user to take a specific action or confirm something.

[0170] MODE FOR CARRYING OUT THE INVENTION

[0171] This invention is a system for detecting early dementia risk in users and notifying medical professionals and the users themselves. The system mainly consists of the following components:

[0172] 1. User Device

[0173] 2. Server

[0174] 3. Speech Recognition Engine

[0175] 4. Natural Language Processing (NLP) Engine

[0176] 5. Risk Assessment Module

[0177] 6. Notification Module

[0178] Data collection

[0179] The user launches an application on the user device and either speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." The device collects the user's voice data and saves it as voice data or saves the text input as is. The voice data is converted into text by a speech recognition engine (e.g., Google® Cloud Speech-to-Text API) within the device.

[0180] Data transmission and analysis

[0181] The device sends the saved text data and the user's profile data (e.g., age, medical history) to a server. The server passes the received data to a natural language processing (NLP) engine (e.g., Google Cloud Natural Language API) for analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text data and understands what the user is saying.

[0182] Risk assessment and reporting

[0183] Based on the extracted keywords, the server calculates a dementia risk score using a risk assessment module (a custom-made algorithm). An appropriate risk level (high risk, medium risk, or low risk) is set based on this score. A report summarizing the risk assessment results is generated, including the user's current risk level and recommended actions (e.g., visiting a specialist). The generated report is sent to the medical professional's device by the notification module, and is also notified on the user's device at the same time. A specific message such as "You are showing signs of forgetfulness. We recommend that you visit a specialist" is displayed on the user's device.

[0184] Continuous monitoring

[0185] Periodic reminders appear on the user's device to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?"). The user answers by voice or text, and the data is sent to the server. The server continuously collects new data and compares it with past data. If a change in condition is detected, the risk assessment is updated. The updated risk assessment results are again communicated to medical professionals and the user via the notification module. If necessary, additional preventive measures or advice are provided.

[0186] Specific examples

[0187] 1. Entering the user's health status

[0188] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[0189] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[0190] 2. Specific examples of data analysis

[0191] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[0192] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[0193] 3. Specific examples of results reporting

[0194] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[0195] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[0196] 4. Specific examples of continuous monitoring

[0197] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[0198] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[0199] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[0200] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[0201] Prompt Sentence Examples

[0202] "I've been getting really forgetful lately"

[0203] "Please extract keywords from the following text to assess the risk of dementia: 'I've been feeling increasingly forgetful recently.'"

[0204] "Generate a report showing users as medium risk. Include risk level and recommended actions."

[0205] Have you had any problems in your daily life recently?

[0206] In this way, the system detects users' dementia risk early and supports effective preventative measures through continuous monitoring and the provision of appropriate advice.

[0207] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0208] Step 1: User Data Entry

[0209] The user starts a terminal application and speaks about their health condition or daily life, or inputs text. For example, they might say, "I often forget where I put my keys these days." The input in this case is voice data or text data. Specifically, the user speaks to the terminal or inputs text.

[0210] Step 2: Collecting audio data and converting it to text

[0211] The device collects the user's voice using a microphone and saves it as voice data. It then converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The input is voice data, and the output is text data. Specifically, the microphone detects the voice, and the server sends the voice data to a cloud service for conversion into text.

[0212] Step 3: Send text and profile data

[0213] The device sends the collected text data and the user's profile data (e.g., age, medical history) to the server. The input is the text data and profile data stored on the device, and the output is the data sent to the server. The specific operation is that the device sends the data to the server via the Internet.

[0214] Step 4: Natural Language Processing of the Data

[0215] The server passes the received text data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input is text data, and the output is extracted keywords and phrases. Specifically, the NLP engine analyzes the text and extracts specific keywords and phrases.

[0216] Step 5: Risk assessment

[0217] The server uses a risk assessment module (a custom-made algorithm) based on the extracted keywords to calculate a dementia risk score. The input is the extracted keywords, and the output is the risk score. The specific operation is that the risk assessment module evaluates the extracted keywords and calculates the risk score.

[0218] Step 6: Reporting the results of the evaluation

[0219] The server generates a report summarizing the risk assessment results. The report includes the user's risk level and recommended actions (e.g., consulting a specialist). The input is the risk score, and the output is a report of the assessment results. The specific operation is for the server to compile the risk assessment results into a document.

[0220] Step 7: Notification of evaluation results

[0221] The generated report is sent to the medical professional's terminal by the notification module, and simultaneously notified to the user's terminal. The input is the report of the assessment result, and the output is the notification sent to the medical professional and the user. The specific operation is that the notification module sends the report using a secure communication protocol.

[0222] Step 8: Continuous monitoring

[0223] The device periodically displays a reminder to the user to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). The user inputs new data by voice or text, which is then sent to the server. The input is the new data, and the output is the data sent to the server. The specific operation is that the device periodically displays a reminder message and collects new data from the user.

[0224] Step 9: Reanalyze data and update risk assessment

[0225] The server analyzes the newly collected data again using the natural language processing engine and compares it with past data. If a change in state is detected, it updates the risk assessment. The input is the new data and past data, and the output is an updated risk assessment. Specifically, the server analyzes the new data and updates the risk assessment based on the results.

[0226] Step 10: Notification of updated evaluation results

[0227] The updated risk assessment results are again notified to medical professionals and users through the notification module. If necessary, additional preventive measures or advice are provided. The input is the updated risk assessment, and the output is the notification sent to the medical professional and user. The specific operation is that the notification module sends the updated assessment results and provides the user with appropriate preventive measures or advice.

[0228] (Application example 1)

[0229] 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."

[0230] In today's world, early detection of dementia and appropriate care are essential, but because elderly people themselves are often unaware of the condition and regular checkups are difficult, monitoring by medical professionals and care facilities is often insufficient. Furthermore, dementia risk assessments are often temporary, with no continuous data collection or detection of changes in condition. Therefore, a system is needed for continuous monitoring and risk assessment updates in daily life, which will enable timely medical responses and appropriate care.

[0231] 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.

[0232] In this invention, the server includes a means for analyzing voice data from the user in real time and extracting important keywords, a means for displaying periodic reminders on the care robot to encourage continuous data collection, and a means for detecting changes in condition by comparing with past data and updating risk assessment. This makes it possible to continuously monitor the dementia risk of elderly people in their daily lives and quickly grasp any changes, thereby providing appropriate medical responses and preventive measures.

[0233] "Voice or text data" refers to voice information uttered by the user or text information input by the user, and is basic data for the system to analyze.

[0234] A "natural language processing engine" refers to algorithms or software that analyzes collected voice or text data, extracts keywords and phrases, and understands their meaning.

[0235] "Signs of dementia" are indicators that indicate the early stages of symptoms in which memory and thinking ability decline and interfere with daily life.

[0236] "Risk assessment" refers to the process of assessing a user's likelihood of dementia as a number or category based on the analysis results.

[0237] "Health Professional" refers to a person, such as a doctor or nurse, who has specific medical knowledge and is qualified to appropriately assess, diagnose, and treat a user's health condition.

[0238] "Care robots" are robots designed to assist the elderly and people who require care, and are devices equipped with voice recognition, data collection, reminder functions, etc.

[0239] "Reminders" refer to notifications and messages that periodically alert the user, and serve to collect new data and provide health management advice.

[0240] "Status change" refers to a change in the user's health condition or cognitive ability over time, and refers to a fluctuation compared to before.

[0241] "Real-time analysis" refers to the process of processing collected data immediately and quickly generating analytical results.

[0242] "Important keywords" refer to words or phrases extracted from user utterances or input text that have a particularly specific meaning in risk assessment.

[0243] System Configuration

[0244] The system of the present invention is a comprehensive support system for early detection of dementia risk in users and notifying medical professionals and care staff. The system is composed of the following components:

[0245] 1. User Device

[0246] 2. Server

[0247] 3. Speech Recognition Engine

[0248] 4. Natural Language Processing (NLP) Engine

[0249] 5. Risk Assessment Module

[0250] 6. Notification Module

[0251] Audio data collection

[0252] First, the user speaks about their health condition or daily life situation in front of the device, or inputs text. For example, the user might say, "I often forget where I put my keys these days." This speech is collected using the device's microphone and saved as voice data. The voice data is then converted into text using a voice recognition engine.

[0253] Data transmission and analysis

[0254] The user device sends the collected text data and user profile data (e.g., age, medical history) to the server. The server then analyzes the received data using a natural language processing engine to extract specific keywords and phrases (e.g., "forget" and "recent"). The risk assessment module then calculates a dementia risk score based on the extracted keywords and sets an appropriate risk level (high risk, medium risk, or low risk).

[0255] Reporting and notification of results

[0256] The server generates a report summarizing the risk assessment results and sends it to medical professionals and care staff via the notification module. At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[0257] Continuous monitoring

[0258] The system displays regular reminders to the user to collect new data. For example, it might ask, "Have you had any problems in your daily life recently?" The new data collected is sent to the server, and if a change in condition is detected compared with past data, the risk assessment is updated. Again, the updated risk assessment results are notified to medical professionals and care staff, who will provide additional preventive measures or advice as needed.

[0259] Hardware and Software

[0260] Hardware: Microphone, nursing robot (or a home PC)

[0261] Software: Python, Speech Recognition library, Scikit-learn, natural language processing engine, data analysis algorithms

[0262] Specific examples

[0263] 1. Entering the user's health status

[0264] The user says, "I've been getting worse recently," and the speech recognition engine converts this speech into text, generating text data such as "I've been getting worse recently."

[0265] 2. Data Analysis

[0266] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent." The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[0267] 3. Reporting and Notification of Results

[0268] The server generates a report containing the assessment result of "medium risk" and sends it to a medical professional. The user is notified of the symptoms of memory loss and is advised to consult a medical specialist as soon as possible.

[0269] 4. Continuous monitoring

[0270] A reminder is periodically displayed on the user's device asking, "Have you had any trouble in your daily life recently?" The user answers, "I often forget where I put my keys," and this data is sent to the server. The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk." A medical professional is notified of the latest assessment results, and the user is informed, "You are currently forgetting things more frequently. Please consult a specialist immediately."

[0271] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0272] Step 1:

[0273] The user starts up the device and inputs their health condition and daily life situation as voice or text data. If voice data is collected using a microphone, the user's speech is converted into text by a voice recognition engine. For example, the user might say, "I often forget where I put my keys these days." The input for this step is the user's voice or text data, and the output is text data.

[0274] Step 2:

[0275] The device sends the collected text data to the server. User profile data (e.g., age, medical history) is also sent at the same time. The input of this step is the text data and user profile data, and the output is the data sent to the server.

[0276] Step 3:

[0277] The server passes the received data to a natural language processing (NLP) engine to extract specific keywords or phrases. For example, keywords such as "forget" and "recent" can be extracted. The input for this step is text data, and the output is the extracted keywords.

[0278] Step 4:

[0279] The server calculates a dementia risk score using a risk assessment module based on the extracted keywords and sets a risk level (high, medium, or low risk). For example, it calculates a risk score based on the frequency of appearance of the keywords "forget" and "recent" and determines a medium risk. The input for this step is the extracted keywords, and the output is a risk score and risk level.

[0280] Step 5:

[0281] The server generates a report summarizing the risk assessment results and sends it to medical professionals and users through the notification module. For example, a report containing the assessment result of "medium risk" may be generated, with the message "There are signs of forgetfulness. Please consult a specialist as soon as possible." The input of this step is the risk score and risk level, and the output is the generated report and notification.

[0282] Step 6:

[0283] For continuous monitoring, the server displays periodic reminders on the user's device. For example, it displays a reminder such as "Have you had any troubles in your daily life recently?" The input of this step is the reminder setting data, and the output is the reminder displayed on the user's device.

[0284] Step 7:

[0285] The user responds to the reminder by entering new voice or text data, for example, "I often forget where I put my keys." The input for this step is the user's voice or text data, and the output is the new text data.

[0286] Step 8:

[0287] The device sends newly collected data to the server and compares it with past data to detect changes in the state. For example, by comparing past data with new data, it can determine that "the frequency of forgetfulness is increasing." The inputs of this step are new text data and past data, and the output is the analysis results.

[0288] Step 9:

[0289] The server updates the risk assessment based on the status change and notifies the medical professional and the user of the latest assessment result. For example, the updated result to "high risk" is notified to the medical professional, and the user is sent a message saying, "Your forgetfulness is currently increasing. Please consult a specialist immediately." The input of this step is the analysis result, and the output is the updated risk assessment result and notification.

[0290] 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.

[0291] System Overview

[0292] This patented system detects the user's risk of dementia at an early stage and, by analyzing the user's emotions, enables more accurate risk assessment and continuous health management. The system includes the following components:

[0293] 1. User Device

[0294] 2. Server

[0295] 3. Speech Recognition Engine

[0296] 4. Natural Language Processing (NLP) Engine

[0297] 5. Emotion Engine

[0298] 6. Risk Assessment Module

[0299] 7. Notification Module

[0300] System Operation Details

[0301] Data collection

[0302] 1. Users

[0303] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0304] For example, a user may say, "I often forget where I put my keys these days."

[0305] 2. Terminal

[0306] The device collects the user's voice and stores it as voice data.

[0307] When the user inputs text, the text data is saved as is.

[0308] The voice data is converted into text by the device's voice recognition engine.

[0309] Data transmission and analysis

[0310] 1. Terminal

[0311] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[0312] 2. Server

[0313] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[0314] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[0315] 3. Server

[0316] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[0317] The emotion engine tags emotions and attaches the data as emotional energy.

[0318] 4. Server

[0319] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[0320] Taking emotional data into account also allows for more accurate risk assessment.

[0321] Results report

[0322] 1. Server

[0323] Generate a report summarizing the risk assessment results.

[0324] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[0325] 2. Notification Module

[0326] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[0327] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0328] 3. Terminal

[0329] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[0330] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[0331] Continuous monitoring

[0332] 1. Terminal

[0333] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[0334] 2. Users

[0335] The user responds to the reminder by entering new information about their health condition via voice or text.

[0336] For example, you might answer, "I often forget where I put my keys."

[0337] 3. Terminal

[0338] Collect new voice data and convert it into text using a speech recognition engine.

[0339] The converted text data or the directly input text data is sent to the server.

[0340] 4. Server

[0341] The server receives the new data and re-analyzes it to compare it with the previous data.

[0342] If a change in state is detected, the risk assessment module updates the risk score.

[0343] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[0344] 5. Server

[0345] Generate a new report with the updated risk assessment results.

[0346] This report will again be communicated to medical professionals and users.

[0347] 6. Notification Module

[0348] If necessary, include additional precautions or advice in your report.

[0349] 7. Terminal

[0350] The updated assessment results and recommended actions are displayed on the user's device.

[0351] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[0352] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[0353] Specific example explanation

[0354] 1. Entering the user's health status

[0355] The user says aloud, "I've been getting more and more forgetful lately."

[0356] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[0357] 2. Specific examples of data analysis

[0358] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[0359] The server uses an emotion engine to detect the emotion "sadness" from the user's voice.

[0360] The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user as "medium risk."

[0361] 3. Specific examples of results reporting

[0362] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[0363] The user will be notified with a recommended action such as "You are showing signs of forgetfulness. Please consult a specialist as soon as possible," along with advice such as "You seem to be experiencing a lot of emotional fluctuations recently. Please take a moderate break."

[0364] 4. Specific examples of continuous monitoring

[0365] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[0366] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[0367] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[0368] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[0369] Additionally, if fluctuations in emotional data are observed, you will be notified with the message, "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits."

[0370] By taking into account the user's emotional data, this system enables more accurate early detection of dementia risk and provides appropriate preventive measures.

[0371] The processing flow will be explained below.

[0372] Step 1:

[0373] User

[0374] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0375] For example, a user may say, "I often forget where I put my keys these days."

[0376] Step 2:

[0377] Terminal

[0378] The device collects the user's voice and stores it as voice data.

[0379] When the user inputs text, the text data is saved.

[0380] The voice data is converted into text by the device's voice recognition engine.

[0381] Step 3:

[0382] Terminal

[0383] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[0384] Step 4:

[0385] server

[0386] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[0387] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[0388] Step 5:

[0389] server

[0390] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[0391] The emotion engine tags emotions and appends the data as emotional information.

[0392] Step 6:

[0393] server

[0394] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[0395] Taking emotional data into account also allows for more accurate risk assessment.

[0396] Step 7:

[0397] server

[0398] Generate a report summarizing the risk assessment results.

[0399] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[0400] Step 8:

[0401] Notification Module

[0402] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[0403] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0404] Step 9:

[0405] Terminal

[0406] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[0407] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[0408] Step 10:

[0409] Terminal

[0410] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[0411] Step 11:

[0412] User

[0413] The user responds to the reminder by entering new information about their health condition via voice or text.

[0414] For example, you might answer, "I often forget where I put my keys."

[0415] Step 12:

[0416] Terminal

[0417] Collect new voice data and convert it into text using a speech recognition engine.

[0418] The converted text data or the directly input text data is sent to the server.

[0419] Step 13:

[0420] server

[0421] The server receives the new data and re-analyzes it to compare it with the previous data.

[0422] If a change in state is detected, the risk assessment module updates the risk score.

[0423] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[0424] Step 14:

[0425] server

[0426] Generate a new report with the updated risk assessment results.

[0427] This report will again be communicated to medical professionals and users.

[0428] Step 15:

[0429] Notification Module

[0430] If necessary, include additional precautions or advice in your report.

[0431] Step 16:

[0432] Terminal

[0433] The updated assessment results and recommended actions are displayed on the user's device.

[0434] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[0435] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[0436] This series of processes enables early detection of a user's dementia risk, and further analysis of emotional data can improve the accuracy of risk assessment and support intervention at the appropriate time.

[0437] Example 2

[0438] 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."

[0439] In modern society, early detection of dementia and continuous health management are important issues. In particular, there is a need to detect the risk of dementia early and take necessary measures. However, current systems are inadequate in not only detecting signs of dementia but also taking into account the user's emotional state to provide more accurate risk assessment and appropriate advice. Therefore, there is a need for a comprehensive risk assessment system that also takes into account the user's emotional data.

[0440] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0441] In this invention, the server includes means for collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia and emotions, means for performing a risk assessment based on the analysis results and the detected emotion data, means for notifying medical professionals and the user of preventive measures and health management advice based on the assessment results and emotions, means for periodically collecting new data from the user, means for comparing past data with new data to analyze changes in the user's condition and emotional fluctuations, means for updating the ongoing risk assessment based on the analysis results, means for notifying medical professionals and the user of preventive measures and advice based on the updated assessment results and emotional fluctuations, means for providing the user with preventive measures and advice based on the analysis results and the emotional data, and means for displaying reminders for applying the preventive measures and advice to the user's daily life. This enables more accurate risk assessment and appropriate advice that takes emotion data into account.

[0442] "User" refers to an individual who uses the system and inputs information about their health condition and daily life through voice or text.

[0443] "Voice data" is digital data that contains information input by voice by the user.

[0444] "Text data" is character string data that contains information entered by the user in text form.

[0445] A "natural language processing engine" is a software engine that analyzes and understands voice and text data, extracting keywords and phrases and analyzing their meaning.

[0446] The "emotion engine" is a software engine that detects emotions from a user's voice data and text data and tags the emotions.

[0447] "Risk Assessment Module" is a software module for calculating a user's dementia risk score based on data obtained from the natural language processing engine and the emotion engine.

[0448] "Assessment results" are information including the user's dementia risk score calculated by the risk assessment module and related analysis results.

[0449] "Preventive measures" are actions or measures recommended to users based on the results of risk assessment.

[0450] "Health management advice" is specific suggestions or recommendations for maintaining or improving the user's health.

[0451] "Notification Module" is a software module for notifying medical professionals and users of assessment results, preventative measures, and health care advice.

[0452] "Reminder" refers to a function that periodically notifies the user about new data input and application to daily life.

[0453] "Analysis results" is a general term for the data generated by the natural language processing engine and emotion engine, and the assessment results created by the risk assessment module.

[0454] This invention is a system that realizes more accurate risk assessment and continuous health management by detecting a user's dementia risk at an early stage and analyzing the user's emotions. The system includes a user terminal, a server, a voice recognition engine, a natural language processing (NLP) engine, an emotion engine, a risk assessment module, and a notification module.

[0455] System configuration

[0456] Hardware and Software

[0457] User device: A device (e.g., smartphone, tablet, PC) through which a user provides voice or text input.

[0458] Server: A central processing unit for data analysis and risk assessment. Uses a cloud-based or on-premise server.

[0459] Speech recognition engine: Software used to convert user voice data into text (e.g., Google Cloud Speech-to-Text, Amazon Transcribe).

[0460] Natural Language Processing (NLP) engine: Software for analyzing text data and extracting keywords and phrases (e.g., spaCy, NLTK).

[0461] Emotion engine: Software for detecting and tagging emotions from a user's voice and text data (e.g., IBM Watson® Tone Analyzer).

[0462] Risk Assessment Module: Software that calculates a risk score based on data obtained from the natural language processing engine and sentiment engine.

[0463] Notification module: Software for notifying users and medical professionals of assessment results and health care advice.

[0464] System Operation

[0465] Data collection

[0466] The user launches the device application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is converted into text by the device's voice recognition engine.

[0467] Data transmission and analysis

[0468] The converted text data and the user's profile data (such as age and medical history) are sent from the device to the server. The server then passes this data to a natural language processing engine to begin analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[0469] Sentiment Analysis and Risk Assessment

[0470] The server then uses an emotion engine to analyze emotions from the user's voice and text data. The emotion engine then tags the data with emotions and adds them as emotional energy. Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score. Taking emotion data into account allows for more accurate risk assessment.

[0471] Reporting and notification of results

[0472] A report summarizing the risk assessment results is generated. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[0473] Specific examples

[0474] For example, a user might say, "I've been getting more forgetful lately." The device's speech recognition engine converts this into text, generating text data such as "I've been getting more forgetful lately." The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recently." At the same time, the emotion engine detects the emotion "sadness" from the user's voice. The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user to be at "medium risk." The server generates a report containing the "medium risk" assessment result and sends it to a medical professional. The user is notified of the recommended action, "You are showing signs of forgetfulness. Consult a specialist as soon as possible," along with advice such as "You seem to have experienced frequent emotional fluctuations recently. Take appropriate breaks."

[0475] Prompt Sentence Examples

[0476] "Please explain what emotion tag the emotion engine will assign when a user says, 'I've been getting more and more forgetful lately.' Also, please explain in detail the process by which the risk assessment module determines the risk to be medium."

[0477] This invention makes it possible to provide more accurate early detection of dementia risk and appropriate preventive measures that also take into account the user's emotional data.

[0478] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0479] Step 1: Data entry

[0480] Input: Voice or text data about the user's health and daily life

[0481] Output: User voice or text data is collected

[0482] The user starts the terminal application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is collected by the terminal.

[0483] Step 2: Data conversion

[0484] Input: User's voice data

[0485] Output: Audio data is converted to text data

[0486] The device converts the collected voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). For example, a speech sentence such as "I often forget where I put my keys these days" is converted into text such as "I often forget where I put my keys these days."

[0487] Step 3: Send data

[0488] Input: Text data and user profile data (e.g., age, medical history)

[0489] Output: Text data and profile data are sent to the server.

[0490] The converted text data and the user's profile data (age, medical history, etc.) are sent from the device to the server. For example, the text data "I often forget where I put my keys these days" along with the user's age and medical history are sent to the server.

[0491] Step 4: Natural Language Processing

[0492] Input: Text data

[0493] Output: Parsed keywords and phrases

[0494] The server passes the received text data to a natural language processing (NLP) engine (e.g., spaCy) and begins analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[0495] Step 5: Sentiment Analysis

[0496] Input: Text data

[0497] Output: Emotion data with emotion tags

[0498] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. The emotion engine tags the data with emotions and adds them as emotional energy. For example, an emotion tag such as "sadness" is added.

[0499] Step 6: Risk assessment

[0500] Input: Parsed keywords and sentiment data

[0501] Output: Dementia risk score

[0502] The server's risk assessment module calculates a dementia risk score based on the extracted keywords and emotion data. For example, based on the keywords "where do I put my keys" and "often forgetting" and the emotion data of "sadness," the risk assessment module may assess the risk as medium.

[0503] Step 7: Results generation and notification

[0504] Input: Risk assessment results

[0505] Output: Risk assessment report and notification messages

[0506] The server generates a report summarizing the risk assessment results. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[0507] Step 8: Continuous monitoring

[0508] Input: New audio or text data

[0509] Output: Updated risk assessment results

[0510] The user's device periodically displays reminders to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). In response to the reminders, the user inputs new health status information by voice or text. The new voice data is again converted into text by the speech recognition engine, and the converted text data or directly entered text data is sent to the server. The server receives the new data and analyzes it again to compare it with past data. If a change in status is detected, the risk assessment module updates the risk score. The updated risk assessment results are generated as a new report and notified to medical professionals and the user.

[0511] Such steps allow for comprehensive monitoring of the user's health and emotional state and provide appropriate risk assessment and advice.

[0512] (Application example 2)

[0513] 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."

[0514] The present invention relates to a system for managing a user's health. In particular, it aims to provide a system that can detect the risk of dementia early by having the user input voice and text data in a physical store, and further analyze emotional fluctuations to perform risk assessment. Another objective is to provide a mechanism that can recommend a consultation with a specialist based on the risk assessment results and support the user in improving their daily life.

[0515] The identification processing 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 collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia, means for performing a risk assessment based on the analysis results, means for notifying a medical professional and the user of the assessment results, means for the user to record their health status at a physical store and analyze the data to continuously manage their health, means for recommending a visit to a specialist based on the data analysis results, a reminder function for providing health management advice, means for providing the user with preventive measures and advice based on the analysis results, means for displaying reminders for applying the preventive measures and advice to the user's daily life, and means for analyzing the user's health status in real time and notifying the results. This allows the user to continuously manage their health status and to consult a specialist at the appropriate time.

[0516] "User" means a person who uses the system to record their health status and receive risk assessments and advice from medical professionals.

[0517] "Voice or text data" refers to voice or text data input by the user regarding their health condition or daily life.

[0518] A "natural language processing engine" is a technology that analyzes collected text data and extracts specific keywords and phrases.

[0519] "Signs of dementia" are signs that indicate the possibility of early dementia, which are inferred from the user's health condition and behavior.

[0520] "Risk assessment" is the process of calculating a risk score for the user's health status based on the analyzed data.

[0521] A "healthcare professional" is a medical professional whose role is to provide assessment results and advice.

[0522] "Brick and mortar store" refers to a physical store where users visit and use services or products.

[0523] "Health status" refers to the physical and mental state of a user in their daily life.

[0524] "Continuous health management" refers to the activity of managing a user's health condition over the long term by periodically collecting and analyzing the user's health data.

[0525] The "means for recommending a consultation with a specialist" is a mechanism for recommending that the user be examined by a specialist based on the risk assessment results.

[0526] "Health management advice" is specific guidance and advice for maintaining and improving the user's health in their daily lives.

[0527] The "reminder function" is a mechanism that provides notifications and alarms to prompt users to take specific actions or enter specific data.

[0528] "Real-time analysis" refers to the process of processing user data instantly and quickly calculating results.

[0529] The "risk assessment result" is the result of an assessment of the user's health condition obtained through analysis.

[0530] "Applying to daily life" refers to incorporating the provided advice and preventative measures into the user's daily life.

[0531] MODE FOR CARRYING OUT THE INVENTION

[0532] System Overview

[0533] The system of the present invention collects and analyzes users' voice or text data to detect signs of dementia and perform risk assessment. It also supports health management in physical stores and includes a mechanism for recommending consultations with specialists. The system includes the following main components:

[0534] 1. User Device

[0535] 2. Server

[0536] 3. Speech Recognition Engine

[0537] 4. Natural Language Processing Engine

[0538] 5. Sentiment Analysis Engine

[0539] 6. Risk Assessment Module

[0540] 7. Notification Module

[0541] 8. Interactive Kiosks in Brick-and-mortar Stores

[0542] Generating a Program

[0543] The system program consists of the following steps:

[0544] Hardware and software used

[0545] 1. Smartphone application: iOS, ANDROID (registered trademark) platform

[0546] 2. Speech recognition engine: Google Cloud Speech-to-Text API

[0547] 3. Natural Language Processing Engine: IBM Watson NLP

[0548] 4. Sentiment analysis engine: Microsoft® Azure® Text Analytics API

[0549] 5. Database: Firebase, MySQL (registered trademark)

[0550] 6. Cloud Server: AWS (registered trademark) EC2, Google Cloud Platform

[0551] Program processing

[0552] Data collection

[0553] Users input voice or text data using a smartphone app or an interactive kiosk terminal in a physical store. For example, a user might input, "I've been getting worse at forgetting things lately." This data is converted into text by the device's speech recognition engine (Google Cloud Speech-to-Text API).

[0554] Data transmission and analysis

[0555] The collected text data is sent to a cloud server using a secure protocol (HTTPS). The server analyzes the received data using a natural language processing engine (IBM Watson NLP) to extract specific keywords and phrases. At the same time, it calculates the user's sentiment score using a sentiment analysis engine (Microsoft Azure Text Analytics API).

[0556] Risk Assessment

[0557] The server-side risk assessment module assesses the user's dementia risk based on keywords extracted by natural language processing and the results of sentiment analysis. This assessment is quantified as a risk score.

[0558] Reporting and notification of results

[0559] Based on the evaluation results and emotion data, the server generates a detailed report and notifies the user and medical professionals, including recommendations for specialist consultations and advice on daily living.

[0560] Continuous monitoring

[0561] Users receive periodic reminders on their smartphones to collect new data, and the server receives the new data, compares it with past data, analyzes changes in status, and updates the risk assessment.

[0562] Specific example explanation

[0563] A user uses an interactive kiosk terminal in a physical store to voice-input, "I've been forgetting things a lot lately." This voice data is converted into text by a speech recognition engine and sent to a server. The server then analyzes the data using a natural language processing engine and a sentiment analysis engine, extracting the keyword "forgetfulness" and the emotion "sadness." A risk assessment module calculates a risk score based on this and determines the user as "medium risk." This assessment result is notified to the user and a medical professional, and a message appears on the user's smartphone stating, "You are showing signs of forgetfulness. We recommend that you see a specialist."

[0564] Prompt Sentence Examples

[0565] "Please tell me the specific hardware configuration and processing steps for designing an application that allows users to record their health status by voice in a physical store and analyzes the data in real time to detect early dementia risk."

[0566] This completes the description of the embodiment of the invention. This system allows users to continuously manage their health status and consult a specialist at the appropriate time.

[0567] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0568] Step 1: Enter your data

[0569] A user inputs voice or text data using an interactive kiosk terminal in a physical store or a smartphone app. For example, the user might say, "I've been getting more and more forgetful lately." This data input is stored on the terminal in the form of voice or text data.

[0570] Input: User voice or text data

[0571] Output: Saved audio or text data

[0572] Step 2: Voice Recognition

[0573] The device's speech recognition engine converts the stored voice data into text by analyzing the voice waveform and generating the corresponding text data using the Google Cloud Speech-to-Text API.

[0574] Input: Saved audio data

[0575] Output: Text data

[0576] Step 3: Sending data

[0577] The device sends the generated text data to a cloud server using a secure protocol (HTTPS), ensuring data integrity and confidentiality.

[0578] Input: Text data

[0579] Output: Text data sent to the server

[0580] Step 4: Natural Language Processing

[0581] The server analyzes the received text data using a natural language processing (NLP) engine. Specifically, it uses IBM Watson NLP to extract specific keywords and phrases and understand what the user is saying.

[0582] Input: Text data sent to the server

[0583] Output: Extracted keywords and phrases

[0584] Step 5: Sentiment Analysis

[0585] The server uses a sentiment analysis engine to calculate the user's sentiment score from the received text data, and adds sentiment tags (e.g., joy, sadness, anger) from the text using the Microsoft Azure Text Analytics API.

[0586] Input: Text data sent to the server

[0587] Output: Text data with sentiment scores

[0588] Step 6: Risk assessment

[0589] The server-side risk assessment module calculates a risk score based on keywords extracted by natural language processing and the emotion score. This risk score quantifies the user's dementia risk.

[0590] Input: Keywords, text data with sentiment scores

[0591] Output: Risk score

[0592] Step 7: Generate results

[0593] The server generates a detailed report based on the risk assessment results and emotion data, including the current risk level, the detected emotion data, and recommended actions (e.g., consulting a specialist).

[0594] Input: Risk score, sentiment data

[0595] Output: Evaluation result report

[0596] Step 8: Notification

[0597] The server then notifies the user and medical professionals of the generated report, sending the results to the user within the smartphone app and to medical professionals using a secure communication protocol.

[0598] Input: Evaluation result report

[0599] Output: Notified evaluation result report

[0600] Step 9: Continuous monitoring

[0601] Users receive periodic reminders via their smartphone app to enter new data, which is then sent back to the server via the same process flow, updating the risk assessment.

[0602] Input: New voice or text data

[0603] Output: Updated risk assessment results

[0604] The above is a concrete flow of the processing steps in this system, which allows users to continuously manage their health status and receive medical examinations from specialists at appropriate times.

[0605] 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.

[0606] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0607] 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.

[0608] [Second embodiment]

[0609] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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).

[0615] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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."

[0621] System Overview

[0622] The patented system is designed to detect early dementia risk in users and notify medical professionals and the users themselves. The system primarily consists of the following components:

[0623] 1. User Device

[0624] 2. Server

[0625] 3. Speech Recognition Engine

[0626] 4. Natural Language Processing (NLP) Engine

[0627] 5. Risk Assessment Module

[0628] 6. Notification Module

[0629] System Operation Details

[0630] Data collection

[0631] 1. Users

[0632] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0633] For example, a user may say, "I often forget where I put my keys these days."

[0634] 2. Terminal

[0635] The device collects the user's voice and stores it as audio data, or stores the text input as is.

[0636] The voice data is converted into text by the device's voice recognition engine.

[0637] Data transmission and analysis

[0638] 1. Terminal

[0639] The stored text data and the user's profile data (e.g., age, medical history) are sent to a server.

[0640] 2. Server

[0641] The server passes the received data to a natural language processing engine for analysis.

[0642] The NLP engine extracts specific keywords and phrases (e.g., "forget" and "recent") from text data and understands what the user is saying.

[0643] 3. Server

[0644] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[0645] Based on this score, an appropriate risk level (high risk, medium risk, low risk) is set.

[0646] Results report

[0647] 1. Server

[0648] A report summarizing the risk assessment results is generated.

[0649] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[0650] 2. Notification Module

[0651] The report is sent to the medical professional's device using a secure communication protocol.

[0652] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0653] 3. Terminal

[0654] The user's device will display a specific message such as, "You are showing signs of forgetfulness. We recommend that you see a specialist."

[0655] Continuous monitoring

[0656] 1. Terminal

[0657] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[0658] The user enters the answer by voice or text.

[0659] 2. Server

[0660] New data is continually collected and compared with past data.

[0661] If a change in status is detected, the risk assessment is updated.

[0662] 3. Notification Module

[0663] The updated risk assessment results are again communicated to medical professionals and users.

[0664] Additional precautions and advice will be provided where necessary.

[0665] Specific example explanation

[0666] 1. Entering the user's health status

[0667] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[0668] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[0669] 2. Specific examples of data analysis

[0670] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[0671] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[0672] 3. Specific examples of results reporting

[0673] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[0674] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[0675] 4. Specific examples of continuous monitoring

[0676] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[0677] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[0678] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[0679] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[0680] The system will support early detection and prevention of dementia through continuous data collection and risk assessment.

[0681] The processing flow will be explained below.

[0682] Step 1:

[0683] User

[0684] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0685] For example, a user may say, "I often forget where I put my keys these days."

[0686] Step 2:

[0687] Terminal

[0688] The device collects the user's voice and stores it as voice data.

[0689] When the user inputs text, the text data is saved as is.

[0690] The voice data is converted into text by the device's voice recognition engine.

[0691] Step 3:

[0692] Terminal

[0693] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[0694] Step 4:

[0695] server

[0696] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[0697] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[0698] Step 5:

[0699] server

[0700] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[0701] Based on this score, the system assigns an appropriate risk level (high risk, medium risk, low risk).

[0702] Step 6:

[0703] server

[0704] Generate a report summarizing the risk assessment results.

[0705] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[0706] Step 7:

[0707] server

[0708] The notification module sends the report to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[0709] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0710] Step 8:

[0711] Terminal

[0712] A specific message such as "You are showing signs of forgetfulness. We recommend that you see a specialist" will be displayed on the user's device.

[0713] Step 9:

[0714] Terminal

[0715] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[0716] Step 10:

[0717] User

[0718] The user responds to the reminder by entering new information about their health condition via voice or text.

[0719] For example, the user may respond, "I often forget where I put my keys."

[0720] Step 11:

[0721] Terminal

[0722] Collect new voice data and convert it into text using a speech recognition engine.

[0723] The converted text data or the directly input text data is sent to the server.

[0724] Step 12:

[0725] server

[0726] The server receives the new data and re-analyzes it to compare it with the previous data.

[0727] If a change in state is detected, the risk assessment module updates the risk score.

[0728] Step 13:

[0729] server

[0730] Generate a new report with the updated risk assessment results.

[0731] This report will again be communicated to medical professionals and users.

[0732] Step 14:

[0733] server

[0734] If necessary, include additional precautions or advice in your report.

[0735] Step 15:

[0736] Terminal

[0737] The updated assessment results and recommended actions are displayed on the user's device.

[0738] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[0739] This series of processes enables early detection of a user's dementia risk and supports intervention at the appropriate time.

[0740] Example 1

[0741] 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."

[0742] Currently, early detection and prevention of dementia requires a great deal of effort and specialized knowledge, and many people are unable to see a specialist or take the necessary measures at the appropriate time. For this reason, there is a need for a system that can detect users' dementia risk early and provide appropriate advice.

[0743] 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.

[0744] In this invention, the server includes means for collecting voice or text data from a user, means for converting the collected data into text using a voice recognition engine, means for analyzing the converted text data using a natural language processing engine to detect signs of dementia, means for conducting a risk assessment based on the analysis results, means for generating a report of the assessment results, and means for notifying a medical professional and the user of the generated report. This makes it possible to detect a user's risk of dementia early and provide appropriate advice or encourage the user to see a specialist.

[0745] "Voice or text data" refers to information input by the user in voice or text format about their health condition or daily life.

[0746] A "voice recognition engine" is a software or hardware technology for converting voice data into text data.

[0747] A "natural language processing engine" is a technology that extracts specific keywords and phrases from text data and understands the context.

[0748] "Signs of dementia" are characteristics or patterns that are revealed in a user's statements or behavior that may indicate a risk of dementia.

[0749] "Risk assessment" is the analytical process of quantifying or categorizing a user's dementia risk based on collected data.

[0750] A "report" is a document that summarizes the results of a risk assessment and includes the user's current risk level and recommended actions.

[0751] "Notification" is the act of communicating generated reports or important information to a user or medical professional.

[0752] "Preventive measures" are advice that indicates specific actions or efforts that the user should take to prevent the progression of dementia.

[0753] A "reminder" is a notification or message that is displayed periodically to prompt the user to take a specific action or confirm something.

[0754] MODE FOR CARRYING OUT THE INVENTION

[0755] This invention is a system for detecting early dementia risk in users and notifying medical professionals and the users themselves. The system mainly consists of the following components:

[0756] 1. User Device

[0757] 2. Server

[0758] 3. Speech Recognition Engine

[0759] 4. Natural Language Processing (NLP) Engine

[0760] 5. Risk Assessment Module

[0761] 6. Notification Module

[0762] Data collection

[0763] The user launches the application on the user device and either speaks about their health condition or daily life, or inputs text. For example, the user might say, "I often forget where I put my keys these days." The device collects the user's voice data and saves it as voice data, or saves the text input as is. The voice data is converted into text by the device's voice recognition engine (for example, Google Cloud Speech-to-Text API).

[0764] Data transmission and analysis

[0765] The device sends the saved text data and the user's profile data (e.g., age, medical history) to a server. The server passes the received data to a natural language processing (NLP) engine (e.g., Google Cloud Natural Language API) for analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text data and understands what the user is saying.

[0766] Risk assessment and reporting

[0767] Based on the extracted keywords, the server calculates a dementia risk score using a risk assessment module (a custom-made algorithm). An appropriate risk level (high risk, medium risk, or low risk) is set based on this score. A report summarizing the risk assessment results is generated, including the user's current risk level and recommended actions (e.g., visiting a specialist). The generated report is sent to the medical professional's device by the notification module, and is also notified on the user's device at the same time. A specific message such as "You are showing signs of forgetfulness. We recommend that you visit a specialist" is displayed on the user's device.

[0768] Continuous monitoring

[0769] Periodic reminders appear on the user's device to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?"). The user answers by voice or text, and the data is sent to the server. The server continuously collects new data and compares it with past data. If a change in condition is detected, the risk assessment is updated. The updated risk assessment results are again communicated to medical professionals and the user via the notification module. If necessary, additional preventive measures or advice are provided.

[0770] Specific examples

[0771] 1. Entering the user's health status

[0772] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[0773] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[0774] 2. Specific examples of data analysis

[0775] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[0776] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[0777] 3. Specific examples of results reporting

[0778] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[0779] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[0780] 4. Specific examples of continuous monitoring

[0781] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[0782] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[0783] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[0784] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[0785] Prompt Sentence Examples

[0786] "I've been getting really forgetful lately"

[0787] "Please extract keywords from the following text to assess the risk of dementia: 'I've been feeling increasingly forgetful recently.'"

[0788] "Generate a report showing users as medium risk. Include risk level and recommended actions."

[0789] Have you had any problems in your daily life recently?

[0790] In this way, the system detects users' dementia risk early and supports effective preventative measures through continuous monitoring and the provision of appropriate advice.

[0791] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0792] Step 1: User Data Entry

[0793] The user starts a terminal application and speaks about their health condition or daily life, or inputs text. For example, they might say, "I often forget where I put my keys these days." The input in this case is voice data or text data. Specifically, the user speaks to the terminal or inputs text.

[0794] Step 2: Collecting audio data and converting it to text

[0795] The device collects the user's voice using a microphone and saves it as voice data. It then converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The input is voice data, and the output is text data. Specifically, the microphone detects the voice, and the server sends the voice data to a cloud service for conversion into text.

[0796] Step 3: Send text and profile data

[0797] The device sends the collected text data and the user's profile data (e.g., age, medical history) to the server. The input is the text data and profile data stored on the device, and the output is the data sent to the server. The specific operation is that the device sends the data to the server via the Internet.

[0798] Step 4: Natural Language Processing of the Data

[0799] The server passes the received text data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input is text data, and the output is extracted keywords and phrases. Specifically, the NLP engine analyzes the text and extracts specific keywords and phrases.

[0800] Step 5: Risk assessment

[0801] The server uses a risk assessment module (a custom-made algorithm) based on the extracted keywords to calculate a dementia risk score. The input is the extracted keywords, and the output is the risk score. The specific operation is that the risk assessment module evaluates the extracted keywords and calculates the risk score.

[0802] Step 6: Reporting the results of the evaluation

[0803] The server generates a report summarizing the risk assessment results. The report includes the user's risk level and recommended actions (e.g., consulting a specialist). The input is the risk score, and the output is a report of the assessment results. The specific operation is for the server to compile the risk assessment results into a document.

[0804] Step 7: Notification of evaluation results

[0805] The generated report is sent to the medical professional's terminal by the notification module, and simultaneously notified to the user's terminal. The input is the report of the assessment result, and the output is the notification sent to the medical professional and the user. The specific operation is that the notification module sends the report using a secure communication protocol.

[0806] Step 8: Continuous monitoring

[0807] The device periodically displays a reminder to the user to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). The user inputs new data by voice or text, which is then sent to the server. The input is the new data, and the output is the data sent to the server. The specific operation is that the device periodically displays a reminder message and collects new data from the user.

[0808] Step 9: Reanalyze data and update risk assessment

[0809] The server analyzes the newly collected data again using the natural language processing engine and compares it with past data. If a change in state is detected, it updates the risk assessment. The input is the new data and past data, and the output is an updated risk assessment. Specifically, the server analyzes the new data and updates the risk assessment based on the results.

[0810] Step 10: Notification of updated evaluation results

[0811] The updated risk assessment results are again notified to medical professionals and users through the notification module. If necessary, additional preventive measures or advice are provided. The input is the updated risk assessment, and the output is the notification sent to the medical professional and user. The specific operation is that the notification module sends the updated assessment results and provides the user with appropriate preventive measures or advice.

[0812] (Application example 1)

[0813] 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."

[0814] In today's world, early detection of dementia and appropriate care are essential, but because elderly people themselves are often unaware of the condition and regular checkups are difficult, monitoring by medical professionals and care facilities is often insufficient. Furthermore, dementia risk assessments are often temporary, with no continuous data collection or detection of changes in condition. Therefore, a system is needed for continuous monitoring and risk assessment updates in daily life, which will enable timely medical responses and appropriate care.

[0815] 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.

[0816] In this invention, the server includes a means for analyzing voice data from the user in real time and extracting important keywords, a means for displaying periodic reminders on the care robot to encourage continuous data collection, and a means for detecting changes in condition by comparing with past data and updating risk assessment. This makes it possible to continuously monitor the dementia risk of elderly people in their daily lives and quickly grasp any changes, thereby providing appropriate medical responses and preventive measures.

[0817] "Voice or text data" refers to voice information uttered by the user or text information input by the user, and is basic data for the system to analyze.

[0818] A "natural language processing engine" refers to algorithms or software that analyzes collected voice or text data, extracts keywords and phrases, and understands their meaning.

[0819] "Signs of dementia" are indicators that indicate the early stages of symptoms in which memory and thinking ability decline and interfere with daily life.

[0820] "Risk assessment" refers to the process of assessing a user's likelihood of dementia as a number or category based on the analysis results.

[0821] "Health Professional" refers to a person, such as a doctor or nurse, who has specific medical knowledge and is qualified to appropriately assess, diagnose, and treat a user's health condition.

[0822] "Care robots" are robots designed to assist the elderly and people who require care, and are devices equipped with voice recognition, data collection, reminder functions, etc.

[0823] "Reminders" refer to notifications and messages that periodically alert the user, and serve to collect new data and provide health management advice.

[0824] "Status change" refers to a change in the user's health condition or cognitive ability over time, and refers to a fluctuation compared to before.

[0825] "Real-time analysis" refers to the process of processing collected data immediately and quickly generating analytical results.

[0826] "Important keywords" refer to words or phrases extracted from user utterances or input text that have a particularly specific meaning in risk assessment.

[0827] System Configuration

[0828] The system of the present invention is a comprehensive support system for early detection of dementia risk in users and notifying medical professionals and care staff. The system is composed of the following components:

[0829] 1. User Device

[0830] 2. Server

[0831] 3. Speech Recognition Engine

[0832] 4. Natural Language Processing (NLP) Engine

[0833] 5. Risk Assessment Module

[0834] 6. Notification Module

[0835] Audio data collection

[0836] First, the user speaks about their health condition or daily life situation in front of the device, or inputs text. For example, the user might say, "I often forget where I put my keys these days." This speech is collected using the device's microphone and saved as voice data. The voice data is then converted into text using a voice recognition engine.

[0837] Data transmission and analysis

[0838] The user device sends the collected text data and user profile data (e.g., age, medical history) to the server. The server then analyzes the received data using a natural language processing engine to extract specific keywords and phrases (e.g., "forget" and "recent"). The risk assessment module then calculates a dementia risk score based on the extracted keywords and sets an appropriate risk level (high risk, medium risk, or low risk).

[0839] Reporting and notification of results

[0840] The server generates a report summarizing the risk assessment results and sends it to medical professionals and care staff via the notification module. At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[0841] Continuous monitoring

[0842] The system displays regular reminders to the user to collect new data. For example, it might ask, "Have you had any problems in your daily life recently?" The new data collected is sent to the server, and if a change in condition is detected compared with past data, the risk assessment is updated. Again, the updated risk assessment results are notified to medical professionals and care staff, who will provide additional preventive measures or advice as needed.

[0843] Hardware and Software

[0844] Hardware: Microphone, nursing robot (or a home PC)

[0845] Software: Python, Speech Recognition library, Scikit-learn, natural language processing engine, data analysis algorithms

[0846] Specific examples

[0847] 1. Entering the user's health status

[0848] The user says, "I've been getting worse recently," and the speech recognition engine converts this speech into text, generating text data such as "I've been getting worse recently."

[0849] 2. Data Analysis

[0850] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent." The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[0851] 3. Reporting and Notification of Results

[0852] The server generates a report containing the assessment result of "medium risk" and sends it to a medical professional. The user is notified of the symptoms of memory loss and is advised to consult a medical specialist as soon as possible.

[0853] 4. Continuous monitoring

[0854] A reminder is periodically displayed on the user's device asking, "Have you had any trouble in your daily life recently?" The user answers, "I often forget where I put my keys," and this data is sent to the server. The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk." A medical professional is notified of the latest assessment results, and the user is informed, "You are currently forgetting things more frequently. Please consult a specialist immediately."

[0855] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0856] Step 1:

[0857] The user starts up the device and inputs their health condition and daily life situation as voice or text data. If voice data is collected using a microphone, the user's speech is converted into text by a voice recognition engine. For example, the user might say, "I often forget where I put my keys these days." The input for this step is the user's voice or text data, and the output is text data.

[0858] Step 2:

[0859] The device sends the collected text data to the server. User profile data (e.g., age, medical history) is also sent at the same time. The input of this step is the text data and user profile data, and the output is the data sent to the server.

[0860] Step 3:

[0861] The server passes the received data to a natural language processing (NLP) engine to extract specific keywords or phrases. For example, keywords such as "forget" and "recent" can be extracted. The input for this step is text data, and the output is the extracted keywords.

[0862] Step 4:

[0863] The server calculates a dementia risk score using a risk assessment module based on the extracted keywords and sets a risk level (high, medium, or low risk). For example, it calculates a risk score based on the frequency of appearance of the keywords "forget" and "recent" and determines a medium risk. The input for this step is the extracted keywords, and the output is a risk score and risk level.

[0864] Step 5:

[0865] The server generates a report summarizing the risk assessment results and sends it to medical professionals and users through the notification module. For example, a report containing the assessment result of "medium risk" may be generated, with the message "There are signs of forgetfulness. Please consult a specialist as soon as possible." The input of this step is the risk score and risk level, and the output is the generated report and notification.

[0866] Step 6:

[0867] For continuous monitoring, the server displays periodic reminders on the user's device. For example, it displays a reminder such as "Have you had any troubles in your daily life recently?" The input of this step is the reminder setting data, and the output is the reminder displayed on the user's device.

[0868] Step 7:

[0869] The user responds to the reminder by entering new voice or text data, for example, "I often forget where I put my keys." The input for this step is the user's voice or text data, and the output is the new text data.

[0870] Step 8:

[0871] The device sends newly collected data to the server and compares it with past data to detect changes in the state. For example, by comparing past data with new data, it can determine that "the frequency of forgetfulness is increasing." The inputs of this step are new text data and past data, and the output is the analysis results.

[0872] Step 9:

[0873] The server updates the risk assessment based on the status change and notifies the medical professional and the user of the latest assessment result. For example, the updated result to "high risk" is notified to the medical professional, and the user is sent a message saying, "Your forgetfulness is currently increasing. Please consult a specialist immediately." The input of this step is the analysis result, and the output is the updated risk assessment result and notification.

[0874] 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.

[0875] System Overview

[0876] This patented system detects the user's risk of dementia at an early stage and, by analyzing the user's emotions, enables more accurate risk assessment and continuous health management. The system includes the following components:

[0877] 1. User Device

[0878] 2. Server

[0879] 3. Speech Recognition Engine

[0880] 4. Natural Language Processing (NLP) Engine

[0881] 5. Emotion Engine

[0882] 6. Risk Assessment Module

[0883] 7. Notification Module

[0884] System Operation Details

[0885] Data collection

[0886] 1. Users

[0887] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0888] For example, a user may say, "I often forget where I put my keys these days."

[0889] 2. Terminal

[0890] The device collects the user's voice and stores it as voice data.

[0891] When the user inputs text, the text data is saved as is.

[0892] The voice data is converted into text by the device's voice recognition engine.

[0893] Data transmission and analysis

[0894] 1. Terminal

[0895] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[0896] 2. Server

[0897] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[0898] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[0899] 3. Server

[0900] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[0901] The emotion engine tags emotions and attaches the data as emotional energy.

[0902] 4. Server

[0903] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[0904] Taking emotional data into account also allows for more accurate risk assessment.

[0905] Results report

[0906] 1. Server

[0907] Generate a report summarizing the risk assessment results.

[0908] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[0909] 2. Notification Module

[0910] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[0911] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0912] 3. Terminal

[0913] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[0914] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[0915] Continuous monitoring

[0916] 1. Terminal

[0917] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[0918] 2. Users

[0919] The user responds to the reminder by entering new information about their health condition via voice or text.

[0920] For example, you might answer, "I often forget where I put my keys."

[0921] 3. Terminal

[0922] Collect new voice data and convert it into text using a speech recognition engine.

[0923] The converted text data or the directly input text data is sent to the server.

[0924] 4. Server

[0925] The server receives the new data and re-analyzes it to compare it with the previous data.

[0926] If a change in state is detected, the risk assessment module updates the risk score.

[0927] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[0928] 5. Server

[0929] Generate a new report with the updated risk assessment results.

[0930] This report will again be communicated to medical professionals and users.

[0931] 6. Notification Module

[0932] If necessary, include additional precautions or advice in your report.

[0933] 7. Terminal

[0934] The updated assessment results and recommended actions are displayed on the user's device.

[0935] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[0936] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[0937] Specific example explanation

[0938] 1. Entering the user's health status

[0939] The user says aloud, "I've been getting more and more forgetful lately."

[0940] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[0941] 2. Specific examples of data analysis

[0942] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[0943] The server uses an emotion engine to detect the emotion "sadness" from the user's voice.

[0944] The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user as "medium risk."

[0945] 3. Specific examples of results reporting

[0946] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[0947] The user will be notified with a recommended action such as "You are showing signs of forgetfulness. Please consult a specialist as soon as possible," along with advice such as "You seem to be experiencing a lot of emotional fluctuations recently. Please take a moderate break."

[0948] 4. Specific examples of continuous monitoring

[0949] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[0950] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[0951] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[0952] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[0953] Additionally, if fluctuations in emotional data are observed, you will be notified with the message, "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits."

[0954] By taking into account the user's emotional data, this system enables more accurate early detection of dementia risk and provides appropriate preventive measures.

[0955] The processing flow will be explained below.

[0956] Step 1:

[0957] User

[0958] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[0959] For example, a user may say, "I often forget where I put my keys these days."

[0960] Step 2:

[0961] Terminal

[0962] The device collects the user's voice and stores it as voice data.

[0963] When the user inputs text, the text data is saved.

[0964] The voice data is converted into text by the device's voice recognition engine.

[0965] Step 3:

[0966] Terminal

[0967] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[0968] Step 4:

[0969] server

[0970] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[0971] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[0972] Step 5:

[0973] server

[0974] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[0975] The emotion engine tags emotions and appends the data as emotional information.

[0976] Step 6:

[0977] server

[0978] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[0979] Taking emotional data into account also allows for more accurate risk assessment.

[0980] Step 7:

[0981] server

[0982] Generate a report summarizing the risk assessment results.

[0983] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[0984] Step 8:

[0985] Notification Module

[0986] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[0987] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[0988] Step 9:

[0989] Terminal

[0990] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[0991] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[0992] Step 10:

[0993] Terminal

[0994] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[0995] Step 11:

[0996] User

[0997] The user responds to the reminder by entering new information about their health condition via voice or text.

[0998] For example, you might answer, "I often forget where I put my keys."

[0999] Step 12:

[1000] Terminal

[1001] Collect new voice data and convert it into text using a speech recognition engine.

[1002] The converted text data or the directly input text data is sent to the server.

[1003] Step 13:

[1004] server

[1005] The server receives the new data and re-analyzes it to compare it with the previous data.

[1006] If a change in state is detected, the risk assessment module updates the risk score.

[1007] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[1008] Step 14:

[1009] server

[1010] Generate a new report with the updated risk assessment results.

[1011] This report will again be communicated to medical professionals and users.

[1012] Step 15:

[1013] Notification Module

[1014] If necessary, include additional precautions or advice in your report.

[1015] Step 16:

[1016] Terminal

[1017] The updated assessment results and recommended actions are displayed on the user's device.

[1018] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[1019] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[1020] This series of processes enables early detection of a user's dementia risk, and further analysis of emotional data can improve the accuracy of risk assessment and support intervention at the appropriate time.

[1021] Example 2

[1022] 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."

[1023] In modern society, early detection of dementia and continuous health management are important issues. In particular, there is a need to detect the risk of dementia early and take necessary measures. However, current systems are inadequate in not only detecting signs of dementia but also taking into account the user's emotional state to provide more accurate risk assessment and appropriate advice. Therefore, there is a need for a comprehensive risk assessment system that also takes into account the user's emotional data.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1025] In this invention, the server includes means for collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia and emotions, means for performing a risk assessment based on the analysis results and the detected emotion data, means for notifying medical professionals and the user of preventive measures and health management advice based on the assessment results and emotions, means for periodically collecting new data from the user, means for comparing past data with new data to analyze changes in the user's condition and emotional fluctuations, means for updating the ongoing risk assessment based on the analysis results, means for notifying medical professionals and the user of preventive measures and advice based on the updated assessment results and emotional fluctuations, means for providing the user with preventive measures and advice based on the analysis results and the emotional data, and means for displaying reminders for applying the preventive measures and advice to the user's daily life. This enables more accurate risk assessment and appropriate advice that takes emotion data into account.

[1026] "User" refers to an individual who uses the system and inputs information about their health condition and daily life through voice or text.

[1027] "Voice data" is digital data that contains information input by voice by the user.

[1028] "Text data" is character string data that contains information entered by the user in text form.

[1029] A "natural language processing engine" is a software engine that analyzes and understands voice and text data, extracting keywords and phrases and analyzing their meaning.

[1030] The "emotion engine" is a software engine that detects emotions from a user's voice data and text data and tags the emotions.

[1031] "Risk Assessment Module" is a software module for calculating a user's dementia risk score based on data obtained from the natural language processing engine and the emotion engine.

[1032] "Assessment results" are information including the user's dementia risk score calculated by the risk assessment module and related analysis results.

[1033] "Preventive measures" are actions or measures recommended to users based on the results of risk assessment.

[1034] "Health management advice" is specific suggestions or recommendations for maintaining or improving the user's health.

[1035] "Notification Module" is a software module for notifying medical professionals and users of assessment results, preventative measures, and health care advice.

[1036] "Reminder" refers to a function that periodically notifies the user about new data input and application to daily life.

[1037] "Analysis results" is a general term for the data generated by the natural language processing engine and emotion engine, and the assessment results created by the risk assessment module.

[1038] This invention is a system that realizes more accurate risk assessment and continuous health management by detecting a user's dementia risk at an early stage and analyzing the user's emotions. The system includes a user terminal, a server, a voice recognition engine, a natural language processing (NLP) engine, an emotion engine, a risk assessment module, and a notification module.

[1039] System configuration

[1040] Hardware and Software

[1041] User device: A device (e.g., smartphone, tablet, PC) through which a user provides voice or text input.

[1042] Server: A central processing unit for data analysis and risk assessment. Uses a cloud-based or on-premise server.

[1043] Speech recognition engine: Software used to convert user voice data into text (e.g., Google Cloud Speech-to-Text, Amazon Transcribe).

[1044] Natural Language Processing (NLP) engine: Software for analyzing text data and extracting keywords and phrases (e.g., spaCy, NLTK).

[1045] Emotion engine: Software for detecting and tagging emotions from user voice and text data (e.g., IBM Watson Tone Analyzer).

[1046] Risk Assessment Module: Software that calculates a risk score based on data obtained from the natural language processing engine and sentiment engine.

[1047] Notification module: Software for notifying users and medical professionals of assessment results and health care advice.

[1048] System Operation

[1049] Data collection

[1050] The user launches the device application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is converted into text by the device's voice recognition engine.

[1051] Data transmission and analysis

[1052] The converted text data and the user's profile data (such as age and medical history) are sent from the device to the server. The server then passes this data to a natural language processing engine to begin analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[1053] Sentiment Analysis and Risk Assessment

[1054] The server then uses an emotion engine to analyze emotions from the user's voice and text data. The emotion engine then tags the data with emotions and adds them as emotional energy. Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score. Taking emotion data into account allows for more accurate risk assessment.

[1055] Reporting and notification of results

[1056] A report summarizing the risk assessment results is generated. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[1057] Specific examples

[1058] For example, a user might say, "I've been getting more forgetful lately." The device's speech recognition engine converts this into text, generating text data such as "I've been getting more forgetful lately." The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recently." At the same time, the emotion engine detects the emotion "sadness" from the user's voice. The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user to be at "medium risk." The server generates a report containing the "medium risk" assessment result and sends it to a medical professional. The user is notified of the recommended action, "You are showing signs of forgetfulness. Consult a specialist as soon as possible," along with advice such as "You seem to have experienced frequent emotional fluctuations recently. Take appropriate breaks."

[1059] Prompt Sentence Examples

[1060] "Please explain what emotion tag the emotion engine will assign when a user says, 'I've been getting more and more forgetful lately.' Also, please explain in detail the process by which the risk assessment module determines the risk to be medium."

[1061] This invention makes it possible to provide more accurate early detection of dementia risk and appropriate preventive measures that also take into account the user's emotional data.

[1062] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1063] Step 1: Data entry

[1064] Input: Voice or text data about the user's health and daily life

[1065] Output: User voice or text data is collected

[1066] The user starts the terminal application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is collected by the terminal.

[1067] Step 2: Data conversion

[1068] Input: User's voice data

[1069] Output: Audio data is converted to text data

[1070] The device converts the collected voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). For example, a speech sentence such as "I often forget where I put my keys these days" is converted into text such as "I often forget where I put my keys these days."

[1071] Step 3: Send data

[1072] Input: Text data and user profile data (e.g., age, medical history)

[1073] Output: Text data and profile data are sent to the server.

[1074] The converted text data and the user's profile data (age, medical history, etc.) are sent from the device to the server. For example, the text data "I often forget where I put my keys these days" along with the user's age and medical history are sent to the server.

[1075] Step 4: Natural Language Processing

[1076] Input: Text data

[1077] Output: Parsed keywords and phrases

[1078] The server passes the received text data to a natural language processing (NLP) engine (e.g., spaCy) and begins analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[1079] Step 5: Sentiment Analysis

[1080] Input: Text data

[1081] Output: Emotion data with emotion tags

[1082] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. The emotion engine tags the data with emotions and adds them as emotional energy. For example, an emotion tag such as "sadness" is added.

[1083] Step 6: Risk assessment

[1084] Input: Parsed keywords and sentiment data

[1085] Output: Dementia risk score

[1086] The server's risk assessment module calculates a dementia risk score based on the extracted keywords and emotion data. For example, based on the keywords "where do I put my keys" and "often forgetting" and the emotion data of "sadness," the risk assessment module may assess the risk as medium.

[1087] Step 7: Results generation and notification

[1088] Input: Risk assessment results

[1089] Output: Risk assessment report and notification messages

[1090] The server generates a report summarizing the risk assessment results. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[1091] Step 8: Continuous monitoring

[1092] Input: New audio or text data

[1093] Output: Updated risk assessment results

[1094] The user's device periodically displays reminders to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). In response to the reminders, the user inputs new health status information by voice or text. The new voice data is again converted into text by the speech recognition engine, and the converted text data or directly entered text data is sent to the server. The server receives the new data and analyzes it again to compare it with past data. If a change in status is detected, the risk assessment module updates the risk score. The updated risk assessment results are generated as a new report and notified to medical professionals and the user.

[1095] Such steps allow for comprehensive monitoring of the user's health and emotional state and provide appropriate risk assessment and advice.

[1096] (Application example 2)

[1097] 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."

[1098] The present invention relates to a system for managing a user's health. In particular, it aims to provide a system that can detect the risk of dementia early by having the user input voice and text data in a physical store, and further analyze emotional fluctuations to perform risk assessment. Another objective is to provide a mechanism that can recommend a consultation with a specialist based on the risk assessment results and support the user in improving their daily life.

[1099] The identification processing 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 collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia, means for performing a risk assessment based on the analysis results, means for notifying a medical professional and the user of the assessment results, means for the user to record their health status at a physical store and analyze the data to continuously manage their health, means for recommending a visit to a specialist based on the data analysis results, a reminder function for providing health management advice, means for providing the user with preventive measures and advice based on the analysis results, means for displaying reminders for applying the preventive measures and advice to the user's daily life, and means for analyzing the user's health status in real time and notifying the results. This allows the user to continuously manage their health status and to consult a specialist at the appropriate time.

[1100] "User" means a person who uses the system to record their health status and receive risk assessments and advice from medical professionals.

[1101] "Voice or text data" refers to voice or text data input by the user regarding their health condition or daily life.

[1102] A "natural language processing engine" is a technology that analyzes collected text data and extracts specific keywords and phrases.

[1103] "Signs of dementia" are signs that indicate the possibility of early dementia, which are inferred from the user's health condition and behavior.

[1104] "Risk assessment" is the process of calculating a risk score for the user's health status based on the analyzed data.

[1105] A "healthcare professional" is a medical professional whose role is to provide assessment results and advice.

[1106] "Brick and mortar store" refers to a physical store where users visit and use services or products.

[1107] "Health status" refers to the physical and mental state of a user in their daily life.

[1108] "Continuous health management" refers to the activity of managing a user's health condition over the long term by periodically collecting and analyzing the user's health data.

[1109] The "means for recommending a consultation with a specialist" is a mechanism for recommending that the user be examined by a specialist based on the risk assessment results.

[1110] "Health management advice" is specific guidance and advice for maintaining and improving the user's health in their daily lives.

[1111] The "reminder function" is a mechanism that provides notifications and alarms to prompt users to take specific actions or enter specific data.

[1112] "Real-time analysis" refers to the process of processing user data instantly and quickly calculating results.

[1113] The "risk assessment result" is the result of an assessment of the user's health condition obtained through analysis.

[1114] "Applying to daily life" refers to incorporating the provided advice and preventative measures into the user's daily life.

[1115] MODE FOR CARRYING OUT THE INVENTION

[1116] System Overview

[1117] The system of the present invention collects and analyzes users' voice or text data to detect signs of dementia and perform risk assessment. It also supports health management in physical stores and includes a mechanism for recommending consultations with specialists. The system includes the following main components:

[1118] 1. User Device

[1119] 2. Server

[1120] 3. Speech Recognition Engine

[1121] 4. Natural Language Processing Engine

[1122] 5. Sentiment Analysis Engine

[1123] 6. Risk Assessment Module

[1124] 7. Notification Module

[1125] 8. Interactive Kiosks in Brick-and-mortar Stores

[1126] Generating a Program

[1127] The system program consists of the following steps:

[1128] Hardware and software used

[1129] 1. Smartphone application: iOS, Android platform

[1130] 2. Speech recognition engine: Google Cloud Speech-to-Text API

[1131] 3. Natural Language Processing Engine: IBM Watson NLP

[1132] 4. Sentiment Analysis Engine: Microsoft Azure Text Analytics API

[1133] 5. Database: Firebase, MySQL

[1134] 6. Cloud Server: AWS EC2, Google Cloud Platform

[1135] Program processing

[1136] Data collection

[1137] Users input voice or text data using a smartphone app or an interactive kiosk terminal in a physical store. For example, a user might input, "I've been getting worse at forgetting things lately." This data is converted into text by the device's speech recognition engine (Google Cloud Speech-to-Text API).

[1138] Data transmission and analysis

[1139] The collected text data is sent to a cloud server using a secure protocol (HTTPS). The server analyzes the received data using a natural language processing engine (IBM Watson NLP) to extract specific keywords and phrases. At the same time, it calculates the user's sentiment score using a sentiment analysis engine (Microsoft Azure Text Analytics API).

[1140] Risk Assessment

[1141] The server-side risk assessment module assesses the user's dementia risk based on keywords extracted by natural language processing and the results of sentiment analysis. This assessment is quantified as a risk score.

[1142] Reporting and notification of results

[1143] Based on the evaluation results and emotion data, the server generates a detailed report and notifies the user and medical professionals, including recommendations for specialist consultations and advice on daily living.

[1144] Continuous monitoring

[1145] Users receive periodic reminders on their smartphones to collect new data, and the server receives the new data, compares it with past data, analyzes changes in status, and updates the risk assessment.

[1146] Specific example explanation

[1147] A user uses an interactive kiosk terminal in a physical store to voice-input, "I've been forgetting things a lot lately." This voice data is converted into text by a speech recognition engine and sent to a server. The server then analyzes the data using a natural language processing engine and a sentiment analysis engine, extracting the keyword "forgetfulness" and the emotion "sadness." A risk assessment module calculates a risk score based on this and determines the user as "medium risk." This assessment result is notified to the user and a medical professional, and a message appears on the user's smartphone stating, "You are showing signs of forgetfulness. We recommend that you see a specialist."

[1148] Prompt Sentence Examples

[1149] "Please tell me the specific hardware configuration and processing steps for designing an application that allows users to record their health status by voice in a physical store and analyzes the data in real time to detect early dementia risk."

[1150] This completes the description of the embodiment of the invention. This system allows users to continuously manage their health status and consult a specialist at the appropriate time.

[1151] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1152] Step 1: Enter your data

[1153] A user inputs voice or text data using an interactive kiosk terminal in a physical store or a smartphone app. For example, the user might say, "I've been getting more and more forgetful lately." This data input is stored on the terminal in the form of voice or text data.

[1154] Input: User voice or text data

[1155] Output: Saved audio or text data

[1156] Step 2: Voice Recognition

[1157] The device's speech recognition engine converts the stored voice data into text by analyzing the voice waveform and generating the corresponding text data using the Google Cloud Speech-to-Text API.

[1158] Input: Saved audio data

[1159] Output: Text data

[1160] Step 3: Sending data

[1161] The device sends the generated text data to a cloud server using a secure protocol (HTTPS), ensuring data integrity and confidentiality.

[1162] Input: Text data

[1163] Output: Text data sent to the server

[1164] Step 4: Natural Language Processing

[1165] The server analyzes the received text data using a natural language processing (NLP) engine. Specifically, it uses IBM Watson NLP to extract specific keywords and phrases and understand what the user is saying.

[1166] Input: Text data sent to the server

[1167] Output: Extracted keywords and phrases

[1168] Step 5: Sentiment Analysis

[1169] The server uses a sentiment analysis engine to calculate the user's sentiment score from the received text data, and adds sentiment tags (e.g., joy, sadness, anger) from the text using the Microsoft Azure Text Analytics API.

[1170] Input: Text data sent to the server

[1171] Output: Text data with sentiment scores

[1172] Step 6: Risk assessment

[1173] The server-side risk assessment module calculates a risk score based on keywords extracted by natural language processing and the emotion score. This risk score quantifies the user's dementia risk.

[1174] Input: Keywords, text data with sentiment scores

[1175] Output: Risk score

[1176] Step 7: Generate results

[1177] The server generates a detailed report based on the risk assessment results and emotion data, including the current risk level, the detected emotion data, and recommended actions (e.g., consulting a specialist).

[1178] Input: Risk score, sentiment data

[1179] Output: Evaluation result report

[1180] Step 8: Notification

[1181] The server then notifies the user and medical professionals of the generated report, sending the results to the user within the smartphone app and to medical professionals using a secure communication protocol.

[1182] Input: Evaluation result report

[1183] Output: Notified evaluation result report

[1184] Step 9: Continuous monitoring

[1185] Users receive periodic reminders via their smartphone app to enter new data, which is then sent back to the server via the same process flow, updating the risk assessment.

[1186] Input: New voice or text data

[1187] Output: Updated risk assessment results

[1188] The above is a concrete flow of the processing steps in this system, which allows users to continuously manage their health status and receive medical examinations from specialists at appropriate times.

[1189] 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.

[1190] 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.

[1191] 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.

[1192] [Third embodiment]

[1193] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1194] 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.

[1195] 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).

[1196] 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.

[1197] 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.

[1198] 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).

[1199] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] 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.

[1204] 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."

[1205] System Overview

[1206] The patented system is designed to detect early dementia risk in users and notify medical professionals and the users themselves. The system primarily consists of the following components:

[1207] 1. User Device

[1208] 2. Server

[1209] 3. Speech Recognition Engine

[1210] 4. Natural Language Processing (NLP) Engine

[1211] 5. Risk Assessment Module

[1212] 6. Notification Module

[1213] System Operation Details

[1214] Data collection

[1215] 1. Users

[1216] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[1217] For example, a user may say, "I often forget where I put my keys these days."

[1218] 2. Terminal

[1219] The device collects the user's voice and stores it as audio data, or stores the text input as is.

[1220] The voice data is converted into text by the device's voice recognition engine.

[1221] Data transmission and analysis

[1222] 1. Terminal

[1223] The stored text data and the user's profile data (e.g., age, medical history) are sent to a server.

[1224] 2. Server

[1225] The server passes the received data to a natural language processing engine for analysis.

[1226] The NLP engine extracts specific keywords and phrases (e.g., "forget" and "recent") from text data and understands what the user is saying.

[1227] 3. Server

[1228] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[1229] Based on this score, an appropriate risk level (high risk, medium risk, low risk) is set.

[1230] Results report

[1231] 1. Server

[1232] A report summarizing the risk assessment results is generated.

[1233] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[1234] 2. Notification Module

[1235] The report is sent to the medical professional's device using a secure communication protocol.

[1236] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[1237] 3. Terminal

[1238] The user's device will display a specific message such as, "You are showing signs of forgetfulness. We recommend that you see a specialist."

[1239] Continuous monitoring

[1240] 1. Terminal

[1241] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[1242] The user enters the answer by voice or text.

[1243] 2. Server

[1244] New data is continually collected and compared with past data.

[1245] If a change in status is detected, the risk assessment is updated.

[1246] 3. Notification Module

[1247] The updated risk assessment results are again communicated to medical professionals and users.

[1248] Additional precautions and advice will be provided where necessary.

[1249] Specific example explanation

[1250] 1. Entering the user's health status

[1251] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[1252] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[1253] 2. Specific examples of data analysis

[1254] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[1255] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[1256] 3. Specific examples of results reporting

[1257] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[1258] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[1259] 4. Specific examples of continuous monitoring

[1260] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[1261] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[1262] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[1263] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[1264] The system will support early detection and prevention of dementia through continuous data collection and risk assessment.

[1265] The processing flow will be explained below.

[1266] Step 1:

[1267] User

[1268] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[1269] For example, a user may say, "I often forget where I put my keys these days."

[1270] Step 2:

[1271] Terminal

[1272] The device collects the user's voice and stores it as voice data.

[1273] When the user inputs text, the text data is saved as is.

[1274] The voice data is converted into text by the device's voice recognition engine.

[1275] Step 3:

[1276] Terminal

[1277] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[1278] Step 4:

[1279] server

[1280] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[1281] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[1282] Step 5:

[1283] server

[1284] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[1285] Based on this score, the system assigns an appropriate risk level (high risk, medium risk, low risk).

[1286] Step 6:

[1287] server

[1288] Generate a report summarizing the risk assessment results.

[1289] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[1290] Step 7:

[1291] server

[1292] The notification module sends the report to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[1293] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[1294] Step 8:

[1295] Terminal

[1296] A specific message such as "You are showing signs of forgetfulness. We recommend that you see a specialist" will be displayed on the user's device.

[1297] Step 9:

[1298] Terminal

[1299] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[1300] Step 10:

[1301] User

[1302] The user responds to the reminder by entering new information about their health condition via voice or text.

[1303] For example, the user may respond, "I often forget where I put my keys."

[1304] Step 11:

[1305] Terminal

[1306] Collect new voice data and convert it into text using a speech recognition engine.

[1307] The converted text data or the directly input text data is sent to the server.

[1308] Step 12:

[1309] server

[1310] The server receives the new data and re-analyzes it to compare it with the previous data.

[1311] If a change in state is detected, the risk assessment module updates the risk score.

[1312] Step 13:

[1313] server

[1314] Generate a new report with the updated risk assessment results.

[1315] This report will again be communicated to medical professionals and users.

[1316] Step 14:

[1317] server

[1318] If necessary, include additional precautions or advice in your report.

[1319] Step 15:

[1320] Terminal

[1321] The updated assessment results and recommended actions are displayed on the user's device.

[1322] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[1323] This series of processes enables early detection of a user's dementia risk and supports intervention at the appropriate time.

[1324] Example 1

[1325] 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."

[1326] Currently, early detection and prevention of dementia requires a great deal of effort and specialized knowledge, and many people are unable to see a specialist or take the necessary measures at the appropriate time. For this reason, there is a need for a system that can detect users' dementia risk early and provide appropriate advice.

[1327] 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.

[1328] In this invention, the server includes means for collecting voice or text data from a user, means for converting the collected data into text using a voice recognition engine, means for analyzing the converted text data using a natural language processing engine to detect signs of dementia, means for conducting a risk assessment based on the analysis results, means for generating a report of the assessment results, and means for notifying a medical professional and the user of the generated report. This makes it possible to detect a user's risk of dementia early and provide appropriate advice or encourage the user to see a specialist.

[1329] "Voice or text data" refers to information input by the user in voice or text format about their health condition or daily life.

[1330] A "voice recognition engine" is a software or hardware technology for converting voice data into text data.

[1331] A "natural language processing engine" is a technology that extracts specific keywords and phrases from text data and understands the context.

[1332] "Signs of dementia" are characteristics or patterns that are revealed in a user's statements or behavior that may indicate a risk of dementia.

[1333] "Risk assessment" is the analytical process of quantifying or categorizing a user's dementia risk based on collected data.

[1334] A "report" is a document that summarizes the results of a risk assessment and includes the user's current risk level and recommended actions.

[1335] "Notification" is the act of communicating generated reports or important information to a user or medical professional.

[1336] "Preventive measures" are advice that indicates specific actions or efforts that the user should take to prevent the progression of dementia.

[1337] A "reminder" is a notification or message that is displayed periodically to prompt the user to take a specific action or confirm something.

[1338] MODE FOR CARRYING OUT THE INVENTION

[1339] This invention is a system for detecting early dementia risk in users and notifying medical professionals and the users themselves. The system mainly consists of the following components:

[1340] 1. User Device

[1341] 2. Server

[1342] 3. Speech Recognition Engine

[1343] 4. Natural Language Processing (NLP) Engine

[1344] 5. Risk Assessment Module

[1345] 6. Notification Module

[1346] Data collection

[1347] The user launches the application on the user device and either speaks about their health condition or daily life, or inputs text. For example, the user might say, "I often forget where I put my keys these days." The device collects the user's voice data and saves it as voice data, or saves the text input as is. The voice data is converted into text by the device's voice recognition engine (for example, Google Cloud Speech-to-Text API).

[1348] Data transmission and analysis

[1349] The device sends the saved text data and the user's profile data (e.g., age, medical history) to a server. The server passes the received data to a natural language processing (NLP) engine (e.g., Google Cloud Natural Language API) for analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text data and understands what the user is saying.

[1350] Risk assessment and reporting

[1351] Based on the extracted keywords, the server calculates a dementia risk score using a risk assessment module (a custom-made algorithm). An appropriate risk level (high risk, medium risk, or low risk) is set based on this score. A report summarizing the risk assessment results is generated, including the user's current risk level and recommended actions (e.g., visiting a specialist). The generated report is sent to the medical professional's device by the notification module, and is also notified on the user's device at the same time. A specific message such as "You are showing signs of forgetfulness. We recommend that you visit a specialist" is displayed on the user's device.

[1352] Continuous monitoring

[1353] Periodic reminders appear on the user's device to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?"). The user answers by voice or text, and the data is sent to the server. The server continuously collects new data and compares it with past data. If a change in condition is detected, the risk assessment is updated. The updated risk assessment results are again communicated to medical professionals and the user via the notification module. If necessary, additional preventive measures or advice are provided.

[1354] Specific examples

[1355] 1. Entering the user's health status

[1356] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[1357] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[1358] 2. Specific examples of data analysis

[1359] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[1360] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[1361] 3. Specific examples of results reporting

[1362] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[1363] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[1364] 4. Specific examples of continuous monitoring

[1365] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[1366] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[1367] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[1368] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[1369] Prompt Sentence Examples

[1370] "I've been getting really forgetful lately"

[1371] "Please extract keywords from the following text to assess the risk of dementia: 'I've been feeling increasingly forgetful recently.'"

[1372] "Generate a report showing users as medium risk. Include risk level and recommended actions."

[1373] Have you had any problems in your daily life recently?

[1374] In this way, the system detects users' dementia risk early and supports effective preventative measures through continuous monitoring and the provision of appropriate advice.

[1375] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1376] Step 1: User Data Entry

[1377] The user starts a terminal application and speaks about their health condition or daily life, or inputs text. For example, they might say, "I often forget where I put my keys these days." The input in this case is voice data or text data. Specifically, the user speaks to the terminal or inputs text.

[1378] Step 2: Collecting audio data and converting it to text

[1379] The device collects the user's voice using a microphone and saves it as voice data. It then converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The input is voice data, and the output is text data. Specifically, the microphone detects the voice, and the server sends the voice data to a cloud service for conversion into text.

[1380] Step 3: Send text and profile data

[1381] The device sends the collected text data and the user's profile data (e.g., age, medical history) to the server. The input is the text data and profile data stored on the device, and the output is the data sent to the server. The specific operation is that the device sends the data to the server via the Internet.

[1382] Step 4: Natural Language Processing of the Data

[1383] The server passes the received text data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input is text data, and the output is extracted keywords and phrases. Specifically, the NLP engine analyzes the text and extracts specific keywords and phrases.

[1384] Step 5: Risk assessment

[1385] The server uses a risk assessment module (a custom-made algorithm) based on the extracted keywords to calculate a dementia risk score. The input is the extracted keywords, and the output is the risk score. The specific operation is that the risk assessment module evaluates the extracted keywords and calculates the risk score.

[1386] Step 6: Reporting the results of the evaluation

[1387] The server generates a report summarizing the risk assessment results. The report includes the user's risk level and recommended actions (e.g., consulting a specialist). The input is the risk score, and the output is a report of the assessment results. The specific operation is for the server to compile the risk assessment results into a document.

[1388] Step 7: Notification of evaluation results

[1389] The generated report is sent to the medical professional's terminal by the notification module, and simultaneously notified to the user's terminal. The input is the report of the assessment result, and the output is the notification sent to the medical professional and the user. The specific operation is that the notification module sends the report using a secure communication protocol.

[1390] Step 8: Continuous monitoring

[1391] The device periodically displays a reminder to the user to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). The user inputs new data by voice or text, which is then sent to the server. The input is the new data, and the output is the data sent to the server. The specific operation is that the device periodically displays a reminder message and collects new data from the user.

[1392] Step 9: Reanalyze data and update risk assessment

[1393] The server analyzes the newly collected data again using the natural language processing engine and compares it with past data. If a change in state is detected, it updates the risk assessment. The input is the new data and past data, and the output is an updated risk assessment. Specifically, the server analyzes the new data and updates the risk assessment based on the results.

[1394] Step 10: Notification of updated evaluation results

[1395] The updated risk assessment results are again notified to medical professionals and users through the notification module. If necessary, additional preventive measures or advice are provided. The input is the updated risk assessment, and the output is the notification sent to the medical professional and user. The specific operation is that the notification module sends the updated assessment results and provides the user with appropriate preventive measures or advice.

[1396] (Application example 1)

[1397] 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."

[1398] In today's world, early detection of dementia and appropriate care are essential, but because elderly people themselves are often unaware of the condition and regular checkups are difficult, monitoring by medical professionals and care facilities is often insufficient. Furthermore, dementia risk assessments are often temporary, with no continuous data collection or detection of changes in condition. Therefore, a system is needed for continuous monitoring and risk assessment updates in daily life, which will enable timely medical responses and appropriate care.

[1399] 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.

[1400] In this invention, the server includes a means for analyzing voice data from the user in real time and extracting important keywords, a means for displaying periodic reminders on the care robot to encourage continuous data collection, and a means for detecting changes in condition by comparing with past data and updating risk assessment. This makes it possible to continuously monitor the dementia risk of elderly people in their daily lives and quickly grasp any changes, thereby providing appropriate medical responses and preventive measures.

[1401] "Voice or text data" refers to voice information uttered by the user or text information input by the user, and is basic data for the system to analyze.

[1402] A "natural language processing engine" refers to algorithms or software that analyzes collected voice or text data, extracts keywords and phrases, and understands their meaning.

[1403] "Signs of dementia" are indicators that indicate the early stages of symptoms in which memory and thinking ability decline and interfere with daily life.

[1404] "Risk assessment" refers to the process of assessing a user's likelihood of dementia as a number or category based on the analysis results.

[1405] "Health Professional" refers to a person, such as a doctor or nurse, who has specific medical knowledge and is qualified to appropriately assess, diagnose, and treat a user's health condition.

[1406] "Care robots" are robots designed to assist the elderly and people who require care, and are devices equipped with voice recognition, data collection, reminder functions, etc.

[1407] "Reminders" refer to notifications and messages that periodically alert the user, and serve to collect new data and provide health management advice.

[1408] "Status change" refers to a change in the user's health condition or cognitive ability over time, and refers to a fluctuation compared to before.

[1409] "Real-time analysis" refers to the process of processing collected data immediately and quickly generating analytical results.

[1410] "Important keywords" refer to words or phrases extracted from user utterances or input text that have a particularly specific meaning in risk assessment.

[1411] System Configuration

[1412] The system of the present invention is a comprehensive support system for early detection of dementia risk in users and notifying medical professionals and care staff. The system is composed of the following components:

[1413] 1. User Device

[1414] 2. Server

[1415] 3. Speech Recognition Engine

[1416] 4. Natural Language Processing (NLP) Engine

[1417] 5. Risk Assessment Module

[1418] 6. Notification Module

[1419] Audio data collection

[1420] First, the user speaks about their health condition or daily life situation in front of the device, or inputs text. For example, the user might say, "I often forget where I put my keys these days." This speech is collected using the device's microphone and saved as voice data. The voice data is then converted into text using a voice recognition engine.

[1421] Data transmission and analysis

[1422] The user device sends the collected text data and user profile data (e.g., age, medical history) to the server. The server then analyzes the received data using a natural language processing engine to extract specific keywords and phrases (e.g., "forget" and "recent"). The risk assessment module then calculates a dementia risk score based on the extracted keywords and sets an appropriate risk level (high risk, medium risk, or low risk).

[1423] Reporting and notification of results

[1424] The server generates a report summarizing the risk assessment results and sends it to medical professionals and care staff via the notification module. At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[1425] Continuous monitoring

[1426] The system displays regular reminders to the user to collect new data. For example, it might ask, "Have you had any problems in your daily life recently?" The new data collected is sent to the server, and if a change in condition is detected compared with past data, the risk assessment is updated. Again, the updated risk assessment results are notified to medical professionals and care staff, who will provide additional preventive measures or advice as needed.

[1427] Hardware and Software

[1428] Hardware: Microphone, nursing robot (or a home PC)

[1429] Software: Python, Speech Recognition library, Scikit-learn, natural language processing engine, data analysis algorithms

[1430] Specific examples

[1431] 1. Entering the user's health status

[1432] The user says, "I've been getting worse recently," and the speech recognition engine converts this speech into text, generating text data such as "I've been getting worse recently."

[1433] 2. Data Analysis

[1434] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent." The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[1435] 3. Reporting and Notification of Results

[1436] The server generates a report containing the assessment result of "medium risk" and sends it to a medical professional. The user is notified of the symptoms of memory loss and is advised to consult a medical specialist as soon as possible.

[1437] 4. Continuous monitoring

[1438] A reminder is periodically displayed on the user's device asking, "Have you had any trouble in your daily life recently?" The user answers, "I often forget where I put my keys," and this data is sent to the server. The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk." A medical professional is notified of the latest assessment results, and the user is informed, "You are currently forgetting things more frequently. Please consult a specialist immediately."

[1439] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1440] Step 1:

[1441] The user starts up the device and inputs their health condition and daily life situation as voice or text data. If voice data is collected using a microphone, the user's speech is converted into text by a voice recognition engine. For example, the user might say, "I often forget where I put my keys these days." The input for this step is the user's voice or text data, and the output is text data.

[1442] Step 2:

[1443] The device sends the collected text data to the server. User profile data (e.g., age, medical history) is also sent at the same time. The input of this step is the text data and user profile data, and the output is the data sent to the server.

[1444] Step 3:

[1445] The server passes the received data to a natural language processing (NLP) engine to extract specific keywords or phrases. For example, keywords such as "forget" and "recent" can be extracted. The input for this step is text data, and the output is the extracted keywords.

[1446] Step 4:

[1447] The server calculates a dementia risk score using a risk assessment module based on the extracted keywords and sets a risk level (high, medium, or low risk). For example, it calculates a risk score based on the frequency of appearance of the keywords "forget" and "recent" and determines a medium risk. The input for this step is the extracted keywords, and the output is a risk score and risk level.

[1448] Step 5:

[1449] The server generates a report summarizing the risk assessment results and sends it to medical professionals and users through the notification module. For example, a report containing the assessment result of "medium risk" may be generated, with the message "There are signs of forgetfulness. Please consult a specialist as soon as possible." The input of this step is the risk score and risk level, and the output is the generated report and notification.

[1450] Step 6:

[1451] For continuous monitoring, the server displays periodic reminders on the user's device. For example, it displays a reminder such as "Have you had any troubles in your daily life recently?" The input of this step is the reminder setting data, and the output is the reminder displayed on the user's device.

[1452] Step 7:

[1453] The user responds to the reminder by entering new voice or text data, for example, "I often forget where I put my keys." The input for this step is the user's voice or text data, and the output is the new text data.

[1454] Step 8:

[1455] The device sends newly collected data to the server and compares it with past data to detect changes in the state. For example, by comparing past data with new data, it can determine that "the frequency of forgetfulness is increasing." The inputs of this step are new text data and past data, and the output is the analysis results.

[1456] Step 9:

[1457] The server updates the risk assessment based on the status change and notifies the medical professional and the user of the latest assessment result. For example, the updated result to "high risk" is notified to the medical professional, and the user is sent a message saying, "Your forgetfulness is currently increasing. Please consult a specialist immediately." The input of this step is the analysis result, and the output is the updated risk assessment result and notification.

[1458] 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.

[1459] System Overview

[1460] This patented system detects the user's risk of dementia at an early stage and, by analyzing the user's emotions, enables more accurate risk assessment and continuous health management. The system includes the following components:

[1461] 1. User Device

[1462] 2. Server

[1463] 3. Speech Recognition Engine

[1464] 4. Natural Language Processing (NLP) Engine

[1465] 5. Emotion Engine

[1466] 6. Risk Assessment Module

[1467] 7. Notification Module

[1468] System Operation Details

[1469] Data collection

[1470] 1. Users

[1471] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[1472] For example, a user may say, "I often forget where I put my keys these days."

[1473] 2. Terminal

[1474] The device collects the user's voice and stores it as voice data.

[1475] When the user inputs text, the text data is saved as is.

[1476] The voice data is converted into text by the device's voice recognition engine.

[1477] Data transmission and analysis

[1478] 1. Terminal

[1479] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[1480] 2. Server

[1481] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[1482] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[1483] 3. Server

[1484] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[1485] The emotion engine tags emotions and attaches the data as emotional energy.

[1486] 4. Server

[1487] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[1488] Taking emotional data into account also allows for more accurate risk assessment.

[1489] Results report

[1490] 1. Server

[1491] Generate a report summarizing the risk assessment results.

[1492] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[1493] 2. Notification Module

[1494] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[1495] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[1496] 3. Terminal

[1497] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[1498] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[1499] Continuous monitoring

[1500] 1. Terminal

[1501] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[1502] 2. Users

[1503] The user responds to the reminder by entering new information about their health condition via voice or text.

[1504] For example, you might answer, "I often forget where I put my keys."

[1505] 3. Terminal

[1506] Collect new voice data and convert it into text using a speech recognition engine.

[1507] The converted text data or the directly input text data is sent to the server.

[1508] 4. Server

[1509] The server receives the new data and re-analyzes it to compare it with the previous data.

[1510] If a change in state is detected, the risk assessment module updates the risk score.

[1511] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[1512] 5. Server

[1513] Generate a new report with the updated risk assessment results.

[1514] This report will again be communicated to medical professionals and users.

[1515] 6. Notification Module

[1516] If necessary, include additional precautions or advice in your report.

[1517] 7. Terminal

[1518] The updated assessment results and recommended actions are displayed on the user's device.

[1519] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[1520] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[1521] Specific example explanation

[1522] 1. Entering the user's health status

[1523] The user says aloud, "I've been getting more and more forgetful lately."

[1524] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[1525] 2. Specific examples of data analysis

[1526] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[1527] The server uses an emotion engine to detect the emotion "sadness" from the user's voice.

[1528] The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user as "medium risk."

[1529] 3. Specific examples of results reporting

[1530] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[1531] The user will be notified with a recommended action such as "You are showing signs of forgetfulness. Please consult a specialist as soon as possible," along with advice such as "You seem to be experiencing a lot of emotional fluctuations recently. Please take a moderate break."

[1532] 4. Specific examples of continuous monitoring

[1533] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[1534] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[1535] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[1536] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[1537] Additionally, if fluctuations in emotional data are observed, you will be notified with the message, "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits."

[1538] By taking into account the user's emotional data, this system enables more accurate early detection of dementia risk and provides appropriate preventive measures.

[1539] The processing flow will be explained below.

[1540] Step 1:

[1541] User

[1542] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[1543] For example, a user may say, "I often forget where I put my keys these days."

[1544] Step 2:

[1545] Terminal

[1546] The device collects the user's voice and stores it as voice data.

[1547] When the user inputs text, the text data is saved.

[1548] The voice data is converted into text by the device's voice recognition engine.

[1549] Step 3:

[1550] Terminal

[1551] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[1552] Step 4:

[1553] server

[1554] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[1555] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[1556] Step 5:

[1557] server

[1558] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[1559] The emotion engine tags emotions and appends the data as emotional information.

[1560] Step 6:

[1561] server

[1562] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[1563] Taking emotional data into account also allows for more accurate risk assessment.

[1564] Step 7:

[1565] server

[1566] Generate a report summarizing the risk assessment results.

[1567] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[1568] Step 8:

[1569] Notification Module

[1570] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[1571] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[1572] Step 9:

[1573] Terminal

[1574] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[1575] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[1576] Step 10:

[1577] Terminal

[1578] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[1579] Step 11:

[1580] User

[1581] The user responds to the reminder by entering new information about their health condition via voice or text.

[1582] For example, you might answer, "I often forget where I put my keys."

[1583] Step 12:

[1584] Terminal

[1585] Collect new voice data and convert it into text using a speech recognition engine.

[1586] The converted text data or the directly input text data is sent to the server.

[1587] Step 13:

[1588] server

[1589] The server receives the new data and re-analyzes it to compare it with the previous data.

[1590] If a change in state is detected, the risk assessment module updates the risk score.

[1591] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[1592] Step 14:

[1593] server

[1594] Generate a new report with the updated risk assessment results.

[1595] This report will again be communicated to medical professionals and users.

[1596] Step 15:

[1597] Notification Module

[1598] If necessary, include additional precautions or advice in your report.

[1599] Step 16:

[1600] Terminal

[1601] The updated assessment results and recommended actions are displayed on the user's device.

[1602] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[1603] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[1604] This series of processes enables early detection of a user's dementia risk, and further analysis of emotional data can improve the accuracy of risk assessment and support intervention at the appropriate time.

[1605] Example 2

[1606] 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."

[1607] In modern society, early detection of dementia and continuous health management are important issues. In particular, there is a need to detect the risk of dementia early and take necessary measures. However, current systems are inadequate in not only detecting signs of dementia but also taking into account the user's emotional state to provide more accurate risk assessment and appropriate advice. Therefore, there is a need for a comprehensive risk assessment system that also takes into account the user's emotional data.

[1608] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1609] In this invention, the server includes means for collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia and emotions, means for performing a risk assessment based on the analysis results and the detected emotion data, means for notifying medical professionals and the user of preventive measures and health management advice based on the assessment results and emotions, means for periodically collecting new data from the user, means for comparing past data with new data to analyze changes in the user's condition and emotional fluctuations, means for updating the ongoing risk assessment based on the analysis results, means for notifying medical professionals and the user of preventive measures and advice based on the updated assessment results and emotional fluctuations, means for providing the user with preventive measures and advice based on the analysis results and the emotional data, and means for displaying reminders for applying the preventive measures and advice to the user's daily life. This enables more accurate risk assessment and appropriate advice that takes emotion data into account.

[1610] "User" refers to an individual who uses the system and inputs information about their health condition and daily life through voice or text.

[1611] "Voice data" is digital data that contains information input by voice by the user.

[1612] "Text data" is character string data that contains information entered by the user in text form.

[1613] A "natural language processing engine" is a software engine that analyzes and understands voice and text data, extracting keywords and phrases and analyzing their meaning.

[1614] The "emotion engine" is a software engine that detects emotions from a user's voice data and text data and tags the emotions.

[1615] "Risk Assessment Module" is a software module for calculating a user's dementia risk score based on data obtained from the natural language processing engine and the emotion engine.

[1616] "Assessment results" are information including the user's dementia risk score calculated by the risk assessment module and related analysis results.

[1617] "Preventive measures" are actions or measures recommended to users based on the results of risk assessment.

[1618] "Health management advice" is specific suggestions or recommendations for maintaining or improving the user's health.

[1619] "Notification Module" is a software module for notifying medical professionals and users of assessment results, preventative measures, and health care advice.

[1620] "Reminder" refers to a function that periodically notifies the user about new data input and application to daily life.

[1621] "Analysis results" is a general term for the data generated by the natural language processing engine and emotion engine, and the assessment results created by the risk assessment module.

[1622] This invention is a system that realizes more accurate risk assessment and continuous health management by detecting a user's dementia risk at an early stage and analyzing the user's emotions. The system includes a user terminal, a server, a voice recognition engine, a natural language processing (NLP) engine, an emotion engine, a risk assessment module, and a notification module.

[1623] System configuration

[1624] Hardware and Software

[1625] User device: A device (e.g., smartphone, tablet, PC) through which a user provides voice or text input.

[1626] Server: A central processing unit for data analysis and risk assessment. Uses a cloud-based or on-premise server.

[1627] Speech recognition engine: Software used to convert user voice data into text (e.g., Google Cloud Speech-to-Text, Amazon Transcribe).

[1628] Natural Language Processing (NLP) engine: Software for analyzing text data and extracting keywords and phrases (e.g., spaCy, NLTK).

[1629] Emotion engine: Software for detecting and tagging emotions from user voice and text data (e.g., IBM Watson Tone Analyzer).

[1630] Risk Assessment Module: Software that calculates a risk score based on data obtained from the natural language processing engine and sentiment engine.

[1631] Notification module: Software for notifying users and medical professionals of assessment results and health care advice.

[1632] System Operation

[1633] Data collection

[1634] The user launches the device application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is converted into text by the device's voice recognition engine.

[1635] Data transmission and analysis

[1636] The converted text data and the user's profile data (such as age and medical history) are sent from the device to the server. The server then passes this data to a natural language processing engine to begin analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[1637] Sentiment Analysis and Risk Assessment

[1638] The server then uses an emotion engine to analyze emotions from the user's voice and text data. The emotion engine then tags the data with emotions and adds them as emotional energy. Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score. Taking emotion data into account allows for more accurate risk assessment.

[1639] Reporting and notification of results

[1640] A report summarizing the risk assessment results is generated. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[1641] Specific examples

[1642] For example, a user might say, "I've been getting more forgetful lately." The device's speech recognition engine converts this into text, generating text data such as "I've been getting more forgetful lately." The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recently." At the same time, the emotion engine detects the emotion "sadness" from the user's voice. The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user to be at "medium risk." The server generates a report containing the "medium risk" assessment result and sends it to a medical professional. The user is notified of the recommended action, "You are showing signs of forgetfulness. Consult a specialist as soon as possible," along with advice such as "You seem to have experienced frequent emotional fluctuations recently. Take appropriate breaks."

[1643] Prompt Sentence Examples

[1644] "Please explain what emotion tag the emotion engine will assign when a user says, 'I've been getting more and more forgetful lately.' Also, please explain in detail the process by which the risk assessment module determines the risk to be medium."

[1645] This invention makes it possible to provide more accurate early detection of dementia risk and appropriate preventive measures that also take into account the user's emotional data.

[1646] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1647] Step 1: Data entry

[1648] Input: Voice or text data about the user's health and daily life

[1649] Output: User voice or text data is collected

[1650] The user starts the terminal application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is collected by the terminal.

[1651] Step 2: Data conversion

[1652] Input: User's voice data

[1653] Output: Audio data is converted to text data

[1654] The device converts the collected voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). For example, a speech sentence such as "I often forget where I put my keys these days" is converted into text such as "I often forget where I put my keys these days."

[1655] Step 3: Send data

[1656] Input: Text data and user profile data (e.g., age, medical history)

[1657] Output: Text data and profile data are sent to the server.

[1658] The converted text data and the user's profile data (age, medical history, etc.) are sent from the device to the server. For example, the text data "I often forget where I put my keys these days" along with the user's age and medical history are sent to the server.

[1659] Step 4: Natural Language Processing

[1660] Input: Text data

[1661] Output: Parsed keywords and phrases

[1662] The server passes the received text data to a natural language processing (NLP) engine (e.g., spaCy) and begins analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[1663] Step 5: Sentiment Analysis

[1664] Input: Text data

[1665] Output: Emotion data with emotion tags

[1666] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. The emotion engine tags the data with emotions and adds them as emotional energy. For example, an emotion tag such as "sadness" is added.

[1667] Step 6: Risk assessment

[1668] Input: Parsed keywords and sentiment data

[1669] Output: Dementia risk score

[1670] The server's risk assessment module calculates a dementia risk score based on the extracted keywords and emotion data. For example, based on the keywords "where do I put my keys" and "often forgetting" and the emotion data of "sadness," the risk assessment module may assess the risk as medium.

[1671] Step 7: Results generation and notification

[1672] Input: Risk assessment results

[1673] Output: Risk assessment report and notification messages

[1674] The server generates a report summarizing the risk assessment results. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[1675] Step 8: Continuous monitoring

[1676] Input: New audio or text data

[1677] Output: Updated risk assessment results

[1678] The user's device periodically displays reminders to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). In response to the reminders, the user inputs new health status information by voice or text. The new voice data is again converted into text by the speech recognition engine, and the converted text data or directly entered text data is sent to the server. The server receives the new data and analyzes it again to compare it with past data. If a change in status is detected, the risk assessment module updates the risk score. The updated risk assessment results are generated as a new report and notified to medical professionals and the user.

[1679] Such steps allow for comprehensive monitoring of the user's health and emotional state and provide appropriate risk assessment and advice.

[1680] (Application example 2)

[1681] 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."

[1682] The present invention relates to a system for managing a user's health. In particular, it aims to provide a system that can detect the risk of dementia early by having the user input voice and text data in a physical store, and further analyze emotional fluctuations to perform risk assessment. Another objective is to provide a mechanism that can recommend a consultation with a specialist based on the risk assessment results and support the user in improving their daily life.

[1683] The identification processing 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 collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia, means for performing a risk assessment based on the analysis results, means for notifying a medical professional and the user of the assessment results, means for the user to record their health status at a physical store and analyze the data to continuously manage their health, means for recommending a visit to a specialist based on the data analysis results, a reminder function for providing health management advice, means for providing the user with preventive measures and advice based on the analysis results, means for displaying reminders for applying the preventive measures and advice to the user's daily life, and means for analyzing the user's health status in real time and notifying the results. This allows the user to continuously manage their health status and to consult a specialist at the appropriate time.

[1684] "User" means a person who uses the system to record their health status and receive risk assessments and advice from medical professionals.

[1685] "Voice or text data" refers to voice or text data input by the user regarding their health condition or daily life.

[1686] A "natural language processing engine" is a technology that analyzes collected text data and extracts specific keywords and phrases.

[1687] "Signs of dementia" are signs that indicate the possibility of early dementia, which are inferred from the user's health condition and behavior.

[1688] "Risk assessment" is the process of calculating a risk score for the user's health status based on the analyzed data.

[1689] A "healthcare professional" is a medical professional whose role is to provide assessment results and advice.

[1690] "Brick and mortar store" refers to a physical store where users visit and use services or products.

[1691] "Health status" refers to the physical and mental state of a user in their daily life.

[1692] "Continuous health management" refers to the activity of managing a user's health condition over the long term by periodically collecting and analyzing the user's health data.

[1693] The "means for recommending a consultation with a specialist" is a mechanism for recommending that the user be examined by a specialist based on the risk assessment results.

[1694] "Health management advice" is specific guidance and advice for maintaining and improving the user's health in their daily lives.

[1695] The "reminder function" is a mechanism that provides notifications and alarms to prompt users to take specific actions or enter specific data.

[1696] "Real-time analysis" refers to the process of processing user data instantly and quickly calculating results.

[1697] The "risk assessment result" is the result of an assessment of the user's health condition obtained through analysis.

[1698] "Applying to daily life" refers to incorporating the provided advice and preventative measures into the user's daily life.

[1699] MODE FOR CARRYING OUT THE INVENTION

[1700] System Overview

[1701] The system of the present invention collects and analyzes users' voice or text data to detect signs of dementia and perform risk assessment. It also supports health management in physical stores and includes a mechanism for recommending consultations with specialists. The system includes the following main components:

[1702] 1. User Device

[1703] 2. Server

[1704] 3. Speech Recognition Engine

[1705] 4. Natural Language Processing Engine

[1706] 5. Sentiment Analysis Engine

[1707] 6. Risk Assessment Module

[1708] 7. Notification Module

[1709] 8. Interactive Kiosks in Brick-and-mortar Stores

[1710] Generating a Program

[1711] The system program consists of the following steps:

[1712] Hardware and software used

[1713] 1. Smartphone application: iOS, Android platform

[1714] 2. Speech recognition engine: Google Cloud Speech-to-Text API

[1715] 3. Natural Language Processing Engine: IBM Watson NLP

[1716] 4. Sentiment Analysis Engine: Microsoft Azure Text Analytics API

[1717] 5. Database: Firebase, MySQL

[1718] 6. Cloud Server: AWS EC2, Google Cloud Platform

[1719] Program processing

[1720] Data collection

[1721] Users input voice or text data using a smartphone app or an interactive kiosk terminal in a physical store. For example, a user might input, "I've been getting worse at forgetting things lately." This data is converted into text by the device's speech recognition engine (Google Cloud Speech-to-Text API).

[1722] Data transmission and analysis

[1723] The collected text data is sent to a cloud server using a secure protocol (HTTPS). The server analyzes the received data using a natural language processing engine (IBM Watson NLP) to extract specific keywords and phrases. At the same time, it calculates the user's sentiment score using a sentiment analysis engine (Microsoft Azure Text Analytics API).

[1724] Risk Assessment

[1725] The server-side risk assessment module assesses the user's dementia risk based on keywords extracted by natural language processing and the results of sentiment analysis. This assessment is quantified as a risk score.

[1726] Reporting and notification of results

[1727] Based on the evaluation results and emotion data, the server generates a detailed report and notifies the user and medical professionals, including recommendations for specialist consultations and advice on daily living.

[1728] Continuous monitoring

[1729] Users receive periodic reminders on their smartphones to collect new data, and the server receives the new data, compares it with past data, analyzes changes in status, and updates the risk assessment.

[1730] Specific example explanation

[1731] A user uses an interactive kiosk terminal in a physical store to voice-input, "I've been forgetting things a lot lately." This voice data is converted into text by a speech recognition engine and sent to a server. The server then analyzes the data using a natural language processing engine and a sentiment analysis engine, extracting the keyword "forgetfulness" and the emotion "sadness." A risk assessment module calculates a risk score based on this and determines the user as "medium risk." This assessment result is notified to the user and a medical professional, and a message appears on the user's smartphone stating, "You are showing signs of forgetfulness. We recommend that you see a specialist."

[1732] Prompt Sentence Examples

[1733] "Please tell me the specific hardware configuration and processing steps for designing an application that allows users to record their health status by voice in a physical store and analyzes the data in real time to detect early dementia risk."

[1734] This completes the description of the embodiment of the invention. This system allows users to continuously manage their health status and consult a specialist at the appropriate time.

[1735] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1736] Step 1: Enter your data

[1737] A user inputs voice or text data using an interactive kiosk terminal in a physical store or a smartphone app. For example, the user might say, "I've been getting more and more forgetful lately." This data input is stored on the terminal in the form of voice or text data.

[1738] Input: User voice or text data

[1739] Output: Saved audio or text data

[1740] Step 2: Voice Recognition

[1741] The device's speech recognition engine converts the stored voice data into text by analyzing the voice waveform and generating the corresponding text data using the Google Cloud Speech-to-Text API.

[1742] Input: Saved audio data

[1743] Output: Text data

[1744] Step 3: Sending data

[1745] The device sends the generated text data to a cloud server using a secure protocol (HTTPS), ensuring data integrity and confidentiality.

[1746] Input: Text data

[1747] Output: Text data sent to the server

[1748] Step 4: Natural Language Processing

[1749] The server analyzes the received text data using a natural language processing (NLP) engine. Specifically, it uses IBM Watson NLP to extract specific keywords and phrases and understand what the user is saying.

[1750] Input: Text data sent to the server

[1751] Output: Extracted keywords and phrases

[1752] Step 5: Sentiment Analysis

[1753] The server uses a sentiment analysis engine to calculate the user's sentiment score from the received text data, and adds sentiment tags (e.g., joy, sadness, anger) from the text using the Microsoft Azure Text Analytics API.

[1754] Input: Text data sent to the server

[1755] Output: Text data with sentiment scores

[1756] Step 6: Risk assessment

[1757] The server-side risk assessment module calculates a risk score based on keywords extracted by natural language processing and the emotion score. This risk score quantifies the user's dementia risk.

[1758] Input: Keywords, text data with sentiment scores

[1759] Output: Risk score

[1760] Step 7: Generate results

[1761] The server generates a detailed report based on the risk assessment results and emotion data, including the current risk level, the detected emotion data, and recommended actions (e.g., consulting a specialist).

[1762] Input: Risk score, sentiment data

[1763] Output: Evaluation result report

[1764] Step 8: Notification

[1765] The server then notifies the user and medical professionals of the generated report, sending the results to the user within the smartphone app and to medical professionals using a secure communication protocol.

[1766] Input: Evaluation result report

[1767] Output: Notified evaluation result report

[1768] Step 9: Continuous monitoring

[1769] Users receive periodic reminders via their smartphone app to enter new data, which is then sent back to the server via the same process flow, updating the risk assessment.

[1770] Input: New voice or text data

[1771] Output: Updated risk assessment results

[1772] The above is a concrete flow of the processing steps in this system, which allows users to continuously manage their health status and receive medical examinations from specialists at appropriate times.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] [Fourth embodiment]

[1777] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1778] 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.

[1779] 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).

[1780] 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.

[1781] 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.

[1782] 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).

[1783] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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."

[1790] System Overview

[1791] The patented system is designed to detect early dementia risk in users and notify medical professionals and the users themselves. The system primarily consists of the following components:

[1792] 1. User Device

[1793] 2. Server

[1794] 3. Speech Recognition Engine

[1795] 4. Natural Language Processing (NLP) Engine

[1796] 5. Risk Assessment Module

[1797] 6. Notification Module

[1798] System Operation Details

[1799] Data collection

[1800] 1. Users

[1801] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[1802] For example, a user may say, "I often forget where I put my keys these days."

[1803] 2. Terminal

[1804] The device collects the user's voice and stores it as audio data, or stores the text input as is.

[1805] The voice data is converted into text by the device's voice recognition engine.

[1806] Data transmission and analysis

[1807] 1. Terminal

[1808] The stored text data and the user's profile data (e.g., age, medical history) are sent to a server.

[1809] 2. Server

[1810] The server passes the received data to a natural language processing engine for analysis.

[1811] The NLP engine extracts specific keywords and phrases (e.g., "forget" and "recent") from text data and understands what the user is saying.

[1812] 3. Server

[1813] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[1814] Based on this score, an appropriate risk level (high risk, medium risk, low risk) is set.

[1815] Results report

[1816] 1. Server

[1817] A report summarizing the risk assessment results is generated.

[1818] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[1819] 2. Notification Module

[1820] The report is sent to the medical professional's device using a secure communication protocol.

[1821] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[1822] 3. Terminal

[1823] The user's device will display a specific message such as, "You are showing signs of forgetfulness. We recommend that you see a specialist."

[1824] Continuous monitoring

[1825] 1. Terminal

[1826] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[1827] The user enters the answer by voice or text.

[1828] 2. Server

[1829] New data is continually collected and compared with past data.

[1830] If a change in status is detected, the risk assessment is updated.

[1831] 3. Notification Module

[1832] The updated risk assessment results are again communicated to medical professionals and users.

[1833] Additional precautions and advice will be provided where necessary.

[1834] Specific example explanation

[1835] 1. Entering the user's health status

[1836] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[1837] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[1838] 2. Specific examples of data analysis

[1839] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[1840] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[1841] 3. Specific examples of results reporting

[1842] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[1843] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[1844] 4. Specific examples of continuous monitoring

[1845] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[1846] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[1847] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[1848] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[1849] The system will support early detection and prevention of dementia through continuous data collection and risk assessment.

[1850] The processing flow will be explained below.

[1851] Step 1:

[1852] User

[1853] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[1854] For example, a user may say, "I often forget where I put my keys these days."

[1855] Step 2:

[1856] Terminal

[1857] The device collects the user's voice and stores it as voice data.

[1858] When the user inputs text, the text data is saved as is.

[1859] The voice data is converted into text by the device's voice recognition engine.

[1860] Step 3:

[1861] Terminal

[1862] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[1863] Step 4:

[1864] server

[1865] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[1866] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[1867] Step 5:

[1868] server

[1869] Based on the extracted keywords, the risk assessment module calculates a dementia risk score.

[1870] Based on this score, the system assigns an appropriate risk level (high risk, medium risk, low risk).

[1871] Step 6:

[1872] server

[1873] Generate a report summarizing the risk assessment results.

[1874] The report includes the user's current risk level and recommended actions (e.g., see a specialist).

[1875] Step 7:

[1876] server

[1877] The notification module sends the report to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[1878] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[1879] Step 8:

[1880] Terminal

[1881] A specific message such as "You are showing signs of forgetfulness. We recommend that you see a specialist" will be displayed on the user's device.

[1882] Step 9:

[1883] Terminal

[1884] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[1885] Step 10:

[1886] User

[1887] The user responds to the reminder by entering new information about their health condition via voice or text.

[1888] For example, the user may respond, "I often forget where I put my keys."

[1889] Step 11:

[1890] Terminal

[1891] Collect new voice data and convert it into text using a speech recognition engine.

[1892] The converted text data or the directly input text data is sent to the server.

[1893] Step 12:

[1894] server

[1895] The server receives the new data and re-analyzes it to compare it with the previous data.

[1896] If a change in state is detected, the risk assessment module updates the risk score.

[1897] Step 13:

[1898] server

[1899] Generate a new report with the updated risk assessment results.

[1900] This report will again be communicated to medical professionals and users.

[1901] Step 14:

[1902] server

[1903] If necessary, include additional precautions or advice in your report.

[1904] Step 15:

[1905] Terminal

[1906] The updated assessment results and recommended actions are displayed on the user's device.

[1907] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[1908] This series of processes enables early detection of a user's dementia risk and supports intervention at the appropriate time.

[1909] Example 1

[1910] 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."

[1911] Currently, early detection and prevention of dementia requires a great deal of effort and specialized knowledge, and many people are unable to see a specialist or take the necessary measures at the appropriate time. For this reason, there is a need for a system that can detect users' dementia risk early and provide appropriate advice.

[1912] 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.

[1913] In this invention, the server includes means for collecting voice or text data from a user, means for converting the collected data into text using a voice recognition engine, means for analyzing the converted text data using a natural language processing engine to detect signs of dementia, means for conducting a risk assessment based on the analysis results, means for generating a report of the assessment results, and means for notifying a medical professional and the user of the generated report. This makes it possible to detect a user's risk of dementia early and provide appropriate advice or encourage the user to see a specialist.

[1914] "Voice or text data" refers to information input by the user in voice or text format about their health condition or daily life.

[1915] A "voice recognition engine" is a software or hardware technology for converting voice data into text data.

[1916] A "natural language processing engine" is a technology that extracts specific keywords and phrases from text data and understands the context.

[1917] "Signs of dementia" are characteristics or patterns that are revealed in a user's statements or behavior that may indicate a risk of dementia.

[1918] "Risk assessment" is the analytical process of quantifying or categorizing a user's dementia risk based on collected data.

[1919] A "report" is a document that summarizes the results of a risk assessment and includes the user's current risk level and recommended actions.

[1920] "Notification" is the act of communicating generated reports or important information to a user or medical professional.

[1921] "Preventive measures" are advice that indicates specific actions or efforts that the user should take to prevent the progression of dementia.

[1922] A "reminder" is a notification or message that is displayed periodically to prompt the user to take a specific action or confirm something.

[1923] MODE FOR CARRYING OUT THE INVENTION

[1924] This invention is a system for detecting early dementia risk in users and notifying medical professionals and the users themselves. The system mainly consists of the following components:

[1925] 1. User Device

[1926] 2. Server

[1927] 3. Speech Recognition Engine

[1928] 4. Natural Language Processing (NLP) Engine

[1929] 5. Risk Assessment Module

[1930] 6. Notification Module

[1931] Data collection

[1932] The user launches the application on the user device and either speaks about their health condition or daily life, or inputs text. For example, the user might say, "I often forget where I put my keys these days." The device collects the user's voice data and saves it as voice data, or saves the text input as is. The voice data is converted into text by the device's voice recognition engine (for example, Google Cloud Speech-to-Text API).

[1933] Data transmission and analysis

[1934] The device sends the saved text data and the user's profile data (e.g., age, medical history) to a server. The server passes the received data to a natural language processing (NLP) engine (e.g., Google Cloud Natural Language API) for analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text data and understands what the user is saying.

[1935] Risk assessment and reporting

[1936] Based on the extracted keywords, the server calculates a dementia risk score using a risk assessment module (a custom-made algorithm). An appropriate risk level (high risk, medium risk, or low risk) is set based on this score. A report summarizing the risk assessment results is generated, including the user's current risk level and recommended actions (e.g., visiting a specialist). The generated report is sent to the medical professional's device by the notification module, and is also notified on the user's device at the same time. A specific message such as "You are showing signs of forgetfulness. We recommend that you visit a specialist" is displayed on the user's device.

[1937] Continuous monitoring

[1938] Periodic reminders appear on the user's device to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?"). The user answers by voice or text, and the data is sent to the server. The server continuously collects new data and compares it with past data. If a change in condition is detected, the risk assessment is updated. The updated risk assessment results are again communicated to medical professionals and the user via the notification module. If necessary, additional preventive measures or advice are provided.

[1939] Specific examples

[1940] 1. Entering the user's health status

[1941] The user speaks to the terminal, "I've been getting more and more forgetful lately."

[1942] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[1943] 2. Specific examples of data analysis

[1944] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[1945] The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[1946] 3. Specific examples of results reporting

[1947] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[1948] The user is notified of the recommended action: "You are showing signs of forgetfulness. Please consult a specialist as soon as possible."

[1949] 4. Specific examples of continuous monitoring

[1950] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[1951] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[1952] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[1953] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[1954] Prompt Sentence Examples

[1955] "I've been getting really forgetful lately"

[1956] "Please extract keywords from the following text to assess the risk of dementia: 'I've been feeling increasingly forgetful recently.'"

[1957] "Generate a report showing users as medium risk. Include risk level and recommended actions."

[1958] Have you had any problems in your daily life recently?

[1959] In this way, the system detects users' dementia risk early and supports effective preventative measures through continuous monitoring and the provision of appropriate advice.

[1960] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1961] Step 1: User Data Entry

[1962] The user starts a terminal application and speaks about their health condition or daily life, or inputs text. For example, they might say, "I often forget where I put my keys these days." The input in this case is voice data or text data. Specifically, the user speaks to the terminal or inputs text.

[1963] Step 2: Collecting audio data and converting it to text

[1964] The device collects the user's voice using a microphone and saves it as voice data. It then converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The input is voice data, and the output is text data. Specifically, the microphone detects the voice, and the server sends the voice data to a cloud service for conversion into text.

[1965] Step 3: Send text and profile data

[1966] The device sends the collected text data and the user's profile data (e.g., age, medical history) to the server. The input is the text data and profile data stored on the device, and the output is the data sent to the server. The specific operation is that the device sends the data to the server via the Internet.

[1967] Step 4: Natural Language Processing of the Data

[1968] The server passes the received text data to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. The input is text data, and the output is extracted keywords and phrases. Specifically, the NLP engine analyzes the text and extracts specific keywords and phrases.

[1969] Step 5: Risk assessment

[1970] The server uses a risk assessment module (a custom-made algorithm) based on the extracted keywords to calculate a dementia risk score. The input is the extracted keywords, and the output is the risk score. The specific operation is that the risk assessment module evaluates the extracted keywords and calculates the risk score.

[1971] Step 6: Reporting the results of the evaluation

[1972] The server generates a report summarizing the risk assessment results. The report includes the user's risk level and recommended actions (e.g., consulting a specialist). The input is the risk score, and the output is a report of the assessment results. The specific operation is for the server to compile the risk assessment results into a document.

[1973] Step 7: Notification of evaluation results

[1974] The generated report is sent to the medical professional's terminal by the notification module, and simultaneously notified to the user's terminal. The input is the report of the assessment result, and the output is the notification sent to the medical professional and the user. The specific operation is that the notification module sends the report using a secure communication protocol.

[1975] Step 8: Continuous monitoring

[1976] The device periodically displays a reminder to the user to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). The user inputs new data by voice or text, which is then sent to the server. The input is the new data, and the output is the data sent to the server. The specific operation is that the device periodically displays a reminder message and collects new data from the user.

[1977] Step 9: Reanalyze data and update risk assessment

[1978] The server analyzes the newly collected data again using the natural language processing engine and compares it with past data. If a change in state is detected, it updates the risk assessment. The input is the new data and past data, and the output is an updated risk assessment. Specifically, the server analyzes the new data and updates the risk assessment based on the results.

[1979] Step 10: Notification of updated evaluation results

[1980] The updated risk assessment results are again notified to medical professionals and users through the notification module. If necessary, additional preventive measures or advice are provided. The input is the updated risk assessment, and the output is the notification sent to the medical professional and user. The specific operation is that the notification module sends the updated assessment results and provides the user with appropriate preventive measures or advice.

[1981] (Application example 1)

[1982] 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."

[1983] In today's world, early detection of dementia and appropriate care are essential, but because elderly people themselves are often unaware of the condition and regular checkups are difficult, monitoring by medical professionals and care facilities is often insufficient. Furthermore, dementia risk assessments are often temporary, with no continuous data collection or detection of changes in condition. Therefore, a system is needed for continuous monitoring and risk assessment updates in daily life, which will enable timely medical responses and appropriate care.

[1984] 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.

[1985] In this invention, the server includes a means for analyzing voice data from the user in real time and extracting important keywords, a means for displaying periodic reminders on the care robot to encourage continuous data collection, and a means for detecting changes in condition by comparing with past data and updating risk assessment. This makes it possible to continuously monitor the dementia risk of elderly people in their daily lives and quickly grasp any changes, thereby providing appropriate medical responses and preventive measures.

[1986] "Voice or text data" refers to voice information uttered by the user or text information input by the user, and is basic data for the system to analyze.

[1987] A "natural language processing engine" refers to algorithms or software that analyzes collected voice or text data, extracts keywords and phrases, and understands their meaning.

[1988] "Signs of dementia" are indicators that indicate the early stages of symptoms in which memory and thinking ability decline and interfere with daily life.

[1989] "Risk assessment" refers to the process of assessing a user's likelihood of dementia as a number or category based on the analysis results.

[1990] "Health Professional" refers to a person, such as a doctor or nurse, who has specific medical knowledge and is qualified to appropriately assess, diagnose, and treat a user's health condition.

[1991] "Care robots" are robots designed to assist the elderly and people who require care, and are devices equipped with voice recognition, data collection, reminder functions, etc.

[1992] "Reminders" refer to notifications and messages that periodically alert the user, and serve to collect new data and provide health management advice.

[1993] "Status change" refers to a change in the user's health condition or cognitive ability over time, and refers to a fluctuation compared to before.

[1994] "Real-time analysis" refers to the process of processing collected data immediately and quickly generating analytical results.

[1995] "Important keywords" refer to words or phrases extracted from user utterances or input text that have a particularly specific meaning in risk assessment.

[1996] System Configuration

[1997] The system of the present invention is a comprehensive support system for early detection of dementia risk in users and notifying medical professionals and care staff. The system is composed of the following components:

[1998] 1. User Device

[1999] 2. Server

[2000] 3. Speech Recognition Engine

[2001] 4. Natural Language Processing (NLP) Engine

[2002] 5. Risk Assessment Module

[2003] 6. Notification Module

[2004] Audio data collection

[2005] First, the user speaks about their health condition or daily life situation in front of the device, or inputs text. For example, the user might say, "I often forget where I put my keys these days." This speech is collected using the device's microphone and saved as voice data. The voice data is then converted into text using a voice recognition engine.

[2006] Data transmission and analysis

[2007] The user device sends the collected text data and user profile data (e.g., age, medical history) to the server. The server then analyzes the received data using a natural language processing engine to extract specific keywords and phrases (e.g., "forget" and "recent"). The risk assessment module then calculates a dementia risk score based on the extracted keywords and sets an appropriate risk level (high risk, medium risk, or low risk).

[2008] Reporting and notification of results

[2009] The server generates a report summarizing the risk assessment results and sends it to medical professionals and care staff via the notification module. At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[2010] Continuous monitoring

[2011] The system displays regular reminders to the user to collect new data. For example, it might ask, "Have you had any problems in your daily life recently?" The new data collected is sent to the server, and if a change in condition is detected compared with past data, the risk assessment is updated. Again, the updated risk assessment results are notified to medical professionals and care staff, who will provide additional preventive measures or advice as needed.

[2012] Hardware and Software

[2013] Hardware: Microphone, nursing robot (or a home PC)

[2014] Software: Python, Speech Recognition library, Scikit-learn, natural language processing engine, data analysis algorithms

[2015] Specific examples

[2016] 1. Entering the user's health status

[2017] The user says, "I've been getting worse recently," and the speech recognition engine converts this speech into text, generating text data such as "I've been getting worse recently."

[2018] 2. Data Analysis

[2019] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent." The risk assessment module calculates a risk score based on these keywords and determines the user as a "medium risk."

[2020] 3. Reporting and Notification of Results

[2021] The server generates a report containing the assessment result of "medium risk" and sends it to a medical professional. The user is notified of the symptoms of memory loss and is advised to consult a medical specialist as soon as possible.

[2022] 4. Continuous monitoring

[2023] A reminder is periodically displayed on the user's device asking, "Have you had any trouble in your daily life recently?" The user answers, "I often forget where I put my keys," and this data is sent to the server. The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk." A medical professional is notified of the latest assessment results, and the user is informed, "You are currently forgetting things more frequently. Please consult a specialist immediately."

[2024] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2025] Step 1:

[2026] The user starts up the device and inputs their health condition and daily life situation as voice or text data. If voice data is collected using a microphone, the user's speech is converted into text by a voice recognition engine. For example, the user might say, "I often forget where I put my keys these days." The input for this step is the user's voice or text data, and the output is text data.

[2027] Step 2:

[2028] The device sends the collected text data to the server. User profile data (e.g., age, medical history) is also sent at the same time. The input of this step is the text data and user profile data, and the output is the data sent to the server.

[2029] Step 3:

[2030] The server passes the received data to a natural language processing (NLP) engine to extract specific keywords or phrases. For example, keywords such as "forget" and "recent" can be extracted. The input for this step is text data, and the output is the extracted keywords.

[2031] Step 4:

[2032] The server calculates a dementia risk score using a risk assessment module based on the extracted keywords and sets a risk level (high, medium, or low risk). For example, it calculates a risk score based on the frequency of appearance of the keywords "forget" and "recent" and determines a medium risk. The input for this step is the extracted keywords, and the output is a risk score and risk level.

[2033] Step 5:

[2034] The server generates a report summarizing the risk assessment results and sends it to medical professionals and users through the notification module. For example, a report containing the assessment result of "medium risk" may be generated, with the message "There are signs of forgetfulness. Please consult a specialist as soon as possible." The input of this step is the risk score and risk level, and the output is the generated report and notification.

[2035] Step 6:

[2036] For continuous monitoring, the server displays periodic reminders on the user's device. For example, it displays a reminder such as "Have you had any troubles in your daily life recently?" The input of this step is the reminder setting data, and the output is the reminder displayed on the user's device.

[2037] Step 7:

[2038] The user responds to the reminder by entering new voice or text data, for example, "I often forget where I put my keys." The input for this step is the user's voice or text data, and the output is the new text data.

[2039] Step 8:

[2040] The device sends newly collected data to the server and compares it with past data to detect changes in the state. For example, by comparing past data with new data, it can determine that "the frequency of forgetfulness is increasing." The inputs of this step are new text data and past data, and the output is the analysis results.

[2041] Step 9:

[2042] The server updates the risk assessment based on the status change and notifies the medical professional and the user of the latest assessment result. For example, the updated result to "high risk" is notified to the medical professional, and the user is sent a message saying, "Your forgetfulness is currently increasing. Please consult a specialist immediately." The input of this step is the analysis result, and the output is the updated risk assessment result and notification.

[2043] 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.

[2044] System Overview

[2045] This patented system detects the user's risk of dementia at an early stage and, by analyzing the user's emotions, enables more accurate risk assessment and continuous health management. The system includes the following components:

[2046] 1. User Device

[2047] 2. Server

[2048] 3. Speech Recognition Engine

[2049] 4. Natural Language Processing (NLP) Engine

[2050] 5. Emotion Engine

[2051] 6. Risk Assessment Module

[2052] 7. Notification Module

[2053] System Operation Details

[2054] Data collection

[2055] 1. Users

[2056] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[2057] For example, a user may say, "I often forget where I put my keys these days."

[2058] 2. Terminal

[2059] The device collects the user's voice and stores it as voice data.

[2060] When the user inputs text, the text data is saved as is.

[2061] The voice data is converted into text by the device's voice recognition engine.

[2062] Data transmission and analysis

[2063] 1. Terminal

[2064] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[2065] 2. Server

[2066] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[2067] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[2068] 3. Server

[2069] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[2070] The emotion engine tags emotions and attaches the data as emotional energy.

[2071] 4. Server

[2072] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[2073] Taking emotional data into account also allows for more accurate risk assessment.

[2074] Results report

[2075] 1. Server

[2076] Generate a report summarizing the risk assessment results.

[2077] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[2078] 2. Notification Module

[2079] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[2080] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[2081] 3. Terminal

[2082] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[2083] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[2084] Continuous monitoring

[2085] 1. Terminal

[2086] Periodic reminders are displayed to the user to prompt them to collect new data (e.g., "Have you had any problems in your daily life recently?").

[2087] 2. Users

[2088] The user responds to the reminder by entering new information about their health condition via voice or text.

[2089] For example, you might answer, "I often forget where I put my keys."

[2090] 3. Terminal

[2091] Collect new voice data and convert it into text using a speech recognition engine.

[2092] The converted text data or the directly input text data is sent to the server.

[2093] 4. Server

[2094] The server receives the new data and re-analyzes it to compare it with the previous data.

[2095] If a change in state is detected, the risk assessment module updates the risk score.

[2096] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[2097] 5. Server

[2098] Generate a new report with the updated risk assessment results.

[2099] This report will again be communicated to medical professionals and users.

[2100] 6. Notification Module

[2101] If necessary, include additional precautions or advice in your report.

[2102] 7. Terminal

[2103] The updated assessment results and recommended actions are displayed on the user's device.

[2104] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[2105] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[2106] Specific example explanation

[2107] 1. Entering the user's health status

[2108] The user says aloud, "I've been getting more and more forgetful lately."

[2109] The device's voice recognition engine converts this into text, generating text data such as "I've been having a bad memory lately."

[2110] 2. Specific examples of data analysis

[2111] The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recent."

[2112] The server uses an emotion engine to detect the emotion "sadness" from the user's voice.

[2113] The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user as "medium risk."

[2114] 3. Specific examples of results reporting

[2115] The server generates a report containing the "medium risk" assessment result and sends it to a medical professional.

[2116] The user will be notified with a recommended action such as "You are showing signs of forgetfulness. Please consult a specialist as soon as possible," along with advice such as "You seem to be experiencing a lot of emotional fluctuations recently. Please take a moderate break."

[2117] 4. Specific examples of continuous monitoring

[2118] A reminder will be displayed periodically on the user's device asking, "Have you had any problems in your daily life recently?"

[2119] The user answers, "I often forget where I put my keys," and this data is sent to the server.

[2120] The server analyzes the new data, determines that "the frequency of forgetfulness is increasing," and updates the risk assessment to "high risk."

[2121] A medical professional will be notified of the latest evaluation results and the user will be informed that "You are currently experiencing increased forgetfulness. Please consult a medical specialist immediately."

[2122] Additionally, if fluctuations in emotional data are observed, you will be notified with the message, "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits."

[2123] By taking into account the user's emotional data, this system enables more accurate early detection of dementia risk and provides appropriate preventive measures.

[2124] The processing flow will be explained below.

[2125] Step 1:

[2126] User

[2127] The user starts the terminal application and speaks or inputs text about their health condition and daily life.

[2128] For example, a user may say, "I often forget where I put my keys these days."

[2129] Step 2:

[2130] Terminal

[2131] The device collects the user's voice and stores it as voice data.

[2132] When the user inputs text, the text data is saved.

[2133] The voice data is converted into text by the device's voice recognition engine.

[2134] Step 3:

[2135] Terminal

[2136] The stored text data and user profile data (e.g., age, medical history) are sent to the server.

[2137] Step 4:

[2138] server

[2139] The server passes the received data to a natural language processing (NLP) engine and begins analysis.

[2140] The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from text data and understands what the user is saying.

[2141] Step 5:

[2142] server

[2143] The server uses an emotion engine to analyze emotions (e.g., joy, sadness, anger) from the user's voice data and text data.

[2144] The emotion engine tags emotions and appends the data as emotional information.

[2145] Step 6:

[2146] server

[2147] Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score.

[2148] Taking emotional data into account also allows for more accurate risk assessment.

[2149] Step 7:

[2150] server

[2151] Generate a report summarizing the risk assessment results.

[2152] The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., see a specialist).

[2153] Step 8:

[2154] Notification Module

[2155] The report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS).

[2156] At the same time, the user's device will be notified of the risk assessment results along with preventive measures and health management advice.

[2157] Step 9:

[2158] Terminal

[2159] The user's device will display a specific message: "You are showing signs of forgetfulness. We recommend that you see a specialist."

[2160] It also displays emotion-based advice such as, "You seem to be experiencing a lot of emotional fluctuations lately. Take some time to relax."

[2161] Step 10:

[2162] Terminal

[2163] Display periodic reminders to prompt the user to enter new data (e.g., "Have you had any problems in your daily life recently?").

[2164] Step 11:

[2165] User

[2166] The user responds to the reminder by entering new information about their health condition via voice or text.

[2167] For example, you might answer, "I often forget where I put my keys."

[2168] Step 12:

[2169] Terminal

[2170] Collect new voice data and convert it into text using a speech recognition engine.

[2171] The converted text data or the directly input text data is sent to the server.

[2172] Step 13:

[2173] server

[2174] The server receives the new data and re-analyzes it to compare it with the previous data.

[2175] If a change in state is detected, the risk assessment module updates the risk score.

[2176] The emotion engine also performs a re-analysis to detect emotional fluctuations.

[2177] Step 14:

[2178] server

[2179] Generate a new report with the updated risk assessment results.

[2180] This report will again be communicated to medical professionals and users.

[2181] Step 15:

[2182] Notification Module

[2183] If necessary, include additional precautions or advice in your report.

[2184] Step 16:

[2185] Terminal

[2186] The updated assessment results and recommended actions are displayed on the user's device.

[2187] For example, you may be notified that "You are currently experiencing increased forgetfulness. Please consult a specialist immediately."

[2188] In addition, if fluctuations in emotional data are observed, a notification such as "Your emotions do not appear to be stable. We recommend that you review your lifestyle habits in the future" will be displayed.

[2189] This series of processes enables early detection of a user's dementia risk, and further analysis of emotional data can improve the accuracy of risk assessment and support intervention at the appropriate time.

[2190] Example 2

[2191] 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."

[2192] In modern society, early detection of dementia and continuous health management are important issues. In particular, there is a need to detect the risk of dementia early and take necessary measures. However, current systems are inadequate in not only detecting signs of dementia but also taking into account the user's emotional state to provide more accurate risk assessment and appropriate advice. Therefore, there is a need for a comprehensive risk assessment system that also takes into account the user's emotional data.

[2193] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2194] In this invention, the server includes means for collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia and emotions, means for performing a risk assessment based on the analysis results and the detected emotion data, means for notifying medical professionals and the user of preventive measures and health management advice based on the assessment results and emotions, means for periodically collecting new data from the user, means for comparing past data with new data to analyze changes in the user's condition and emotional fluctuations, means for updating the ongoing risk assessment based on the analysis results, means for notifying medical professionals and the user of preventive measures and advice based on the updated assessment results and emotional fluctuations, means for providing the user with preventive measures and advice based on the analysis results and the emotional data, and means for displaying reminders for applying the preventive measures and advice to the user's daily life. This enables more accurate risk assessment and appropriate advice that takes emotion data into account.

[2195] "User" refers to an individual who uses the system and inputs information about their health condition and daily life through voice or text.

[2196] "Voice data" is digital data that contains information input by voice by the user.

[2197] "Text data" is character string data that contains information entered by the user in text form.

[2198] A "natural language processing engine" is a software engine that analyzes and understands voice and text data, extracting keywords and phrases and analyzing their meaning.

[2199] The "emotion engine" is a software engine that detects emotions from a user's voice data and text data and tags the emotions.

[2200] "Risk Assessment Module" is a software module for calculating a user's dementia risk score based on data obtained from the natural language processing engine and the emotion engine.

[2201] "Assessment results" are information including the user's dementia risk score calculated by the risk assessment module and related analysis results.

[2202] "Preventive measures" are actions or measures recommended to users based on the results of risk assessment.

[2203] "Health management advice" is specific suggestions or recommendations for maintaining or improving the user's health.

[2204] "Notification Module" is a software module for notifying medical professionals and users of assessment results, preventative measures, and health care advice.

[2205] "Reminder" refers to a function that periodically notifies the user about new data input and application to daily life.

[2206] "Analysis results" is a general term for the data generated by the natural language processing engine and emotion engine, and the assessment results created by the risk assessment module.

[2207] This invention is a system that realizes more accurate risk assessment and continuous health management by detecting a user's dementia risk at an early stage and analyzing the user's emotions. The system includes a user terminal, a server, a voice recognition engine, a natural language processing (NLP) engine, an emotion engine, a risk assessment module, and a notification module.

[2208] System configuration

[2209] Hardware and Software

[2210] User device: A device (e.g., smartphone, tablet, PC) through which a user provides voice or text input.

[2211] Server: A central processing unit for data analysis and risk assessment. Uses a cloud-based or on-premise server.

[2212] Speech recognition engine: Software used to convert user voice data into text (e.g., Google Cloud Speech-to-Text, Amazon Transcribe).

[2213] Natural Language Processing (NLP) engine: Software for analyzing text data and extracting keywords and phrases (e.g., spaCy, NLTK).

[2214] Emotion engine: Software for detecting and tagging emotions from user voice and text data (e.g., IBM Watson Tone Analyzer).

[2215] Risk Assessment Module: Software that calculates a risk score based on data obtained from the natural language processing engine and sentiment engine.

[2216] Notification module: Software for notifying users and medical professionals of assessment results and health care advice.

[2217] System Operation

[2218] Data collection

[2219] The user launches the device application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is converted into text by the device's voice recognition engine.

[2220] Data transmission and analysis

[2221] The converted text data and the user's profile data (such as age and medical history) are sent from the device to the server. The server then passes this data to a natural language processing engine to begin analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[2222] Sentiment Analysis and Risk Assessment

[2223] The server then uses an emotion engine to analyze emotions from the user's voice and text data. The emotion engine then tags the data with emotions and adds them as emotional energy. Based on the extracted keywords and emotion data, the risk assessment module calculates a dementia risk score. Taking emotion data into account allows for more accurate risk assessment.

[2224] Reporting and notification of results

[2225] A report summarizing the risk assessment results is generated. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[2226] Specific examples

[2227] For example, a user might say, "I've been getting more forgetful lately." The device's speech recognition engine converts this into text, generating text data such as "I've been getting more forgetful lately." The server receives this text data and uses a natural language processing engine to extract keywords such as "forgetfulness" and "recently." At the same time, the emotion engine detects the emotion "sadness" from the user's voice. The risk assessment module calculates a risk score based on these keywords and emotion data and determines the user to be at "medium risk." The server generates a report containing the "medium risk" assessment result and sends it to a medical professional. The user is notified of the recommended action, "You are showing signs of forgetfulness. Consult a specialist as soon as possible," along with advice such as "You seem to have experienced frequent emotional fluctuations recently. Take appropriate breaks."

[2228] Prompt Sentence Examples

[2229] "Please explain what emotion tag the emotion engine will assign when a user says, 'I've been getting more and more forgetful lately.' Also, please explain in detail the process by which the risk assessment module determines the risk to be medium."

[2230] This invention makes it possible to provide more accurate early detection of dementia risk and appropriate preventive measures that also take into account the user's emotional data.

[2231] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2232] Step 1: Data entry

[2233] Input: Voice or text data about the user's health and daily life

[2234] Output: User voice or text data is collected

[2235] The user starts the terminal application and speaks or inputs text about their health condition or daily life. For example, the user might say, "I often forget where I put my keys these days." This voice data is collected by the terminal.

[2236] Step 2: Data conversion

[2237] Input: User's voice data

[2238] Output: Audio data is converted to text data

[2239] The device converts the collected voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). For example, a speech sentence such as "I often forget where I put my keys these days" is converted into text such as "I often forget where I put my keys these days."

[2240] Step 3: Send data

[2241] Input: Text data and user profile data (e.g., age, medical history)

[2242] Output: Text data and profile data are sent to the server.

[2243] The converted text data and the user's profile data (age, medical history, etc.) are sent from the device to the server. For example, the text data "I often forget where I put my keys these days" along with the user's age and medical history are sent to the server.

[2244] Step 4: Natural Language Processing

[2245] Input: Text data

[2246] Output: Parsed keywords and phrases

[2247] The server passes the received text data to a natural language processing (NLP) engine (e.g., spaCy) and begins analysis. The NLP engine extracts specific keywords and phrases (e.g., "forget" or "recent") from the text and understands what the user is saying.

[2248] Step 5: Sentiment Analysis

[2249] Input: Text data

[2250] Output: Emotion data with emotion tags

[2251] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze emotions from the user's voice and text data. The emotion engine tags the data with emotions and adds them as emotional energy. For example, an emotion tag such as "sadness" is added.

[2252] Step 6: Risk assessment

[2253] Input: Parsed keywords and sentiment data

[2254] Output: Dementia risk score

[2255] The server's risk assessment module calculates a dementia risk score based on the extracted keywords and emotion data. For example, based on the keywords "where do I put my keys" and "often forgetting" and the emotion data of "sadness," the risk assessment module may assess the risk as medium.

[2256] Step 7: Results generation and notification

[2257] Input: Risk assessment results

[2258] Output: Risk assessment report and notification messages

[2259] The server generates a report summarizing the risk assessment results. The report includes the user's current risk level, detected emotional data, and recommended actions (e.g., consulting a specialist). This report is sent to the medical professional's device using a secure communication protocol (e.g., HTTPS). At the same time, the user's device is notified of the risk assessment results along with preventive measures and health management advice.

[2260] Step 8: Continuous monitoring

[2261] Input: New audio or text data

[2262] Output: Updated risk assessment results

[2263] The user's device periodically displays reminders to encourage the collection of new data (e.g., "Have you had any problems in your daily life recently?"). In response to the reminders, the user inputs new health status information by voice or text. The new voice data is again converted into text by the speech recognition engine, and the converted text data or directly entered text data is sent to the server. The server receives the new data and analyzes it again to compare it with past data. If a change in status is detected, the risk assessment module updates the risk score. The updated risk assessment results are generated as a new report and notified to medical professionals and the user.

[2264] Such steps allow for comprehensive monitoring of the user's health and emotional state and provide appropriate risk assessment and advice.

[2265] (Application example 2)

[2266] 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."

[2267] The present invention relates to a system for managing a user's health. In particular, it aims to provide a system that can detect the risk of dementia early by having the user input voice and text data in a physical store, and further analyze emotional fluctuations to perform risk assessment. Another objective is to provide a mechanism that can recommend a consultation with a specialist based on the risk assessment results and support the user in improving their daily life.

[2268] The identification processing 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 collecting voice or text data from the user, means for analyzing the collected data using a natural language processing engine to detect signs of dementia, means for performing a risk assessment based on the analysis results, means for notifying a medical professional and the user of the assessment results, means for the user to record their health status at a physical store and analyze the data to continuously manage their health, means for recommending a visit to a specialist based on the data analysis results, a reminder function for providing health management advice, means for providing the user with preventive measures and advice based on the analysis results, means for displaying reminders for applying the preventive measures and advice to the user's daily life, and means for analyzing the user's health status in real time and notifying the results. This allows the user to continuously manage their health status and to consult a specialist at the appropriate time.

[2269] "User" means a person who uses the system to record their health status and receive risk assessments and advice from medical professionals.

[2270] "Voice or text data" refers to voice or text data input by the user regarding their health condition or daily life.

[2271] A "natural language processing engine" is a technology that analyzes collected text data and extracts specific keywords and phrases.

[2272] "Signs of dementia" are signs that indicate the possibility of early dementia, which are inferred from the user's health condition and behavior.

[2273] "Risk assessment" is the process of calculating a risk score for the user's health status based on the analyzed data.

[2274] A "healthcare professional" is a medical professional whose role is to provide assessment results and advice.

[2275] "Brick and mortar store" refers to a physical store where users visit and use services or products.

[2276] "Health status" refers to the physical and mental state of a user in their daily life.

[2277] "Continuous health management" refers to the activity of managing a user's health condition over the long term by periodically collecting and analyzing the user's health data.

[2278] The "means for recommending a consultation with a specialist" is a mechanism for recommending that the user be examined by a specialist based on the risk assessment results.

[2279] "Health management advice" is specific guidance and advice for maintaining and improving the user's health in their daily lives.

[2280] The "reminder function" is a mechanism that provides notifications and alarms to prompt users to take specific actions or enter specific data.

[2281] "Real-time analysis" refers to the process of processing user data instantly and quickly calculating results.

[2282] The "risk assessment result" is the result of an assessment of the user's health condition obtained through analysis.

[2283] "Applying to daily life" refers to incorporating the provided advice and preventative measures into the user's daily life.

[2284] MODE FOR CARRYING OUT THE INVENTION

[2285] System Overview

[2286] The system of the present invention collects and analyzes users' voice or text data to detect signs of dementia and perform risk assessment. It also supports health management in physical stores and includes a mechanism for recommending consultations with specialists. The system includes the following main components:

[2287] 1. User Device

[2288] 2. Server

[2289] 3. Speech Recognition Engine 【2...

Claims

1. means for collecting voice or text data from a user; A method for analyzing collected data using a natural language processing engine to detect signs of dementia, and means for performing risk assessment based on the analysis results; The system includes a means for communicating the results of the assessment to a medical professional and the user.

2. a means for periodically collecting new data from the user; A means for comparing past data with new data to analyze changes in the user's state; means for updating a continuous risk assessment based on the results of said analysis; 10. The system of claim 1, further comprising means for notifying medical professionals and users of updated assessment results.

3. A means for providing preventive measures and advice to users based on the analysis results; The system of claim 1 , further comprising means for displaying reminders for applying the preventive measures and advice to the user's daily life.

Images