An intelligent robot management system and method for health monitoring

Abstract

The present invention discloses an intelligent robot management system and method for health monitoring, which belongs to the field of data management technology. The system of the present invention includes: a data management module, a historical data analysis module, a real-time monitoring and data processing module, a health assessment and suggestion module, and a user interface and feedback module; the data management module is responsible for extracting and preprocessing the basic information and physical examination report data of the target user from the database; the historical data analysis module calculates the trend evaluation index using the user's historical monitoring data; the real-time monitoring and data processing module collects and analyzes the user monitoring data in real time, and compares it with the trend evaluation index threshold; the trend evaluation index calculation module outputs corresponding information based on the trend evaluation index calculated by the real-time data; the user interface and feedback module displays the real-time trend evaluation index, the historical data analysis results and the output information through a visual interface.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an intelligent robot management system and method for health monitoring. Background Art

[0002] With the advancement of technology and rising awareness of health, health monitoring devices are becoming increasingly common in daily life. Currently, health monitoring devices on the market primarily focus on collecting basic physiological data, such as heart rate, blood pressure, and blood sugar. These devices use sensors to measure various physiological parameters in real time and issue alerts when abnormal values ​​are detected, helping users understand their health status.

[0003] While existing smart health monitoring devices can help users monitor their health by measuring basic physiological data in real time, they still have some significant limitations. One major issue is that these devices typically rely on preset static parameter thresholds to determine whether health status is abnormal. This static approach fails to account for individual characteristics of each user, such as differences in age, gender, physical fitness, and daily activity levels. Due to the lack of personalized adjustments, monitoring results may not be precise or accurate enough to fully reflect the user's actual health status. For example, age, gender, weight, lifestyle, and even genetic factors can affect a person's normal blood pressure range. Therefore, understanding an individual's safe blood pressure range requires a judgment based on their specific circumstances. However, current devices have difficulty distinguishing these differences, making monitoring results less targeted and ineffective in reflecting the user's health status. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent robot management system and method for health monitoring to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An intelligent robot management method for health monitoring, the method comprising the following steps:

[0007] Step S100: Obtain basic information of different target users from the database, analyze the basic information of all target users, and thus construct a target user dataset; based on the target user's physical examination report, classify the elements in the target user dataset to obtain basic information features of different categories of target users;

[0008] Step S200. For each category of target users, obtain corresponding historical monitoring data, analyze the historical monitoring data, and thus obtain the historical monitoring data trend curve corresponding to the target user; analyze the historical monitoring data trend curve in combination with the basic information characteristics of the target user to obtain the monitoring key points;

[0009] Step S300. Based on the monitoring key points and in combination with the corresponding historical monitoring data, the deviation between the target user's historical monitoring data and the corresponding standard parameters is evaluated to obtain the target user's trend evaluation index and the trend evaluation index threshold of the corresponding category;

[0010] Step S400. Using the intelligent robot, real-time monitoring data of the current user is collected and analyzed to obtain a real-time monitoring data trend curve; obtaining the usage record of the current user using the intelligent robot, determining whether the current user is a new user based on the usage record, and obtaining basic information characteristics of the current user based on the determination result;

[0011] Step S500. Obtain the real-time monitoring data trend curve and basic information characteristics of the current user, analyze the real-time monitoring data trend curve and basic information characteristics of the current user, and calculate the real-time trend evaluation index of the current user; compare the size relationship between the real-time trend evaluation index and the trend evaluation index threshold of the corresponding category, and output corresponding notification information based on the judgment result of the size relationship.

[0012] Furthermore, step S100 includes:

[0013] S101. The target user's basic information refers to various static and dynamic data related to the target user's personal health; wherein, the static data refers to relatively fixed and infrequently changing data, such as age, gender, height, weight, physical condition, underlying medical history, family medical history, etc.; the dynamic data refers to real-time or regularly updated data that can be collected within a specific time period, such as physiological parameters, exercise and activity data, sleep data, mood and emotion data, and environmental data, etc.; extract the target user's number, summarize the target user's basic information according to the number, and convert the basic information of the target user corresponding to each number into a unified format. The basic information of the target user corresponding to a number is used as an element, and the different elements are summarized to construct a target user data set;

[0014] S102. Obtain the physical examination reports of all target users, analyze the abnormal parameters in the physical examination reports, extract the names corresponding to the abnormal parameters, and classify the basic information of the target users with the same abnormal parameter names into one category, thereby dividing the elements in the target user data set into several categories; for each category, perform an intersection operation on each data item of the element in the target user data set, extract the result of the intersection operation as the basic information feature, and traverse all categories in turn to obtain the basic information features of target users in different categories.

[0015] This system considers both static and dynamic data, providing a comprehensive overview of a user's health status. Static data such as age and gender provide a basic health background, while dynamic data such as physiological parameters and exercise activity data provide real-time updates of health status, enabling comprehensive monitoring of user health. By using intersection operations to extract basic information features for each user category, it effectively summarizes the common characteristics across different user categories. These features provide a key reference for health status assessment, making health management more scientific and systematic.

[0016] Furthermore, step S200 includes:

[0017] S201. For each category of target users, extract the physical examination report time of the corresponding target user, obtain historical monitoring data before the physical examination report time, and divide the historical monitoring data into several data segments according to the continuous time period corresponding to the historical monitoring data; for each data segment, represent the data points corresponding to the corresponding historical monitoring data in a plane rectangular coordinate system in chronological order, and connect the data points in chronological order to obtain several historical monitoring data trend curves; and each historical monitoring data corresponds to several historical monitoring data trend curves;

[0018] S202. Extract historical monitoring data trend curves related to the basic information features, represent these historical monitoring data trend curves in the same rectangular coordinate system, arbitrarily select one historical monitoring data trend curve as a fixed curve, and sequentially move the remaining historical monitoring data trend curves on the fixed curve according to their corresponding starting points, thereby obtaining overlapping line segments between the historical monitoring data trend curves and the fixed curves. Summarize all overlapping line segments to obtain the parameter range Q1 of the historical monitoring data of the corresponding target user;

[0019] S203. Obtain the standard parameter interval Q0 of the historical monitoring data corresponding to the parameter interval Q1, and compare the size relationship between the standard parameter interval Q0 and the parameter interval Q1; if Q1⊂Q0, extract the historical monitoring data points in the historical monitoring data that only belong to the standard parameter interval Q0 and those that neither belong to the standard parameter interval Q0 nor to the parameter interval Q1 as monitoring key points; if Q0⊂Q1, extract the historical monitoring data points that do not belong to the parameter interval Q1 as monitoring key points; if Q0=Q1, extract the historical monitoring data points that do not belong to the standard parameter interval Q0 as monitoring key points.

[0020] By obtaining historical monitoring data for each category of target users and conducting detailed analysis, a more accurate trend curve for historical monitoring data can be obtained, which makes it possible to identify health trends and changes over a longer period of time. Analyzing the trend curve for historical data in combination with the basic information characteristics of the target users allows for a more personalized assessment of each user's health status, which means that the monitoring and analysis results can be more targeted, providing individualized health management solutions rather than a one-size-fits-all solution. By analyzing the trend curve for historical monitoring data, key monitoring points can be identified. These key points represent important change nodes in the user's health status and can serve as the basis for further health assessment and intervention, thereby improving the effectiveness of health management.

[0021] Furthermore, step S300 includes:

[0022] For each data segment corresponding to the historical monitoring data of each target user, the corresponding monitoring key point is extracted, and the difference between the monitoring key point and the average value of the corresponding standard parameter interval Q0 is calculated and the absolute value is taken for standardization to obtain the corresponding deviation value z; according to the weight and deviation value of each monitoring key point, the weighted deviation sum is calculated, and the weight of the monitoring key point is the frequency of the corresponding value in the data segment; the trend evaluation index H of the target user is calculated, and the specific calculation formula is:

[0023] H=1-[Σ i∈[1,k] (wi*zi) / (Σ i∈[1,k] wi)],

[0024] Among them, i represents the monitoring key point number, which is a positive integer between 1 and k, wi represents the weight corresponding to the i-th monitoring key point, and zi represents the deviation value of the i-th monitoring key point; for each category of target users, target users with normal physical examination reports are extracted, and the trend evaluation index H of the data segment closest to the physical examination report time of the target users with normal physical examination reports is used as the corresponding trend evaluation index threshold, and the trend evaluation index thresholds of the target users with normal physical examination reports are extracted and the average value is calculated as the trend evaluation index threshold H0 of the corresponding category; the parameter interval range Q1 of all historical monitoring data corresponding to the target users with normal physical examination reports are unioned with the corresponding standard parameter interval range Q0, and the obtained parameter interval range Q2 is associated with the corresponding category.

[0025] Furthermore, step S400 includes:

[0026] Using an intelligent robot, real-time monitoring data of the current user is collected in real time, and the trend curve of the real-time monitoring data is obtained in the same analysis method as the historical monitoring data; the usage record of the current user using the intelligent robot is obtained, and whether the current user is a new user is determined based on the usage record. If there is no usage record of the current user using the intelligent robot, the current user is determined to be a new user, and the current user enters basic information; the basic information of the current user is calculated to be similar to the basic information of the target user, and the basic information features corresponding to the target user with the greatest similarity are selected as the basic information features of the current user; if there is a usage record of the current user using the intelligent robot, the basic information features of the current user are obtained based on the usage record.

[0027] Furthermore, step S500 includes:

[0028] S501. Obtain the real-time monitoring data trend curve and basic information characteristics of the current user, analyze the real-time monitoring data trend curve and basic information characteristics of the current user with reference to the analysis process of the historical monitoring data trend curve and the corresponding basic information characteristics, and calculate the real-time trend evaluation index H1 of the current user; according to the basic information characteristics of the current user, determine the category of the current user, and extract the trend evaluation index threshold H0 of the corresponding category;

[0029] S502. Compare the size relationship between the real-time trend assessment index and the trend assessment index threshold of the corresponding category. If the real-time trend assessment index H1 is less than the trend assessment index threshold H0 of the corresponding category, and the real-time monitoring data belongs to the standard parameter interval Q0, it means that the real-time monitoring data of the current user is within the standard parameter interval, and there is no need to dynamically adjust the parameter interval of the monitoring data, then the standard parameter interval Q0 is output; if the real-time trend assessment index H1 is less than the trend assessment index threshold H0 of the corresponding category, and there are data points in the real-time monitoring data that do not belong to the standard parameter interval Q0, it means that there are individual data in the real-time monitoring data of the current user that are not within the standard parameter interval, but it is not certain whether the current user has health problems, so the parameter interval of the monitoring data needs to be dynamically adjusted, then the parameter interval Q2 of the corresponding category of the current user is output; if the real-time trend assessment index H1 is greater than the trend assessment index threshold H0 of the corresponding category, it means that the current user may have health problems, but the severity of the health problems needs to be further analyzed, then the standard parameter interval Q0 and the parameter interval Q2 of the corresponding category of the current user are output.

[0030] An intelligent robot management system for health monitoring, the system includes: a data management module, a historical data analysis module, a real-time monitoring and data processing module, a trend assessment index calculation module, and a user interface and feedback module;

[0031] The data management module obtains the basic information of different target users from the database, analyzes and classifies the basic information, constructs the target user data set, and obtains the basic information characteristics of target users of different categories; the historical data analysis module obtains the corresponding historical monitoring data for each category of target users, analyzes the historical monitoring data, and generates a historical monitoring data trend curve; according to the basic information characteristics of the target users, the historical monitoring data trend curve is analyzed and the monitoring key points are extracted; the real-time monitoring and data processing module collects the monitoring data of the current user in real time, determines whether the user is a new user, and obtains and matches the basic information; analyzes the trend of the real-time monitoring data, evaluates the real-time trend evaluation index of the current user, and compares it with the trend evaluation index threshold of the corresponding category; the trend evaluation index calculation module makes a judgment based on the real-time trend evaluation index of the current user and the trend evaluation index threshold, and outputs the corresponding information based on the judgment result; the user interface and feedback module provides a user interface to display the real-time trend evaluation index, historical data analysis results and output information.

[0032] Furthermore, the data management module includes a user information collection unit, a physical examination report analysis unit, and a basic information feature extraction unit;

[0033] The user information collection unit obtains the basic information of different target users from the database, extracts and summarizes the target user's ID and basic information, converts it into a unified format, and constructs a target user data set; the physical examination report analysis unit obtains the user's physical examination report, extracts abnormal parameters from it, and classifies the user based on the abnormal parameters; the basic information feature extraction unit performs an intersection operation on the basic information of each category of users based on the classification results to extract basic information features;

[0034] The historical data analysis module includes a historical monitoring data acquisition unit, a historical data trend curve generation unit, a historical data analysis unit, and a key point extraction unit;

[0035] The historical monitoring data acquisition unit extracts the historical monitoring data before the physical examination report time of the target user and divides it into several data segments; the historical data trend curve generation unit generates a historical monitoring data trend curve based on the historical monitoring data; the historical data analysis unit associates the historical monitoring data trend curve with the basic information features, generates overlapping line segments and calculates the parameter interval range Q1; the key point extraction unit compares the standard parameter interval range Q0 with the parameter interval range Q1 to extract the monitoring key points.

[0036] Furthermore, the real-time monitoring and data processing module includes a real-time data acquisition unit, a user identification and information acquisition unit, and a real-time data trend analysis unit;

[0037] The real-time data acquisition unit uses an intelligent robot to collect the monitoring data of the current user in real time and generate a real-time monitoring data trend curve; the user identification and information acquisition unit determines whether the current user is a new user, obtains or inputs the basic information of the current user, and performs similarity calculation to determine the basic information characteristics; the real-time data trend analysis unit analyzes the real-time monitoring data trend curve and calculates the real-time trend evaluation index H1 of the current user in combination with the basic information characteristics.

[0038] Furthermore, the trend evaluation index calculation module includes a trend evaluation index calculation unit and a judgment unit;

[0039] The trend assessment index calculation unit calculates the trend assessment index H and the trend assessment index threshold H0 of different categories based on historical monitoring data and monitoring key points; the judgment unit compares the size relationship between the real-time trend assessment index H1 and the trend assessment index threshold H0;

[0040] The user interface and feedback module includes a user input unit and a data display unit;

[0041] The user input unit allows the user to input basic information and feedback information; the data display unit displays the collected real-time data, historical data trends and the judgment results of the judgment unit to the user.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] Basic information of different target users is obtained from the database and analyzed to construct a target user dataset. This allows the system to consider each user's personalized characteristics (such as age, gender, physical condition, and underlying medical history), improving the accuracy and targeting of monitoring. This personalized assessment takes into account differences between users and more accurately reflects their health status than traditional universal parameter thresholds. By collecting the current user's monitoring data in real time and combining it with their basic information characteristics, similarity is calculated for new users. The basic information characteristics corresponding to the target user with the highest similarity are selected as the basic information characteristics of the current user. In this way, even new users can immediately enjoy personalized monitoring services. By analyzing the trend curve of the user's historical monitoring data and combining it with basic information characteristics, the system can identify key monitoring points. These key points can serve as the basis for further health assessment and intervention, thereby improving the effectiveness of health management. The system uses intelligent robots to collect the current user's real-time monitoring data in real time, analyze it in combination with basic information characteristics, and calculate a real-time trend assessment index. By comparing it with the trend assessment index threshold for the corresponding category, the system outputs a corresponding parameter range based on the user's real-time health status, thereby adjusting the parameter range based on the user's personalized data, rather than relying on fixed static thresholds. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 This is a schematic diagram of an intelligent robot management system module for health monitoring according to the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0047] See also Figure 1 , the present invention provides a technical solution:

[0048] An intelligent robot management system for health monitoring, the system includes: a data management module, a historical data analysis module, a real-time monitoring and data processing module, a trend assessment index calculation module, and a user interface and feedback module;

[0049] The data management module obtains the basic information of different target users from the database, analyzes and classifies the basic information, constructs the target user data set, and obtains the basic information characteristics of target users of different categories; the historical data analysis module obtains the corresponding historical monitoring data for each category of target users, analyzes the historical monitoring data, and generates a historical monitoring data trend curve; according to the basic information characteristics of the target users, the historical monitoring data trend curve is analyzed and the monitoring key points are extracted; the real-time monitoring and data processing module collects the monitoring data of the current user in real time, determines whether the user is a new user, and obtains and matches the basic information; analyzes the trend of the real-time monitoring data, evaluates the real-time trend evaluation index of the current user, and compares it with the trend evaluation index threshold of the corresponding category; the trend evaluation index calculation module makes a judgment based on the real-time trend evaluation index of the current user and the trend evaluation index threshold, and outputs the corresponding information based on the judgment result; the user interface and feedback module provides a user interface to display the real-time trend evaluation index, historical data analysis results and output information.

[0050] The data management module includes a user information collection unit, a physical examination report analysis unit, and a basic information feature extraction unit;

[0051] The user information collection unit obtains the basic information of different target users from the database, extracts and summarizes the target user's ID and basic information, converts it into a unified format, and constructs a target user data set; the physical examination report analysis unit obtains the user's physical examination report, extracts abnormal parameters from it, and classifies the user based on the abnormal parameters; the basic information feature extraction unit performs an intersection operation on the basic information of each category of users based on the classification results to extract basic information features;

[0052] The historical data analysis module includes a historical monitoring data acquisition unit, a historical data trend curve generation unit, a historical data analysis unit, and a key point extraction unit;

[0053] The historical monitoring data acquisition unit extracts the historical monitoring data before the physical examination report time of the target user and divides it into several data segments; the historical data trend curve generation unit generates a historical monitoring data trend curve based on the historical monitoring data; the historical data analysis unit associates the historical monitoring data trend curve with the basic information features, generates overlapping line segments and calculates the parameter interval range Q1; the key point extraction unit compares the standard parameter interval range Q0 with the parameter interval range Q1 to extract the monitoring key points.

[0054] The real-time monitoring and data processing module includes a real-time data acquisition unit, a user identification and information acquisition unit, and a real-time data trend analysis unit;

[0055] The real-time data acquisition unit uses an intelligent robot to collect the monitoring data of the current user in real time and generate a real-time monitoring data trend curve; the user identification and information acquisition unit determines whether the current user is a new user, obtains or inputs the basic information of the current user, and performs similarity calculation to determine the basic information characteristics; the real-time data trend analysis unit analyzes the real-time monitoring data trend curve and calculates the real-time trend evaluation index H1 of the current user in combination with the basic information characteristics.

[0056] The trend evaluation index calculation module includes a trend evaluation index calculation unit and a judgment unit;

[0057] The trend assessment index calculation unit calculates the trend assessment index H and the trend assessment index threshold H0 of different categories based on historical monitoring data and monitoring key points; the judgment unit compares the size relationship between the real-time trend assessment index H1 and the trend assessment index threshold H0;

[0058] The user interface and feedback module includes a user input unit and a data display unit;

[0059] The user input unit allows the user to input basic information and feedback information; the data display unit displays the collected real-time data, historical data trends and the judgment results of the judgment unit to the user.

[0060] An intelligent robot management method for health monitoring, the method comprising the following steps:

[0061] Step S100: Obtain basic information of different target users from the database, analyze the basic information of all target users, and thus construct a target user dataset; based on the target user's physical examination report, classify the elements in the target user dataset to obtain basic information features of different categories of target users;

[0062] Step S200. For each category of target users, obtain corresponding historical monitoring data, analyze the historical monitoring data, and thus obtain the historical monitoring data trend curve corresponding to the target user; analyze the historical monitoring data trend curve in combination with the basic information characteristics of the target user to obtain the monitoring key points;

[0063] Step S300. Based on the monitoring key points and in combination with the corresponding historical monitoring data, the deviation between the target user's historical monitoring data and the corresponding standard parameters is evaluated to obtain the target user's trend evaluation index and the trend evaluation index threshold of the corresponding category;

[0064] Step S400. Using the intelligent robot, real-time monitoring data of the current user is collected and analyzed to obtain a real-time monitoring data trend curve; obtaining the usage record of the current user using the intelligent robot, determining whether the current user is a new user based on the usage record, and obtaining basic information characteristics of the current user based on the determination result;

[0065] Step S500. Obtain the real-time monitoring data trend curve and basic information characteristics of the current user, analyze the real-time monitoring data trend curve and basic information characteristics of the current user, and calculate the real-time trend evaluation index of the current user; compare the size relationship between the real-time trend evaluation index and the trend evaluation index threshold of the corresponding category, and output corresponding notification information based on the judgment result of the size relationship.

[0066] Step S100 includes:

[0067] S101. The target user's basic information refers to various static and dynamic data related to the target user's personal health; wherein, the static data refers to relatively fixed and infrequently changing data, such as age, gender, height, weight, physical condition, underlying medical history, family medical history, etc.; the dynamic data refers to real-time or regularly updated data that can be collected within a specific time period, such as physiological parameters, exercise and activity data, sleep data, mood and emotion data, and environmental data, etc.; extract the target user's number, summarize the target user's basic information according to the number, and convert the basic information of the target user corresponding to each number into a unified format. The basic information of the target user corresponding to a number is used as an element, and the different elements are summarized to construct a target user data set;

[0068] S102. Obtain the physical examination reports of all target users, analyze the abnormal parameters in the physical examination reports, extract the names corresponding to the abnormal parameters, and classify the basic information of the target users with the same abnormal parameter names into one category, thereby dividing the elements in the target user data set into several categories; for each category, perform an intersection operation on each data item of the element in the target user data set, extract the result of the intersection operation as the basic information feature, and traverse all categories in turn to obtain the basic information features of target users in different categories.

[0069] This system considers both static and dynamic data, providing a comprehensive overview of a user's health status. Static data such as age and gender provide a basic health background, while dynamic data such as physiological parameters and exercise activity data provide real-time updates of health status, enabling comprehensive monitoring of user health. By using intersection operations to extract basic information features for each user category, it effectively summarizes the common characteristics across different user categories. These features provide a key reference for health status assessment, making health management more scientific and systematic.

[0070] In this embodiment, it is assumed that the static data in the user basic information is age, weight, basic disease history, and family medical history, and the dynamic data is blood pressure, heart rate, and environmental data; three target users are obtained, namely: target user 1, target user 2, and target user 3, and in a certain physical examination report, it is found that target user 1 and target user 2 both have abnormal blood pressure, while the physical examination report of target user 3 does not have abnormal blood pressure; the basic information of target user 1 and target user 2 are classified into the same category, that is, the abnormal blood pressure category, and target user 3 is classified into the normal blood pressure category; for the abnormal blood pressure category, the elements corresponding to target user 1 and target user 2 are extracted from the target user data set, and each data item in the elements corresponding to target user 1 and target user 2 (age, weight, basic disease history, family medical history, and dynamic data are blood pressure, heart rate, and environmental data) is union calculated. Assuming that the union calculation result is age, weight, and basic disease history, then age, weight, and basic disease history are used as the basic information features of the abnormal blood pressure category.

[0071] Step S200 includes:

[0072] S201. For each category of target users, extract the physical examination report time of the corresponding target user, obtain historical monitoring data before the physical examination report time, and divide the historical monitoring data into several data segments according to the continuous time period corresponding to the historical monitoring data; for each data segment, represent the data points corresponding to the corresponding historical monitoring data in a plane rectangular coordinate system in chronological order, and connect the data points in chronological order to obtain several historical monitoring data trend curves; and each historical monitoring data corresponds to several historical monitoring data trend curves;

[0073] S202. Extract historical monitoring data trend curves related to the basic information features, represent these historical monitoring data trend curves in the same rectangular coordinate system, arbitrarily select one historical monitoring data trend curve as a fixed curve, and sequentially move the remaining historical monitoring data trend curves on the fixed curve according to their corresponding starting points, thereby obtaining overlapping line segments between the historical monitoring data trend curves and the fixed curves. Summarize all overlapping line segments to obtain the parameter range Q1 of the historical monitoring data of the corresponding target user;

[0074] S203. Obtain the standard parameter interval Q0 of the historical monitoring data corresponding to the parameter interval Q1, and compare the size relationship between the standard parameter interval Q0 and the parameter interval Q1; if Q1⊂Q0, extract the historical monitoring data points in the historical monitoring data that only belong to the standard parameter interval Q0 and those that neither belong to the standard parameter interval Q0 nor to the parameter interval Q1 as monitoring key points; if Q0⊂Q1, extract the historical monitoring data points that do not belong to the parameter interval Q1 as monitoring key points; if Q0=Q1, extract the historical monitoring data points that do not belong to the standard parameter interval Q0 as monitoring key points.

[0075] By obtaining historical monitoring data for each category of target users and conducting detailed analysis, a more accurate trend curve for historical monitoring data can be obtained, which makes it possible to identify health trends and changes over a longer period of time. Analyzing the trend curve for historical data in combination with the basic information characteristics of the target users allows for a more personalized assessment of each user's health status, which means that the monitoring and analysis results can be more targeted, providing individualized health management solutions rather than a one-size-fits-all solution. By analyzing the trend curve for historical monitoring data, key monitoring points can be identified. These key points represent important change nodes in the user's health status and can serve as the basis for further health assessment and intervention, thereby improving the effectiveness of health management.

[0076] Step S300 includes:

[0077] For each data segment corresponding to the historical monitoring data of each target user, the corresponding monitoring key point is extracted, and the difference between the monitoring key point and the average value of the corresponding standard parameter interval Q0 is calculated and the absolute value is taken for standardization to obtain the corresponding deviation value z; according to the weight and deviation value of each monitoring key point, the weighted deviation sum is calculated, and the weight of the monitoring key point is the frequency of the corresponding value in the data segment; the trend evaluation index H of the target user is calculated, and the specific calculation formula is:

[0078] H=1-[Σ i∈[1,k] (wi*zi) / (Σ i∈[1,k] wi)],

[0079] Among them, i represents the monitoring key point number, which is a positive integer between 1 and k, wi represents the weight corresponding to the i-th monitoring key point, and zi represents the deviation value of the i-th monitoring key point; for each category of target users, target users with normal physical examination reports are extracted, and the trend evaluation index H of the data segment closest to the physical examination report time of the target users with normal physical examination reports is used as the corresponding trend evaluation index threshold, and the trend evaluation index thresholds of the target users with normal physical examination reports are extracted and the average value is calculated as the trend evaluation index threshold H0 of the corresponding category; the parameter interval range Q1 of all historical monitoring data corresponding to the target users with normal physical examination reports are unioned with the corresponding standard parameter interval range Q0, and the obtained parameter interval range Q2 is associated with the corresponding category.

[0080] Step S400 includes:

[0081] Using an intelligent robot, real-time monitoring data of the current user is collected in real time, and the trend curve of the real-time monitoring data is obtained in the same analysis method as the historical monitoring data; the usage record of the current user using the intelligent robot is obtained, and whether the current user is a new user is determined based on the usage record. If there is no usage record of the current user using the intelligent robot, the current user is determined to be a new user, and the current user enters basic information; the basic information of the current user is calculated to be similar to the basic information of the target user, and the basic information features corresponding to the target user with the greatest similarity are selected as the basic information features of the current user; if there is a usage record of the current user using the intelligent robot, the basic information features of the current user are obtained based on the usage record.

[0082] Step S500 includes:

[0083] S501. Obtain the real-time monitoring data trend curve and basic information characteristics of the current user, analyze the real-time monitoring data trend curve and basic information characteristics of the current user with reference to the analysis process of the historical monitoring data trend curve and the corresponding basic information characteristics, and calculate the real-time trend evaluation index H1 of the current user; according to the basic information characteristics of the current user, determine the category of the current user, and extract the trend evaluation index threshold H0 of the corresponding category;

[0084] S502. Compare the size relationship between the real-time trend assessment index and the trend assessment index threshold of the corresponding category. If the real-time trend assessment index H1 is less than the trend assessment index threshold H0 of the corresponding category, and the real-time monitoring data belongs to the standard parameter interval Q0, it means that the real-time monitoring data of the current user is within the standard parameter interval, and there is no need to dynamically adjust the parameter interval of the monitoring data, then the standard parameter interval Q0 is output; if the real-time trend assessment index H1 is less than the trend assessment index threshold H0 of the corresponding category, and there are data points in the real-time monitoring data that do not belong to the standard parameter interval Q0, it means that there are individual data in the real-time monitoring data of the current user that are not within the standard parameter interval, but it is not certain whether the current user has health problems, so the parameter interval of the monitoring data needs to be dynamically adjusted, then the parameter interval Q2 of the corresponding category of the current user is output; if the real-time trend assessment index H1 is greater than the trend assessment index threshold H0 of the corresponding category, it means that the current user may have health problems, but the severity of the health problems needs to be further analyzed, then the standard parameter interval Q0 and the parameter interval Q2 of the corresponding category of the current user are output.

[0085] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0086] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An intelligent robot management method for health monitoring, characterized in that: The method comprises the following steps: Step S100. Obtain basic information of different target users from the database, analyze the basic information of all target users, and thus construct a target user data set; classify the elements in the target user data set based on the physical examination report of the target user, and thus obtain basic information features of target users of different categories; Step S200. For each category of target users, obtain corresponding historical monitoring data, analyze the historical monitoring data, and obtain the historical monitoring data trend curve corresponding to the target user; analyze the historical monitoring data trend curve in combination with the basic information characteristics of the target user, and obtain the key points of monitoring; Step S300. According to the monitoring key points, combined with the corresponding historical monitoring data, the deviation between the target user's historical monitoring data and the corresponding standard parameters is evaluated, so as to obtain the trend evaluation index of the target user and the trend evaluation index threshold of the corresponding category; Step S400. Using the intelligent robot, collect the real-time monitoring data of the current user in real time, analyze the real-time monitoring data, and obtain the real-time monitoring data trend curve; obtain the usage record of the current user using the intelligent robot, determine whether the current user is a new user according to the usage record, and obtain the basic information characteristics of the current user according to the determination result; Step S500. Obtain the real-time monitoring data trend curve and basic information characteristics of the current user, analyze the real-time monitoring data trend curve and basic information characteristics of the current user, calculate the real-time trend evaluation index of the current user; compare the size relationship between the real-time trend evaluation index and the trend evaluation index threshold of the corresponding category, and output corresponding notification information based on the judgment result of the size relationship; The step S200 includes: S201. For each category of target users, extract the physical examination report time of the corresponding target user, obtain the historical monitoring data before the physical examination report time, and divide the historical monitoring data into several data segments according to the continuous time period corresponding to the historical monitoring data; for each data segment, represent the data points corresponding to the corresponding historical monitoring data in a plane rectangular coordinate system in chronological order, and connect the data points in chronological order, so as to obtain several trend curves of historical monitoring data; S202. Extract the historical monitoring data trend curve related to the basic information feature, represent the historical monitoring data trend curve in the same rectangular coordinate system, arbitrarily select one historical monitoring data trend curve as a fixed curve, and move the remaining historical monitoring data trend curves on the fixed curve in sequence according to the corresponding starting points, so as to obtain the overlapping line segments between the historical monitoring data trend curve and the fixed curve, summarize all the overlapping line segments, and obtain the parameter interval range Q1 of the historical monitoring data of the corresponding target user; S203. Obtain the standard parameter interval Q0 of the historical monitoring data corresponding to the parameter interval Q1, and compare the size relationship between the standard parameter interval Q0 and the parameter interval Q1; if Q1⊂Q0, extract the historical monitoring data points that only belong to the standard parameter interval Q0 and those that neither belong to the standard parameter interval Q0 nor to the parameter interval Q1 in the historical monitoring data as the key monitoring points; if Q0⊂Q1, extract the historical monitoring data points that do not belong to the parameter interval Q1 as the key monitoring points; if Q0=Q1, extract the historical monitoring data points that do not belong to the standard parameter interval Q0 as the key monitoring points; The step S300 includes: For each data segment corresponding to the historical monitoring data of each target user, the corresponding monitoring key point is extracted, and the difference between the monitoring key point and the average value of the corresponding standard parameter interval range Q0 is calculated and the absolute value is taken for standardization, so as to obtain the corresponding deviation value z; according to the weight and deviation value of each monitoring key point, the weighted deviation sum is calculated, and the weight of the monitoring key point is the frequency of the corresponding value in the data segment; the trend evaluation index H of the target user is calculated, and the specific calculation formula is: H=1-[Σ i∈[1,k] (wi*zi) / (Σ i∈[1,k] wi)], Among them, i represents the monitoring key point number, which is a positive integer between 1 and k, wi represents the weight corresponding to the i-th monitoring key point, and zi represents the deviation value of the i-th monitoring key point; for each category of target users, target users with normal physical examination reports are extracted, and the trend evaluation index H of the data segment closest to the physical examination report time of the target users with normal physical examination reports is used as the corresponding trend evaluation index threshold, the trend evaluation index thresholds of the target users with normal physical examination reports are extracted and the average value is calculated as the trend evaluation index threshold H0 of the corresponding category; the parameter interval range Q1 of all historical monitoring data corresponding to the target users with normal physical examination reports are unioned with the corresponding standard parameter interval range Q0, and the obtained parameter interval range Q2 is associated with the corresponding category.

2. The intelligent robot management method for health monitoring according to claim 1, characterized in that: The step S100 includes: S101. The basic information of the target user refers to various static and dynamic data related to the personal health of the target user; extract the target user's number, summarize the basic information of the target user according to the number, convert the format of the basic information of the target user corresponding to each number into a unified format, take the basic information of the target user corresponding to a number as an element, summarize different elements, and thus construct a target user data set; S102. Obtain the physical examination reports of all target users, analyze the abnormal parameters in the physical examination reports, extract the names corresponding to the abnormal parameters, and classify the basic information of the target users with the same abnormal parameter names into one category, thereby dividing the elements in the target user data set into several categories; for each category, perform an intersection operation on each data item of the element in the target user data set, extract the result of the intersection operation as the basic information feature, and traverse all categories in turn to obtain the basic information features of target users of different categories.

3. The intelligent robot management method for health monitoring according to claim 1, characterized in that: The step S400 includes: Using an intelligent robot, real-time monitoring data of the current user is collected in real time, and the trend curve of the real-time monitoring data is obtained in the same analysis method as the historical monitoring data; the usage record of the current user using the intelligent robot is obtained, and whether the current user is a new user is determined based on the usage record. If there is no usage record of the current user using the intelligent robot, the current user is determined to be a new user, and the current user enters basic information; the basic information of the current user is calculated to be similar to the basic information of the target user, and the basic information features corresponding to the target user with the greatest similarity are selected as the basic information features of the current user; if there is a usage record of the current user using the intelligent robot, the basic information features of the current user are obtained based on the usage record.

4. The intelligent robot management method for health monitoring according to claim 1, characterized in that: The step S500 includes: S501. Obtain the real-time monitoring data trend curve and basic information characteristics of the current user, analyze the real-time monitoring data trend curve and basic information characteristics of the current user with reference to the analysis process of the historical monitoring data trend curve and the corresponding basic information characteristics, and calculate the real-time trend evaluation index H1 of the current user; according to the basic information characteristics of the current user, determine the category of the current user, and extract the trend evaluation index threshold H0 of the corresponding category; S502. Compare the size relationship between the real-time trend evaluation index and the trend evaluation index threshold of the corresponding category. If the real-time trend evaluation index H1 is less than the trend evaluation index threshold H0 of the corresponding category, and the real-time monitoring data belongs to the standard parameter interval Q0, then output the standard parameter interval Q0; if the real-time trend evaluation index H1 is less than the trend evaluation index threshold H0 of the corresponding category, and there are data points in the real-time monitoring data that do not belong to the standard parameter interval Q0, then output the parameter interval Q2 of the category corresponding to the current user; if the real-time trend evaluation index H1 is greater than the trend evaluation index threshold H0 of the corresponding category, then output the standard parameter interval Q0 and the parameter interval Q2 of the category corresponding to the current user.

5. An intelligent robot management system for health monitoring, applied to an intelligent robot management method for health monitoring according to any one of claims 1 to 4, characterized in that: The system includes: a data management module, a historical data analysis module, a real-time monitoring and data processing module, a trend assessment index calculation module, and a user interface and feedback module; The data management module obtains basic information of different target users from the database, analyzes and classifies the basic information, constructs a target user data set, and obtains basic information characteristics of target users of different categories; the historical data analysis module obtains corresponding historical monitoring data for each category of target users, analyzes the historical monitoring data, and generates a trend curve of historical monitoring data; analyzes the trend curve of historical monitoring data according to the basic information characteristics of the target users, and extracts key monitoring points; the real-time monitoring and data processing module collects the monitoring data of the current user in real time, determines whether the user is a new user, and obtains and matches basic information; analyzes the trend of real-time monitoring data, evaluates the real-time trend evaluation index of the current user, and compares it with the trend evaluation index threshold of the corresponding category; the trend evaluation index calculation module makes a judgment based on the real-time trend evaluation index of the current user and the trend evaluation index threshold, and outputs corresponding information based on the judgment result; the user interface and feedback module provides a user interface to display the real-time trend evaluation index, historical data analysis results and output information.

6. The intelligent robot management system for health monitoring according to claim 5, characterized in that: The data management module includes a user information collection unit, a physical examination report analysis unit and a basic information feature extraction unit; The user information collection unit obtains basic information of different target users from the database, extracts and summarizes the target user's number and basic information, converts them into a unified format, and constructs a target user data set; the physical examination report analysis unit obtains the user's physical examination report, extracts abnormal parameters from it, and classifies the user based on the abnormal parameters; the basic information feature extraction unit performs an intersection operation on the basic information of each category of users according to the classification result to extract basic information features; The historical data analysis module includes a historical monitoring data acquisition unit, a historical data trend curve generation unit, a historical data analysis unit and a key point extraction unit; The historical monitoring data acquisition unit extracts the historical monitoring data before the physical examination report time of the target user and divides it into several data segments; the historical data trend curve generation unit generates a historical monitoring data trend curve based on the historical monitoring data; the historical data analysis unit associates the historical monitoring data trend curve with the basic information features, generates overlapping line segments and calculates the parameter interval range Q1; the key point extraction unit compares the standard parameter interval range Q0 with the parameter interval range Q1 to extract the monitoring key points.

7. The intelligent robot management system for health monitoring according to claim 5, characterized in that: The real-time monitoring and data processing module includes a real-time data acquisition unit, a user identification and information acquisition unit, and a real-time data trend analysis unit; The real-time data collection unit uses an intelligent robot to collect the monitoring data of the current user in real time and generate a real-time monitoring data trend curve; The user identification and information acquisition unit determines whether the current user is a new user, obtains or inputs the basic information of the current user, and performs similarity calculation to determine the basic information characteristics; the real-time data trend analysis unit analyzes the real-time monitoring data trend curve, and calculates the real-time trend evaluation index H1 of the current user in combination with the basic information characteristics.

8. The intelligent robot management system for health monitoring according to claim 5, characterized in that: The trend assessment index calculation module includes a trend assessment index calculation unit and a judgment unit; The trend assessment index calculation unit calculates the trend assessment index H and trend assessment index thresholds H0 of different categories according to historical monitoring data and monitoring key points; The judgment unit compares the magnitude relationship between the real-time trend evaluation index H1 and the trend evaluation index threshold H0; The user interface and feedback module includes a user input unit and a data display unit; The user input unit allows the user to input basic information and feedback information; the data display unit displays the collected real-time data, historical data trends and the judgment results of the judgment unit to the user.

Images