System and method for coping with health care abnormity based on Internet of Things technology

Abstract

The invention belongs to the technical field of health monitoring, and provides a health care abnormity coping system and method based on the Internet of Things technology. The method comprises the steps that a first real-time physiological signal of a target health care object is received, a normal threshold range corresponding to the target health care object is called, and when the first real-time physiological signal exceeds the normal threshold range, first positioning information of the target health care object is obtained; acquiring second real-time physiological signals of other health-care objects in a specified range, and analyzing each second real-time physiological signal by using a deep analysis model to obtain a physiological feature matching probability; if the physiological feature matching probability is higher than a first threshold value, sending a reminding signal to a first terminal of the target health-care object; otherwise, sending a reminding signal to the first terminal and the first monitoring terminal of the target health-care object at the same time. According to the method, comprehensive analysis is carried out by combining the real-time physiological signals, the positioning information and the surrounding health-care object data, and the accuracy of abnormity judgment can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of health monitoring technology, and in particular to a health care abnormality response system and method based on Internet of Things technology. Background Art

[0002] As the global population ages, the importance of the healthcare industry becomes increasingly prominent. The traditional healthcare service model has gradually exposed many shortcomings in the face of the growing number of elderly people and diverse health needs. For example, in terms of daily health monitoring, it often relies on regular manual inspections, which is not only inefficient, but also difficult to achieve real-time and comprehensive tracking of the physical condition of the healthcare recipients. Once health abnormalities occur, such as sudden illness, falls and other emergencies, failure to detect and take effective measures in time may lead to serious consequences.

[0003] At the same time, the Internet of Things technology has achieved rapid development in recent years. Through various sensors, smart devices and network connections, the Internet of Things can realize information exchange and communication between objects and objects, and between people and objects. Applying the Internet of Things technology to the field of health care can provide new solutions for abnormal health care responses. With the help of various wearable devices and environmental sensors, the physiological data (such as heart rate, blood pressure, sleep quality, etc.) and environmental data (such as temperature, humidity, air quality, etc.) of health care objects can be collected in real time. These data are transmitted to the data processing center through the network, and are analyzed in real time using big data analysis and artificial intelligence algorithms. Once an abnormal situation is found, the system can quickly issue an alarm and promptly notify relevant medical staff or family members to take countermeasures.

[0004] However, the current recognition strategy for health care anomalies is mainly based on a preset physiological signal threshold range, that is, when the measured physiological signal exceeds the threshold range, it is determined that the health care subject has an abnormal physical condition. However, due to a variety of normal conditions, the physiological characteristics of the health care subject may also exceed the above threshold range. For example, when the health care subject participates in group activities (such as running), the heart rate will increase, but at this time the health care subject is not in an abnormal physical state. Therefore, the existing health care anomaly response method based on a fixed threshold range still needs to further improve its anomaly recognition accuracy. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a health care abnormality response method, system, electronic device, computer storage medium and computer program product based on Internet of Things technology.

[0006] The present invention provides a method for coping with health care anomalies based on Internet of Things technology, which is applied to a cloud platform. The method comprises the following steps: receiving a first real-time physiological signal of a target health care object and retrieving a normal threshold range corresponding to the target health care object, and when the first real-time physiological signal exceeds the normal threshold range, further acquiring first positioning information of the target health care object; acquiring second real-time physiological signals of other health care objects within a specified range, and analyzing each of the second real-time physiological signals using a deep analysis model to obtain a physiological feature matching probability; wherein the specified range is a circular range defined by a preset distance based on the first positioning information; if the physiological feature matching probability is higher than a first threshold, sending a reminder signal to the first terminal of the target health care object; otherwise, sending a reminder signal to the first terminal and the first monitoring terminal of the target health care object at the same time.

[0007] In some embodiments, the normal threshold range is determined by: retrieving the historical physiological signals of the target health care object, and dividing the historical physiological signals into a first group of historical physiological signals and a second group of historical physiological signals according to whether there is an abnormal confirmation signal; wherein, each historical physiological signal in the first group of historical physiological signals has no abnormal confirmation signal, and each historical physiological signal in the second group of historical physiological signals has an abnormal confirmation signal; clustering the first group of historical physiological signals and the second group of historical physiological signals to obtain the equivalent value of the first physiological signal and the equivalent value of the second physiological signal located at the center of the cluster, respectively; calculating the difference between the equivalent value of the second physiological signal and the equivalent value of the first physiological signal, and determining the upper floating value and the lower floating value according to the upper adjustment coefficient, the lower adjustment coefficient and the difference, respectively, adding and subtracting the equivalent value of the first physiological signal from the upper floating value and the lower floating value, respectively, to obtain the normal threshold range; wherein, the upper adjustment coefficient is greater than the lower adjustment coefficient.

[0008] In some embodiments, the preset distance is determined in the following manner: scene attribute information of the geographical area where the target health care object is located is determined based on the first positioning information, and the scene attribute information corresponds to the closed area of ​​the geographical area; the preset distance is determined based on the size of the closed area.

[0009] In some embodiments, the use of a deep analysis model to analyze each of the second real-time physiological signals to obtain a physiological feature matching probability includes: analyzing the distance stability between the second positioning information corresponding to each of the second real-time physiological signals and the first positioning information, and classifying the second real-time physiological signals whose distance stability is higher than a first preset value into a participating group, and classifying the second real-time physiological signals whose distance stability is not higher than the first preset value into a non-participating group; using the first deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the participating group to obtain a first physiological feature matching probability; and using the second deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the non-participating group to obtain a second physiological feature matching probability; and performing weighted calculation on the first physiological feature matching probability and the second physiological feature matching probability based on corresponding weighted values, respectively, to obtain the physiological feature matching probability.

[0010] In some embodiments, the simultaneously sending of reminder signals to the first terminal and the first monitoring terminal of the target health care object includes: if the first real-time physiological signal exceeds the normal threshold range and reaches a second preset value, and the distance between the first monitoring terminal of the target health care object and the first terminal is greater than a third preset value, then simultaneously sending reminder signals to the second terminals of multiple other health care objects within the specified range and the corresponding second monitoring terminals.

[0011] The present invention also provides a health care abnormality response system based on Internet of Things technology, which is applied to a cloud platform, and the system includes a first receiving and processing unit, a second receiving and processing unit, and a response processing unit; the first receiving and processing unit is used to receive a first real-time physiological signal of a target health care object and retrieve a normal threshold range corresponding to the target health care object, and when the first real-time physiological signal exceeds the normal threshold range, further obtain the first positioning information of the target health care object; the second receiving and processing unit is used to obtain the second real-time physiological signals of other health care objects within a specified range, and use a deep analysis model to analyze each of the second real-time physiological signals to obtain a physiological feature matching probability; wherein the specified range is a circular range defined by a preset distance based on the first positioning information; the response processing unit is used to send a reminder signal to the first terminal of the target health care object if the physiological feature matching probability is higher than the first threshold; otherwise, a reminder signal is sent to the first terminal and the first monitoring terminal of the target health care object at the same time.

[0012] In some embodiments, the normal threshold range is determined by: retrieving the historical physiological signals of the target health care object, and dividing the historical physiological signals into a first group of historical physiological signals and a second group of historical physiological signals according to whether there is an abnormal confirmation signal; wherein, each historical physiological signal in the first group of historical physiological signals has no abnormal confirmation signal, and each historical physiological signal in the second group of historical physiological signals has an abnormal confirmation signal; clustering the first group of historical physiological signals and the second group of historical physiological signals to obtain the equivalent value of the first physiological signal and the equivalent value of the second physiological signal located at the center of the cluster, respectively; calculating the difference between the equivalent value of the second physiological signal and the equivalent value of the first physiological signal, and determining the upper floating value and the lower floating value according to the upper adjustment coefficient, the lower adjustment coefficient and the difference, respectively, adding and subtracting the equivalent value of the first physiological signal from the upper floating value and the lower floating value, respectively, to obtain the normal threshold range; wherein, the upper adjustment coefficient is greater than the lower adjustment coefficient.

[0013] In some embodiments, the preset distance is determined in the following manner: scene attribute information of the geographical area where the target health care object is located is determined based on the first positioning information, and the scene attribute information corresponds to the closed area of ​​the geographical area; the preset distance is determined based on the size of the closed area.

[0014] In some embodiments, the second receiving and processing unit is specifically used to: analyze the distance stability between the second positioning information corresponding to each of the second real-time physiological signals and the first positioning information, and classify the second real-time physiological signals whose distance stability is higher than the first preset value into a participating group, and classify the second real-time physiological signals whose distance stability is not higher than the first preset value into a non-participating group; use the first deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the participating group to obtain a first physiological feature matching probability; and use the second deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the non-participating group to obtain a second physiological feature matching probability; and perform weighted calculation on the first physiological feature matching probability and the second physiological feature matching probability based on corresponding weighted values, respectively, to obtain the physiological feature matching probability.

[0015] In some embodiments, the response processing unit is specifically used to: if the first real-time physiological signal exceeds the normal threshold range to reach a second preset value, and the distance between the first monitoring terminal of the target health care object and the first terminal is greater than a third preset value, then a reminder signal is sent to the second terminals of multiple other health care objects within the specified range and the corresponding second monitoring terminals at the same time.

[0016] The present invention also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0017] The present invention also provides a computer storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above methods can be implemented.

[0018] The present invention also provides a computer program product, wherein the computer program product includes computer program codes, and the computer program codes are executed by a processor of an electronic device to implement the steps of any one of the above methods.

[0019] The beneficial effect of the present invention is that the present invention can significantly improve the accuracy of abnormal judgment by combining real-time physiological signals, positioning information and surrounding health care object data for comprehensive analysis. For example, when judging the abnormal heart rate of the elderly, it can distinguish whether it is caused by individual health problems or group exercise behavior, avoiding unnecessary panic and waste of medical resources. At the same time, the present invention can also adopt different response strategies based on the relative situation of the physiological feature matching probability obtained by analysis and the first threshold, thereby significantly improving the efficiency of health care abnormal response. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flow chart of a method for coping with health care anomalies based on Internet of Things technology disclosed in an embodiment of the present invention.

[0022] Figure 2 It is a structural diagram of the deep analysis model disclosed in the embodiment of the present invention.

[0023] Figure 3 It is a structural schematic diagram of a health care abnormality response system based on Internet of Things technology disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0025] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0026] In traditional health care abnormality recognition, the physical condition of the health care subject is judged to be abnormal only based on the preset physiological signal threshold. For example, the normal range of heart rate is set to 60-100 beats / minute. When the measured heart rate exceeds this range, the physical condition is considered abnormal. However, when the health care subject participates in group activities such as running, the heart rate may reach 130 beats / minute, but this is a normal exercise reaction, not a physical abnormality. This leads to the existing health care abnormality response method based on a fixed threshold range, and the abnormality recognition accuracy is not high.

[0027] In view of the above technical problems, Figure 1 As shown, an embodiment of the present invention discloses a method for responding to health care abnormalities based on Internet of Things technology, which is applied to a cloud platform. The method includes the following steps: S1, receiving a first real-time physiological signal of a target health care object and retrieving a normal threshold range corresponding to the target health care object, and when the first real-time physiological signal exceeds the normal threshold range, further acquiring first positioning information of the target health care object.

[0028] Specifically: the target health care object wears wearable devices or other monitoring devices, which can collect the first real-time physiological signals of the target health care object, including but not limited to heart rate, blood pressure, skin electrical signals, body temperature, etc., and the cloud platform receives this signal. At the same time, the cloud platform retrieves the normal threshold range corresponding to the target health care object pre-stored in the cloud, which is a personalized indicator set based on comprehensive factors such as the personal physical condition and past health data of the target health care object. When the first real-time physiological signal exceeds the normal threshold range, it indicates that there may be an abnormal situation. At this time, the cloud platform further obtains the first positioning information of the target health care object.

[0029] For example, if the smart bracelet worn by the target health care subject monitors the heart rate in real time and uploads it to the cloud, the cloud platform will retrieve the normal heart rate threshold range of 60-100 beats / minute. When the heart rate is monitored to be 120 beats / minute, it exceeds the above threshold range. The current first positioning information is then obtained through the positioning device carried by the elderly (such as a smart bracelet with built-in GPS).

[0030] S2, obtaining the second real-time physiological signals of other health care objects within the specified range, using the deep analysis model to analyze each of the second real-time physiological signals, and obtaining the physiological feature matching probability; wherein, the specified range is a circular range defined by a preset distance based on the first positioning information.

[0031] Specifically: Based on the first positioning information, a circle range is defined according to a preset distance (for example, 50 meters), and other health care objects are searched within this specified range. The cloud platform obtains the second real-time physiological signals of these other health care objects, which also come from their respective wearable devices or other monitoring devices. Then, the deep analysis model is used to analyze each second real-time physiological signal to obtain the physiological feature matching probability of other health care objects and the target health care object. The physiological feature matching probability refers to the probability that the target health care object and other health care objects are jointly carrying out group activities (for example, running together, playing badminton, square dancing, etc.).

[0032] S3: If the physiological feature matching probability is higher than a first threshold, a reminder signal is sent to the first terminal of the target health care object; otherwise, a reminder signal is sent to the first terminal and the first monitoring terminal of the target health care object at the same time.

[0033] Specifically: compare the obtained physiological feature matching probability with the first threshold. If the physiological feature matching probability is higher than the first threshold, it means that the abnormal physiological signal of the target health care object may be caused by normal group activities. For example, the heart rate generally increases during group exercise in the park. At this time, only the first terminal of the target health care object (such as the elderly’s own mobile phone) is sent a reminder signal to inform the current physiological signal status and remind them to pay attention to their own situation. However, if the physiological feature matching probability is lower than the first threshold, it means that the abnormal physiological signal of the target health care object may be caused by individual health problems. In order to ensure timely processing, a reminder signal is sent to the first terminal and the first monitoring terminal (such as the mobile phones of the elderly’s children and family doctors) of the target health care object at the same time, so that the guardian can take quick measures to ensure the health and safety of the health care object.

[0034] The present invention can significantly improve the accuracy of abnormal judgment by combining real-time physiological signals, positioning information, and surrounding health care object data for comprehensive analysis. For example, when judging the abnormal heart rate of the elderly, it can distinguish whether it is caused by individual health problems or normal participation in group activities, avoiding unnecessary panic and waste of medical resources. At the same time, the present invention can also adopt different response strategies based on the relative situation of the physiological feature matching probability obtained by analysis and the first threshold, thereby significantly improving the efficiency of health care abnormal response.

[0035] In some embodiments, the normal threshold range is determined by: retrieving the historical physiological signals of the target health care object, and dividing the historical physiological signals into a first group of historical physiological signals and a second group of historical physiological signals according to whether there is an abnormal confirmation signal; wherein, each historical physiological signal in the first group of historical physiological signals has no abnormal confirmation signal, and each historical physiological signal in the second group of historical physiological signals has an abnormal confirmation signal; clustering the first group of historical physiological signals and the second group of historical physiological signals to obtain the equivalent value of the first physiological signal and the equivalent value of the second physiological signal located at the center of the cluster, respectively; calculating the difference between the equivalent value of the second physiological signal and the equivalent value of the first physiological signal, and determining the upper floating value and the lower floating value according to the upper adjustment coefficient, the lower adjustment coefficient and the difference, respectively, adding and subtracting the equivalent value of the first physiological signal from the upper floating value and the lower floating value, respectively, to obtain the normal threshold range; wherein, the upper adjustment coefficient is greater than the lower adjustment coefficient.

[0036] In this embodiment, the cloud platform or other storage devices store historical physiological signals of the target health care object, covering data collected by various monitoring devices in the past period of time, such as heart rate, blood pressure, blood oxygen saturation, etc. Then, these historical physiological signals are classified according to whether there are abnormal confirmation signals. The abnormal confirmation signals mainly come from the diagnosis of medical staff, the feedback of the health care object itself, or other abnormal event records. If a historical physiological signal is not associated with an abnormal confirmation signal, it is classified into the first group of historical physiological signals; if a historical physiological signal is associated with an abnormal confirmation signal, it is classified into the second group of historical physiological signals. For example, in the blood pressure data of a health care object in the past six months, the blood pressure data in the daily stable state is classified into the first group, and the data of abnormal blood pressure fluctuations during illness and hospitalization are marked as the second group.

[0037] For the above two different groups of historical physiological signals, cluster analysis techniques are used to find the core trend of each group of data, that is, the cluster center. For the first group of historical physiological signals representing the normal state, the physiological signal value corresponding to the cluster center obtained after clustering (generally the mean of multiple physiological signals, weighted mean, etc.) is the first physiological signal equivalent value, which concentrates on the typical signal characteristics of the health care object under the normal physiological state. Similarly, cluster analysis is performed on the second group of historical physiological signals representing abnormal states, and the cluster center obtained corresponds to the second physiological signal equivalent value, reflecting the physiological signal characteristics under abnormal conditions. For example, after clustering the first group of normal blood pressure data, the average normal blood pressure value is 120 / 80mmHg (equivalent value of the first physiological signal), and the average abnormal blood pressure value obtained by clustering the second group of abnormal blood pressure data is 160 / 100mmHg (equivalent value of the second physiological signal).

[0038] Calculate the difference between the equivalent value of the second physiological signal and the equivalent value of the first physiological signal, and the difference characterizes the degree of difference between the physiological signals of the target health care object in normal and abnormal states. At the same time, in order to judge abnormal situations more prudently and prevent normal physiological fluctuations from being misjudged as abnormal, the present invention further sets an upper adjustment coefficient and a lower adjustment coefficient that are less than 0.5 (for 1 / 2 of the difference), and the two coefficients are used to appropriately reduce the above difference. Under normal circumstances, the physiological signals of health care objects are more likely to float up within the normal range, and less likely to float down within the normal range. Therefore, the present invention sets the upper adjustment coefficient to be greater than the lower adjustment coefficient, for example, the upper adjustment coefficient is 0.45 and the lower adjustment coefficient is 0.4. The upper adjustment coefficient and the lower adjustment coefficient are multiplied by the above difference respectively to obtain the upper floating value and the lower floating value, and then the normal threshold range is determined.

[0039] The normal threshold range determined in this way closely fits the actual physiological condition of the health care subject and can significantly improve the accuracy of abnormal judgment.

[0040] In some embodiments, the preset distance is determined in the following manner: scene attribute information of the geographical area where the target health care object is located is determined based on the first positioning information, and the scene attribute information corresponds to the closed area of ​​the geographical area; the preset distance is determined based on the size of the closed area.

[0041] In this embodiment, the cloud platform analyzes the relevant characteristics of the geographical area where the target health care object is located based on the first positioning information, thereby determining its scene attribute information. The scene attribute information includes the enclosed area of ​​the geographical area. For example, if the target health care object is located in a building unit in a community, this is a closed space. Through geographic information system (GIS) data or pre-entered site information, it can be known that the enclosed area of ​​the building unit is 100 square meters; if it is located in, for example, a fitness venue in a nursing home, the fitness venue is not completely enclosed, but it can be divided into a relatively closed activity range according to its boundaries and functional areas. It is assumed that its enclosed area is calculated to be 500 square meters.

[0042] Due to differences in the distribution of people and range of activities in geographical areas with different enclosed areas, different preset distances are required to reasonably collect the physiological signals of surrounding health care objects. Areas with smaller enclosed areas can generally only accommodate a small number of people for group exercise at the same time, such as following a video blogger to exercise and keep fit at home in a building unit. At this time, the preset distance can be set shorter, such as 5 meters, to ensure that the collected surrounding data is relevant and effective. For fitness venues with an enclosed area of ​​500 square meters, large-scale group activities are often held, such as square dancing, fun sports, etc. In order to obtain enough and representative physiological signals from surrounding health care objects, the preset distance may be set to a radius of 50 meters.

[0043] By dynamically adjusting the preset distance according to the enclosed area, it is possible to more accurately collect peripheral data that is valuable for judging the physiological state of the target health care subject in different scenarios, thereby improving the accuracy and reliability of abnormal judgment based on peripheral data.

[0044] In some embodiments, the use of a deep analysis model to analyze each of the second real-time physiological signals to obtain a physiological feature matching probability includes: analyzing the distance stability between the second positioning information corresponding to each of the second real-time physiological signals and the first positioning information, and classifying the second real-time physiological signals whose distance stability is higher than a first preset value into a participating group, and classifying the second real-time physiological signals whose distance stability is not higher than the first preset value into a non-participating group; using the first deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the participating group to obtain a first physiological feature matching probability; and using the second deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the non-participating group to obtain a second physiological feature matching probability; and performing weighted calculation on the first physiological feature matching probability and the second physiological feature matching probability based on corresponding weighted values, respectively, to obtain the physiological feature matching probability.

[0045] In this embodiment, the distance stability between the second positioning information corresponding to each second real-time physiological signal and the first positioning information of the target health care object is first analyzed. The distance stability reflects the change in the relative position between other health care objects and the target health care object. For example, if the distance between a health care object and the target health care object is always kept within a small fluctuation range over a period of time, it means that the distance stability is high, and the two may be running or dancing together; on the contrary, if the distance fluctuation is large, the distance stability is low, and the other health care object may be a spectator. According to the pre-set first preset value, the selected other health care objects are divided into a participating group and a non-participating group, respectively, wherein the second real-time physiological signal in the participating group comes from the surrounding health care objects with a relatively stable relative position to the target health care object, and its physiological signal may be more closely related to the physiological state of the target health care object; while the second real-time physiological signal in the non-participating group is less closely related to the physiological state of the target health care object, but can be used to indirectly analyze whether the target health care object is performing group exercise in a normal physical state, for example, the audience will also be excited by the group activity, resulting in an enhancement of their physiological signal (the enhancement is generally weaker than that of the group activity participants).

[0046] For the above different groups of signals, such as Figure 2As shown, the present invention constructs a first depth analysis model and a second depth analysis model based on a convolutional neural network (CNN) or a recurrent neural network (RNN). The two models can respectively extract features from each second real-time physiological signal of the above-mentioned participating group and non-participating group to obtain key information related to the physiological characteristics of the target health care object, and then perform deep analysis and processing on it to obtain the first physiological characteristic matching probability and the second physiological characteristic matching probability. Among them, the first physiological characteristic matching probability directly reflects the similarity between the physiological characteristics of the surrounding health care objects and the target health care objects in the participating group, and the second physiological characteristic matching probability indirectly reflects the similarity between the physiological characteristics of the surrounding health care objects and the target health care objects in the non-participating group. It should be noted that the first depth analysis model is obtained by training based on the physiological signals of each health care object directly participating in the group activity, and the second depth analysis model is obtained by training based on the physiological signals of each health care object directly participating in the group activity and watching the group activity, that is, the second depth analysis model can analyze the intrinsic correlation between the physiological signals of the viewer and the physiological signals of the participant, and then be used to indirectly analyze whether the target health care object is performing group activities.

[0047] In order to comprehensively consider the impact of the two groups of signals on the matching probability of the physiological characteristics of the target health care object, the first physiological characteristic matching probability and the second physiological characteristic matching probability are weighted calculated based on the corresponding weighted values, and the weighted value of the first physiological characteristic matching probability is higher than the weighted value of the second physiological characteristic matching probability.

[0048] In some embodiments, the simultaneously sending of reminder signals to the first terminal and the first monitoring terminal of the target health care object includes: if the first real-time physiological signal exceeds the normal threshold range and reaches a second preset value, and the distance between the first monitoring terminal of the target health care object and the first terminal is greater than a third preset value, then simultaneously sending reminder signals to the second terminals of multiple other health care objects within the specified range and the corresponding second monitoring terminals.

[0049] In this embodiment, when the system detects that the first real-time physiological signal of the target health care object exceeds the normal threshold range, and the degree of this exceeding reaches the second preset value, it indicates that the physiological state of the target health care object is very likely to be seriously abnormal. At the same time, if it is found that the distance between the first monitoring terminal of the target health care object and the first terminal (i.e., the device carried by the health care object himself, such as a mobile phone) is greater than the third preset value, it means that the family members, family doctors, etc. carrying the first monitoring terminal cannot directly monitor, intervene and rescue the target health care object in time.

[0050] At this time, the cloud platform will not only send reminder signals to the first terminal and the first monitoring terminal of the target health care object, but also send reminder signals to the second terminals of multiple other health care objects within the specified range and the second monitoring terminals corresponding to these second terminals. In this way, when the target health care object is in an emergency and the main guardian cannot arrive in time, the power of other health care objects in the surrounding area can be used to provide help to the target health care object more quickly.

[0051] like Figure 3 As shown, the embodiment of the present invention also discloses that the present invention also provides a health care abnormality response system based on the Internet of Things technology, which is applied to a cloud platform, and the system includes a first receiving and processing unit, a second receiving and processing unit, and a response processing unit; the first receiving and processing unit is used to receive a first real-time physiological signal of a target health care object and retrieve a normal threshold range corresponding to the target health care object, and when the first real-time physiological signal exceeds the normal threshold range, further obtain the first positioning information of the target health care object; the second receiving and processing unit is used to obtain the second real-time physiological signals of other health care objects within a specified range, and use a deep analysis model to analyze each of the second real-time physiological signals to obtain a physiological feature matching probability; wherein the specified range is a circular range defined by a preset distance based on the first positioning information; the response processing unit is used to send a reminder signal to the first terminal of the target health care object if the physiological feature matching probability is higher than the first threshold; otherwise, a reminder signal is sent to the first terminal and the first monitoring terminal of the target health care object at the same time.

[0052] In some embodiments, the normal threshold range is determined by: retrieving the historical physiological signals of the target health care object, and dividing the historical physiological signals into a first group of historical physiological signals and a second group of historical physiological signals according to whether there is an abnormal confirmation signal; wherein, each historical physiological signal in the first group of historical physiological signals has no abnormal confirmation signal, and each historical physiological signal in the second group of historical physiological signals has an abnormal confirmation signal; clustering the first group of historical physiological signals and the second group of historical physiological signals to obtain the equivalent value of the first physiological signal and the equivalent value of the second physiological signal located at the center of the cluster, respectively; calculating the difference between the equivalent value of the second physiological signal and the equivalent value of the first physiological signal, and determining the upper floating value and the lower floating value according to the upper adjustment coefficient, the lower adjustment coefficient and the difference, respectively, adding and subtracting the equivalent value of the first physiological signal from the upper floating value and the lower floating value, respectively, to obtain the normal threshold range; wherein, the upper adjustment coefficient is greater than the lower adjustment coefficient.

[0053] In some embodiments, the preset distance is determined in the following manner: scene attribute information of the geographical area where the target health care object is located is determined based on the first positioning information, and the scene attribute information corresponds to the closed area of ​​the geographical area; the preset distance is determined based on the size of the closed area.

[0054] In some embodiments, the second receiving and processing unit is specifically used to: analyze the distance stability between the second positioning information corresponding to each of the second real-time physiological signals and the first positioning information, and classify the second real-time physiological signals whose distance stability is higher than the first preset value into a participating group, and classify the second real-time physiological signals whose distance stability is not higher than the first preset value into a non-participating group; use the first deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the participating group to obtain a first physiological feature matching probability; and use the second deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the non-participating group to obtain a second physiological feature matching probability; and perform weighted calculation on the first physiological feature matching probability and the second physiological feature matching probability based on corresponding weighted values, respectively, to obtain the physiological feature matching probability.

[0055] In some embodiments, the response processing unit is specifically used to: if the first real-time physiological signal exceeds the normal threshold range to reach a second preset value, and the distance between the first monitoring terminal of the target health care object and the first terminal is greater than a third preset value, then a reminder signal is sent to the second terminals of multiple other health care objects within the specified range and the corresponding second monitoring terminals at the same time.

[0056] The system in this embodiment adopts all the technical solutions of the above embodiments, and therefore has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0057] An embodiment of the present invention further discloses an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0058] The embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above methods can be implemented.

[0059] An embodiment of the present invention further discloses a computer program product, wherein the computer program product includes computer program codes, and when the computer program codes are executed by a processor of an electronic device, the steps of any one of the above methods are implemented.

[0060] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0061] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0062] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0063] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A health care abnormality response method based on Internet of Things technology, applied to a cloud platform, characterized by: The method includes the following steps: receiving a first real-time physiological signal of a target health care object and retrieving a normal threshold range corresponding to the target health care object, and when the first real-time physiological signal exceeds the normal threshold range, further obtaining the first positioning information of the target health care object; obtaining the second real-time physiological signals of other health care objects within a specified range, and using a deep analysis model to analyze each of the second real-time physiological signals to obtain a physiological feature matching probability; wherein the specified range is a circular range defined by a preset distance based on the first positioning information; if the physiological feature matching probability is higher than a first threshold, sending a reminder signal to the first terminal of the target health care object; otherwise, sending a reminder signal to the first terminal and the first monitoring terminal of the target health care object at the same time.

2. According to claim 1, a method for dealing with health care anomalies based on Internet of Things technology is characterized by: The normal threshold range is determined in the following manner: the historical physiological signals of the target health care object are retrieved, and the historical physiological signals are divided into a first group of historical physiological signals and a second group of historical physiological signals according to whether there are abnormal confirmation signals; wherein, each historical physiological signal in the first group of historical physiological signals has no abnormal confirmation signal, and each historical physiological signal in the second group of historical physiological signals has an abnormal confirmation signal; the first group of historical physiological signals and the second group of historical physiological signals are clustered to obtain the equivalent value of the first physiological signal and the equivalent value of the second physiological signal located at the cluster center, respectively; the difference between the equivalent value of the second physiological signal and the equivalent value of the first physiological signal is calculated, and the upper floating value and the lower floating value are determined according to the upper adjustment coefficient, the lower adjustment coefficient and the difference, and the first physiological signal equivalent value is added to and subtracted from the upper floating value and the lower floating value, respectively, to obtain the normal threshold range; wherein, the upper adjustment coefficient is greater than the lower adjustment coefficient.

3. According to claim 1, a method for dealing with health care anomalies based on Internet of Things technology is characterized by: The preset distance is determined in the following manner: based on the first positioning information, scene attribute information of the geographical area where the target health care object is located is determined, and the scene attribute information corresponds to the closed area of ​​the geographical area; and the preset distance is determined based on the size of the closed area.

4. According to claim 1, a health care abnormality response method based on Internet of Things technology is characterized by: The use of the deep analysis model to analyze each of the second real-time physiological signals to obtain the physiological feature matching probability includes: analyzing the distance stability between the second positioning information corresponding to each of the second real-time physiological signals and the first positioning information, classifying the second real-time physiological signals whose distance stability is higher than the first preset value into a participating group, and classifying the second real-time physiological signals whose distance stability is not higher than the first preset value into a non-participating group; using the first deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the participating group to obtain the first physiological feature matching probability; and using the second deep analysis model to perform feature extraction and deep analysis on each of the second real-time physiological signals in the non-participating group to obtain the second physiological feature matching probability; and performing weighted calculation on the first physiological feature matching probability and the second physiological feature matching probability based on corresponding weighted values, respectively, to obtain the physiological feature matching probability.

5. According to claim 1, a method for dealing with health care anomalies based on Internet of Things technology is characterized by: The method of simultaneously sending a reminder signal to the first terminal and the first monitoring terminal of the target health care object includes: if the first real-time physiological signal exceeds the normal threshold range and reaches a second preset value, and the distance between the first monitoring terminal of the target health care object and the first terminal is greater than a third preset value, then simultaneously sending a reminder signal to the second terminals of multiple other health care objects within the specified range and the corresponding second monitoring terminals.

6. A health care abnormality response system based on Internet of Things technology, applied to a cloud platform, characterized by: The system includes a first receiving and processing unit, a second receiving and processing unit, and a response processing unit; the first receiving and processing unit is used to receive a first real-time physiological signal of a target health care object and retrieve a normal threshold range corresponding to the target health care object, and when the first real-time physiological signal exceeds the normal threshold range, further obtain the first positioning information of the target health care object; the second receiving and processing unit is used to obtain the second real-time physiological signals of other health care objects within a specified range, and use a deep analysis model to analyze each of the second real-time physiological signals to obtain a physiological feature matching probability; wherein the specified range is a circular range defined by a preset distance based on the first positioning information; the response processing unit is used to send a reminder signal to the first terminal of the target health care object if the physiological feature matching probability is higher than the first threshold; otherwise, a reminder signal is sent to the first terminal and the first monitoring terminal of the target health care object at the same time.

7. The health care abnormality response system based on the Internet of Things technology according to claim 6 is characterized by: The normal threshold range is determined in the following manner: the historical physiological signals of the target health care object are retrieved, and the historical physiological signals are divided into a first group of historical physiological signals and a second group of historical physiological signals according to whether there are abnormal confirmation signals; wherein, each historical physiological signal in the first group of historical physiological signals has no abnormal confirmation signal, and each historical physiological signal in the second group of historical physiological signals has an abnormal confirmation signal; the first group of historical physiological signals and the second group of historical physiological signals are clustered to obtain the equivalent value of the first physiological signal and the equivalent value of the second physiological signal located at the cluster center, respectively; the difference between the equivalent value of the second physiological signal and the equivalent value of the first physiological signal is calculated, and the upper floating value and the lower floating value are determined according to the upper adjustment coefficient, the lower adjustment coefficient and the difference, and the first physiological signal equivalent value is added to and subtracted from the upper floating value and the lower floating value, respectively, to obtain the normal threshold range; wherein, the upper adjustment coefficient is greater than the lower adjustment coefficient.

8. An electronic device, comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the method according to any one of claims 1 to 5 when executing the computer program.

9. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

10. A computer program product, comprising computer program code, characterized in that: The computer program code is executed by a processor of an electronic device to implement the method according to any one of claims 1 to 5.

Images