Gynecological nursing monitoring and early warning system based on artificial intelligence

Abstract

The invention relates to the technical field of risk monitoring and early warning, in particular to a gynecological nursing monitoring and early warning system based on artificial intelligence, which is provided with a data acquisition module, a feature analysis module, a feature recognition module, a feature verification module and a monitoring and early warning module. Physiological parameters and motion parameters of a person to be monitored are acquired through the data acquisition module, motion tendency parameters are determined through the feature analysis module, feature monitoring time periods are screened, and motion amount fluctuation parameters are determined through the feature recognition module, so that whether the person to be monitored has the risk that the motion amount exceeds the standard or not is judged. The characteristic verification module determines the motion characteristic characterization parameters and constructs the motion characteristic fluctuation curve, and the monitoring early warning module determines the risk tendency parameters to determine whether to send the motion amount abnormal risk early warning, so that whether to send the motion amount abnormal risk early warning is judged according to the physiological parameters and motion conditions of the person to be monitored. And the efficiency and the reliability of the gynecological nursing monitoring and early warning system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of risk monitoring and early warning, and particularly relates to a gynecological nursing monitoring and early warning system based on artificial intelligence. BACKGROUND

[0002] In the rehabilitation process of gynecological postoperative patients such as hysterectomy, pelvic floor repair, and ovarian cyst removal, moderate exercise can help recovery. Early postoperative exercise can accelerate intestinal peristalsis, reduce the risk of intestinal adhesion, promote blood circulation, and enhance pelvic floor muscle tension. For example, after laparoscopic hysterectomy, postoperative moderate ambulation can shorten the time of exhaust and reduce complications such as abdominal distension. However, the exercise needs of such patients require special attention. Excessive exercise may cause wound traction, bleeding, and increased pain, and even delay healing. Therefore, during gynecological nursing, the physical condition of patients during exercise needs to be monitored and warned in a timely manner. Traditional nursing relies on manual recording, such as patient self-reported exercise and nurse regular measurement of heart rate, which cannot capture the dynamic correlation between physiological parameters and exercise behavior. Therefore, it is an urgent technical problem to timely monitor and warn the exercise risk of gynecological special groups and improve the efficiency and reliability of the gynecological nursing monitoring and early warning system.

[0003] For example, Chinese Patent No. CN117672532B discloses a hospitalized patient nursing risk assessment and early warning monitoring system and method, which relates to the field of risk assessment and early warning. It first acquires patient physiological sign text data, patient carbon dioxide partial pressure values at multiple predetermined time points collected by a monitoring device, and patient end-tidal carbon dioxide concentration values at multiple predetermined time points collected by a monitoring device. Then, using deep learning technology, it performs feature extraction and correlation analysis on the three. Finally, through a classifier, a classification result is obtained to generate a hospitalized patient respiratory failure risk assessment level, thereby realizing automatic assessment and early intervention.

[0004] The existing technology also has the following problems: The existing technology does not consider that patient self-reported exercise, nurse regular measurement of heart rate, and the like cannot capture the dynamic correlation between physiological parameters and exercise behavior, affecting the reliability of exercise monitoring. The existing technology cannot determine whether to send an exercise amount abnormal risk warning based on the physiological parameters and exercise of the monitored person, affecting the efficiency and reliability of the gynecological nursing monitoring and early warning system. SUMMARY

[0005] Therefore, the present application provides a gynecological nursing monitoring and early warning system based on artificial intelligence to overcome the problem that the existing technology cannot determine whether to send an exercise amount abnormal risk warning based on the physiological parameters and exercise of the monitored person, affecting the efficiency and reliability of the gynecological nursing monitoring and early warning system.

[0006] To achieve the above object, the present application provides a gynecological nursing monitoring and early warning system based on artificial intelligence, comprising: a data acquisition module configured to acquire physiological parameters and motion parameters of a subject to be monitored; a feature analysis module connected to the data acquisition module and configured to determine a motion tendency parameter based on the physiological parameters of the subject to be monitored within a preset monitoring period, and to screen a feature monitoring period based on the motion tendency parameter and the motion parameters; a feature recognition module connected to the data acquisition module and the feature analysis module, and configured to acquire the motion parameters of the subject to be monitored within the feature monitoring period, to determine a motion amount fluctuation parameter based on the comparison between the motion parameters within each feature monitoring period, and to determine whether the subject to be monitored has a risk of excessive motion amount; a feature verification module connected to the data acquisition module and the feature recognition module, and configured to determine a motion feature representation parameter based on the motion parameters and the physiological parameters of the feature monitoring period according to the determination result of the risk of excessive motion amount, and to construct a motion feature fluctuation curve based on the motion feature representation parameter; a monitoring and early warning module connected to the feature verification module and configured to determine a risk tendency parameter based on the motion risk fluctuation curve, and to determine whether to send an abnormal motion risk early warning.

[0007] Further, the feature analysis module is configured to determine a motion tendency parameter, wherein, the feature analysis module divides the preset monitoring period into a plurality of monitoring periods, and determines the difference between the maximum value and the minimum value of the physiological parameters within the period as the motion tendency parameter.

[0008] Further, the feature analysis module is configured to screen a feature monitoring period, wherein, the feature analysis module screens the monitoring period as a feature monitoring period based on the determination result that the motion tendency parameter and the motion parameter of the monitoring period meet the feature monitoring period condition; the feature monitoring period condition is that the motion tendency parameter exceeds a preset motion tendency parameter threshold value, and the motion parameter exceeds a preset motion parameter threshold value.

[0009] Further, the feature recognition module is configured to determine a motion amount fluctuation parameter, wherein, the feature recognition module acquires the motion data of adjacent feature monitoring periods in time sequence, and determines the difference between the motion data of the latter feature monitoring period and the motion data of the former feature monitoring period in the adjacent feature monitoring periods as a motion amplitude parameter; the average value of the motion amplitude parameter is determined as the motion amount fluctuation parameter.

[0010] Further, the feature identification module is configured to determine whether the to-be-monitored person has a risk of exceeding the exercise amount, wherein The feature identification module determines that the to-be-monitored person has a risk of exceeding the exercise amount based on a determination result that the exercise amount fluctuation parameter of the to-be-monitored person meets a risk exceeding condition. The risk exceeding condition is that the exercise amount fluctuation parameter exceeds a preset exercise amount fluctuation parameter threshold.

[0011] Further, the feature verification module is configured to determine the exercise feature representation parameter based on the exercise parameter and the physiological parameter of the feature monitoring period according to a determination result that the to-be-monitored person has a risk of exceeding the exercise amount.

[0012] Further, the feature verification module is configured to determine the exercise feature representation parameter, wherein The feature verification module obtains a ratio of the first exercise feature to the second exercise feature, and determines a ratio of the ratio to a resting physiological parameter threshold as the exercise feature representation parameter. The feature verification module obtains the average physiological parameter and the exercise amplitude parameter of the adjacent feature monitoring periods, and determines an absolute value of a difference between the average physiological parameters of the adjacent feature monitoring periods as the first exercise feature of a previous feature monitoring period in the adjacent feature monitoring periods. The feature verification module determines an absolute value of the exercise amplitude parameter of the adjacent feature monitoring periods as the second exercise feature of the previous feature monitoring period in the adjacent feature monitoring periods.

[0013] Further, the exercise feature fluctuation curve establishes a rectangular coordinate system with time as the horizontal axis and the numerical value of the exercise feature representation parameter as the vertical axis, and is fitted according to a plurality of exercise feature points, wherein the exercise feature points are determined according to the exercise feature representation parameter and a midpoint time of the feature monitoring period in which the exercise feature representation parameter is located.

[0014] Further, the monitoring and warning module is configured to determine the risk tendency parameter, wherein The monitoring and warning module calculates a difference value of the slopes at the adjacent exercise feature points, and determines an average value of the difference value as the risk tendency parameter.

[0015] Further, the monitoring and warning module is configured to determine whether to send an exercise amount abnormal risk warning, wherein The monitoring and warning module determines to send the exercise amount abnormal risk warning based on a determination result that the risk tendency parameter of the to-be-monitored person meets a risk warning condition. The risk warning condition is that the risk tendency parameter exceeds a preset risk tendency parameter threshold.

[0016] Compared with the prior art, the present application has the beneficial effects that the present application is provided with a data acquisition module, a feature analysis module, a feature recognition module, a feature verification module, and a monitoring and early warning module, the physiological parameters and the motion parameters of the to-be-monitored person are acquired through the data acquisition module, the motion tendency parameters are determined through the feature analysis module, the feature monitoring period is screened, the motion amount fluctuation parameters are determined through the feature recognition module to determine whether the to-be-monitored person has a motion amount exceeding the standard risk, the motion feature representation parameters are determined through the feature verification module to construct the motion feature fluctuation curve, the risk tendency parameters are determined through the monitoring and early warning module to determine whether to send a motion amount abnormal risk early warning, and then, it is determined whether to send a motion amount abnormal risk early warning according to the physiological parameters and the motion condition of the to-be-monitored person, and the efficiency and reliability of the gynecological nursing monitoring and early warning system are improved.

[0017] Especially, the feature analysis module screens the feature monitoring period based on the motion tendency parameters and the motion parameters, which can be understood as accurately locking the period in which the motion actually affects the physiology, avoiding invalid monitoring, focusing the subsequent risk analysis on the truly meaningful motion period, improving the monitoring efficiency, the motion tendency parameters are based on the individual physiological parameter difference value, automatically adapt to the basic state of different patients, such as the heart rate fluctuation threshold of young patients can be slightly wide, and the threshold of elderly patients is more strict, avoiding the one-size-fits-all leading to missed or misjudgment, providing a high-quality data basis for subsequent risk analysis, the risk parameters determined based on the feature monitoring period data, such as the motion feature representation parameters, can better reflect the actual impact of the motion on the body, laying a foundation for accurate early warning, the present application screens the feature monitoring period based on the physiological parameters and the motion condition of the to-be-monitored person through the feature analysis module, and the efficiency and reliability of the gynecological nursing monitoring and early warning system are improved.

[0018] Especially, the application determines the motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period through the feature recognition module to determine whether the monitored person has the risk of excessive motion amount, and it can be understood that the key period is focused on, the motion parameters of the monitored person are obtained in the feature monitoring period, invalid data interference is avoided, the fluctuation stability is taken as the core, the gynecological postoperative recovery demand is matched, the gynecological postoperative patient performs appropriate motion to help recovery, and the sudden motion amount surge is more likely to cause wound traction, bleeding and other risks. By calculating the fluctuation amplitude of adjacent periods, the sudden change risk can be directly captured, which is more suitable for clinical needs than simply looking at whether the single motion amount is excessive, the early warning timeliness and effectiveness are improved, and the potential risk trend is identified in advance instead of only aiming at the occurred excessive, even if the single motion amount is not excessive, but the fluctuation parameter is excessive, which can prompt the risk of abnormal motion rhythm, and early warning is performed to gain time for intervention. The application determines the motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period through the feature recognition module to determine whether the monitored person has the risk of excessive motion amount, and further, the efficiency and reliability of the gynecological nursing monitoring and early warning system are improved according to the physiological parameters and motion conditions of the monitored person to determine whether there is the risk of excessive motion amount.

[0019] Especially, the application determines the motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period through the feature recognition module to determine whether the monitored person has the risk of excessive motion amount, and it can be understood that the key period is focused on, the motion parameters of the monitored person are obtained in the feature monitoring period, invalid data interference is avoided, the fluctuation stability is taken as the core, the gynecological postoperative recovery demand is matched, the gynecological postoperative patient performs appropriate motion to help recovery, and the sudden motion amount surge is more likely to cause wound traction, bleeding and other risks. By calculating the fluctuation amplitude of adjacent periods, the sudden change risk can be directly captured, which is more suitable for clinical needs than simply looking at whether the single motion amount is excessive, the early warning timeliness and effectiveness are improved, and the potential risk trend is identified in advance instead of only aiming at the occurred excessive, even if the single motion amount is not excessive, but the fluctuation parameter is excessive, which can prompt the risk of abnormal motion rhythm, and early warning is performed to gain time for intervention. The application determines the motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period through the feature recognition module to determine whether the monitored person has the risk of excessive motion amount, and further, the efficiency and reliability of the gynecological nursing monitoring and early warning system are improved according to the physiological parameters and motion conditions of the monitored person to determine whether there is the risk of excessive motion amount. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1A function block diagram of the gynecological nursing monitoring and early warning system based on artificial intelligence according to the embodiment of the present application; Figure 2 A logic flow chart for the feature analysis module to screen the feature monitoring period according to the embodiment of the present application; Figure 3 A logic flow chart for the feature recognition module to determine whether the monitored person has a risk of excessive exercise according to the embodiment of the present application; Figure 4 A logic flow chart for the monitoring and early warning module to determine whether to send an exercise abnormal risk early warning according to the embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the objects and advantages of the present application clearer, the present application will be further described below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0022] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present application and are not used to limit the protection scope of the present application.

[0023] It should be noted that in the description of the present application, the terms indicating the direction or positional relationship such as "upper", "lower", "inner", "outer" and the like are based on the direction or positional relationship shown in the drawings, which is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0024] In addition, it should also be noted that in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be direct connection, or indirect connection through an intermediate medium, or internal communication of two elements. Those skilled in the art can understand the specific meaning of the above terms in the present application according to the specific circumstances.

[0025] Please refer to Figure 1 shown, which is a function block diagram of the gynecological nursing monitoring and early warning system based on artificial intelligence according to the embodiment of the present application, the gynecological nursing monitoring and early warning system based on artificial intelligence according to the present application comprises: The data acquisition module is used to acquire the physiological parameters and exercise parameters of the monitored person; Specifically, the specific structure of the data acquisition module is not limited in the embodiment of the application, preferably, it can be a wrist optical heart rate sensor and a three-axis acceleration sensor, integrated in a medical-grade smart bracelet, irradiating the wrist skin through a green LED light source, capturing the change of blood light transmittance when the blood vessels pulsate to output the heart rate data in real time, identifying the gait characteristics by combining the algorithm with the acceleration change when the human body moves, and counting the steps in real time, so as to obtain the physiological parameters and the motion parameters of the to-be-monitored person, wherein the physiological parameter is the heart rate, and the motion parameter is the step count, which will not be repeated here.

[0026] The feature analysis module is connected with the data acquisition module, and is used to determine a motion tendency parameter according to the physiological parameters of the to-be-monitored person in a preset monitoring period, and screen a feature monitoring period based on the motion tendency parameter and the motion parameter. Specifically, the preset monitoring period can be set by a person skilled in the art according to the accuracy requirement of the gynecological nursing monitoring and early warning system, the higher the accuracy requirement is, the shorter the preset monitoring period is, and the preset monitoring period can be [12, 24] h, preferably, the preset monitoring period can be 20 h.

[0027] Specifically, the specific structure of the feature analysis module is not limited in the embodiment of the application, preferably, it can be a microprocessor, used to determine the motion tendency parameter and screen the feature monitoring period, which will not be repeated here.

[0028] The feature recognition module is connected with the data acquisition module and the feature analysis module respectively, and is used to obtain the motion parameters of the to-be-monitored person in the feature monitoring period, determine a motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period, and determine whether the to-be-monitored person has a motion amount exceeding standard risk. Specifically, the specific structure of the feature recognition module is not limited in the embodiment of the application, preferably, it can be a processor used in a computer, used to determine the motion amount fluctuation parameter and determine whether the to-be-monitored person has the motion amount exceeding standard risk, which will not be repeated here.

[0029] The feature verification module is connected with the data acquisition module and the feature recognition module respectively, and is used to determine a motion feature representation parameter according to the motion parameters and the physiological parameters of the feature monitoring period according to the determination result of the motion amount exceeding standard risk, and construct a motion feature fluctuation curve based on the motion feature representation parameter. Specifically, the specific structure of the feature verification module is not limited in the embodiment of the application, preferably, it can be a microprocessor, used to determine the motion feature representation parameter and construct the motion feature fluctuation curve, which will not be repeated here.

[0030] A monitoring and early warning module is connected with the feature verification module, and is configured to determine a risk tendency parameter based on the motion risk fluctuation curve, so as to determine whether to send a motion abnormal risk early warning.

[0031] Specifically, the monitoring and early warning module is preferably a processor used in a computer, which is configured to determine the risk tendency parameter and determine whether to send the motion abnormal risk early warning, and details are not described herein.

[0032] Specifically, the feature analysis module is configured to determine a motion tendency parameter, wherein, The feature analysis module divides the preset monitoring period into a plurality of monitoring time periods, and determines a difference between a maximum value of the physiological parameter and a minimum value of the physiological parameter in the time period as the motion tendency parameter.

[0033] Specifically, the duration of the monitoring time period is a product of the duration of the preset monitoring period and a division factor, the division factor can be set by a person skilled in the art according to the accuracy requirement of the gynecological nursing monitoring and early warning system, the higher the accuracy requirement, the smaller the division factor, and the value range of the division factor can be [0.1, 0.3], and preferably, the division factor can be 0.2.

[0034] Referring to Figure 2 The feature analysis module is configured to screen the feature monitoring time period, wherein, The feature analysis module screens the monitoring time period as the feature monitoring time period based on the determination result that the motion tendency parameter and the motion parameter of the monitoring time period meet the feature monitoring time period condition; If the motion tendency parameter and the motion parameter of the monitoring time period do not meet the feature monitoring time period condition, the feature analysis module does not screen the monitoring time period; The feature monitoring time period condition is that the motion tendency parameter exceeds a preset motion tendency parameter threshold value, and the motion parameter exceeds a preset motion parameter threshold value.

[0035] Specifically, the preset motion tendency parameter threshold is a product of a motion tendency parameter reference value and a motion tendency factor, and the preset motion parameter threshold is a product of a motion parameter reference value and a motion parameter factor, the motion parameter reference value is an average value of motion parameters of the to-be-monitored person in the historical data in the same physical condition, the motion tendency parameter reference value is an average value of motion tendency parameters of the to-be-monitored person in the historical data in the same physical condition, the motion tendency factor and the motion parameter factor can be set by a person skilled in the art according to the accuracy requirement of the gynecological nursing monitoring and early warning system, the higher the accuracy requirement, the smaller the motion tendency factor and the motion parameter factor, the value range of the motion tendency factor can be [1.15, 1.35], preferably, 1.25, and the value range of the motion parameter factor can be [1.1, 1.3], preferably, 1.2.

[0036] Specifically, the embodiment of the present application filters the feature monitoring period based on the motion tendency parameter and the motion parameter through the feature analysis module. It can be understood that the period in which motion actually affects physiology is accurately locked, invalid monitoring is avoided, the subsequent risk analysis is focused on the truly meaningful motion period, the monitoring efficiency is improved, the motion tendency parameter is automatically adapted to the basic state of different patients based on the individual physiological parameter difference, for example, the heart rate fluctuation threshold of a young patient can be slightly wide, and the threshold of an elderly patient is more stringent, avoiding missed or misjudgment caused by one-size-fits-all, and providing a high-quality data basis for subsequent risk analysis, the risk parameter determined based on the feature monitoring period data, such as the motion feature representation parameter, can better reflect the actual impact of motion on the body, and lay a foundation for accurate early warning. The embodiment of the present application filters the feature monitoring period based on the motion tendency parameter and the motion parameter through the feature analysis module, and then realizes filtering the feature monitoring period according to the physiological parameters and motion of the to-be-monitored person, improving the efficiency and reliability of the gynecological nursing monitoring and early warning system.

[0037] Specifically, it can be understood that the motion tendency parameter, i.e., the heart rate difference, can reflect the effectiveness of exercise load. When exercising, the oxygen consumption of muscles increases, and the heart needs to increase the heart rate to meet the blood supply demand. The higher the exercise intensity and the more stable the duration, the greater the fluctuation amplitude of the heart rate from the resting state to the exercise state, and the more significant the difference between the maximum value and the minimum value. By the motion parameter, it is ensured that the motion is the cause of the change in heart rate. If the step frequency does not meet the standard, even if the heart rate difference is large, it may be caused by emotional fluctuations and has nothing to do with exercise, and does not need to be selected as a motion-related feature period. When the step frequency meets the standard, the increase in the heart rate difference is more likely to be a causal result of increased oxygen consumption caused by exercise, which in turn causes the heart rate to adjust. Therefore, it realizes filtering the feature monitoring period according to the physiological parameters and motion of the to-be-monitored person, improving the efficiency and reliability of the gynecological nursing monitoring and early warning system.

[0038] Specifically, the feature recognition module is configured to determine a motion amount fluctuation parameter, wherein, The feature recognition module acquires motion data of adjacent feature monitoring time periods in time sequence, and determines a difference between motion data of a later feature monitoring time period and motion data of an earlier feature monitoring time period in the adjacent feature monitoring time periods as a motion amplitude parameter. An average value of the motion amplitude parameter is determined as the motion amount fluctuation parameter.

[0039] Referring to Figure 3 The feature recognition module determines whether the to-be-monitored person has a motion amount exceeding risk, wherein, The feature recognition module determines that the to-be-monitored person has a motion amount exceeding risk based on a determination result that the motion amount fluctuation parameter of the to-be-monitored person meets an exceeding risk condition. If the motion amount fluctuation parameter of the to-be-monitored person does not meet the exceeding risk condition, the feature recognition module determines that the to-be-monitored person does not have a motion amount exceeding risk. The exceeding risk condition is that the motion amount fluctuation parameter exceeds a preset motion amount fluctuation parameter threshold.

[0040] Specifically, the preset motion amount fluctuation parameter threshold is a product of a motion amount fluctuation parameter reference value and a motion amount fluctuation factor. The motion amount fluctuation parameter reference value is an average value of motion amount fluctuation parameters of to-be-monitored persons with the same physical condition in historical data. The motion amount fluctuation factor can be set by a person skilled in the art according to the accuracy requirement of the gynecological nursing monitoring and early warning system. The higher the accuracy requirement, the smaller the motion amount fluctuation factor. The value range can be [1.15, 1.4], and preferably, the value can be 1.2.

[0041] Specifically, the embodiment of the present application determines the motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period through the feature recognition module to determine whether the motion amount of the monitored person exceeds the standard, and it can be understood that the key period is focused on, the motion parameters of the monitored person are obtained in the feature monitoring period, invalid data interference is avoided, the fluctuation stability is taken as the core, and the gynecological postoperative recovery demand is met. When the gynecological postoperative patient performs appropriate motion to help recovery, sudden motion amount surge is more likely to cause wound traction, bleeding and other risks. By calculating the fluctuation amplitude of adjacent periods, the sudden change risk can be directly captured, which is more in line with clinical needs than simply looking at whether the single motion amount exceeds the standard. The early warning timeliness and effectiveness are improved, and the potential risk trend is identified in advance rather than only for the occurred exceeding. Even if the single motion amount does not exceed, but the fluctuation parameter exceeds, it can prompt the risk of abnormal motion rhythm, and early warning is performed to gain time for intervention. The embodiment of the present application determines the motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period through the feature recognition module to determine whether the motion amount of the monitored person exceeds the standard, and further, the efficiency and reliability of the gynecological nursing monitoring and early warning system are improved.

[0042] Specifically, it can be understood that in the preset monitoring period, the motion of the monitored person should tend to be stable or slightly increase, so as to avoid the risk of sudden motion amount surge causing wound traction, bleeding and other risks affecting recovery. By quantifying the motion amount change amplitude of the feature monitoring period, it is determined whether the monitored person has the exceeding risk caused by abnormal fluctuation of motion intensity. The motion amplitude parameter is the motion data difference value of adjacent periods, which represents the motion amount change of two motion periods. The average value of the motion amplitude parameters of multiple adjacent periods is obtained to obtain the motion amount fluctuation parameter, which eliminates the interference of single accidental fluctuation and reflects the stability of overall motion intensity. The larger the motion amount fluctuation parameter is, the more unstable the motion is, the larger the motion amount increase is, and the more likely the motion amount exceeds the standard. Further, the efficiency and reliability of the gynecological nursing monitoring and early warning system are improved.

[0043] Specifically, the feature verification module determines the motion feature representation parameter according to the motion parameters and physiological parameters of the feature monitoring period based on the determination result that the monitored person has the motion amount exceeding risk. If the monitored person does not have the motion amount exceeding risk, the motion feature representation parameter is not determined.

[0044] Specifically, the feature verification module is used to determine the motion feature representation parameter, wherein, The feature verification module obtains a ratio of the first motion feature and the second motion feature, and determines a ratio of the ratio and a resting physiological parameter threshold as the motion feature representation parameter; The feature verification module obtains an average physiological parameter and a motion amplitude parameter of adjacent feature monitoring time periods, and determines an absolute value of a difference of the average physiological parameter of the adjacent feature monitoring time periods as the first motion feature of a previous feature monitoring time period in the adjacent feature monitoring time periods. The feature verification module obtains an average physiological parameter and a motion amplitude parameter of adjacent feature monitoring time periods, and determines an absolute value of a difference of the average physiological parameter of the adjacent feature monitoring time periods as the first motion feature of a previous feature monitoring time period in the adjacent feature monitoring time periods.

[0045] Specifically, the resting physiological parameter threshold is a resting heart rate of the current to-be-monitored person, which is obtained through historical monitoring data.

[0046] Specifically, it can be understood that the first motion feature is an absolute value of a difference of the average physiological parameter of the adjacent feature monitoring time periods, the heart rate is a direct response of the body to the motion, and can represent the actual influence degree of the motion on the body, the second motion feature is an absolute value of a change of the motion amplitude of the adjacent feature monitoring time periods, and can represent the stimulation intensity of the motion on the body, the ratio of the first motion feature and the second motion feature can represent the physiological response intensity caused by the motion, the larger the ratio, the greater the physiological fluctuation caused by the same motion amplitude change, which means that the body is less adapted to the current motion intensity, the smaller the ratio, the smaller the influence of the motion on the physiological state, and the better the adaptability of the body to the motion, and the resting physiological parameter threshold, i.e. the resting heart rate, is a baseline of the basic state of the individual body, and reflects the physiological normality of the to-be-monitored person, i.e. the gynecological postoperative patient, when not moving, the ratio of the first motion feature and the second motion feature is divided by the resting physiological parameter threshold, which anchors the correlation between the motion and the physiology to the individual basic state, not simply looking at the motion intensity or simply looking at the physiological change, but focusing on whether the actual influence of the motion on the body is within the individual's bearing range, and thus, the efficiency and reliability of the gynecological nursing monitoring and early warning system are improved.

[0047] Specifically, the motion feature fluctuation curve establishes a rectangular coordinate system with time as the horizontal axis and the value of the motion feature representation parameter as the vertical axis, and is fitted according to a plurality of motion feature points, which are determined according to the motion feature representation parameter and the midpoint time of the feature monitoring time period in which the motion feature representation parameter is located.

[0048] Specifically, the way of constructing the motion feature fluctuation curve is not limited, for example, the motion feature fluctuation curve can be fitted by using matlab related fitting software, which will not be described here.

[0049] Specifically, the monitoring and early warning module is used to determine a risk tendency parameter, wherein, The monitoring and early warning module calculates the difference of the slopes at adjacent motion feature points, and determines the average value of the difference as the risk tendency parameter.

[0050] Please refer to Figure 4 The logic flow chart of the monitoring and early warning module for determining whether to send the exercise amount abnormality risk early warning is shown in the figure, and the monitoring and early warning module is used to determine whether to send the exercise amount abnormality risk early warning, wherein, The monitoring and early warning module determines to send the exercise amount abnormality risk early warning based on the determination result that the risk tendency parameter of the to-be-monitored person meets the risk early warning condition; If the risk tendency parameter of the to-be-monitored person does not meet the risk early warning condition, the monitoring and early warning module determines not to send the exercise amount abnormality risk early warning; The risk early warning condition is that the risk tendency parameter exceeds a preset risk tendency parameter threshold.

[0051] Specifically, the preset risk tendency parameter threshold is the product of a risk tendency parameter reference value and a risk tendency factor, the risk tendency parameter reference value is the average value of the risk tendency parameters of the to-be-monitored persons with the same body condition in the historical data, and the risk tendency factor can be set by a person skilled in the art according to the accuracy requirement of the gynecological nursing monitoring and early warning system, the higher the accuracy requirement, the smaller the risk tendency factor, and the value range can be [1.1, 1.3], preferably, it can be 1.2.

[0052] Specifically, the embodiment of the present application constructs a motion characteristic fluctuation curve based on the motion characteristic representation parameter through the feature verification module and the monitoring and early warning module, and determines the risk tendency parameter according to the motion risk fluctuation curve to determine whether to send a motion abnormal risk early warning. It can be understood that through further analysis of the association between the physiological parameter and the motion parameter, the one-sidedness of a single parameter is avoided. The motion characteristic representation parameter reflects the matching degree of the two through the association of the motion amplitude and the physiological fluctuation, and is more suitable for the core demand of postoperative recovery than a single parameter, that is, the premise of promoting recovery through motion is that the body can adapt. The resting physiological parameter threshold is used as a benchmark for the resting value of the monitor, avoiding the problem of judging all monitors by a unified standard. For example, there is a difference in the motion physiological response between young patients and old patients. The slope change of the motion characteristic fluctuation curve can represent the development trend of the risk. If the motion characteristic parameter of the monitor has not yet exceeded, but the difference value of the curve slope continues to increase, the risk tendency parameter can capture this signal in advance, and early risk warning is performed. Abnormal parameters at a single time point may be accidental, but frequent and intense changes in trends are more likely to be a continuous signal that the body cannot adapt to the motion rhythm. The risk tendency parameter filters accidental fluctuations by calculating the average value of the slope difference, focuses on continuous risks, and reduces false positives. Furthermore, it realizes whether to send a motion abnormal risk early warning according to the physiological parameters and motion of the monitor, improves the efficiency and reliability of the gynecological nursing monitoring and early warning system.

[0053] So far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to related technical features without departing from the principles of the present application, and the technical solutions after these changes or replacements will fall within the protection scope of the present application.

[0054] The above description is only the preferred embodiments of the present application and is not intended to limit the present application; for those skilled in the art, the present application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based gynecological care monitoring and early warning system, characterized in that, The application comprises: a data acquisition module for acquiring physiological parameters and motion parameters of a subject to be monitored; a feature analysis module connected to the data acquisition module for determining a motion tendency parameter based on the physiological parameters of the subject to be monitored in a preset monitoring period, and screening a feature monitoring period based on the motion tendency parameter and the motion parameters; a feature recognition module connected to the data acquisition module and the feature analysis module for acquiring the motion parameters of the subject to be monitored in the feature monitoring period, determining a motion amount fluctuation parameter based on the comparison between the motion parameters in each feature monitoring period, and determining whether the subject to be monitored has a motion amount exceeding risk; a feature verification module connected to the data acquisition module and the feature recognition module for determining a motion feature representation parameter based on the motion parameters and the physiological parameters of the feature monitoring period according to the determination result of the motion amount exceeding risk, and constructing a motion feature fluctuation curve based on the motion feature representation parameter; a monitoring and early warning module connected to the feature verification module for determining a risk tendency parameter based on the motion risk fluctuation curve, and determining whether to send a motion amount abnormal risk early warning.

2. The artificial intelligence based gynecological care monitoring and alert system as claimed in claim 1, wherein, The feature analysis module is configured to determine a motion tendency parameter, wherein, the feature analysis module divides the preset monitoring period into a plurality of monitoring periods, and determines the difference between the maximum value and the minimum value of the physiological parameters in each period as the motion tendency parameter. 3.The gynecological care monitoring and early warning system based on artificial intelligence according to claim 2, characterized in that, The feature analysis module is configured to screen a feature monitoring period, wherein, the feature analysis module screens the monitoring period as the feature monitoring period based on the determination result that the motion tendency parameter and the motion parameter of the monitoring period meet the feature monitoring period condition; the feature monitoring period condition is that the motion tendency parameter exceeds a preset motion tendency parameter threshold value, and the motion parameter exceeds a preset motion parameter threshold value.

4. The artificial intelligence based gynecological care monitoring and alert system as claimed in claim 3, wherein, The feature recognition module is configured to determine a motion amount fluctuation parameter, wherein, the feature recognition module acquires the motion data of adjacent feature monitoring periods in time sequence, and determines the difference between the motion data of the latter feature monitoring period and the motion data of the former feature monitoring period as a motion amplitude parameter; the average value of the motion amplitude parameter is determined as the motion amount fluctuation parameter.

5. The artificial intelligence based gynecological care monitoring and alert system as claimed in claim 4, wherein, The feature recognition module is configured to determine whether the subject to be monitored has a motion amount exceeding risk, wherein, the feature recognition module determines that the subject to be monitored has a motion amount exceeding risk based on the determination result that the motion amount fluctuation parameter of the subject to be monitored meets an exceeding risk condition; the exceeding risk condition is that the motion amount fluctuation parameter exceeds a preset motion amount fluctuation parameter threshold value.

6. The artificial intelligence based gynecological care monitoring and alert system as claimed in claim 5, wherein, The feature verification module determines a motion feature representation parameter based on the motion parameters and the physiological parameters of the feature monitoring period according to the determination result that the subject to be monitored has a motion amount exceeding risk.

7. The artificial intelligence based gynecological care monitoring and alert system as claimed in claim 6, wherein, The feature verification module is configured to determine a motion feature representation parameter, wherein, the feature verification module acquires the ratio of a first motion feature to a second motion feature, and determines the ratio of the ratio to a resting physiological parameter threshold value as the motion feature representation parameter; The feature verification module obtains the average physiological parameters and the motion amplitude parameters of adjacent feature monitoring time periods, determines the absolute value of the difference of the average physiological parameters of adjacent feature monitoring time periods as the first motion feature of a previous feature monitoring time period in the adjacent feature monitoring time periods; The absolute value of the motion amplitude parameters of adjacent feature monitoring time periods is determined as the second motion feature of a previous feature monitoring time period in the adjacent feature monitoring time periods.

8. The artificial intelligence based gynecological care monitoring and alert system as claimed in claim 7, wherein, The motion feature fluctuation curve establishes a rectangular coordinate system with time as the horizontal axis and the value of the motion feature characteristic parameter as the vertical axis, and is fitted according to a plurality of motion feature points, which are determined according to the motion feature characteristic parameter and the midpoint time of the feature monitoring time period in which the motion feature characteristic parameter is located. 9.The gynecological care monitoring and early warning system based on artificial intelligence according to claim 8, characterized in that, The monitoring and early warning module is used to determine a risk tendency parameter, wherein, The monitoring and early warning module calculates the difference of the slopes at adjacent motion feature points, and determines the average value of the difference as the risk tendency parameter. 10.The gynecological care monitoring and early warning system based on artificial intelligence according to claim 9, characterized in that, The monitoring and early warning module is used to determine whether to send a motion amount abnormality risk early warning, wherein, The monitoring and early warning module determines to send a motion amount abnormality risk early warning based on the determination result that the risk tendency parameter of the to-be-monitored person meets a risk early warning condition; The risk early warning condition is that the risk tendency parameter exceeds a preset risk tendency parameter threshold.

Images