Intelligent home-based care remote diagnosis and treatment appointment consultation system

Abstract

The invention discloses an intelligent home-based care remote diagnosis and treatment appointment consultation system which comprises an integrated data collection module, a behavior feature extraction module, a behavior recognition module and a health intervention module. The behavior feature extraction module uses a clustering algorithm to classify the behavior recognition module and recognize different groups, and the groups classified by the clustering algorithm in the behavior recognition module are intervened by the health intervention module. The intelligent home-based care remote diagnosis and treatment appointment consultation system is provided with the data collection module and the behavior feature extraction module, not only can more accurately monitor the health condition of the elderly, but also can provide personalized health suggestions and timely intervention measures by arranging the behavior recognition module and the health intervention module, so that the intelligent home-based care remote diagnosis and treatment appointment consultation system is more convenient to use. And the practicability and user experience of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of home-based elderly care diagnosis and treatment, and in particular to an intelligent home-based elderly care remote diagnosis and treatment appointment consultation system. Background Art

[0002] With the development of society, population aging has become a trend of social development. Developing the aging industry is an important part of coping with an aging society, meeting the needs of a large number of elderly people, and promoting the coordinated development of the economy and society.

[0003] In order to enhance the comprehensiveness and security of health and safety monitoring for the elderly, it is necessary to establish a health and safety joint monitoring system with the authorization of the users, so that the health and safety data of the elderly can truly serve the elderly themselves, so that multiple people and institutions can manage the health of the elderly at the same time, and when problems arise, they can get the care of their children, the attention of nursing homes and the community, and get solutions provided by doctors at the first time. When services are needed, they can quickly and accurately obtain relevant services, making life more convenient for the elderly.

[0004] At present, through the organic combination of simple and easy-to-use interactive service platforms, remote terminal monitoring systems and wearable devices, users in remote villages, community centers and cities can automatically record and instantly transmit extremely valuable and important health data to their medical and health service institutions. Continuous health monitoring and real-time data establishment can effectively help users understand their physical conditions, prevent sudden illnesses, and reduce the occurrence of users' hospitalization and emergency visits.

[0005] However, due to the complex physical conditions of the elderly, the various portable body indicator detection products currently used can detect and deal with some sudden accidents, but it is difficult to ensure the accuracy of the alarm and false alarms are prone to occur; and sometimes the elderly may have some mild symptoms and do not want to go to the hospital for treatment, so how to strike a balance between them is currently a major problem; and in the case of different physical conditions and living habits of different elderly people, if the same judgment criteria are still used to judge and warn the physical condition of each elderly person, large errors are inevitable. Therefore, how to provide personalized health management services for each elderly person more conveniently is also a problem that needs to be solved at present. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent home-based elderly care remote diagnosis and treatment appointment consultation system, which is equipped with a data collection module and a behavior feature extraction module. It can not only monitor the health status of the elderly more accurately, but also has a behavior recognition module and a health intervention module, and can provide personalized health advice and timely intervention measures, thereby improving the practicality of the system and user experience.

[0007] The present invention provides a smart home-based elderly care remote diagnosis and treatment appointment consultation system, comprising an integrated data collection module, a behavior feature extraction module, a behavior recognition module, and a health intervention module. The behavior feature extraction module extracts content in the integrated data collection module, the behavior feature extraction module uses a clustering algorithm to classify the behavior recognition module to identify different groups, and the groups classified by the clustering algorithm in the behavior recognition module are intervened through the health intervention module.

[0008] Preferably, the data collection module includes system login behavior, function usage behavior, interactive behavior, and device usage behavior. The system login behavior includes the time, frequency, and usage duration of the elderly logging into the system every day. The function usage behavior includes the frequency with which the elderly use the health monitoring function, appointment consultation function, and rehabilitation training function in the system. The interactive behavior includes the consulting content, feedback information, and interaction frequency of the elderly's interaction with the system. The device usage behavior includes the elderly's login frequency of using smart bracelets, data upload frequency, and smart bracelet failure frequency.

[0009] Preferably, the behavior feature extraction module includes login features, function usage features, interaction features and device usage features. The login features include calculating the average daily login time, login frequency and usage duration; the function usage features include calculating the health monitoring frequency, appointment consultation frequency and rehabilitation training frequency; the interaction features include analyzing the sentiment analysis of the consultation content, feedback satisfaction and interaction frequency; the device usage features include calculating the usage frequency of smart bracelets, the frequency of data upload and the failure frequency of smart bracelets.

[0010] Preferably, the behavior recognition module includes cluster analysis and anomaly detection. The cluster analysis uses a clustering algorithm to classify the behavior characteristics of the elderly, and the anomaly detection uses an anomaly detection algorithm to identify abnormal behavior patterns.

[0011] Preferably, the health intervention module includes health advice generation and intervention measures. The health advice generation includes behavioral characteristic advice and anomaly detection advice. The behavioral characteristic advice generates personalized health advice for the elderly grouped with different behavioral characteristics, and the anomaly detection advice provides targeted health advice for the elderly who have detected anomalies.

[0012] Preferably, the behavioral characteristics suggested include a high-frequency use group, a low-frequency use group, a positive interaction group, and a negative interaction group.

[0013] Preferably, anomaly detection suggestions include decreased login frequency, reduced function usage, and dissatisfied feedback.

[0014] Preferably, automatic intervention includes automatically sending health tips, encouragement messages and rehabilitation training videos; manual intervention includes not logging in for a long time and frequently giving unsatisfactory feedback.

[0015] Therefore, the present invention adopts the above-mentioned intelligent home-based elderly care remote diagnosis and treatment appointment consultation system, which is equipped with a data collection module and a behavior feature extraction module. It can not only monitor the health status of the elderly more accurately, but also has a behavior recognition module and a health intervention module. It can also provide personalized health advice and timely intervention measures, thereby improving the practicality of the system and user experience.

[0016] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is an overall system schematic diagram of a base of a smart home-based elderly care remote diagnosis and treatment reservation consultation system of the present invention; Figure 2 A system schematic diagram of an integrated data collection module of a base of a smart home-based elderly care remote diagnosis and treatment reservation consultation system of the present invention; Figure 3 It is a system schematic diagram of a behavior feature extraction module of a base of a smart home-based elderly care remote diagnosis and treatment reservation consultation system of the present invention; Figure 4 A system schematic diagram of a health intervention module of a base of a smart home-based elderly care remote diagnosis and treatment reservation consultation system of the present invention; Figure 5 This is a system schematic diagram of health advice generation and intervention measures for a base of a smart home-based elderly care remote diagnosis and treatment appointment consultation system of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0019] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0020] The words "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprises" and similar terms mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0021] Embodiment 1 like Figure 1-Figure 5 As shown, the present invention provides an intelligent home-based elderly care remote diagnosis and treatment appointment consultation system, including an integrated data collection module, a behavior feature extraction module, a behavior recognition module, and a health intervention module. The behavior feature extraction module extracts the content in the integrated data collection module, and the behavior feature extraction module uses a clustering algorithm to classify the behavior recognition module to identify different groups. The groups classified by the clustering algorithm in the behavior recognition module are intervened through the health intervention module.

[0022] The data collection module includes system login behavior, function usage behavior, interactive behavior, and device usage behavior. The system login behavior includes the time, frequency, and usage duration of the elderly logging into the system every day. The method for calculating the time the elderly log into the system every day is: recording the time points when the elderly log into the system every day, including the first login time and the last login time. The method for calculating the frequency of the elderly logging into the system every day is: recording the number of times the elderly log into the system every day; the method for calculating the usage duration of the elderly logging into the system every day is: recording the total time the elderly stay in the system after each login.

[0023] Understand usage habits: By recording the time, frequency, and duration of the elderly's daily logins to the system, we can understand the elderly's usage habits and active time periods, thereby optimizing the system's service time and function recommendations. Evaluate engagement: Login frequency and usage duration can reflect the elderly's engagement with the system, help identify high-engagement and low-engagement users, and provide a basis for personalized intervention. Timely detection of abnormalities: A sudden decrease in login frequency or usage duration may indicate that the elderly's health status or usage habits have changed, requiring timely attention and intervention.

[0024] Function usage behavior includes the frequency with which the elderly use the health monitoring function, appointment consultation function, and rehabilitation training function in the system. The health monitoring function includes recording the frequency with which the elderly use the health monitoring function, including the number of uploads of monitoring data such as heart rate, blood pressure, and blood sugar.

[0025] Function optimization: Understanding the frequency of use of different functions by the elderly can help system developers optimize function design and improve user experience. Personalized recommendation: According to the usage preferences of the elderly, the system can recommend functions that better meet their needs to improve the practicality and attractiveness of the system. Health monitoring: High-frequency use of health monitoring functions may indicate that the elderly are more concerned about their own health and need more health advice and intervention. The appointment consultation function includes recording the frequency of the elderly using the appointment consultation function, including the number of doctor appointments, the types of questions consulted, etc. The rehabilitation training function includes recording the frequency of the elderly using the rehabilitation training function, including the completed training projects and the duration of training. Interactive behavior includes the consultation content, feedback information and interaction frequency of the elderly's interaction with the system. The consultation content includes recording the content of the questions consulted by the elderly in the system, including text descriptions and voice records. Feedback information includes recording the elderly's feedback on system services, including satisfaction evaluation, improvement suggestions, etc.; interaction frequency includes recording the frequency of the elderly's interaction with the system, including sending messages, participating in questionnaires, etc.; emotional support: By analyzing the emotional tendency of the interactive content, you can understand the psychological state of the elderly and provide emotional support and psychological counseling. Improve satisfaction: High interaction frequency and high satisfaction feedback can enhance the elderly's trust and dependence on the system and enhance their enthusiasm for using the system. Timely response: Timely response to the elderly’s inquiries and feedback can improve their satisfaction and enhance the system’s service quality and user stickiness.

[0026] Device usage behavior Device usage behavior includes the login frequency, data upload frequency, and smart bracelet failure frequency of the elderly. Device maintenance: By recording the device login frequency and data upload frequency, device failures can be discovered in a timely manner, and maintenance and replacement suggestions can be provided to ensure the normal operation of the device. Data integrity: A high data upload frequency can ensure the integrity and timeliness of health data and provide accurate data support for health assessment and intervention. User education: For the elderly who use the device less frequently, usage guidance can be provided to improve their acceptance and ability to use smart devices.

[0027] Login frequency includes recording the login frequency of the elderly using the smart bracelet; data upload includes recording the frequency and timeliness of the elderly uploading health data using smart devices; smart bracelet failure records the failure of the smart bracelet, including device loss of connection, data abnormality, etc.; Preprocess all data, including data cleaning and data normalization; this method is common among people in this field; remove duplicate data: delete duplicate login records, data upload records, etc. to ensure the uniqueness and accuracy of the data. Process missing values: For missing data, use filling methods (such as mean filling and median filling) to process them to avoid incomplete data affecting the analysis results. Identify outliers: Identify and process outliers, such as abnormal login time and abnormal usage time, to ensure the rationality and reliability of the data.

[0028] The behavioral feature extraction module includes login features, function usage features, interaction features, and device usage features. The login features include the calculation of the average login time, login frequency, and usage duration per day. The average login time is to calculate the average login time per day, understand the time distribution of the elderly logging into the system every day, identify active time periods, and optimize the system's service time and function recommendations. The login frequency is to calculate the average number of logins per day; evaluate the elderly's frequency of use of the system, identify high-engagement and low-engagement users, and provide a basis for personalized intervention. The usage duration is to calculate the average length of time the elderly stay in the system after each login. Understand the length of time the elderly stay in the system after each login and evaluate the system's attractiveness and user stickiness.

[0029] Function usage characteristics include calculating the frequency of health monitoring, appointment consultation frequency, and rehabilitation training frequency; the health monitoring frequency includes calculating the average number of times the health monitoring function is used every day. Understand the elderly's use of the health monitoring function, evaluate their level of concern for their own health, and provide a basis for health advice and intervention. The appointment consultation frequency includes calculating the average number of times the appointment consultation function is used every day. Understand the elderly's use of the appointment consultation function, evaluate their demand for medical consultation, and optimize the appointment system and doctor resource allocation. The rehabilitation training frequency calculates the average number of times the rehabilitation training function is used every day. Understand the elderly's use of the rehabilitation training function, evaluate their participation in rehabilitation training, and provide a basis for adjusting the rehabilitation plan.

[0030] Interaction features include sentiment analysis of consulting content, feedback satisfaction, and interaction frequency. Sentiment analysis of consulting content uses natural language processing technology to analyze the emotional tendency of consulting content, understand the emotional tendency of elderly people's consulting content, identify potential psychological problems, and provide emotional support and psychological counseling. Feedback satisfaction includes calculating the average satisfaction evaluation in feedback information, evaluating the elderly's satisfaction with system services, and optimizing system functions and service quality. Interaction frequency includes calculating the average number of interactions with the system per day. Understand the interaction between the elderly and the system and evaluate the system's attractiveness and user stickiness.

[0031] The device usage characteristics include calculating the frequency of use of smart bracelets, the timeliness of data upload, and the frequency of smart bracelet failures. Understand the use of smart bracelets by the elderly and evaluate their acceptance and usage habits of smart bracelets. Calculating the frequency of use of smart bracelets includes calculating the average number of times smart devices are used every day; the frequency of data upload includes calculating the average number of times health data is uploaded every day. The frequency of smart bracelet failures includes calculating the average number of smart bracelet failures. The behavior recognition module includes cluster analysis and anomaly detection. Cluster analysis uses clustering algorithms to classify the behavioral characteristics of the elderly.

[0032] Initialize the centroid, assign samples, update the centroid, and iterate; randomly select K samples as the initial centroid; assign samples: for each data point, calculate the Euclidean distance between it and each centroid, and assign it to the cluster represented by the nearest centroid, and recalculate the centroid of each cluster, that is, the mean of all samples in the cluster.

[0033] Repeat the above steps until the centroid no longer changes or the maximum number of iterations is reached. The K-means clustering algorithm can effectively assign data points to different clusters, thereby classifying the behavioral characteristics of the elderly. This helps to identify the elderly with different behavioral patterns and provide a basis for personalized health advice and intervention.

[0034] Anomaly detection uses anomaly detection algorithms to identify abnormal behavior patterns, and the number of isolated trees is set to 100. The number of samples used to build each isolated tree is usually set to the size of the data set. The proportion of outliers is set according to the actual situation. For example, 0.01 means that the outliers account for 1%. Training model: Assume that X is the preprocessed feature matrix, initialize the anomaly detection algorithm model, and train the model; predict anomalies: predict whether each sample is an outlier; calculate anomaly scores: calculate the anomaly score of each sample. The lower the anomaly score, the more likely the sample is an outlier. Discover health problems in a timely manner Early warning: By monitoring the elderly's login frequency, function usage, interactive behavior, and device usage data, the anomaly detection algorithm can detect potential health problems in a timely manner. For example, if the elderly's login frequency suddenly drops, it may indicate that they are unwell or encounter other problems. Preventive measures: By discovering abnormal behavior patterns in advance, preventive measures can be taken to avoid further deterioration of health problems. For example, if the frequency of uploading the elderly's health monitoring data decreases, the system can remind family members or medical staff to pay attention to the elderly's health status and improve the system's response efficiency. Quick response: The anomaly detection algorithm can quickly identify abnormal behavior, and the system can take corresponding measures immediately. For example, if the elderly's interaction frequency suddenly decreases, the system can automatically send a caring text message or notify family members. Resource optimization: By detecting abnormal behavior in a timely manner, the system can reasonably allocate medical resources to ensure that the elderly can get help in time when needed. For example, if the system detects that the elderly's health status is abnormal, it can prioritize doctors for remote diagnosis and treatment. Improve user experience Personalized services: The anomaly detection algorithm can provide personalized services for each elderly. For example, for elderly people who use the system frequently, more detailed health reports can be provided; for elderly people who use the system less frequently, usage guidance and incentives can be provided. Enhance trust: By timely detecting and handling abnormal behaviors, the system can enhance the trust of the elderly and their families in the system. For example, the system can respond to the elderly's feedback and needs in a timely manner and provide effective health advice and intervention measures. Optimize system functions Function improvement: Anomaly detection algorithms can identify deficiencies in the system and help developers optimize functions. For example, if it is found that the elderly frequently encounter problems when using a certain function, the function can be improved. User education: For the elderly who are not familiar with smart devices, anomaly detection algorithms can identify difficulties in use, and the system can provide usage guidance and educational materials to help the elderly better use the device. Fault warning: By monitoring the usage and failure frequency of devices such as smart bracelets, anomaly detection algorithms can detect device failures in advance and perform maintenance or replacement in time. For example, if the device frequently loses connection or the data is abnormal, the system can notify family members or technicians to check. Extend the life of the equipment: Timely detection and handling of equipment failures can extend the service life of the equipment and reduce maintenance costs. For example, regular maintenance and timely replacement of faulty equipment can ensure the normal operation of the equipment. Psychological support and intervention Emotion analysis: Anomaly detection algorithms can analyze the consultation content and feedback information of the elderly and identify potential psychological problems. For example, if negative emotions frequently appear in the elderly's consultation content, the system can provide psychological counseling and emotional support. Psychological intervention: By timely detecting psychological problems, the system can provide psychological intervention measures to help the elderly maintain a good mental state.For example, the system can recommend psychological counseling videos or contact professional psychologists for consultation. Data-driven decision support data analysis: anomaly detection algorithms can provide rich data support to help system developers and medical staff better understand the health status and behavior patterns of the elderly. For example, by analyzing the frequency and type of abnormal behaviors, more effective health management and intervention strategies can be formulated. Policy formulation: Based on the anomaly detection results, data support can be provided for the formulation of pension policies. For example, by analyzing the health status and behavior patterns of the elderly in different regions, more targeted pension service policies can be formulated. The health intervention module includes health advice generation and intervention measures. Health advice generation includes behavioral feature suggestions and anomaly detection suggestions. Behavioral feature suggestions generate personalized health advice for the elderly grouped by different behavioral characteristics.

[0035] The behavioral characteristics suggested include high-frequency use group, low-frequency use group, positive interaction group and negative interaction group. The high-frequency use group provides more detailed health monitoring reports and preventive health care suggestions. The low-frequency use group provides guidance and incentives for using the system. The positive interaction group provides more interactive content and reward mechanisms. The negative interaction group provides psychological counseling content and encouraging feedback.

[0036] Abnormal detection suggestions provide targeted health suggestions for the elderly who have detected abnormal detections; abnormal detection suggestions include decreased login frequency, reduced function usage, and dissatisfied feedback.

[0037] Login frequency decreases: Send caring text messages to inquire about the elderly’s health and provide emergency contact information. Function usage decreases: Send guidance information on using the system to encourage the elderly to continue using it. Unsatisfactory feedback: Respond to feedback in a timely manner and provide improvement measures and solutions.

[0038] Intervention measures include automatic intervention and manual intervention; automatic intervention is that the system automatically sends health reminders, encouragement information, rehabilitation training videos, and guides the elderly to self-management. Health reminders: regularly send health monitoring reminders to remind the elderly to measure heart rate, blood pressure, etc. Encouragement information: send encouraging information, rehabilitation training videos: enhance the elderly's enthusiasm for use. Provide rehabilitation training videos to guide the elderly to conduct rehabilitation training.

[0039] Manual intervention means that when the system detects serious abnormal behavior, it will automatically notify family members and medical staff and recommend further intervention. Manual intervention includes long-term inactivity and frequent feedback of dissatisfaction. Long-term inactivity: notify family members to pay attention to the health of the elderly and recommend medical staff to follow up by phone. Frequent feedback of dissatisfaction: notify customer service staff to communicate with the elderly in a timely manner to solve the problem.

[0040] Therefore, the present invention adopts the above-mentioned intelligent home-based elderly care remote diagnosis and treatment appointment consultation system, which is equipped with a data collection module and a behavior feature extraction module. It can not only monitor the health status of the elderly more accurately, but also has a behavior recognition module and a health intervention module. It can also provide personalized health advice and timely intervention measures, thereby improving the practicality of the system and user experience.

[0041] The above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A smart home-based elderly care remote diagnosis and treatment appointment consultation system, characterized in that: It includes an integrated data collection module, a behavior feature extraction module, a behavior recognition module, and a health intervention module. The behavior feature extraction module extracts the content in the integrated data collection module. The behavior feature extraction module uses a clustering algorithm to classify the behavior recognition module to identify different groups. The groups classified by the clustering algorithm in the behavior recognition module are intervened through the health intervention module.

2. According to claim 1, a smart home-based elderly care remote diagnosis and treatment appointment consultation system is characterized in that: The data collection module includes system login behavior, function usage behavior, interactive behavior, and device usage behavior. System login behavior includes the time, frequency, and usage duration of the elderly logging into the system every day. Function usage behavior includes the frequency with which the elderly use the health monitoring function, appointment consultation function, and rehabilitation training function in the system. Interactive behavior includes the consultation content, feedback information, and interaction frequency of the elderly's interaction with the system. Device usage behavior includes the elderly's login frequency of using smart bracelets, data upload frequency, and smart bracelet failure frequency.

3. According to claim 1, a smart home-based elderly care remote diagnosis and treatment appointment consultation system is characterized in that: The behavior feature extraction module includes login features, function usage features, interaction features, and device usage features. Login features include the calculation of average daily login time, login frequency, and usage duration; function usage features include the calculation of health monitoring frequency, appointment consultation frequency, and rehabilitation training frequency. The interaction characteristics include sentiment analysis of consulting content, feedback satisfaction, and interaction frequency. The device usage characteristics include calculating the usage frequency of smart bracelets, the frequency of data uploads, and the frequency of smart bracelet failures.

4. According to claim 1, a smart home-based elderly care remote diagnosis and treatment appointment consultation system is characterized in that: The behavior recognition module includes cluster analysis and anomaly detection. Cluster analysis uses clustering algorithms to classify the behavioral characteristics of the elderly, and anomaly detection uses anomaly detection algorithms to identify abnormal behavior patterns.

5. According to claim 1, a smart home-based elderly care remote diagnosis and treatment appointment consultation system is characterized in that: The health intervention module includes health advice generation and intervention measures. Health advice generation includes behavioral feature suggestions and anomaly detection suggestions. Behavioral feature suggestions generate personalized health advice for the elderly grouped with different behavioral features, and anomaly detection suggestions provide targeted health advice for the elderly who have detected anomalies.

6. According to claim 5, a smart home-based elderly care remote diagnosis and treatment appointment consultation system is characterized in that: Intervention measures include automatic intervention and manual intervention.

7. According to claim 5, a smart home-based elderly care remote diagnosis and treatment appointment consultation system is characterized in that: The behavioral characteristics suggested include a high-frequency use group, a low-frequency use group, a positive interaction group, and a negative interaction group.

8. According to claim 5, a smart home-based elderly care remote diagnosis and treatment appointment consultation system is characterized in that: Anomaly detection suggestions include decreased login frequency, reduced feature usage, and dissatisfied feedback.

9. The intelligent home-based elderly care remote diagnosis and treatment appointment consultation system according to claim 6 is characterized in that: Automatic intervention includes automatically sending health tips, encouragement messages and rehabilitation training videos; manual intervention includes long-term absence of login and frequent feedback of dissatisfaction.

Images