CN108511067B - Early warning method and electronic equipment - Google Patents
Early warning method and electronic equipment Download PDFInfo
- Publication number
- CN108511067B CN108511067B CN201810281536.3A CN201810281536A CN108511067B CN 108511067 B CN108511067 B CN 108511067B CN 201810281536 A CN201810281536 A CN 201810281536A CN 108511067 B CN108511067 B CN 108511067B
- Authority
- CN
- China
- Prior art keywords
- data
- health
- value
- histogram
- analyzed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The embodiment of the application provides an early warning method and electronic equipment, wherein the method comprises the following steps: and receiving the health data to be analyzed, which is acquired and sent by the data acquisition terminal of the user to be detected, in the detection period. And obtaining a first deviation value between the health data to be analyzed and group historical data in a historical period and a second deviation value between the health data to be analyzed and individual historical data. And determining whether to generate early warning information according to the relationship between the first deviation value and the second deviation value and a preset threshold value, and if the early warning information is generated, returning the early warning information to the data acquisition terminal or the early warning terminal. According to the early warning scheme, the group historical data and the individual historical data are used as reference objects to realize early warning, and the defect of inaccurate early warning caused by individual difference or incapability of finding the individuals in an abnormal state for a long time is avoided.
Description
Technical Field
The invention relates to the technical field of detection, in particular to an early warning method and electronic equipment.
Background
In a health early warning system in the prior art, artificial threshold parameter setting is often performed according to previous clinical literature data, and when specific health data exceeds a threshold value, early warning information is provided to remind a user of attracting attention. However, the setting of the threshold is usually based on statistical significance, and due to individual differences of human bodies, some fixed thresholds in clinic can only be used as references, and professional personnel are required to further perform specific analysis and adjustment on specific problems. In some occasions requiring automatic analysis and health early warning, because no expert is present at any time, a product designer completes the setting work of a threshold value by a user for the applicability of the method or the device and for avoiding the individual difference of a human body, so that the complete automation cannot be realized, and the health early warning system can be well used only if the user has certain specialty.
Disclosure of Invention
In view of the above, an object of the present application is to provide an early warning method and an electronic device to improve the above problem.
The embodiment of the application provides an early warning method, which is applied to a server in communication connection with a data acquisition terminal and an early warning terminal, and comprises the following steps:
receiving health data to be analyzed, which is acquired and sent by a data acquisition terminal of a user to be detected, in a detection period;
comparing the health data to be analyzed with group historical data in an obtained historical period to obtain a first deviation value between the health data to be analyzed and the group historical data, wherein the group historical data is generated by health data collected by a plurality of data collecting terminals;
comparing the health data to be analyzed with personal historical data in a history period to obtain a second deviation value between the health data to be analyzed and the personal historical data, wherein the personal historical data is generated by the health data of the tested user in the history period;
and determining whether to generate early warning information according to the relationship between the first deviation value and the second deviation value and a preset threshold value, and if the early warning information is generated, returning the early warning information to the data acquisition terminal or the early warning terminal.
Further, the method further comprises:
and updating the group historical data and the individual historical data according to the health data.
Further, the history cycle comprises a plurality of sub-cycles, and the group history data is obtained by:
aiming at each data acquisition terminal in a plurality of data acquisition terminals, acquiring health data of each sampling point of the data acquisition terminal in each sub-period of the history period;
carrying out average calculation on the health data of the corresponding sampling points of the plurality of sub-periods to obtain a first average value of the health data of the same sampling point of each sub-period;
carrying out average calculation on first average values corresponding to the data acquisition terminals to obtain group historical data of each sampling point;
the detection period is consistent with the sub-period, and the step of comparing the health data to be analyzed with the group history data in the obtained history period to obtain a first deviation value between the health data to be analyzed and the group history data comprises the following steps:
aiming at each sampling point, obtaining a data upper limit value and a data lower limit value according to the variance equivalent value of the group historical data of the sampling point and the group historical data of a plurality of sampling points;
and detecting whether the health data corresponding to the sampling points in the health data to be analyzed is between the lower data limit value and the upper data limit value, and if not, calculating a difference value between the health data to be analyzed and the lower data limit value or the upper data limit value to obtain a first deviation value.
Further, the history cycle comprises a plurality of sub-cycles, and the group history data is obtained by:
for each of a plurality of tested users, obtaining health data of each sampling point of the tested user in each sub-period of the history period;
counting the occurrence times of health data with the same value in the plurality of health data;
carrying out average calculation on the statistical results of the sub-periods to obtain the numerical distribution condition of the health data in the historical period;
the method comprises the steps of carrying out average value calculation on the numerical value distribution condition of health data of a plurality of data acquisition terminals to obtain group historical data;
the step of comparing the health data to be analyzed with the obtained group historical data in the historical period to obtain a first deviation value between the health data to be analyzed and the group historical data comprises:
drawing a first data histogram of the group historical data and a second data histogram of the health data to be analyzed;
and obtaining deviation values of the second data histogram and the first data histogram, and obtaining a first deviation value between the health data to be analyzed and the group historical data according to the deviation values.
Further, the step of obtaining a deviation value of the second data histogram from the first data histogram, and obtaining a first deviation value between the health data to be analyzed and the group history data according to the deviation value includes:
respectively acquiring peak data, median data and central data in the second data histogram and the first data histogram;
and obtaining a first deviation value between the health data to be analyzed and the group historical data according to at least one of the difference value of the peak data, the difference value of the median data and the difference value of the central data of the second data histogram and the first data histogram.
Further, the central data is obtained by the following formula:
wherein Hcenter is the central data, Hmin is a minimum horizontal coordinate value in the first data histogram or the second data histogram, Hmax is a maximum horizontal coordinate value in the first data histogram or the second data histogram, H is each health data in the first data histogram or the second data histogram, and p (H) is the occurrence frequency of the corresponding health data.
Further, the step of obtaining a deviation value of the second data histogram from the first data histogram, and obtaining a first deviation value between the health data to be analyzed and the group history data according to the deviation value includes:
respectively carrying out normalization processing on the second data histogram and the first data histogram;
and obtaining a non-overlapping part between the second data histogram and the first data histogram after the normalization processing to obtain a first deviation value between the health data to be analyzed and the group historical data.
Further, the step of determining whether to generate the warning information according to the relationship between the first deviation value and the second deviation value and a preset threshold includes:
and performing weighted superposition on the first deviation value and the second deviation value to obtain a superposition result, detecting whether the superposition result exceeds a preset threshold value, and judging that early warning information needs to be generated if the superposition result exceeds the preset threshold value.
Further, the health data includes at least one of acceleration data, pulse wave data, physiological electrical signals, body impedance, body surface temperature, and blood glucose data.
An embodiment of the present application further provides an electronic device, including:
a memory;
one or more processors; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, for performing the steps of the above-described pre-warning method.
According to the early warning method and the electronic device, the health data to be analyzed of the detected user received in the detection period are respectively compared with the group historical data in the historical period to obtain the first deviation value, and the first deviation value is compared with the personal historical data in the historical period to obtain the second deviation value. The group historical data is generated by health data collected by a plurality of data collecting terminals, and the individual historical data is generated according to the health data of the tested user in a historical period. And determining whether to generate early warning information according to the relationship between the first deviation value and the second deviation value and a preset threshold value. According to the early warning scheme, the group historical data and the individual historical data are used as reference objects to realize early warning, and the defect of inaccurate early warning caused by individual difference or incapability of timely finding the individuals in abnormal states for a long time is avoided.
Furthermore, the early warning scheme can dynamically update the reference object, so that the real-time performance of historical data can be guaranteed to improve the robustness of the system.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic view of an application scenario of an early warning method provided in an embodiment of the present application.
Fig. 2 is a schematic structural block diagram of a server provided in an embodiment of the present application.
Fig. 3 is a flowchart of an early warning method according to an embodiment of the present disclosure.
Fig. 4 is a flowchart of a method for acquiring group history data according to an embodiment of the present disclosure.
Fig. 5 is a flowchart of the substeps of step S120 in fig. 3.
Fig. 6 is a schematic diagram of a distribution of health data in a time domain according to an embodiment of the present application.
Fig. 7 is a second flowchart of a method for acquiring group history data according to an embodiment of the present disclosure.
Fig. 8 is another flowchart of the substeps of step S120 in fig. 3.
Fig. 9 is a schematic diagram of a data histogram provided in an embodiment of the present application.
Fig. 10 is a schematic diagram of a data histogram after normalization processing according to an embodiment of the present application.
Icon: 100-a server; 110-early warning means; 120-a processor; 130-a memory; 200-a data acquisition terminal; 300-early warning end.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Referring to fig. 1, a schematic view of an application scenario of the warning method provided in the embodiment of the present application is shown, where the scenario includes a server 100, a data acquisition terminal 200, and a warning terminal 300. The server 100 is in communication connection with the data acquisition terminal 200 and the early warning terminal 300 to perform data communication or interaction. In this embodiment, the number of the data acquisition terminals 200 and the early warning terminal 300 may be multiple, and the multiple data acquisition terminals 200 and the early warning terminal 300 are in communication connection with the server 100. In this embodiment, the data collecting terminal 200 may be a wearable device, such as a bracelet, a watch, and the like. The early warning terminal 300 may be a terminal device associated with the data acquisition terminal 200, such as a smart phone, a tablet computer, a computer, or the like. The electronic terminal may be an electronic terminal held by the user who holds the data acquisition terminal 200, or an electronic terminal held by a family member of the user. When the early warning is needed, the early warning information can be sent to the early warning terminal 300 to inform the user or the family of the user, so that the early warning purpose is achieved. The server 100 may be a single server, a server cluster, or the like, and is not particularly limited.
Please refer to fig. 2, which is a schematic block diagram of an electronic device according to an embodiment of the present disclosure. In this embodiment, the electronic device may be the server 100, and the server 100 includes the early warning device 110, the processor 120, and the memory 130. The memory 130 is electrically connected to the processor 120 directly or indirectly, so as to implement data transmission or interaction. The early warning device 110 includes at least one software function module which can be stored in the memory 130 in the form of software or firmware or solidified in the operating system of the server 100. The processor 120 is configured to execute executable modules stored in the memory 130, such as software functional modules or computer programs included in the early warning device 110.
Please refer to fig. 3, which is a flowchart illustrating an early warning method applied to the server 100 according to an embodiment of the present invention. It should be noted that the method provided by the present invention is not limited by the specific sequence shown in fig. 3 and described below. The respective steps shown in fig. 3 will be described in detail below.
Step S110, in the detection period, receives the health data to be analyzed, which is collected and sent by the data collection terminal 200 of the detected user.
With the rise of intelligent wearable equipment, the continuous collection of massive dynamic health data becomes possible, a dynamic health big database is formed, and the database comprises heart rate, blood oxygen saturation, respiratory rate, blood pressure, blood sugar, temperature, activity, sleep information and the like of a user. When a user wears the wearable product for a long time, the history data of a past period of time contains the individual's own rules and embodies the individual differences. Meanwhile, health data rules of different groups can be extracted from the health data accumulation of a large number of users.
When the individual data of the user is compared with the self historical data rule and the group historical data rule in the big database, if progressive and sudden deviation occurs, the health state of the user is possibly predicted to generate certain change, and health early warning information is generated for the user, so that the user can consult professional medical care personnel early or take other early intervention measures conveniently. The dynamic health early warning method based on big data avoids the risk of failure of the conventional general criterion during health data analysis caused by differences of individual human bodies, group ages, regions, climates and the like. The method has great value for improving the self-adaption and the robustness of the early warning algorithm of the health early warning device.
In this embodiment, the data acquisition terminal 200 includes a plurality of data sensors, which can be respectively used to obtain one or more health data of acceleration data, pulse wave data, physiological electrical signals, body impedance, body surface temperature, and blood glucose data of a wearing user. The data collection terminal 200 transmits the collected health data to the server 100. The server 100 analyzes and processes the received health data to be analyzed, which is collected and sent by the data collection terminal 200 of the user to be tested, in a detection period, for example, one day or one week, so as to detect whether the health data of the user to be tested is abnormal. The server 100 may obtain the number of steps of the user, sleep quality data of the user, and the like according to the received acceleration data. The heart rate data, the blood oxygen saturation data, the respiration data, the blood pressure and the like of the user can be obtained according to the pulse wave data. The physiological electric signals comprise electrocardiosignals, myoelectric signals, electroencephalogram signals and the like.
Step S120, comparing the health data to be analyzed with group history data in the obtained history period to obtain a first deviation value between the health data to be analyzed and the group history data, wherein the group history data is generated by the health data collected by the plurality of data collecting terminals 200.
Step S130, comparing the health data to be analyzed with the obtained personal history data in the history period to obtain a second deviation value between the health data to be analyzed and the personal history data, where the personal history data is generated from the health data of the tested user in the history period.
In this embodiment, the server 100 may receive and analyze the health data collected and sent by the plurality of data collection terminals 200 to obtain population statistical data, and may also separately count the health data of each data collection terminal 200 for each data collection terminal 200 to obtain individual statistical data.
In this embodiment, the server 100 may perform statistical analysis on the health data received in the history period before the detection period to obtain group history data based on the health data of the plurality of data collection terminals 200 in the history period. For the group history data, the history period may also be a time period synchronized with the detection period, which is not particularly limited. And personal history data for each user based on the health data of its corresponding data collection terminal 200. In consideration of the fact that a fixed and unchangeable early warning rule is often adopted for each user in the prior art, in actual situations, the standards of health data are different due to the difference of constitutions of different users. The early warning rules in the prior art do not form a targeted and customized early warning scheme, so that the problem of inaccurate early warning caused by individual difference is solved. In the embodiment, the above factors are considered, so that the personal history data of the detected user in the history period is used as one reference object, so as to improve the early warning accuracy. In addition, if the user is in an unhealthy state for a long time, if only the personal historical data of the user is taken as a reference, the unhealthy state may not be found in time, and accurate early warning is difficult to be made. Therefore, in this embodiment, health data of a plurality of users in a history period is used to form group history data, and the group history data is also included in reference data of early warning detection of a user to be detected. The health data to be analyzed is compared with personal historical data and group historical data to realize early warning.
In this embodiment, in order to analyze the health data more comprehensively, the health data may be processed to obtain different types of group history data as a comparison basis. Optionally, a time domain analysis may be performed on the health data, referring to fig. 4, and the time domain population history data may be obtained by:
step S210, for each data acquisition terminal 200 in the plurality of data acquisition terminals 200, obtaining health data of each sampling point of the data acquisition terminal 200 in each sub-period of the history period.
Step S220, performing an average calculation on the health data of the corresponding sampling points of the multiple sub-periods to obtain a first average of the health data of the same sampling point of each sub-period.
Step S230, performing an average calculation on the first average values corresponding to the multiple tested users to obtain group history data of each sampling point.
As can be seen from the above, the group history data is generated based on health data of a plurality of users. In this embodiment, the data collected by the data collection terminal 200 of each user may be analyzed, and then the analysis results of a plurality of users may be counted to obtain group history data.
In this embodiment, the history period may be one day, one week, or one month, which is not particularly limited. For example, when the history period is a week, in order to analyze the health data of the user every day, the history period may be divided into a plurality of sub-periods, wherein the sub-period may be a day.
If the sub-period is one day, a plurality of sampling points may be included in the sub-period, and the sampling frequency may be 2 minutes or 10 minutes, which is not limited thereto. The server 100 may receive the health data transmitted from the data collecting terminal 200 at each sampling point. Thus, there are multiple health data for the same sampling point of multiple sub-periods within the history period. For example, 12 points in each sub-period have one health data, if the history period includes 7 sub-periods, the history period has 7 health data of 12 points in total, and the average value of the health data may be calculated to obtain the first average value of the health data of the same sampling point in each sub-period. Therefore, the problem of unreliable data caused by the fact that the data in a certain sub-period is compared independently in the follow-up process can be avoided. It should be noted that the above description of the history period and the sub-period is only an example, and other setting manners may be adopted in implementation, and the embodiment is not particularly limited.
After the health data is analyzed and processed for each data acquisition terminal 200, the average value of the analysis and processing results of the plurality of data acquisition terminals 200 may be calculated to obtain group history data of the plurality of users. In the case of obtaining the group history data in the above manner, in the embodiment, referring to fig. 5, the step S120 may include the following sub-steps:
and step S121, aiming at each sampling point, obtaining a data upper limit value and a data lower limit value according to the variance equivalence of the group historical data of the sampling point and the group historical data of a plurality of sampling points.
Step S122, detecting whether the health data corresponding to the sampling point in the health data to be analyzed is between the data lower limit value and the data upper limit value, and if not, calculating a difference between the health data to be analyzed and the data lower limit value or the data upper limit value to obtain a first deviation value.
After the above steps, it is equivalent to integrate data of multiple users in multiple sub-periods into one sub-period, in this embodiment, the detection period is consistent with the sub-period, that is, if the sub-period is one day, the detection period is also one day. For the group history data of each sampling point in the group history data obtained above, the group history data of the acquisition point may be added with the variance equivalence of the group history data of the plurality of obtained sampling points to obtain an upper data limit value, and the group history data of the acquisition point may be subtracted with the variance equivalence of the group history data of the plurality of obtained sampling points to obtain a lower data limit value. The variance equivalent value may be a multiple value of the variance, such as a variance value multiplied by 2 or a variance value multiplied by 3, and the like, and is not particularly limited.
In this embodiment, the health data to be analyzed includes a plurality of health data, each health data corresponds to each sampling point in the detection period, and the health data obtained at each sampling point can be compared with the upper limit value and the lower limit value of the data obtained according to the group history data. FIG. 6 is a diagram illustrating the distribution of the upper data limit, the lower data limit, and the historical average. The lower data limit, the upper data limit, and the historical average may be generated based on personal historical data or group historical data. If the health data is not between the upper data limit value and the lower data limit value, further detection can be performed. If the health data is larger than the data upper limit value, calculating a difference value between the health data and the data upper limit value, and taking the difference value as a first deviation value between the health data to be analyzed and the group historical data. If the health data are smaller than the data lower limit value, a difference value between the data lower limit value and the health data can be calculated, and the difference value is used as a first deviation value between the health data to be analyzed and the group historical data. The first offset value may be an offset value for a single point, or may be a statistical value of offset values of sampling points in the entire detection period.
In addition to the time domain analysis of the health data in the history period, in this embodiment, a frequency domain analysis of the health data in the history period may be performed, please refer to fig. 7, and the group history data may be obtained through the following steps:
step S310, for each data acquisition terminal 200 in the plurality of data acquisition terminals 200, obtaining health data of each sampling point of the data acquisition terminal 200 in each sub-period of the history period, and counting the occurrence frequency of health data with the same value in the plurality of health data.
Step S320, performing a mean calculation on the statistical results of the multiple sub-periods to obtain a numerical distribution of the health data in the history period.
Step S330, calculating the mean value of the numerical distribution of the health data of the plurality of data acquisition terminals 200 to obtain group history data.
In this embodiment, for each user, in each sub-period of the history period, the health data of each sampling point in the sub-period may be obtained, and the occurrence frequency of the health data with the same value in the sub-period is counted to obtain the occurrence frequency of the health data with each value. And then carrying out mean value calculation on the statistical results of a plurality of sub-periods in the historical period, thus obtaining the numerical value distribution condition of the health data in the historical period.
Through the above steps, the numerical distribution of the health data in the history period of each data acquisition terminal 200 can be obtained, and the results of a plurality of data acquisition terminals 200 can be averaged to obtain group history data based on a plurality of users.
In this embodiment, when obtaining the group history data in this way, please refer to fig. 8, the first deviation value between the data to be analyzed and the group history data can be obtained through the following sub-steps:
and step S123, drawing a first data histogram of the group historical data and a second data histogram of the health data to be analyzed.
Step S124, obtaining a deviation value between the second data histogram and the first data histogram, and obtaining a first deviation value between the health data to be analyzed and the group history data according to the deviation value.
In this embodiment, in order to visually display the distribution of the health data, a first data histogram may be drawn according to the obtained group history data. And after the numerical value distribution condition of the data to be analyzed is obtained according to the obtained data to be analyzed in the detection period in the mode, drawing a second data histogram according to the numerical value distribution condition. And obtaining a first deviation value between the health data to be analyzed and the group historical data according to the deviation value between the first data histogram and the second data histogram. Fig. 9 is a schematic diagram illustrating the first data histogram or the second data histogram provided in this embodiment.
In this embodiment, peak data, median data, and center data in the second data histogram and the first data histogram may be acquired, respectively. The median data is a numerical value that divides the histogram into two and has equal areas on both sides. The center data is the location of the centroid in the histogram. The peak data, median data, and central data reflect the intensity range distribution of the health data of the user over a period of time. The distribution has a close relation with the health condition of the user, and when the histogram characteristic value of the tested user has a significant difference relative to the distribution of the historical period of the tested user or the historical period of the group, the health condition of the tested user is possibly abnormal, and the user needs to be reminded.
Optionally, a first deviation value between the health data to be analyzed and the group history data is obtained according to at least one of a difference value of peak data, a difference value of median data, and a difference value of center data of the second data histogram and the first data histogram. The first deviation value can be obtained according to any one of the three differences, or the first deviation value can be obtained after two kinds of weighted superposition, or the first deviation value can be obtained after the three kinds of differences are weighted superposition. The embodiment is not particularly limited, and may be adjusted according to actual conditions.
Wherein the central data may be obtained by the following formula:
wherein Hcenter is the central data, Hmin is a minimum value of an abscissa in the first data histogram or the second data histogram, Hmax is a maximum value of an abscissa in the first data histogram or the second data histogram, H is each health data value in the first data histogram or the second data histogram, and p (H) is a number of occurrences of the corresponding health data value.
In addition to detecting the deviation of the single point to obtain the first deviation value, in the present embodiment, the first deviation value may also be obtained according to the overall deviation degree. In this embodiment, the second data histogram and the first data histogram may be normalized separately. And obtaining a non-overlapping part between the normalized second data histogram and the first data histogram, wherein the non-overlapping part represents the deviation of the second data histogram relative to the first data histogram. According to the non-overlapping part, a first deviation value between the health data to be analyzed and the group historical data can be obtained. Fig. 10 is a schematic diagram of the first data histogram and the second data histogram after normalization processing.
Through the above steps, the first deviation value between the health data to be analyzed and the group history data can be obtained, and it should be noted that the acquisition manner of the personal history data of the user to be tested and the acquisition manner of the second deviation value between the health data to be analyzed and the personal history data are similar to the acquisition manner of the group history data and the acquisition manner of the first deviation value between the health data to be analyzed and the group history data, respectively, and the difference is that the group history data are for a plurality of users, and the personal history data are for the user to be tested himself. Therefore, the step of obtaining the second deviation value can refer to the above description, and is not repeated herein.
Step S140, determining whether to generate warning information according to a relationship between the first deviation value and the second deviation value, and a preset threshold, and if generating warning information, returning the warning information to the data acquisition terminal 200 or the warning terminal 300.
In this embodiment, the first deviation value between the data to be analyzed and the group history data and the second deviation value between the data to be analyzed and the individual history data are obtained through the above steps. Whether the early warning information needs to be generated or not can be judged according to the relation between the two and a preset threshold value. The first deviation value and the second deviation value can be weighted and overlapped to obtain an overlapping result. And detecting whether the superposition result exceeds a preset threshold value, if so, judging that early warning information needs to be generated, and feeding the early warning information back to the data acquisition terminal 200 of the detected user or the early warning terminal 300 associated with the data acquisition terminal 200 of the detected user. The warning terminal 300 may be a smart phone held by the user to be detected, for example, to notify the user by sending a short message, or a computer of the user to be detected, for example, to notify the user by sending an email. The early warning terminal 300 may also be an electronic terminal held by the family of the detected user, which is associated with the data acquisition terminal 200 of the detected user, so that the family of the detected user can be timely notified to remind the family to pay attention to the health condition of the detected user, thereby avoiding the occurrence of a dangerous condition.
In addition to the above-mentioned determining whether the warning information needs to be generated according to the relationship between the superposition result of the first deviation value and the second deviation value and the preset threshold, in this embodiment, it may also be determined whether the warning information needs to be generated according to the relationship between the first deviation value and the preset threshold or the relationship between the second deviation value and the preset threshold. Whether the early warning information needs to be generated or not can be judged according to the relation between at least one of the first deviation value and the second deviation value and a preset threshold value. The present embodiment is not particularly limited, and may be configured accordingly as required.
In addition, in this embodiment, the group history data and the individual history data may also be dynamically updated, that is, the health data to be analyzed obtained in the detection period may be added to the history data, so as to update the group history data and the individual history data. Therefore, the real-time performance of the historical data can be guaranteed so as to improve the robustness of the system.
In summary, the embodiment of the present application provides an early warning method and an electronic device, in which health data to be analyzed of a detected user received in a detection period is respectively compared with group historical data in a historical period to obtain a first deviation value, and is compared with personal historical data in the historical period to obtain a second deviation value. Wherein the group history data is generated by the health data collected by the plurality of data collecting terminals 200, and the individual history data is generated according to the health data of the tested user in the history period. And determining whether to generate early warning information according to the relationship between the first deviation value and the second deviation value and a preset threshold value. According to the early warning scheme, the group historical data and the individual historical data are used as reference objects to realize early warning, and the defect of inaccurate early warning caused by individual difference or incapability of timely finding the individuals in abnormal states for a long time is avoided. In addition, the reference object can be dynamically updated, so that the real-time performance of historical data is guaranteed, and the robustness of the system is improved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (9)
1. The early warning method is characterized by being applied to a server which is in communication connection with a data acquisition terminal and an early warning end, and comprises the following steps:
receiving health data to be analyzed, which is acquired and sent by a data acquisition terminal of a user to be detected, in a detection period;
comparing the health data to be analyzed with group historical data in an obtained historical period to obtain a first deviation value between the health data to be analyzed and the group historical data, wherein the group historical data is generated by health data collected by a plurality of data collecting terminals;
comparing the health data to be analyzed with personal historical data in a history period to obtain a second deviation value between the health data to be analyzed and the personal historical data, wherein the personal historical data is generated by the health data of the tested user in the history period;
determining whether to generate early warning information according to the relationship between the first deviation value and the second deviation value and a preset threshold value, and if the early warning information is generated, returning the early warning information to the data acquisition terminal or the early warning terminal;
the history cycle comprises a plurality of sub-cycles, and the group history data is obtained by the following steps:
aiming at each data acquisition terminal in a plurality of data acquisition terminals, acquiring health data of each sampling point of the data acquisition terminal in each sub-period of the history period;
carrying out average calculation on the health data of the corresponding sampling points of the plurality of sub-periods to obtain a first average value of the health data of the same sampling point of each sub-period;
carrying out average calculation on first average values corresponding to the data acquisition terminals to obtain group historical data of each sampling point;
the detection period is consistent with the sub-period, and the step of comparing the health data to be analyzed with the group history data in the obtained history period to obtain a first deviation value between the health data to be analyzed and the group history data comprises the following steps:
aiming at each sampling point, obtaining a data upper limit value and a data lower limit value according to the variance equivalent value of the group historical data of the sampling point and the group historical data of a plurality of sampling points;
and detecting whether the health data corresponding to the sampling points in the health data to be analyzed is between the lower data limit value and the upper data limit value, and if not, calculating a difference value between the health data to be analyzed and the lower data limit value or the upper data limit value to obtain a first deviation value.
2. The warning method of claim 1, further comprising:
and updating the group historical data and the individual historical data according to the health data.
3. The warning method of claim 1, wherein the history period comprises a plurality of sub-periods, and the group history data is obtained by:
for each of a plurality of tested users, obtaining health data of each sampling point of the tested user in each sub-period of the history period;
counting the occurrence times of health data with the same value in the plurality of health data;
carrying out average calculation on the statistical results of the sub-periods to obtain the numerical distribution condition of the health data in the historical period;
the method comprises the steps of carrying out average value calculation on the numerical value distribution condition of health data of a plurality of data acquisition terminals to obtain group historical data;
the step of comparing the health data to be analyzed with the obtained group historical data in the historical period to obtain a first deviation value between the health data to be analyzed and the group historical data comprises:
drawing a first data histogram of the group historical data and a second data histogram of the health data to be analyzed;
and obtaining deviation values of the second data histogram and the first data histogram, and obtaining a first deviation value between the health data to be analyzed and the group historical data according to the deviation values.
4. The warning method as claimed in claim 3, wherein the step of obtaining a deviation value of the second data histogram from the first data histogram, and obtaining a first deviation value between the health data to be analyzed and the group history data according to the deviation value comprises:
respectively acquiring peak data, median data and central data in the second data histogram and the first data histogram;
and obtaining a first deviation value between the health data to be analyzed and the group historical data according to at least one of the difference value of the peak data, the difference value of the median data and the difference value of the central data of the second data histogram and the first data histogram.
5. The warning method according to claim 4, wherein the central data is obtained by the following formula:
wherein Hcenter is the central data, Hmin is a minimum horizontal coordinate value in the first data histogram or the second data histogram, Hmax is a maximum horizontal coordinate value in the first data histogram or the second data histogram, H is each health data in the first data histogram or the second data histogram, and p (H) is the occurrence frequency of the corresponding health data.
6. The warning method as claimed in claim 3, wherein the step of obtaining a deviation value of the second data histogram from the first data histogram, and obtaining a first deviation value between the health data to be analyzed and the group history data according to the deviation value comprises:
respectively carrying out normalization processing on the second data histogram and the first data histogram;
and obtaining a non-overlapping part between the second data histogram and the first data histogram after the normalization processing to obtain a first deviation value between the health data to be analyzed and the group historical data.
7. The warning method according to claim 1, wherein the step of determining whether to generate warning information according to the relationship between the first deviation value and the second deviation value and a preset threshold value comprises:
and performing weighted superposition on the first deviation value and the second deviation value to obtain a superposition result, detecting whether the superposition result exceeds a preset threshold value, and judging that early warning information needs to be generated if the superposition result exceeds the preset threshold value.
8. The warning method of claim 1, wherein the health data includes at least one of acceleration data, pulse wave data, physiological electrical signals, body impedance, body surface temperature, and blood glucose data.
9. An electronic device, comprising:
a memory;
one or more processors; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, for performing the steps of the warning method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810281536.3A CN108511067B (en) | 2018-04-02 | 2018-04-02 | Early warning method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810281536.3A CN108511067B (en) | 2018-04-02 | 2018-04-02 | Early warning method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108511067A CN108511067A (en) | 2018-09-07 |
| CN108511067B true CN108511067B (en) | 2020-12-08 |
Family
ID=63379528
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810281536.3A Active CN108511067B (en) | 2018-04-02 | 2018-04-02 | Early warning method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108511067B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109490675B (en) * | 2018-12-27 | 2022-06-28 | 上海辛格林纳新时达电机有限公司 | Early warning method, electronic device and test system |
| CN110473633A (en) * | 2019-08-19 | 2019-11-19 | 泰康保险集团股份有限公司 | Health information management method, device, medium and electronic equipment |
| CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
| CN112256754A (en) * | 2020-10-19 | 2021-01-22 | 柳州市妇幼保健院 | Ultrasonic detection analysis system and method based on standard model |
| CN112885469A (en) * | 2021-02-01 | 2021-06-01 | 中国科学院苏州生物医学工程技术研究所 | Method and system for monitoring vital signs of chronic disease population |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104207753A (en) * | 2013-02-15 | 2014-12-17 | 迈克尔·L·谢尔登 | Personal health monitoring system |
| CN105718732A (en) * | 2016-01-20 | 2016-06-29 | 华中科技大学同济医学院附属协和医院 | Medical data collection and analysis method and system |
| CN106030592A (en) * | 2014-02-19 | 2016-10-12 | 国际商业机器公司 | Developing health information feature abstractions from intra-individual temporal variance heteroskedasticity |
| CN107122587A (en) * | 2017-03-22 | 2017-09-01 | 上海商保通健康科技有限公司 | Layer-stepping personalized health trend evaluation system based on big data |
| CN107145704A (en) * | 2017-03-27 | 2017-09-08 | 西安电子科技大学 | Health medical treatment monitoring, evaluating system and its method for a kind of Community-oriented |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150220839A1 (en) * | 2012-09-07 | 2015-08-06 | Hugh Macnaught | Comparison of user experience with experience of larger group |
-
2018
- 2018-04-02 CN CN201810281536.3A patent/CN108511067B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104207753A (en) * | 2013-02-15 | 2014-12-17 | 迈克尔·L·谢尔登 | Personal health monitoring system |
| CN106030592A (en) * | 2014-02-19 | 2016-10-12 | 国际商业机器公司 | Developing health information feature abstractions from intra-individual temporal variance heteroskedasticity |
| CN105718732A (en) * | 2016-01-20 | 2016-06-29 | 华中科技大学同济医学院附属协和医院 | Medical data collection and analysis method and system |
| CN107122587A (en) * | 2017-03-22 | 2017-09-01 | 上海商保通健康科技有限公司 | Layer-stepping personalized health trend evaluation system based on big data |
| CN107145704A (en) * | 2017-03-27 | 2017-09-08 | 西安电子科技大学 | Health medical treatment monitoring, evaluating system and its method for a kind of Community-oriented |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108511067A (en) | 2018-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108511067B (en) | Early warning method and electronic equipment | |
| JP2018125026A (en) | Systems and methods for analyte data processing and report generation | |
| US20070293731A1 (en) | Systems and Methods for Monitoring and Evaluating Individual Performance | |
| JP6310476B2 (en) | Method and system for reducing the load caused by harmful alarms in clinical settings | |
| JP6368512B2 (en) | Server device, watching system, and program | |
| EP3461403A1 (en) | A method and apparatus for assessing the mobility of a subject | |
| US9672339B2 (en) | Electro-biometric authentication | |
| CN111919242A (en) | System and method for processing multiple signals | |
| US20210161479A1 (en) | A Probability-Based Detector and Controller Apparatus, Method, Computer Program | |
| CN106333643B (en) | User health monitoring method, monitoring device and monitoring terminal | |
| JP6304050B2 (en) | Biological state estimation device | |
| CN112075930B (en) | Analysis early warning device, method and system based on scatter diagram and electronic equipment | |
| CN108281182B (en) | User health monitoring data alarming method and device | |
| CN112315432B (en) | Information monitoring method, information monitoring device and computer readable storage medium | |
| KR101993649B1 (en) | Method and Appatatus for Calculation of Present Life Pattern Regularity against Past Life Pattern Using Gaussian Distribution Model | |
| CN109922718B (en) | Method, apparatus and computer program product for providing dynamic wake alarms | |
| WO2021105314A1 (en) | Method of determining fused sensor measurement and vehicle safety system using the fused sensor measurement | |
| CN108903923B (en) | Health monitoring device, system and method | |
| CN115778341A (en) | Blood pressure measuring method, blood pressure measuring device, smart watch, smart device, blood pressure measuring medium, and program product | |
| CN112244797A (en) | Body state monitoring method and device and storage medium | |
| US20220000415A1 (en) | Epileptic seizure predicting device, method for analyzing electrocardiographic index data, seizure predicting computer program, model constructing device, model constructing method, and model constructing computer program | |
| WO2017109910A1 (en) | Electronic device, determination method, and determination program | |
| CN108510410A (en) | A kind of control method and device of hotel service system | |
| JP7180259B2 (en) | Biological information analysis device, biological information analysis method, and biological information analysis system | |
| US20220359092A1 (en) | A system and method for triggering an action based on a disease severity or affective state of a subject |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |