Sphygmomanometer monitoring abnormity early warning method

Abstract

The invention discloses a sphygmomanometer monitoring abnormity early warning method, and relates to the related field of blood vessel pressure measurement, and the method comprises the following steps: obtaining basic model parameters of a target electronic sphygmomanometer, and configuring an internal self-checking rule; after a blood pressure monitoring request is received, an internal self-checking rule is activated, and an inflation and deflation control node is marked according to an inflation pump and an exhaust valve after internal self-checking is passed; introducing a monitoring preparation condition, wherein the monitoring preparation condition meets the pressure safety constraint; determining an initial resolution according to the pressure sensor, and setting a target resolution in combination with a blood pressure precision requirement; and after a monitoring preparation condition is achieved, setting an abnormal early warning mechanism based on the basic model parameters, the deflation control starting point and the deflation control ending point in combination with the target resolution. The technical problem that an existing sphygmomanometer is not high in monitoring accuracy and applicability in abnormal early warning monitoring, and consequently the abnormal early warning capacity is insufficient is solved, and the technical effects that the accuracy and applicability of blood pressure monitoring are improved, and then the abnormal early warning capacity of equipment is enhanced are achieved.

Description

Technical Field

[0001] The present application relates to the field related to vascular pressure measurement, and in particular to a method for early warning of abnormal monitoring of a sphygmomanometer. Background Art

[0002] Blood pressure monitoring is one of the important indicators for assessing individual health status. With the advancement of technology, electronic blood pressure monitors have gradually become a commonly used blood pressure monitoring tool in homes and medical institutions due to their easy operation. Traditional electronic blood pressure monitors usually rely on built-in sensors and algorithms to measure systolic and diastolic blood pressure when monitoring blood pressure. After receiving a blood pressure monitoring request, these devices will inflate and deflate according to a preset program to measure the user's blood pressure value. However, these devices often lack sufficient intelligence and personalized settings during the monitoring process, resulting in the monitoring results being affected by a variety of factors, such as individual differences between users, differences in device models, etc., which ultimately affects the accuracy and applicability of the measurement results.

[0003] In the current related technologies, the abnormal warning monitoring of blood pressure monitors has the technical problems of low monitoring accuracy and applicability, resulting in insufficient abnormal warning capabilities. Summary of the invention

[0004] The present application provides a method for abnormal warning of blood pressure monitor monitoring, which obtains the basic model parameters of the target electronic blood pressure monitor and uses the built-in microprocessor to configure internal self-check rules. After receiving a blood pressure monitoring request, the internal self-check rules are activated, and the inflation and deflation control nodes are marked according to the inflation pump and the exhaust valve. The initial resolution is determined according to the pressure sensor of the target electronic blood pressure monitor, and the target resolution is set in combination with the user's blood pressure accuracy requirements. After the monitoring preparation conditions are met, technical means such as setting an abnormal warning mechanism based on the basic model parameters, deflation control nodes and target resolution are used to achieve the technical effect of improving the accuracy and applicability of blood pressure monitoring, thereby enhancing the abnormal warning capability of the equipment.

[0005] The present application provides a blood pressure monitor monitoring abnormality warning method, comprising: obtaining basic model parameters of a target electronic blood pressure monitor, and configuring internal self-check rules using a microprocessor built into the target electronic blood pressure monitor; after receiving a blood pressure monitoring request, activating the internal self-check rules, and if the internal self-check passes, marking the inflation and deflation control nodes according to the inflation pump and the exhaust valve of the target electronic blood pressure monitor, the inflation and deflation control nodes including an inflation control starting point and an inflation control end point, and a deflation control starting point and a deflation control end point; introducing a monitoring preparation condition, the monitoring preparation condition satisfies a pressure safety constraint, the pressure safety constraint is used to combine the inflation control starting point and the inflation control end point to uniformly apply pressure to the user's blood vessels with a cuff; determining an initial resolution according to a pressure sensor of the target electronic blood pressure monitor, and setting a target resolution in combination with blood pressure accuracy requirements, the target resolution being not less than a standard resolution, and the target resolution including a systolic pressure resolution and a diastolic pressure resolution; after the monitoring preparation condition is met, setting an abnormality warning mechanism based on the basic model parameters, the deflation control starting point and the deflation control end point, and in combination with the target resolution.

[0006] In a possible implementation, the initial resolution is determined based on the pressure sensor of the target electronic blood pressure monitor, and the target resolution is set in combination with the blood pressure accuracy requirement, and the following processing is performed: based on the target electronic blood pressure monitor, the user registration information is determined, and the user registration information includes the user's age, user gender, user height, and user weight; through the user registration information, the normal fluctuation range that meets the blood pressure accuracy requirement is determined; based on the initial resolution, the target resolution is set according to the upper and lower limits corresponding to the normal fluctuation range that meets the blood pressure accuracy requirement.

[0007] In a possible implementation, the target resolution includes a systolic pressure resolution and a diastolic pressure resolution, and the following processing is performed: according to the pressure sensor of the target electronic blood pressure monitor, in combination with the upper limit corresponding to the normal fluctuation range, a first systolic pressure threshold and a first diastolic pressure threshold are configured; according to the pressure sensor of the target electronic blood pressure monitor, in combination with the lower limit corresponding to the normal fluctuation range, a second systolic pressure threshold and a second diastolic pressure threshold are configured; based on the initial resolution, in combination with the first systolic pressure threshold, the second systolic pressure threshold and the blood pressure accuracy requirement, the systolic pressure resolution in the target resolution is set; based on the initial resolution, in combination with the first diastolic pressure threshold, the second diastolic pressure threshold and the blood pressure accuracy requirement, the diastolic pressure resolution in the target resolution is set.

[0008] In a possible implementation, based on the initial resolution, combined with the first systolic pressure threshold, the second systolic pressure threshold and the blood pressure accuracy requirement, the systolic pressure resolution in the target resolution is set, and the following processing is performed: introduce user multi-dimensional information, use a multi-level linked list architecture to organize data association indexes, and set a data mining mechanism, which is used to optimize search efficiency; based on the data mining mechanism, formulate resolution adjustment rules, and define a loose resolution solution space and a contracted resolution solution space.

[0009] In a possible implementation, the following processing is performed: the user multi-dimensional information includes living habit information and eating habit information corresponding to the user's personal information and family medical history information and historical medical information corresponding to medical health indicators; based on the user multi-dimensional information, multiple jump lists are constructed, wherein each jump list node contains any type of information, and nodes of different levels are connected by pointers to form the multi-level linked list architecture.

[0010] In a possible implementation, the following processing is performed: based on the user's multi-dimensional information, a loose matching strategy is set, and the loose matching strategy includes a first deviation threshold; according to the loose matching strategy, data mining is performed with the first deviation threshold as a constraint condition, and a loose resolution solution space that meets the first data density is set.

[0011] In a possible implementation, the following processing is performed: based on the user's multi-dimensional information, a shrinkage matching strategy is set, the shrinkage matching strategy includes a second deviation threshold, and the first deviation threshold is greater than the second deviation threshold; according to the shrinkage matching strategy, data mining is performed with the second deviation threshold as a constraint condition, and a shrinkage resolution solution space that meets the second data density is set, and the first data density is less than the second data density.

[0012] In a possible implementation, the following processing is performed: based on the user's medical history, a sensitive group is marked, and the sensitive group is a user group that undergoes drug intervention; risk levels are divided through the sensitive group and the remaining user groups, and a risk assessment model is established; based on the risk assessment model, the risk assessment level is obtained, and the risk assessment level is associated and bound one-to-one with the blood pressure accuracy requirement.

[0013] A blood pressure monitor abnormality warning method proposed in the present application is proposed. First, the basic model parameters of the target electronic blood pressure monitor are obtained, and the internal self-check rules are configured using the built-in microprocessor of the target electronic blood pressure monitor. Then, after receiving the blood pressure monitoring request, the internal self-check rules are activated. If the internal self-check passes, the inflation and deflation control nodes are marked according to the inflation pump and the exhaust valve of the target electronic blood pressure monitor. The inflation and deflation control nodes include the inflation control starting point and the inflation control end point, and the deflation control starting point and the deflation control end point. Then, the monitoring preparation conditions are introduced. The monitoring preparation conditions meet the pressure safety constraints. The pressure safety constraints are used to combine the inflation control starting point and the inflation control end point to uniformly apply pressure to the user's blood vessels with the cuff. Then, according to the pressure sensor of the target electronic blood pressure monitor, the initial resolution is determined, and the target resolution is set in combination with the blood pressure accuracy requirements. The target resolution is not lower than the standard resolution. The target resolution includes the systolic pressure resolution and the diastolic pressure resolution. Finally, after the monitoring preparation conditions are met, based on the basic model parameters, the deflation control starting point and the deflation control end point, combined with the target resolution, an abnormal warning mechanism is set, thereby achieving the technical effect of improving the accuracy and applicability of blood pressure monitoring and thereby enhancing the abnormal warning capability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A flow chart of a blood pressure monitor abnormal monitoring warning method provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of a flow chart for setting a target resolution in a blood pressure monitor abnormality warning method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a method for early warning of abnormal monitoring of a blood pressure monitor, such as Figure 1 As shown, the method includes: Step S100, obtain the basic model parameters of the target electronic blood pressure meter, and use the built-in microprocessor of the target electronic blood pressure meter to configure the internal self-test rules. Specifically, by connecting to the target electronic blood pressure meter (which can be wired or wireless), read its manufacturer, model, manufacturing date, specifications, hardware configuration, software version and other basic information from the storage unit or configuration file of the device. Use a microprocessor (i.e., a microcontroller unit, an electronic component for processing data and executing instructions) to load or generate a set of self-test rules according to the device model parameters, including hardware-level health checks such as checking power supply voltage, sensor connection status, button response, screen display, etc., as well as software-level checks, such as verifying program integrity.

[0021] Step S200, after receiving the blood pressure monitoring request, activate the internal self-check rule. If the internal self-check passes, mark the inflation and deflation control nodes according to the inflation pump and exhaust valve of the target electronic sphygmomanometer. The inflation and deflation control nodes include the inflation control starting point and inflation control end point, and the deflation control starting point and deflation control end point. Specifically, the user sends a blood pressure monitoring instruction through an interface (such as a button, a touch screen) or a remote device (such as a mobile phone APP) to execute the self-check rule configured in step S100 to ensure that the device is in good working condition. According to the working characteristics of the device's inflation pump (a device for injecting gas into the cuff of the target electronic sphygmomanometer) and the exhaust valve (a device for releasing the gas in the cuff), determine the starting and ending points of inflation and deflation. These nodes are used to control the inflation and discharge of the gas in the cuff, thereby affecting the pressure on the user's blood vessels.

[0022] Step S300, introduces monitoring preparation conditions, the monitoring preparation conditions satisfy the pressure safety constraint, and the pressure safety constraint is used to combine the inflation control starting point and the inflation control end point so that the cuff can evenly apply pressure to the user's blood vessels. Specifically, the monitoring preparation conditions are introduced, including whether the cuff is worn correctly, whether the user is in a resting state, etc. The monitoring preparation conditions satisfy the pressure safety constraint, that is, by setting a reasonable inflation pressure and rate, it is ensured that the cuff can evenly apply pressure to the user's blood vessels, so that blood pressure can be accurately measured while avoiding discomfort or harm to the user.

[0023] Step S400, determine the initial resolution according to the pressure sensor of the target electronic blood pressure meter, and set the target resolution in combination with the blood pressure accuracy requirements, the target resolution is not lower than the standard resolution, and the target resolution includes the systolic pressure resolution and the diastolic pressure resolution. Specifically, according to the characteristics and performance of the pressure sensor (a device for measuring the gas pressure in the cuff, whose output signal can be used to calculate the blood pressure value), determine its initial resolution when measuring blood pressure, that is, the measurement accuracy of the pressure sensor when it is not adjusted. Combined with the accuracy requirements of blood pressure measurement (such as the accuracy requirements of systolic and diastolic pressures), adjust and set the target resolution (the measurement accuracy of the pressure sensor after adjustment according to the measurement requirements), wherein the target resolution should not be lower than the standard resolution to ensure the accuracy of the measurement.

[0024] like Figure 2As shown, in a possible implementation, the initial resolution is determined according to the pressure sensor of the target electronic blood pressure monitor, and the target resolution is set in combination with the blood pressure accuracy requirements. Step S400 further includes step S410, and the user registration information is determined based on the target electronic blood pressure monitor, and the user registration information includes the user's age, user's gender, user's height, and user's weight. Specifically, when the user uses or sets the target electronic blood pressure monitor for the first time, the system will prompt the user to enter personal basic information, including age, gender, height, and weight. The system stores this information in the built-in memory of the target electronic blood pressure monitor or in a cloud database associated therewith for subsequent use. At the same time, the system will verify the rationality of the input information, such as checking whether the age is within a reasonable range, whether the height and weight are in line with the normal proportions of the human body, etc.

[0025] Step S420, determine the normal fluctuation range that meets the blood pressure accuracy requirement through the user registration information. Specifically, according to the user's age, gender and other information, search the relevant medical standards or database to determine the normal blood pressure fluctuation range for the user group. In combination with individual differences (such as height, weight, etc.), fine-tune the standard range to be closer to the user's actual situation. According to the accuracy requirements of the target electronic blood pressure monitor (such as the accuracy requirements of systolic and diastolic pressure), determine the final normal fluctuation range of blood pressure (the normal fluctuation range of blood pressure values ​​within a certain range determined according to the user registration information and medical standards).

[0026] Step S430, based on the initial resolution, sets the target resolution according to the upper and lower limits corresponding to the normal fluctuation range that meets the blood pressure accuracy requirements. Specifically, the upper and lower limits of the blood pressure measurement are determined according to the normal fluctuation range determined in step S420. According to the initial resolution and accuracy requirements of the target electronic sphygmomanometer, the target resolution that can accurately reflect the fluctuation of the blood pressure value is calculated, that is, the accuracy requirement required by the target electronic sphygmomanometer when measuring blood pressure, that is, the minimum change in the blood pressure value that can be accurately distinguished. The calculated target resolution is applied to the target electronic sphygmomanometer to ensure the accuracy and precision of the measurement. This implementation method generates a target resolution for blood pressure measurement in a personalized manner based on the user's age, gender, height, weight and other information and the accuracy requirements of the target electronic sphygmomanometer, thereby improving the measurement accuracy and user experience of the target electronic sphygmomanometer and enhancing the applicability of the target electronic sphygmomanometer to different users.

[0027] In a possible implementation, the target resolution includes a systolic pressure resolution and a diastolic pressure resolution, and step S430 further includes step S431, configuring a first systolic pressure threshold and a first diastolic pressure threshold according to the pressure sensor of the target electronic blood pressure meter and in combination with the upper limit corresponding to the normal fluctuation range. Specifically, the upper limits of systolic pressure and diastolic pressure are extracted from the normal fluctuation range of the user's blood pressure determined in step S420. Using the pressure sensor characteristics of the target electronic blood pressure meter, these upper limits are converted into thresholds that can be recognized by the pressure sensor, namely, the first systolic pressure threshold and the first diastolic pressure threshold. These thresholds are the basis for the target electronic blood pressure meter to determine whether the blood pressure exceeds the normal upper limit during the monitoring process.

[0028] Step S432, according to the pressure sensor of the target electronic blood pressure meter, in combination with the lower limit corresponding to the normal fluctuation range, configure the second systolic pressure threshold and the second diastolic pressure threshold. Specifically, the lower limit values ​​of systolic pressure and diastolic pressure are also extracted from the normal fluctuation range of the user's blood pressure determined in step S420. Using the pressure sensor characteristics of the target electronic blood pressure meter, these lower limit values ​​are converted into thresholds that can be recognized by the pressure sensor, namely the second systolic pressure threshold and the second diastolic pressure threshold. These thresholds are the basis for the target electronic blood pressure meter to determine whether the blood pressure is lower than the normal lower limit during the monitoring process.

[0029] Step S433, based on the initial resolution, combined with the first systolic pressure threshold, the second systolic pressure threshold and the blood pressure accuracy requirement, the systolic pressure resolution in the target resolution is set. Specifically, according to the blood pressure accuracy requirement, the accuracy requirement of the systolic pressure measurement is analyzed. In combination with the initial resolution, the first systolic pressure threshold and the second systolic pressure threshold, as well as the accuracy requirement of the systolic pressure measurement, the systolic pressure resolution that can meet these conditions is calculated (the minimum change that the target electronic blood pressure monitor can identify when measuring systolic pressure). The calculated systolic pressure resolution is set as a part of the target resolution for subsequent blood pressure monitoring and abnormal warning.

[0030] Step S434, based on the initial resolution, combined with the first diastolic pressure threshold, the second diastolic pressure threshold and the blood pressure accuracy requirement, the diastolic pressure resolution in the target resolution is set. Specifically, the accuracy requirement of the diastolic pressure measurement is also analyzed according to the blood pressure accuracy requirement. Combined with the initial resolution, the first diastolic pressure threshold and the second diastolic pressure threshold, and the accuracy requirement of the diastolic pressure measurement, the diastolic pressure resolution that can meet these conditions is calculated (the minimum change that the target electronic blood pressure meter can identify when measuring the diastolic pressure). The calculated diastolic pressure resolution is set as another part of the target resolution for subsequent blood pressure monitoring and abnormal warning. This implementation method ensures the accuracy of blood pressure measurement and reduces the possibility of false alarms and missed alarms by configuring the threshold according to the normal fluctuation range of the user's blood pressure and setting the resolution in combination with the accuracy requirement of the target electronic blood pressure meter.

[0031] In a possible implementation, based on the initial resolution, combined with the first systolic pressure threshold, the second systolic pressure threshold and the blood pressure accuracy requirement, the systolic pressure resolution in the target resolution is set, and step S433 further includes step S4331, introducing user multidimensional information, using a multi-level linked list architecture for data association index organization, and setting a data mining mechanism, which is used to optimize search efficiency. Specifically, the user multidimensional information is collected, that is, in addition to the basic user registration information (such as age, gender, height, weight), it also includes the user's historical blood pressure data, living habits, family history and other multidimensional information, which is crucial for more accurate assessment of the user's blood pressure status. In order to efficiently manage and retrieve this multidimensional information, a multi-level linked list architecture is used for data association index organization, and each level of the linked list represents a different information dimension, such as age, gender, historical blood pressure data, etc. Through the association between the linked list nodes, specific user information can be quickly located. After constructing the data association index, a data mining mechanism is set up to mine and analyze the user's multi-dimensional information to discover the patterns and trends related to blood pressure changes, including the use of machine learning algorithms for pattern recognition, cluster analysis, prediction, etc., to optimize search efficiency and provide personalized blood pressure management recommendations.

[0032] Step S4332, based on the data mining mechanism, formulate resolution adjustment rules, and define loose resolution solution space and contracted resolution solution space. Specifically, the user's blood pressure data pattern, trend and other information obtained by the data mining mechanism are used to analyze the user's blood pressure change rules and characteristics. Based on the analysis results, formulate adjustment rules for systolic pressure resolution, including dynamically adjusting the resolution accuracy according to factors such as the severity and frequency of the user's blood pressure changes to ensure the accuracy and timeliness of the monitoring results. When formulating the resolution adjustment rules, define a loose resolution solution space for monitoring with a lower resolution when the user's blood pressure is relatively stable or changes little, so as to reduce the burden of data processing. At the same time, define a contracted resolution solution space for monitoring with a higher resolution when the user's blood pressure fluctuates greatly or is abnormal, so as to more accurately capture the details of the blood pressure changes. This implementation method dynamically adjusts the resolution accuracy according to the user's blood pressure change rules and characteristics by introducing multi-dimensional information of the user and data mining mechanism, thereby achieving the technical effect of reducing unnecessary data processing and resource consumption while ensuring the accuracy of the monitoring results.

[0033] In a possible implementation, step S4331 further includes step S43311, and the user multidimensional information includes the living habit information corresponding to the user's personal information, the family medical history information corresponding to the dietary habit information and the medical health indicators, and the historical medical information. Specifically, through questionnaires or user-input, the user's daily activity habits (such as exercise, sleep conditions), dietary preferences (such as salt intake, frequency of high-fat food intake) and other information are collected, and this information is used to analyze the user's lifestyle and its impact on blood pressure. Ask the user whether there is a history of blood pressure-related diseases in the family, and whether the user has suffered from blood pressure-related diseases or received related treatments in the past. This information is used to assess the user's genetic risk and current health status. The above collected information is integrated to form a multidimensional information database of the user, which is the basis for subsequent data mining and analysis.

[0034] Step S43312, construct multiple skip lists according to the user's multi-dimensional information, wherein each skip list node contains any type of information, and connects nodes of different levels through pointers to form the multi-level linked list architecture. Specifically, the skip list is a data structure that allows fast search, insertion and deletion operations. It stores data in a multi-layer linked list and uses pointers to jump between different layers to achieve efficient search. When constructing the multi-level linked list architecture, a skip list is used as the basic structure. Each skip list node (basic element in the skip list) contains a type of information (such as living habits, eating habits, etc.), and connects nodes of different levels through pointers, which form the basis of the multi-level linked list architecture. The skip list nodes of different levels are connected through pointers to form a multi-level linked list architecture, which allows efficient search and indexing according to the user's multi-dimensional information. Using the multi-level linked list architecture, relevant data records can be quickly located according to the user's multi-dimensional information. By optimizing the search algorithm, the search efficiency can be further improved to achieve fast data mining and analysis. This implementation method fully utilizes the user's multi-dimensional information by introducing information such as the user's living habits, eating habits, family medical history and historical medical information, which helps to more accurately assess the user's blood pressure condition, thereby improving the accuracy of resolution adjustment and achieving more efficient monitoring and analysis.

[0035] In a possible implementation, step S4332 further includes step S43321, setting a loose matching strategy based on the user multidimensional information, wherein the loose matching strategy includes a first deviation threshold. Specifically, the collected user multidimensional information is analyzed to determine which information is directly related to blood pressure changes and the strength of the correlation of this information. Based on the information correlation analysis results, a loose matching strategy (a strategy used in the data mining process that allows data points to deviate from the normal fluctuation range within a certain range, thereby increasing the inclusiveness and diversity of the data) is set. This strategy includes a first deviation threshold (a threshold used to measure the degree of deviation between a data point and the normal fluctuation range), which is used to determine which data points can be considered to meet the loose matching conditions in the data mining process.

[0036] Step S43322, according to the loose matching strategy, data mining is performed with the first deviation threshold as a constraint condition, and a loose resolution solution space that meets the first data density is set. Specifically, the data mining mechanism is started to mine and analyze the collected multidimensional information of the user. According to the first deviation threshold set in the loose matching strategy, the data mining results are screened and matched, and the data points that meet the loose matching conditions are taken into consideration. The density of the data points taken into consideration is calculated, and the data density reflects the closeness or distribution between the data points. Based on the calculation result of the data density, a loose resolution solution space that meets the first data density (that is, the data density is small, indicating that the data points are more loosely distributed) is set. This solution space is used to adjust the resolution of systolic and diastolic pressure in subsequent steps to adapt to the blood pressure change characteristics of different users. This implementation method can personalize the systolic pressure resolution according to the health status and living habits of different users by setting a loose matching strategy, thereby improving the accuracy and pertinence of blood pressure monitoring.

[0037] In a possible implementation, step S4332 further includes step S43323, setting a contraction-type matching strategy based on the user multi-dimensional information, wherein the contraction-type matching strategy includes a second deviation threshold, and the first deviation threshold is greater than the second deviation threshold. Specifically, based on the user multi-dimensional information, a more stringent deviation threshold, namely the second deviation threshold, is set for the contraction-type matching strategy (a more stringent matching strategy used to screen data points that are closer to the normal fluctuation range during the data mining process to construct a contraction resolution solution space). This threshold is smaller than the first deviation threshold in the loose matching strategy, that is, it requires a higher degree of deviation of the data points. The second deviation threshold is used as the core parameter of the contraction-type matching strategy, and the relevant data mining parameters and algorithms are configured to support subsequent data mining work.

[0038] Step S43324, according to the contraction matching strategy, data mining is performed with the second deviation threshold as a constraint condition, and a contraction resolution solution space that meets the second data density is set, and the first data density is less than the second data density. Specifically, the data mining mechanism is started, and the multi-dimensional information of the user is mined and analyzed according to the second deviation threshold in the contraction matching strategy. In the data mining process, data points that are closer to the normal fluctuation range are screened out, that is, data points whose deviation is less than the second deviation threshold. Density calculation is performed on the screened data points to obtain the second data density. Since the contraction matching strategy is more stringent, the number of screened data points is small and the data density is high (that is, the data points are closer together). Based on the calculated second data density, a contraction resolution solution space that meets the contraction matching strategy is set. This solution space is used to adjust the resolution of systolic and diastolic pressure in subsequent steps to meet more stringent matching requirements. The above implementation method constructs a loose resolution solution space and a contraction resolution solution space respectively by setting two matching strategies, loose and contraction. The two solution spaces can complement each other to provide more comprehensive data support for blood pressure monitoring, thereby improving the accuracy and precision of blood pressure monitoring.

[0039] In a possible implementation, step S400 further includes step S440, marking a sensitive group based on the user's medical history, where the sensitive group is a user group that has undergone drug intervention. Specifically, the user's medical history data, including past medical history, drug use, surgical records, etc., is obtained from the user registration information or medical record system. The medical history data is analyzed to identify users who are undergoing drug intervention, whose blood pressure may show specific fluctuation patterns or abnormal reactions due to the influence of the drugs. The identified users who are undergoing drug intervention are marked as sensitive groups and recorded in the system for subsequent risk assessment and early warning processing.

[0040] Step S450, divide the risk level by the sensitive group and the remaining user group, and establish a risk assessment model. Specifically, the blood pressure data, living habits, family medical history and other information of the sensitive group and the remaining user group (i.e., the non-sensitive group) are comprehensively analyzed. According to the analysis results, a set of risk level classification standards are formulated, which include multiple dimensions such as the stability of blood pressure values, fluctuation range, user age, health status, etc. According to the classification standards, the sensitive group and the remaining user group are divided into different risk levels, such as low risk, medium risk, high risk, etc. Using machine learning or statistical analysis methods, combined with the blood pressure data of the user group, the risk level classification results and other information, a risk assessment model is constructed. This model can predict the user's risk level based on the user's blood pressure data and other relevant information.

[0041] Step S460, based on the risk assessment model, obtain the risk assessment level, and the risk assessment level is associated and bound one by one with the blood pressure accuracy requirement. Specifically, the target user's blood pressure data, living habits, family medical history and other information are input into the risk assessment model. The risk assessment model calculates the user's risk level based on the input user data and outputs the level. The risk assessment level is associated and bound with the blood pressure accuracy requirement, that is, users with different risk levels require different blood pressure accuracy requirements to ensure the accuracy and effectiveness of blood pressure monitoring. This implementation method can provide users with different risk levels with more accurate monitoring solutions by associating and binding the risk assessment level with the blood pressure accuracy requirement, thereby ensuring the accuracy and effectiveness of blood pressure monitoring.

[0042] Step S500, after the monitoring preparation conditions are met, an abnormal warning mechanism is set based on the basic model parameters, the deflation control starting point and the deflation control end point, combined with the target resolution. Specifically, confirm that all monitoring preparation conditions have been met, including cuff wearing, user status, etc. According to the basic model parameters, deflation control nodes and target resolution of the equipment, a set of abnormal warning rules are set, including abnormal pressure changes during measurement, measurement time is too long or too short, and measurement results are outside the normal range. When an abnormal situation occurs, a warning signal (such as sound, light, screen prompt, etc.) is issued so that users or medical staff can take timely measures. The embodiment of the present application obtains the basic model parameters of the target electronic blood pressure monitor and uses the built-in microprocessor to configure the internal self-check rules. After receiving the blood pressure monitoring request, the internal self-check rules are activated, and the inflation and deflation control nodes are marked according to the inflation pump and the exhaust valve. The initial resolution is determined according to the pressure sensor of the target electronic blood pressure monitor, and the target resolution is set in combination with the user's blood pressure accuracy requirements. After the monitoring preparation conditions are met, technical means such as setting the abnormal warning mechanism based on the basic model parameters, deflation control nodes and target resolution are used to achieve the technical effect of improving the accuracy and applicability of blood pressure monitoring, thereby enhancing the abnormal warning capability of the equipment.

[0043] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A blood pressure monitor monitoring abnormality early warning method, characterized in that: The method comprises: Obtaining basic model parameters of a target electronic blood pressure meter, and configuring internal self-checking rules using a microprocessor built into the target electronic blood pressure meter; After receiving the blood pressure monitoring request, the internal self-check rule is activated. If the internal self-check passes, the inflation and deflation control nodes are marked according to the inflation pump and the exhaust valve of the target electronic blood pressure monitor. The inflation and deflation control nodes include an inflation control starting point and an inflation control end point, and a deflation control starting point and a deflation control end point. Introducing a monitoring preparation condition, wherein the monitoring preparation condition satisfies a pressure safety constraint, wherein the pressure safety constraint is used to combine the inflation control starting point and the inflation control end point so that the cuff uniformly applies compression force to the user's blood vessels; Determine the initial resolution according to the pressure sensor of the target electronic blood pressure meter, and set the target resolution in combination with the blood pressure accuracy requirement, wherein the target resolution is not lower than the standard resolution, and the target resolution includes the systolic pressure resolution and the diastolic pressure resolution; After the monitoring preparation conditions are met, an abnormal warning mechanism is set based on the basic model parameters, the deflation control starting point and the deflation control end point, combined with the target resolution.

2. A blood pressure monitor abnormality early warning method as claimed in claim 1, characterized in that: According to the pressure sensor of the target electronic blood pressure meter, an initial resolution is determined, and in combination with the blood pressure accuracy requirement, a target resolution is set. The method includes: Based on the target electronic blood pressure monitor, determining user registration information, the user registration information including user age, user gender, user height, and user weight; Determining a normal fluctuation range that meets the blood pressure accuracy requirement through the user registration information; Based on the initial resolution, the target resolution is set according to the upper and lower limits corresponding to the normal fluctuation range that meets the blood pressure accuracy requirement.

3. A blood pressure monitor abnormality early warning method as claimed in claim 2, characterized in that: The target resolution includes a systolic pressure resolution and a diastolic pressure resolution, and the method includes: According to the pressure sensor of the target electronic blood pressure meter, in combination with the upper limit corresponding to the normal fluctuation range, a first systolic pressure threshold and a first diastolic pressure threshold are configured; According to the pressure sensor of the target electronic blood pressure meter, in combination with the lower limit corresponding to the normal fluctuation range, a second systolic pressure threshold and a second diastolic pressure threshold are configured; Based on the initial resolution, in combination with the first systolic pressure threshold, the second systolic pressure threshold and the blood pressure accuracy requirement, setting the systolic pressure resolution in the target resolution; Based on the initial resolution, in combination with the first diastolic pressure threshold, the second diastolic pressure threshold and the blood pressure accuracy requirement, the diastolic pressure resolution in the target resolution is set.

4. A blood pressure monitor abnormality early warning method as claimed in claim 3, characterized in that: Based on the initial resolution, in combination with the first systolic pressure threshold, the second systolic pressure threshold and the blood pressure accuracy requirement, the systolic pressure resolution in the target resolution is set, the method comprising: Introducing user multi-dimensional information, using a multi-level linked list architecture to organize data association indexes, and setting up a data mining mechanism, which is used to optimize search efficiency; Based on the data mining mechanism, a resolution adjustment rule is formulated, and a loose resolution solution space and a contracted resolution solution space are defined.

5. A blood pressure monitor monitoring abnormality early warning method as claimed in claim 4, characterized in that: The user multi-dimensional information includes the user's personal information corresponding to the living habits information, eating habits information and medical health indicators corresponding to the family history information, historical medical information; According to the user multi-dimensional information, a plurality of skip lists are constructed, wherein each skip list node contains any type of information, and nodes at different levels are connected through pointers to form the multi-level linked list architecture.

6. A blood pressure monitor abnormality early warning method as claimed in claim 5, characterized in that: Based on the multi-dimensional information of the user, a loose matching strategy is set, wherein the loose matching strategy includes a first deviation threshold; According to the loose matching strategy, data mining is performed with the first deviation threshold as a constraint condition, and a loose resolution solution space that meets the first data density is set.

7. A blood pressure monitor abnormality early warning method as claimed in claim 6, characterized in that: Based on the multi-dimensional information of the user, a contraction-type matching strategy is set, wherein the contraction-type matching strategy includes a second deviation threshold, and the first deviation threshold is greater than the second deviation threshold; According to the shrinkage matching strategy, data mining is performed with the second deviation threshold as a constraint condition, and a shrinkage resolution solution space that meets the second data density is set, and the first data density is less than the second data density.

8. The method for early warning of abnormal monitoring of a blood pressure monitor as claimed in claim 3, characterized in that: The method comprises: Based on the user's medical history, a sensitive group is marked, where the sensitive group is a user group for drug intervention; Based on the sensitive groups and the remaining user groups, risk levels are divided and a risk assessment model is established; Based on the risk assessment model, a risk assessment level is obtained, and the risk assessment level is associated and bound with the blood pressure accuracy requirement one by one.

Images