CN109480816A

CN109480816A - Rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium

Info

Publication number: CN109480816A
Application number: CN201811550238.6A
Authority: CN
Inventors: 汪孔桥; 朱国康; 赵威
Original assignee: Anhui Huami Information Technology Co Ltd
Current assignee: Anhui Huami Information Technology Co Ltd
Priority date: 2018-12-18
Filing date: 2018-12-18
Publication date: 2019-03-19
Also published as: WO2020125078A1

Abstract

The disclosure provides a kind of rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium, which comprises obtains prosodic feature in short-term；The prosodic feature in short-term is the rhythm and pace of moving things data of heart rate signal of the measurand within the first period；If it is determined that the prosodic feature in short-term contains target rhythm of the heart feature, prosodic feature when obtaining long；Prosodic feature is the rhythm and pace of moving things data of heart rate signal of the measurand within the second period when described long；Second period is longer than first period；If it is determined that prosodic feature contains the target rhythm of the heart feature when described long, output measurand has the monitored results of target rhythm of the heart feature.Implement embodiment of the disclosure, can monitor the rhythm of the heart of measurand in conjunction with the heart rate signal of short time interval detection and the heart rate signal of long duration detection, improve the monitoring accuracy to target rhythm of the heart feature.

Description

Rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium

Technical field

This disclosure relates to heart rate signal processing technology field more particularly to a kind of rhythm of the heart monitoring method, device, electronic equipment And computer readable storage medium.

Background technique

The heart rate (heartbeat frequency) of human body is the pseudo-random event of close coupling, dynamic realtime variation complicated and changeable, Intelligent wearable device or other coherent detections by the Medical Devices of ECG monitor etc, bracelet, armband, chest strap etc Equipment can detecte the heart rate signal of human body a certain period.The heart rate signal detected can reflect heartbeat interval (or the heart Dirty bounce rhythm), i.e. reflection cardiac rhythm (the abbreviation rhythm of the heart).

Currently, associated assay devices are the heart rate signal for acquiring certain time period, and by heart rate signal directly with numerical value Or the form of curve image is presented to the user, and needs user oneself that the heart rate signal for observing the period is gone to obtain whether there is certain Heart rhythm conditions occur, such as cardiac arrhythmia, it is difficult to which whether automatically prompting user has certain heart rhythm conditions.

Summary of the invention

To overcome the problems in correlation technique, present disclose provides rhythm of the heart monitoring method, device, electronic equipment and meters Calculation machine readable storage medium storing program for executing.

According to the first aspect of the embodiments of the present disclosure, a kind of rhythm of the heart monitoring method is provided, comprising:

Obtain prosodic feature in short-term；The prosodic feature in short-term is the section of heart rate signal of the measurand within the first period Restrain data；

If it is determined that the prosodic feature in short-term contains target rhythm of the heart feature, prosodic feature when obtaining long；The long time Restrain the rhythm and pace of moving things data that feature is heart rate signal of the measurand within the second period；Second period is longer than described first Period；

If it is determined that prosodic feature contains the target rhythm of the heart feature when described long, output measurand has target rhythm of the heart feature Monitored results.

Optionally, prosodic feature in short-term is obtained, comprising:

For multiple continuous first periods, the heart rate for obtaining the measurand respectively in wherein each first period is believed Number rhythm and pace of moving things data, obtain the prosodic feature in short-term of each first period；

The method also includes following steps:

If in the prosodic feature in short-term of the first period of continuous predetermined number, containing target rhythm of the heart feature, output respectively Measurand has the monitored results of target rhythm of the heart feature.

Optionally, heart rate signal of the measurand within first period are as follows: examined in real time in first period The ECG signal of survey；

Heart rate signal of the measurand within second period are as follows: the PPG of real-time detection in second period Signal.

It is optionally, described to obtain prosodic feature in short-term, comprising:

Obtain the spacing at each pair of adjacent R peak in the ECG signal；

Calculate the first differential and second-order differential at the interval at each pair of adjacent R peak；

The interval at each pair of adjacent R peak, the histogram distribution of the first differential and the second-order differential are counted respectively.

Optionally, the method also includes:

The good model of input pre-training after the histogram distribution counted respectively splicing is calculated；

According to the calculated result that the model exports, show whether the prosodic feature in short-term has target rhythm of the heart feature really Determine result.

Optionally, the model is convolutional neural networks CNN model or 31 layers of AlexNet network model.

Optionally, the prosodic feature when acquisition is long, comprising:

Obtain the spacing at each pair of adjacent pulse peak in the PPG signal；

The first differential for calculating the spacing at each pair of adjacent pulse peak obtained is sample；

Calculated sample is marked in a manner of scatter plot；

Scatter plot is divided into the sub-district of predetermined number；

The number of samples in each sub-district is accumulated, the prosodic feature when characteristic vector of predetermined dimension is described long is obtained.

Optionally, the method also includes:

The good model of prosodic feature input pre-training calculates when will be described long；

According to the calculated result that the model exports, the rhythm and pace of moving things is characterized in no thering is target rhythm of the heart feature really when obtaining described long Determine result.

Optionally, the model is ANN model.

Optionally, the target rhythm of the heart feature includes uneven rhythm of the heart feature.

Optionally, approach described above includes:

It is obtaining in short-term before prosodic feature, from eliminating baseline drift in the heart rate signal of measurand in first period Disturbance and high-frequency noise；

When obtaining long before prosodic feature, from eliminating baseline drift in the heart rate signal of measurand in second period Disturbance and high-frequency noise.

According to the second aspect of an embodiment of the present disclosure, a kind of rhythm of the heart monitoring device is provided, comprising:

Short feature obtains module, is configured as: obtaining prosodic feature in short-term；The prosodic feature in short-term is that measurand exists The rhythm and pace of moving things data of heart rate signal in first period；

Short feature judgment module, is configured as: when the prosodic feature in short-term contains target rhythm of the heart feature, when obtaining long Prosodic feature；Prosodic feature is the rhythm and pace of moving things data of heart rate signal of the measurand within the second period when described long；It is described Second period was longer than first period；

As a result output module is configured as: when prosodic feature contains the target rhythm of the heart feature when described long, tested pair of output As the monitored results with target rhythm of the heart feature.

Optionally, the short feature obtains module, comprising:

Short feature acquisition submodule, is configured as: being directed to multiple continuous first periods, obtains the measurand respectively In the rhythm and pace of moving things data of the wherein heart rate signal of each first period, the prosodic feature in short-term of each first period is obtained；

Described device further includes early warning enhancing module, is configured as:

In the prosodic feature in short-term of the first period of continuous predetermined number, when containing target rhythm of the heart feature respectively, output Measurand has the monitored results of target rhythm of the heart feature.

Optionally, the short feature obtains module, comprising:

First spacing obtains module, is configured as: obtaining the spacing at each pair of adjacent R peak in the ECG signal；

Differential calculation module, is configured as: calculating the first differential and second-order differential at the interval at each pair of adjacent R peak；

Statistics with histogram module, is configured as: count respectively the interval at each pair of adjacent R peak, the first differential and The histogram distribution of the second-order differential.

Optionally, described device further includes short feature judgment module, is configured as:

Optionally, the long feature obtains module, comprising:

Second spacing obtains module, is configured as: obtaining the spacing at each pair of adjacent pulse peak in the PPG signal；

Sample Calculation Block is configured as: the first differential for calculating the spacing at each pair of adjacent pulse peak of acquisition is sample；

Sample labeling module, is configured as: calculated sample is marked in a manner of scatter plot；

Sub-area division module, is configured as: scatter plot is divided into the sub-district of predetermined number；

Long characteristic determination module, is configured as: number of samples of the accumulation in each sub-district obtains the Characteristic Vectors of predetermined dimension Prosodic feature when amount is described long.

Optionally, described device further includes long feature judgment module, is configured as:

Optionally, the model is ANN model.

Optionally, described device includes:

First signal enhancing module, is configured as: before obtaining prosodic feature in short-term, tested pair out of described first period Baseline drift disturbance and high-frequency noise are eliminated in the heart rate signal of elephant；

Second signal enhances module, is configured as: when obtaining long before prosodic feature, tested pair out of described second period Baseline drift disturbance and high-frequency noise are eliminated in the heart rate signal of elephant.

According to the third aspect of an embodiment of the present disclosure, a kind of electronic equipment is provided, comprising:

Processor；

Memory for storage processor executable instruction；

Wherein, the processor is configured to executing the operation in method as described above.

According to a fourth aspect of embodiments of the present disclosure, a kind of computer readable storage medium is provided, calculating is stored thereon with Machine program, when executed by one or more processors, so that processor executes the operation in method as described above.

The technical scheme provided by this disclosed embodiment can include the following benefits:

In the disclosure, by the rhythm and pace of moving things data of heart rate signal of the measurand within the first shorter period, obtain in short-term Prosodic feature, determine it is described prosodic feature has target rhythm of the heart feature in short-term in the case where, then by the measurand compared with The rhythm and pace of moving things data of heart rate signal in the second long period, prosodic feature when obtaining long, and the prosodic feature when determining described long When having target rhythm of the heart feature, output measurand has the monitored results of target rhythm of the heart feature.Compared to only passing through the short period The heart rate signal of detection monitors whether that measurand has the mode of target rhythm of the heart feature, when the disclosure is using monitoring in short-term and being long The mode for monitoring cooperation, can be by the monitored results of the rhythm and pace of moving things data in current short time interval, with the rhythm and pace of moving things data in long duration Monitored results combine, and obtain final monitored results, then export final monitored results, automatic prompt measurand has the target rhythm of the heart While feature, additionally it is possible to improve the accuracy and stability of monitored results.

In the disclosure, if it is confirmed that the rhythm and pace of moving things data of the heart rate signal of continuous multiple first periods have the target rhythm and pace of moving things respectively In the case where feature, the rhythm and pace of moving things data of the heart rate signal of each second period do not have target prosodic feature, and the disclosure can be even When the number of continuous first period is more than scheduled number threshold value, ignore the monitoring knot of the rhythm and pace of moving things data of the rhythm signal of the second period Fruit, output measurand has the monitored results of target rhythm of the heart feature, to prevent missing target rhythm of the heart feature.

In the disclosure, ECG signal and PPG signal can be merged very well to monitor the rhythm of the heart feature of measurand, from different dimensional Degree carries out joint-monitoring to the rhythm of the heart, can be further improved the reliability of rhythm of the heart monitoring.

In the disclosure, with the interval at adjacent R each pair of in ECG signal peak, the histogram of first differential and second-order differential this three Figure distribution can more preferably embody the prosodic feature of the rhythm signal of short time interval, improve the standard of monitored results for prosodic feature in short-term Exactness and stability.

In the disclosure, with each pair of adjacent pulse in PPG signal it is peak-to-peak away from first differential each sub-district of scatter plot number, Prosodic feature when being long can more preferably embody the prosodic feature of the rhythm signal of long duration, improve the accuracy of monitored results with Stability.

In the disclosure, obtain in short-term prosodic feature and it is long when prosodic feature before, respectively from short time interval detect heart rate letter Number with eliminate baseline drift disturbance and high-frequency noise in the heart rate signal of long duration detection, heart rate signal can be enhanced, improve prison Control the accuracy and stability of result.

It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not The disclosure can be limited.

Detailed description of the invention

The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure Example, and together with specification for explaining the principles of this disclosure.

Figure 1A is the application scenario diagram of disclosure rhythm of the heart monitoring shown according to an exemplary embodiment.

Figure 1B is the application scenario diagram for the rhythm of the heart monitoring that the disclosure is shown according to another exemplary embodiment.

Fig. 1 C is the application scenario diagram for the rhythm of the heart monitoring that the disclosure is shown according to another exemplary embodiment.

Fig. 2A is a kind of disclosure flow chart of rhythm of the heart monitoring method shown according to an exemplary embodiment.

Fig. 2 B is a kind of disclosure heart rate signal figure shown according to an exemplary embodiment.

Fig. 2 C is the peak the R schematic diagram extracted in a kind of disclosure heart rate signal shown according to an exemplary embodiment.

Fig. 2 D is a kind of disclosure machine learning model shown according to an exemplary embodiment.

Fig. 2 E is the disclosure another heart rate signal figure shown according to an exemplary embodiment.

Fig. 2 F is the pulse peak signal extracted in the disclosure another heart rate signal shown according to an exemplary embodiment Figure.

Fig. 2 G is the disclosure another machine learning model shown according to an exemplary embodiment.

Fig. 3 is the flow chart of the disclosure another rhythm of the heart monitoring method shown according to an exemplary embodiment.

Fig. 4 is the flow chart of the disclosure another rhythm of the heart monitoring method shown according to an exemplary embodiment.

Fig. 5 is a kind of disclosure block diagram of rhythm of the heart monitoring device shown according to an exemplary embodiment.

Fig. 6 is the block diagram of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment.

Fig. 7 is the block diagram of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment.

Fig. 8 is the block diagram of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment.

Fig. 9 is the block diagram of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment.

Figure 10 is the block diagram of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment.

Figure 11 is the block diagram of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment.

Figure 12 is the architecture diagram of disclosure a kind of electronic equipment shown according to an exemplary embodiment.

Specific embodiment

Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.

It is only to be not intended to be limiting the disclosure merely for for the purpose of describing particular embodiments in the term that the disclosure uses. The "an" of the singular used in disclosure and the accompanying claims book, " described " and "the" are also intended to including majority Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps It may be combined containing one or more associated any or all of project listed.

It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the disclosure A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from In the case where disclosure range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ... When " or " in response to determination ".

This disclosure relates to rhythm of the heart monitoring method, can be applied to the intelligence such as bracelet, wrist-watch, hand strap, armband, chest strap etc Can wearable device, also can be applied to the electronic equipment of intelligent wearable device binding, electronic equipment mentioned herein can be with Be personal computer, laptop computer, cellular phone, camera phone, smart phone, tablet computer, intelligent interaction device, The combination of any several equipment in smart home device etc. or these equipment.

This disclosure relates to rhythm of the heart monitoring method, can also be applied to medical field in electrocardio monitoring device, but need It is emphasized that the rhythm of the heart monitoring method of the disclosure is not intended to the diagnosis of disease and health status, the disclosure first is only defeated Out measurand have target rhythm of the heart feature monitored results, doctor, measurand or other receive the personnel of monitored results, only According only to monitored results, it is difficult to directly make diagnosis to the health status of measurand and with the presence or absence of disease, need doctor into The history patient's condition of medical knowledge, the clinical experience of accumulation, the heart rate signal of checked object, checked object that one step is grasped referring to it Etc. other factors, carry out comprehensive descision can just obtain diagnostic result, according to the monitored results of the disclosure, doctor is difficult to directly determine The health status of its main body and whether suffer from related disease.Secondly, doctor is different, by its medical knowledge and the shadow of clinical experience Loud or measurand the history patient's condition is different, is likely to be obtained entirely different diagnostic result.

In addition, the target rhythm of the heart feature in monitored results, it may be possible to since the ongoing sports of measurand are led It causing, and non-disease or other healthy hidden dangers, it is also possible to a kind of only temporary illusion can be restored by certain rest, because This, according to the monitored results of the disclosure, doctor is difficult to directly determine whether its main body suffers from disease or the risk with disease Degree, direct purpose are not diagnosis.

Referring to the drawings, introduce first it is lower this disclosure relates to rhythm of the heart monitoring certain applications scene:

Please referring to Figure 1A, application scenarios shown in figure 1A may include measurand 110 and heart rate detection equipment 120, In, measurand 110 can be in human body convenient for the position of detection heart rate, such as chest, arm, wrist, the present embodiment it is attached Figure is convenient for illustrating, by taking measurand is wrist as an example.

Heart rate detection equipment 120 can be heart rate sensor, if ECG sensor is (ECG is Electrocardiogram Abbreviation, mean electrocardiogram), (PPG is the abbreviation of Photoplethysmography to PPG sensor, means photoplethysmographic Graphical method), ultrasonic sensor etc.；It is also possible to the intelligent wearable device with heart rate sensor, such as bracelet, wrist-watch, hand The intelligent wearable device of band, armband, chest strap etc；It is also possible to the electronic equipment of intelligent wearable device binding, it is such as personal Computer, laptop computer, cellular phone, camera phone, smart phone, tablet computer, intelligent interaction device, intelligent family Occupy the combination of any several equipment in equipment etc. or these equipment；It can also be the electrocardio monitoring device in medical field Or other are used for the equipment that electrocardio monitors, herein with no restrictions.

The attached drawing of the present embodiment is to be illustrated so that ECG detecting equipment is bracelet as an example convenient for illustrating, heart rate inspection Measurement equipment 120 may include one or more heart rate sensors 121, rhythm of the heart client 122, Display processing module 123 and display Screen 124.The sensor that multiple heart rate sensors 121 can be same type is also possible to different types of sensor.

The mode of the acquisition of heart rate sensor 121 or detection heart rate signal can be determined by its sensor type, as heart rate passes Sensor 121 be ECG sensor can be detected by bioelectricity when detect heart rate signal, wherein the tissue of human body with Current potential and change in polarity can occur during vital movement for cell, these variations are referred to as bioelectricity, and heart biology electricity is raw One kind of object electricity, heart is in each bounce, all along with bioelectric variation.It can capture heart hair by ECG sensor Electric signal out, obtains heart rate signal after digitized processing.

For another example, heart rate sensor 121 be PPG sensor, when detecting heart rate signal, it is contemplated that blood be it is red, Feux rouges is reflected, green light is absorbed, the blood to circulate at specific time wrist can be detected with combining with green LED and photosensitive photodiode Liquid measure obtains heart rate signal.In one example, the light that the light emission of green LED is reflected back to skin, through skin histology is by photosensitive biography Sensor receives and is converted into electric signal, using AD conversion at digital signal, obtains heart rate signal.

Rhythm of the heart client 122, the heart rate signal detected for handling heart rate sensor 121, in the related technology, rhythm of the heart visitor Heart rate signal can be presented in family end 122 in the form of numerical value or curve image, can also extract heart rate signal cardiac bounce interval Data, such as adjacent R peak or the interval data at adjacent pulse peak.It is then possible to by the heartbeat interval data of extraction, or with number Heart rate signal is presented in value or the form of curve image, is sent to Display processing module 123, is sent to display after carrying out display processing 124 display of screen, so that user observes whether heart rate signal has certain heart rhythm conditions.But the professional of doctor etc It determines whether that certain heart rhythm conditions occurs, needs to lead in conjunction with the display content of display screen 124 and the medical knowledge itself grasped Crossing feature extraction and comparing can just observe whether have certain heart rhythm conditions, and whole process is extremely complex, and professional Except user, no relevant medical knowledge, it is difficult to according to display screen 124 show content obtain whether have certain heart rhythm conditions hair It is raw.The embodiment of the present disclosure is directed to these problems, proposes a kind of prison that can be exported test object automatically and have target rhythm of the heart feature Control the rhythm of the heart monitoring method of result.

The rhythm of the heart monitoring method can be applied to rhythm of the heart detection device 120, first by measurand shorter first The rhythm and pace of moving things data of heart rate signal in period, obtain prosodic feature in short-term, have the target rhythm of the heart in the determining prosodic feature in short-term In the case where feature, then pass through the rhythm and pace of moving things data of heart rate signal of the measurand within longer second period, obtains the long time Feature is restrained, and when prosodic feature has target rhythm of the heart feature when determining described long, output measurand has target rhythm of the heart feature Monitored results.Automatic output measurand has the monitored results of target rhythm of the heart feature simultaneously, additionally it is possible to improve monitored results Accuracy and stability.

Here the monitored results exported, can be prosodic feature when determining described long has determining for target rhythm of the heart feature to tie Fruit, such as character information or audio: " prosodic feature has the target rhythm of the heart feature when long " or " measurand has target rhythm of the heart feature "； It can also be the mark of aforementioned definitive result, such as " 1 " indicates target rhythm of the heart feature, and " 0 " indicates no target rhythm of the heart feature.Prison Control result can export in many ways, to prompt measurand or other users, such as: it is output to rhythm of the heart detection device 120 Display screen shows, the audio frequency apparatus that can also be output to rhythm of the heart detection device 120 plays, and can also be output to association or binding Electronic equipment is shown or is played.

In addition, the rhythm of the heart monitoring method of the disclosure can also be applied to the other equipment in addition to rhythm of the heart detection device, specifically Figure 1B can be please referred to B refering to fig. 1, application scenarios shown in Figure 1B may include measurand 210, heart rate detection equipment 220 And electronic equipment 230, wherein measurand 210 can be in human body convenient for detection heart rate signal position, as chest, arm, Wrist etc., the attached drawing of the present embodiment are convenient for illustrating, by taking measurand is wrist as an example.

The composition of heart rate detection equipment 220 and function can be as described in the embodiments that Figure 1A is related to, can also basis Actual scene demand has other components and function, and details are not described herein.

Electronic equipment 230 can be personal computer, laptop computer, cellular phone, camera phone, smart phone, The combination of any several equipment in tablet computer, intelligent interaction device, smart home device etc. or these equipment；Also It can be the electrocardio monitoring device or other equipment for being used for electrocardio monitoring in medical field, herein with no restrictions.

In order to realize that the rhythm of the heart monitors, electronic equipment 230 be associated with or binds with heart rate detection equipment 220, be specifically associated with or Binding mode is referred to related art method, such as: for having the electronic equipment 230 and heart rate detection equipment of WIFI function For 220, the control instruction that user sends from 230 end of electronic equipment, Lai Zhihang can receive after being successfully accessed on router The movement of response.Alternatively, for security reasons, the user in heart rate detection equipment 220 and electronic equipment 230 is logged in account Number establish binding relationship.

In practical application, heart rate detection equipment 220 is after its heart rate sensor collects heart rate signal, Xiang Guanlian or binding Electronic equipment 230 send heart rate signal.

Electronic equipment 230 may include rhythm of the heart client 231, for handling heart rate signal, in the related technology, rhythm of the heart client Heart rate signal can be presented in end 231 in the form of numerical value or curve image, can also extract heart rate signal cardiac bounce space-number According to such as adjacent R peak or the interval data at adjacent pulse peak.It is then possible to by the heartbeat interval data of extraction, or with numerical value Or heart rate signal is presented in the form of curve image, is sent to Display processing module 232, is sent to display screen after carrying out display processing 233 displays, so that user observes whether heart rate signal has certain heart rhythm conditions.From the foregoing, it will be observed that the phase under this application scene There are still the problems under aforementioned applications scene for pass technology.The embodiment of the present disclosure is directed to these problems, and it is automatic defeated to propose a kind of energy Measurand has the rhythm of the heart monitoring method of the monitored results of target rhythm of the heart feature out.

The rhythm of the heart monitoring method can be applied to electronic equipment 320, believe for the heart rate that heart rate detection equipment 310 detects Number, pass through the rhythm and pace of moving things data of heart rate signal of the measurand within the first shorter period first, obtains prosodic feature in short-term, In the case that prosodic feature has target rhythm of the heart feature in short-term described in determining, then through measurand within longer second period The rhythm and pace of moving things data of heart rate signal, prosodic feature when obtaining long, and prosodic feature has target rhythm of the heart feature when determining described long In the case of, output measurand has the monitored results of target rhythm of the heart feature.Automatic output measurand has target rhythm of the heart feature While, additionally it is possible to improve the accuracy and stability of monitored results.

Here for monitored results as previously mentioned, details are not described herein, monitored results can be output to the aobvious of electronic equipment 230 Display screen shows that the audio frequency apparatus that can be output to electronic equipment 230 plays, and can also be output to the progress of rhythm of the heart detection device 220 Display plays.

In addition, the rhythm of the heart monitoring method of the disclosure can also be applied in addition to the electronic equipment of rhythm of the heart detection device, binding Other equipment, specifically can please refer to Fig. 1 C with C refering to fig. 1, application scenarios shown in Fig. 1 C may include measurand 310, Heart rate detection equipment 320, electronic equipment 330 and server 340, wherein measurand 310 can be in human body convenient for the detection heart The position of rate signal, such as chest, arm, wrist, the attached drawing of the present embodiment are convenient for illustrating, using measurand as wrist For.

The composition and function of heart rate detection equipment 320 and electronic equipment 330 are referred to what Figure 1A and Figure 1B was related to Embodiment can also have other components and function according to actual scene demand, and details are not described herein.

In order to realize that the rhythm of the heart monitors, electronic equipment 330 is associated with or binds with rhythm of the heart detection device 320, and server 340 passes through Wired or wireless network is connect with electronic equipment 330.

In practical application, heart rate detection equipment 320 is after its heart rate sensor collects heart rate signal, Xiang Guanlian or binding Electronic equipment 330 send heart rate signal.

Electronic equipment 330 may include rhythm of the heart client, and rhythm of the heart client can send heart rate signal to server 340, In the related technology, heart rate signal can be presented in server 340 in the form of numerical value or curve image, can also extract in heart rate signal Heartbeat interval data, such as adjacent R peak or the interval data at adjacent pulse peak.It is then possible to by between the heartbeat of extraction Every data, or heart rate signal is presented in the form of numerical value or curve image, is sent to electronic equipment 330, electronic equipment 330 carries out It is sent to display screen after display processing to show, so that user observes whether heart rate signal has certain heart rhythm conditions.It can from above Know, there are still the problems under aforementioned applications scene for the relevant technologies under this application scene.The embodiment of the present disclosure is directed to these problems, Propose a kind of rhythm of the heart monitoring method that can export monitored results of the measurand with target rhythm of the heart feature automatically.

The rhythm of the heart monitoring method can be applied to electronics server 340, detect for heart rate detection equipment 320 Heart rate signal passes through the rhythm and pace of moving things data of heart rate signal of the measurand within the first shorter period first, obtains the rhythm and pace of moving things in short-term Feature, determine it is described prosodic feature has target rhythm of the heart feature in short-term in the case where, then by measurand longer second The rhythm and pace of moving things data of heart rate signal in period, prosodic feature when obtaining long, and prosodic feature has the target heart when determining described long When restraining feature, output measurand has the monitored results of target rhythm of the heart feature.Automatic output measurand has the target rhythm of the heart special While sign, additionally it is possible to improve the accuracy and stability of monitored results.

Here for monitored results as previously mentioned, details are not described herein, monitored results can be output to electronic equipment 330, lead to Display screen is crossed show or play out by audio frequency apparatus.Rhythm of the heart detection device can also be output to by electronic equipment 320 are shown or are played.

The rhythm of the heart monitoring method that the lower disclosure described below proposes:

Fig. 2A is please referred to, Fig. 2A is a kind of disclosure process of rhythm of the heart monitoring method shown according to an exemplary embodiment Figure.

Rhythm of the heart monitoring method shown in Fig. 2A can be applied to application scenarios shown in Figure 1A to Fig. 1 C, including step 201-203:

Step S201, prosodic feature in short-term is obtained；The prosodic feature in short-term is the heart of the measurand within the first period The rhythm and pace of moving things data of rate signal.

Step S202, if it is determined that the prosodic feature in short-term contains target rhythm of the heart feature, prosodic feature when obtaining long；Institute Prosodic feature is the rhythm and pace of moving things data of heart rate signal of the measurand within the second period when stating long；Second period is longer than First period.What needs to be explained here is that the rhythm and pace of moving things and the rhythm and pace of moving things in short-term when long, do not have positive connection both on feature representation (the two can have different feature spaces), in one embodiment, the second period can not include first period.Another In embodiment, the second period may include first period.

Step S203, if it is determined that prosodic feature has the target rhythm of the heart feature when described long, output measurand has target The monitored results of rhythm of the heart feature.

The equipment of embodiment of the present disclosure application and the heart rate signal that is related to are referred to phase that Figure 1A to Fig. 1 C is related to inside the Pass Hold, details are not described herein.

Wherein, the first period and the second period can be in advance by the designer of disclosure scheme according to practical application scenes Application demand setting, for example, the first period can be to be any between 30 seconds, 60 seconds or 30 seconds to 60 seconds, the second period was 1 hour Or a few hours.

In practical application, in the heart rate signal that the disclosure can be detected or be acquired from heart rate detection equipment in real time, selection is worked as Heart rate before heart rate signal before the preceding time in the first period, or the newest detection of selection or acquisition time in the first period Then signal extracts prosodic feature in short-term from the heart rate signal of acquisition, prosodic feature can reflect in the first period in short-term for this The rhythm of measurand heartbeat can be by different type characteristic with the demand of application scenarios and the difference of heart rate signal It indicates.Current time mentioned herein can refer to the equipment for obtaining prosodic feature in short-term, when preparing to obtain prosodic feature in short-term Local system time.

For example, the corresponding heart rate signal of prosodic feature (i.e. heart rate signal in the first period) in short-term, is in the first period The ECG signal of real-time detection, in an example, monitoring requirement be not it is especially high, prosodic feature can be phase in heart rate signal in short-term The spacing at the adjacent peak R.The spacing at adjacent R peak mentioned herein can be the position spacing at adjacent R peak, and the peak position R is embodied between the used time When, spacing is the time difference.

In another example, in the high application scenarios of part monitoring requirement, the rhythm of the heart of the disclosure is monitored, in short-term prosodic feature May include the interval at each pair of adjacent R peak in heart rate signal, each pair of adjacent R peak interval first differential and each pair of adjacent R peak The histogram distribution of this three of the second-order differential at interval can obtain prosodic feature in short-term by following operation in some cases:

Obtain the spacing at each pair of adjacent R peak in the ECG signal.

Calculate the first differential and second-order differential at the interval at each pair of adjacent R peak.

The interval at each pair of adjacent R peak, the histogram distribution of the first differential and the second-order differential are counted respectively. Histogram distribution mentioned herein, a series of the case where data distribution being shown by height not equal longitudinal stripe or line segment form, It is also possible to a series of aforementioned height not fitting function of equal longitudinal stripe or line segment.

As shown in Figure 2 B, the heart rate signal of the first period real-time detection is ECG signal, and the peak R RI mark in fig. 2b is horizontal Coordinate is time t, and ordinate is signal strength.It, can be first from figure when obtaining the spacing at each pair of adjacent R peak in the ECG signal The peak R is extracted in the heart rate signal of 2B, the peak R extracted is as shown in Figure 2 C, then, calculates two peaks R of arbitrary neighborhood in Fig. 2 C Abscissa distance, the spacing at each pair of adjacent R peak in available ECG signal.

For another example, heart rate signal is the PPG signal of real-time detection in the first period, and in an example, monitoring requirement is not special Not high, the rhythm of the heart monitoring of the disclosure, prosodic feature can be the spacing at adjacent pulse peak in heart rate signal in short-term.

In another example, in the high application scenarios of part monitoring requirement, the rhythm of the heart of the disclosure is monitored, in short-term prosodic feature May include in heart rate signal each pair of adjacent pulse it is peak-to-peak away from first differential each sub-district of scatter plot number.

Under certain scenes, when detecting or acquiring rhythm signal, it may be breathed, be moved, Hz noise (50Hz), electronics The influence of the factors such as noise, on the collected ECG/PPG signal of institute can overlapped high-frequency sound and baseline drift disturbance, in order to improve prison Accuracy is controlled, needs to eliminate baseline drift and high-frequency noise.The disclosure can obtain in short-term before prosodic feature, from described the Baseline drift disturbance and high-frequency noise are eliminated in one period in the heart rate signal of measurand.In one example, baseline drift is eliminated Disturbance and high-frequency noise can carry out low-pass filtering to signal using a bigger window, obtain low-frequency component (base band letter Number), the baseband signal then is subtracted with original signal, just obtains the signal of baseline, on the signal for removing baseline, can be used Suitable window size carries out smoothly obtaining the signal that high frequency filter is made an uproar.

For aforementioned prosodic feature in short-term, the disclosure can in equipment applied by it, by operating procedure appropriate, Determine whether the prosodic feature in short-term has target prosodic feature.It is introduced by taking ECG signal as an example below several:

The first, prosodic feature is the spacing at adjacent R peak in heart rate signal in short-term, and the disclosure can compare any two pairs of phases The difference of the spacing at the adjacent peak R whether within a predetermined range, alternatively, in different cycles, the difference of the spacing at the adjacent R peak of corresponding position Within a predetermined range whether value, it is determined whether has periodically.

Second, prosodic feature is the spacing at adjacent R peak in heart rate signal in short-term, and the disclosure can be by each pair of adjacent R peak Spacing input trained model in advance and calculated, then determine whether that the target rhythm of the heart is special according to the calculated result of model Sign.Here model can be machine learning model, such as convolutional neural networks CNN model.

The third, prosodic feature includes the histogram distribution at the interval at each pair of adjacent R peak in heart rate signal, Mei Duixiang in short-term The histogram distribution and each pair of adjacent R of the first differential at the interval at the adjacent peak R it is peak-to-peak every second-order differential histogram distribution.

The embodiment of the present disclosure, can by the histogram distribution at the interval at each pair of adjacent R peak, the interval at each pair of adjacent R peak The histogram distribution of first differential and each pair of adjacent R it is peak-to-peak every second-order differential histogram distribution spliced after, obtain The feature of trained model in advance to be entered, then inputs trained model in advance, is determined according to the calculated result of model Whether target rhythm of the heart feature is had.Wherein, the abscissa of histogram distribution is data type, and ordinate is the distribution frequency of data (distribution situation), splicing mentioned herein can sequentially splice histogram, the sequence of splicing in abscissa direction in some cases It may be predetermined that as the histogram distribution at the interval for being predefined as each pair of adjacent R peak, the interval at each pair of adjacent R peak first differential Histogram distribution and each pair of adjacent R it is peak-to-peak every second-order differential histogram distribution；The model of input can be machine learning Model, such as convolutional neural networks CNN model.

In certain example, the feature spliced can quantify to 64 magnitudes, and the data size of trained model is 64x3x1 can be 31 layers of AlexNet network model as shown in Figure 2 D.

In other embodiments, the disclosure can also will in short-term prosodic feature be sent to its applied by equipment be associated with or In the equipment of binding, by operating procedure appropriate in the equipment for being associated with or binding, whether the prosodic feature in short-term is determined There is target prosodic feature, then receives the determination of the equipment return of association or binding as a result, such as referring to Fig.1 C.

In addition, getting the rhythm and pace of moving things in short-term when heart rate signal is the PPG signal or other signals of real-time detection in the first period After feature, when to be equally referred to rhythm signal be the ECG signal of real-time detection in first segment, it is determined whether have the target rhythm and pace of moving things special The mode of sign is determined, the difference is that, the model being related to may be different, can choose and practical application scene The model matched.

From the foregoing, it will be observed that the disclosure is in several ways, can determine whether prosodic feature contains target rhythm of the heart feature in short-term, Can be when prosodic feature in short-term contain target prosodic feature, directly determining measurand does not have target rhythm of the heart feature.In turn, It can not be further processed, alternatively, the monitored results that measurand does not have target rhythm of the heart feature can also be exported.

When prosodic feature in short-term contains target rhythm of the heart feature, the disclosure and indirect output measurand has the target rhythm of the heart The monitored results of feature, but need again by it is long when prosodic feature determine.

In practical application, the disclosure can choose for the second period in real time from the heart rate signal that heart rate detection equipment acquires Interior heart rate signal, prosodic feature when then extracting long from the heart rate signal of acquisition, prosodic feature can reflect when this is long The rhythm of measurand heartbeat in two periods.It, can be by different type with the demand of application scenarios and the difference of heart rate signal Characteristic indicates.Second period mentioned herein can be made of multiple first periods, for example, it may be before current time The second period, the current time refer to obtain it is long when prosodic feature equipment, prepare obtain it is long when prosodic feature when local System time；Second period was also possible to the second period before newest detection time or acquisition time；Second period can be with The second period before the end time for being the first period.

For example, the corresponding heart rate signal of prosodic feature (heart rate signal in the second period) when long, is in the second period The ECG signal of real-time detection, in an example, the monitoring disclosure require be not it is especially high, long prosodic feature can be heart rate signal The spacing at middle adjacent R peak.The spacing at adjacent R peak mentioned herein can be the position spacing at adjacent R peak, and the peak R is embodied between the used time When position, spacing is the time difference.

In another example, certain applications scene needs the rhythm of the heart of the high disclosure to monitor, and prosodic feature may include the heart when long The interval at each pair of adjacent R peak in rate signal, each pair of adjacent R peak interval first differential and each pair of adjacent R it is peak-to-peak every second order The histogram distribution of this three of differential.

For another example, heart rate signal is the PPG signal of real-time detection in the second period, in an example, monitoring disclosure requirement Be not it is especially high, prosodic feature can be the spacing at adjacent pulse peak in heart rate signal when long.

In another example, certain applications scene needs the rhythm of the heart of the high disclosure to monitor, and prosodic feature may include: the heart when long In rate signal each pair of adjacent pulse it is peak-to-peak away from first differential each sub-district of scatter plot number.In some cases, the disclosure can Prosodic feature when obtaining long by following operation:

Obtain the spacing at each pair of adjacent pulse peak in the PPG signal.

The first differential for calculating the spacing at each pair of adjacent pulse peak obtained is sample.

Calculated sample is marked in a manner of scatter plot.

Scatter plot is divided into the sub-district of predetermined number.Here predetermined number can be set according to actual application demand It sets, is such as set as 13.

The number of samples in each sub-district is accumulated, the prosodic feature when characteristic vector of predetermined dimension is described long is obtained.This In predetermined dimension it is consistent with predetermined number, be such as set as 13 dimensions.

PPG signal mentioned herein can be as shown in Figure 2 E, the position pair at the peak R of the position and ECG signal of pulse peak It answers, abscissa is time t, and ordinate is signal strength.Pulse peak is indicated by RI, can be the highest of signal in each period Peak.When obtaining the spacing at each pair of adjacent pulse peak in the PPG signal, pulse first can be extracted from the heart rate signal of Fig. 2 E Peak, the pulse peak extracted is as shown in Figure 2 F, then, calculates the abscissa distance of two pulse peaks of arbitrary neighborhood in Fig. 2 F, can To obtain the spacing at each pair of adjacent pulse peak in PPG signal.In turn, by the spacing available long time at each pair of adjacent pulse peak Restrain feature.

Under certain scenes, when detecting or acquiring rhythm signal, it may be breathed, be moved, Hz noise (50Hz), electronics The influence of the factors such as noise, on the collected ECG/PPG signal of institute can overlapped high-frequency sound and baseline drift disturbance, in order to improve prison Accuracy is controlled, needs to eliminate baseline drift and high-frequency noise.The disclosure, can be when obtaining long before prosodic feature, from described the Baseline drift disturbance and high-frequency noise are eliminated in two periods in the heart rate signal of measurand.

For it is aforementioned long when prosodic feature, the disclosure can in equipment applied by it, by operating procedure appropriate, The rhythm and pace of moving things is characterized in no thering is target prosodic feature when determining described long.It is introduced by taking PPG signal as an example below several:

The first, prosodic feature is the spacing at adjacent pulse peak in heart rate signal when long, and the disclosure can compare any two Whether within a predetermined range to the difference of the spacing at adjacent pulse peak, alternatively, in different cycles, the adjacent pulse peak of corresponding position Spacing difference whether within a predetermined range, it is determined whether have periodically.

Second, prosodic feature is the spacing at adjacent pulse peak in heart rate signal when long, and the disclosure can be by each to adjacent The spacing of pulse peak inputs trained model in advance and is calculated, and then determines whether target according to the calculated result of model Rhythm of the heart feature.Here model can be machine learning model, such as artificial neural network ANN model.

The third, when long prosodic feature include each pair of adjacent pulse it is peak-to-peak away from first differential each sub-district of scatter plot Number, the disclosure can by each pair of adjacent pulse it is peak-to-peak away from first differential each sub-district of scatter plot number, input in advance training Good model, determines whether target rhythm of the heart feature according to the calculated result of model.Here model can be machine learning model, Such as artificial neural network ANN model.

In certain example, trained model is artificial neural network ANN model shown in Fig. 2 G, including 64 implicit nodes, One neuron of each node on behalf, x1 to x13 represent the feature of input, and y1 or y2 are the model calculation.

In other embodiments, the disclosure can also when will be long prosodic feature be sent to its applied by equipment be associated with or In the equipment of binding, by operating procedure appropriate in the equipment for being associated with or binding, the rhythm and pace of moving things is characterized in no when determining described long There is target prosodic feature, then receives the determination of the equipment return of association or binding as a result, such as referring to Fig.1 C.

In addition, getting long Shi Jielv when heart rate signal is the ECG signal or other signals of real-time detection in the second period After feature, when to be equally referred to rhythm signal be the PPG signal of real-time detection in second segment, it is determined whether have the target rhythm and pace of moving things special The mode of sign is determined, the difference is that, the model being related to may be different, can choose and practical application scene The model matched.

In several ways, the rhythm and pace of moving things is characterized in no containing the target rhythm of the heart feature disclosure when can determine long, in the long time When rule feature contains target prosodic feature, directly determining measurand has target rhythm of the heart feature, and can export measurand has mesh The monitored results of rhythm of the heart feature are marked, the mode specifically exported is referred to the embodiment that Figure 1A to Fig. 1 C is related to, no longer superfluous herein It states.Above-mentioned target prosodic feature can be set according to actual application demand, such as set uneven prosodic feature, and one In example, at least partly interval disunity at adjacent R peak or the peak of pulse, and exceed scheduled range, it can indicate uneven Prosodic feature.For another example, neat prosodic feature.

As can be seen from the above embodiments, the rhythm and pace of moving things data of the heart rate signal by measurand within the first shorter period, Obtain prosodic feature in short-term, determine it is described prosodic feature has target rhythm of the heart feature in short-term in the case where, then by described tested The rhythm and pace of moving things data of heart rate signal of the object within longer second period, prosodic feature when obtaining long, and when determining described long When prosodic feature has target rhythm of the heart feature, output measurand has the monitored results of target rhythm of the heart feature.Compared to only passing through The heart rate signal of short period detection monitors whether that measurand has the mode of target rhythm of the heart feature, and the disclosure is used and supervised in short-term Control with it is long when the mode that cooperates of monitoring, can be by the monitored results of the rhythm and pace of moving things data in current short time interval, with the section in long duration The monitored results for restraining data combine, and obtain final monitored results, then export final monitored results, and the automatic measurand that exports has While target rhythm of the heart feature, additionally it is possible to improve the accuracy and stability of monitored results.

In turn, when prosodic feature does not contain target prosodic feature when long, can directly determine measurand does not have target Rhythm of the heart feature.In turn, it can not be further processed, alternatively, the prison that measurand does not have target rhythm of the heart feature can also be exported Control result.

In addition, under certain scenes, it is contemplated that the first period is shorter, and the second period is longer, is determining that prosodic feature contains in short-term Have or without containing after target prosodic feature, rhythm of the heart detection device acquires or the corresponding duration of heart rate signal of detection, less than second Period.The disclosure can repeatedly obtain prosodic feature in short-term and determine whether the rhythm and pace of moving things contains target prosodic feature in short-term.Adjacent two Secondary interval can be the first period, i.e., previous initial time and when being divided into first between previous initial time Section.

Under these scenes, it can check that the prosodic feature in short-term of the heart rate signal of several continuous first periods is determined Contain target prosodic feature.If it exceeds scheduled continuous number, such as scheduled continuous number are 2, tested pair can be determined As there is target rhythm of the heart feature, output measurand has the monitored results of target rhythm of the heart feature.Here the opportunity checked can be length When prosodic feature when not having target rhythm of the heart feature, or when determining that prosodic feature has target rhythm of the heart feature in short-term every time.Fig. 3 is shown A kind of rhythm of the heart monitoring method under these scenes, which may include step S301-305:

Step S301, multiple continuous first periods are directed to, obtain measurand respectively in wherein each first period The rhythm and pace of moving things data of heart rate signal obtain the prosodic feature in short-term of each first period.

Step S302, determine whether the prosodic feature in short-term of each first period contains target prosodic feature respectively.

Step S303, when the prosodic feature in short-term of any one the first period contains target prosodic feature, long Shi Jielv is obtained Feature；Prosodic feature is the rhythm and pace of moving things data of heart rate signal of the measurand within the second period when described long；Described second Period is longer than first period.

Step S304, when prosodic feature has the target rhythm of the heart feature when determining described long, output measurand has the target heart Restrain the monitored results of feature.

Step S305, if it is determined that prosodic feature does not have the target rhythm of the heart feature when described long, in continuous predetermined number the In the prosodic feature in short-term of one period, when containing target rhythm of the heart feature respectively, output measurand has target rhythm of the heart feature Monitored results.

The technology contents that the present embodiment is related to are corresponding to previous embodiment, and details are not described herein.

It for step S305, can be recorded according to determining for step 302, prosodic feature contains target rhythm of the heart spy to statistics in short-term The continuous number of first period of sign, the determining record may include: each first period, the heart rate signal in each first period Rhythm and pace of moving things data whether have the definitive result of target rhythm of the heart feature.

If the continuous number obtained is more than scheduled number threshold value (i.e. scheduled continuous number), measurand is exported Monitored results with target rhythm of the heart feature.Here number threshold value can be set according to actual application demand, such as be set as 2 It is a.

To sum up, the disclosure is if it is confirmed that the rhythm and pace of moving things data of the heart rate signal of continuous multiple first periods have target section respectively In the case where restraining feature, the rhythm and pace of moving things data of the heart rate signal of the second period do not have target prosodic feature, can be continuous first When the number of period is more than scheduled number threshold value, ignore the monitored results of the rhythm and pace of moving things data of the rhythm signal of the second period, it is defeated Measurand has the monitored results of target rhythm of the heart feature out, to prevent missing target rhythm of the heart feature.

By previous embodiment it is found that the heart rate signal of the first period can be ECG signal or PPG signal, the second period Heart rate signal may be ECG signal or PPG signal, specifically what kind of signal, mainly see what rhythm of the heart detection device contains The heart rate sensor of sample.Contain ECG signal sensor and PPG sensor simultaneously in rhythm of the heart detection device, the disclosure can be directed to The heart rate signal and the heart rate signal of the second period of the first period of signal acquisition acquired from same kind of sensor, can also be with The signal acquired from different types of sensor, obtains the heart rate signal and the heart rate signal of the second period of the first period respectively.

Below with the heart rate signal ECG signal of the first period, the heart rate signal of the second period is introduction for PPG signal A kind of rhythm of the heart monitoring method, is referred to Fig. 4, and rhythm of the heart monitoring method shown in Fig. 4 may include step S401-S403:

Step S401, it is special to obtain the rhythm and pace of moving things in short-term for the rhythm and pace of moving things data for obtaining ECG signal of the measurand within the first period Sign.

Step S402, if it is determined that prosodic feature contains target rhythm of the heart feature in short-term, measurand is obtained in the second period The rhythm and pace of moving things data of interior PPG signal, prosodic feature when obtaining long；Second period is longer than first period.

Step S403, if it is determined that prosodic feature has the target rhythm of the heart feature when described long, output measurand has target The monitored results of rhythm of the heart feature.

The technology contents that the embodiment of the present disclosure is related to are corresponding to previous embodiment, and details are not described herein.

It should be noted that, in order to improve monitoring accuracy, the rhythm and pace of moving things in short-term of the embodiment of the present disclosure is special under certain scenes Sign, may include the interval at each pair of adjacent R peak in heart rate signal, each pair of adjacent R peak interval first differential and each pair of adjacent R It is peak-to-peak every second-order differential this three histogram distribution.It, can be by each pair of adjacent R when determining whether containing target prosodic feature The interval at peak, each pair of adjacent R peak interval first differential and each pair of adjacent R it is peak-to-peak every second-order differential this three histogram After distribution is sequentially spliced, the feature of trained model in advance to be entered is obtained, then inputs preparatory trained 31 layers AlexNet network model.

The embodiment of the present disclosure it is long when prosodic feature, may include each pair of adjacent pulse it is peak-to-peak away from first differential in scatterplot Scheme the number of each sub-district.The disclosure can by each pair of adjacent pulse it is peak-to-peak away from first differential each sub-district of scatter plot number, Input trained artificial neural network ANN model in advance.In certain example, trained model is artificial neural network shown in Fig. 2 G Network ANN model, including 64 implicit nodes, one neuron of each node on behalf, x1 to x13 represent input feature, y1 or Y2 is the model calculation.

Corresponding with the embodiment of aforementioned rhythm of the heart monitoring method, the disclosure additionally provides rhythm of the heart monitoring device and its is applied Electronic equipment embodiment.

As shown in figure 5, Fig. 5 is a kind of disclosure block diagram of rhythm of the heart monitoring device shown according to an exemplary embodiment, Described device includes: that short feature obtains module 520, long feature obtains module 550 and result output module 580.

Wherein, short feature obtains module 520, is configured as: obtaining prosodic feature in short-term；The prosodic feature in short-term is quilt Survey the rhythm and pace of moving things data of heart rate signal of the object within the first period.

Long feature obtains module 550, is configured as: when the prosodic feature in short-term contains target rhythm of the heart feature, obtaining Prosodic feature when long；Prosodic feature is the rhythm and pace of moving things data of heart rate signal of the measurand within the second period when described long； Second period is longer than first period.

As a result output module 580 are configured as: when prosodic feature contains the target rhythm of the heart feature when described long, exporting quilt Survey the monitored results that object has target rhythm of the heart feature.

In one example, heart rate signal of the measurand within first period are as follows: in first period in real time The ECG signal of detection；

In another example, the target rhythm of the heart feature includes uneven rhythm of the heart feature.

As seen from the above-described embodiment, the rhythm and pace of moving things data of the heart rate signal by measurand within the first shorter period, Obtain prosodic feature in short-term, determine it is described prosodic feature has target rhythm of the heart feature in short-term in the case where, then by described tested The rhythm and pace of moving things data of heart rate signal of the object within longer second period, prosodic feature when obtaining long, and when determining described long When prosodic feature has target rhythm of the heart feature, output measurand has the monitored results of target rhythm of the heart feature.Compared to only passing through The heart rate signal of short period detection monitors whether that measurand has the mode of target rhythm of the heart feature, and the disclosure is used and supervised in short-term Control with it is long when the mode that cooperates of monitoring, can be by the monitored results of the rhythm and pace of moving things data in current short time interval, with the section in long duration The monitored results for restraining data combine, and obtain final monitored results, then export final monitored results, and the automatic measurand that exports has While target rhythm of the heart feature, additionally it is possible to improve the accuracy and stability of monitored results.

In turn, ECG signal and PPG signal can be merged very well to monitor the rhythm of the heart feature of measurand, from different dimensions pair The rhythm of the heart carries out joint-monitoring, further increases the reliability of rhythm of the heart monitoring.

In turn, the rhythm of the heart feature that can monitor cardiac arrhythmia monitors out the rhythm of the heart feature of cardiac arrhythmia, can be in certain journey User is improved on degree to be vigilant cardiac arrhythmia disease.Here disease can be such as atrial fibrillation.

As shown in fig. 6, Fig. 6 is the frame of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment Figure, on the basis of aforementioned embodiment illustrated in fig. 5, the short feature obtains module 520 and includes: the embodiment

Short feature acquisition submodule 521, is configured as: being directed to multiple continuous first periods, obtains respectively described tested Object obtains the prosodic feature in short-term of each first period in the rhythm and pace of moving things data of the wherein heart rate signal of each first period.

The rhythm of the heart monitoring device can also include that early warning enhances module 540, be configured as:

As seen from the above-described embodiment, if it is confirmed that the rhythm and pace of moving things data of the heart rate signal of continuous multiple first periods have respectively In the case where target prosodic feature, the rhythm and pace of moving things data of the heart rate signal of the second period do not have target prosodic feature, and the disclosure can To ignore the rhythm and pace of moving things data of the rhythm signal of the second period when the number of continuous first period is more than scheduled number threshold value Monitored results, output measurand has the monitored results of target rhythm of the heart feature, to prevent missing target rhythm of the heart feature.

As shown in fig. 7, Fig. 7 is the frame of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment Figure, on the basis of aforementioned embodiment illustrated in fig. 5, the short feature obtains module 520 and includes: the embodiment

First spacing obtains module 522, is configured as: obtaining the spacing at each pair of adjacent R peak in the ECG signal.

Differential calculation module 523, is configured as: calculating the first differential and second-order differential at the interval at each pair of adjacent R peak.

Statistics with histogram module 524, is configured as: counting the interval at each pair of adjacent R peak, the first differential respectively And the histogram distribution of the second-order differential.

As can be seen from the above embodiments, with the single order at the interval at adjacent R each pair of in ECG signal peak, the interval at each pair of adjacent R peak Differential and the histogram distribution counted, for prosodic feature in short-term, the rhythm and pace of moving things that can more preferably embody the rhythm signal of short time interval is special Sign, improves the accuracy and stability of monitored results.

As shown in figure 8, Fig. 8 is the frame of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment Figure, for the embodiment on the basis of aforementioned embodiment illustrated in fig. 7, rhythm of the heart monitoring device can also include short feature judgment module 530, it is configured as:

In one example, the model is 31 layers of AlexNet network model.

As can be seen from the above embodiments, the disclosure is with the interval at adjacent R each pair of in ECG signal peak, the interval at each pair of adjacent R peak First differential and the histogram distribution that counts for prosodic feature in short-term input trained model in advance, can be more rapidly Accurately obtain monitored results.

As shown in figure 9, Fig. 9 is the frame of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment Figure, on the basis of aforementioned embodiment illustrated in fig. 5, the long feature obtains module 550 and includes: the embodiment

Second spacing obtains module 551, is configured as: obtaining the spacing at each pair of adjacent pulse peak in the PPG signal；

Sample Calculation Block 552, is configured as: the first differential for calculating the spacing at each pair of adjacent pulse peak of acquisition is sample This；

Sample labeling module 553, is configured as: calculated sample is marked in a manner of scatter plot；

Sub-area division module 554, is configured as: scatter plot is divided into the sub-district of predetermined number；

Long characteristic determination module 555, is configured as: number of samples of the accumulation in each sub-district obtains the spy of predetermined dimension Levy prosodic feature when vector is described long.

As can be seen from the above embodiments, with each pair of adjacent pulse in PPG signal it is peak-to-peak away from first differential in each son of scatter plot The number in area, prosodic feature when being long can more preferably embody the prosodic feature of the rhythm signal of long duration, improve monitored results Accuracy and stability.

As shown in Figure 10, Figure 10 is the frame of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment Figure, on the basis of aforementioned embodiment illustrated in fig. 9, rhythm of the heart monitoring device can also include: the embodiment

Long feature judgment module 560, is configured as:

In one example, the model is ANN model.

As can be seen from the above embodiments, with each pair of adjacent pulse in PPG signal it is peak-to-peak away from first differential in each son of scatter plot The number in area, prosodic feature when being long, and will be long when prosodic feature input trained module, can more preferably embody long duration Rhythm signal prosodic feature, while improving the accuracy and stability of monitored results, improve rhythm of the heart monitoring efficiency.

As shown in figure 11, Figure 11 is the frame of the disclosure another rhythm of the heart monitoring device shown according to an exemplary embodiment Figure, on the basis of aforementioned embodiment illustrated in fig. 5, rhythm of the heart monitoring device can also include: the embodiment

First signal enhancing module 510, is configured as: before obtaining prosodic feature in short-term, the quilt out of described first period It surveys and eliminates baseline drift disturbance and high-frequency noise in the heart rate signal of object.

Second signal enhances module 540, is configured as: when obtaining long before prosodic feature, the quilt out of described second period It surveys and eliminates baseline drift disturbance and high-frequency noise in the heart rate signal of object.

As can be seen from the above embodiments, obtain in short-term prosodic feature and it is long when prosodic feature before, respectively from short time interval detect Heart rate signal and long duration detection heart rate signal in eliminate baseline drift disturbance and high-frequency noise, heart rate letter can be enhanced Number, improve the accuracy and stability of monitored results.

Correspondingly, the disclosure also provides a kind of electronic equipment, comprising:

Processor；

Memory for storage processor executable instruction；

Wherein, the processor is configured to executing the operation in rhythm of the heart monitoring method as described above.

The disclosure also provides a kind of computer readable storage medium, is stored thereon with computer program, when by one or more When a processor executes, so that processor executes the operation in method as described above.

The function of modules and the realization process of effect are specifically detailed in above-mentioned rhythm of the heart monitoring in above-mentioned rhythm of the heart monitoring device The realization process of step is corresponded in method, details are not described herein.

For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit The module of explanation may or may not be physically separated, and the component shown as module can be or can also be with It is not physical module, it can it is in one place, or may be distributed on multiple network modules.It can be according to actual The purpose for needing to select some or all of the modules therein to realize disclosure scheme.Those of ordinary skill in the art are not paying Out in the case where creative work, it can understand and implement.

Figure 12 is that a kind of structure of the electronic equipment of rhythm of the heart monitoring device application shown according to an exemplary embodiment is shown It is intended to.

As shown in figure 12, a kind of electronic equipment 1200 shown according to an exemplary embodiment, which can To be the intelligent wearable device of bracelet, wrist-watch, hand strap, armband, chest strap etc；It can also be the electricity of intelligent wearable device binding Sub- equipment, electronic equipment mentioned herein can be personal computer, laptop computer, cellular phone, camera phone, intelligence The group of any several equipment in phone, tablet computer, intelligent interaction device, smart home device etc. or these equipment It closes；It can also be the electrocardio monitoring device in medical field.

Referring to Fig.1 2, electronic equipment 1200 may include following one or more components: processing component 1201, memory 1202, power supply module 1203, multimedia component 1204, audio component 1205, the interface 1206 of input/output (I/O), sensor Component 1207 and communication component 1208.

The integrated operation of the usual control device 1200 of processing component 1201, such as with display, telephone call, data communication, Camera operation and record operate associated operation.Processing component 1201 may include one or more processors 1209 to execute Instruction, to perform all or part of the steps of the methods described above.In addition, processing component 1201 may include one or more moulds Block, convenient for the interaction between processing component 1201 and other components.For example, processing component 1201 may include multi-media module, To facilitate the interaction between multimedia component 1204 and processing component 1201.

Memory 1202 is configured as storing various types of data to support the operation in electronic equipment 1200.These numbers According to example include any application or method for being operated on electronic equipment 1200 instruction, contact data, electricity Talk about book data, message, picture, video etc..Memory 1202 can be by any kind of volatibility or non-volatile memory device Or their combination is realized, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or CD.

Power supply module 1203 provides electric power for the various assemblies of electronic equipment 1200.Power supply module 1203 may include power supply Management system, one or more power supplys and other generates, managees, and distributes associated group of electric power with for electronic equipment 1200 Part.

Multimedia component 1204 includes the screen of one output interface of offer between the electronic equipment 1200 and user Curtain.In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touching Panel, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touchings Sensor is touched to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or cunning The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments In, multimedia component 1204 includes a front camera and/or rear camera.When electronic equipment 1200 is in operation mould Formula, such as in a shooting mode or a video mode, front camera and/or rear camera can receive external multi-medium data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom energy Power.

Audio component 1205 is configured as output and/or input audio signal.For example, audio component 1205 includes a wheat Gram wind (MIC), when electronic equipment 1200 is in operation mode, when such as call mode, recording mode, and voice recognition mode, Mike Wind is configured as receiving external audio signal.The received audio signal can be further stored in memory 1202 or via Communication component 1208 is sent.In some embodiments, audio component 1205 further includes a loudspeaker, for exporting audio letter Number.

I/O interface 1202 provides interface, above-mentioned peripheral interface module between processing component 1201 and peripheral interface module It can be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and Locking press button.

Sensor module 1207 includes one or more sensors, for providing the shape of various aspects for electronic equipment 1200 State assessment.For example, sensor module 1207 can detecte the state that opens/closes of electronic equipment 1200, component it is relatively fixed Position, such as the component are the display and keypad of electronic equipment 1200, and sensor module 1207 can also detect electronics and set For 1200 or the position change of 1,200 1 components of electronic equipment, the existence or non-existence that user contacts with electronic equipment 1200, The temperature change in 1200 orientation of electronic equipment or acceleration/deceleration and electronic equipment 1200.Sensor module 1207 may include connecing Nearly sensor is configured to detect the presence of nearby objects without any physical contact.Sensor module 1207 is also It may include optical sensor, such as CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, should Sensor module 1207 can also include acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor, heart rate letter Number sensor or temperature sensor.

Communication component 1208 is configured to facilitate the logical of wired or wireless way between electronic equipment 1200 and other equipment Letter.Electronic equipment 1200 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.One In a exemplary embodiment, communication component 1208 via broadcast channel receive broadcast singal from external broadcasting management system or Broadcast related information.In one exemplary embodiment, the communication component 1208 further includes near-field communication (NFC) module, with Promote short range communication.For example, can be based on radio frequency identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology surpasses Broadband (UWB) technology, bluetooth (BT) technology and other technologies are realized.

In the exemplary embodiment, electronic equipment 1200 can by one or more application specific integrated circuit (ASIC), Digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field-programmable gate array It arranges (FPGA), controller, microcontroller, microprocessor or other electron component to realize, for executing the above method.

In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided It such as include the memory 1202 of instruction, above-metioned instruction can be executed by the processor 1209 of electronic equipment 1200 to complete above-mentioned side Method.For example, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic Band, floppy disk and optical data storage devices etc..

Wherein, when the instruction in the storage medium is executed by the processor, so that before device 1200 is able to carry out State rhythm of the heart monitoring method.

Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure Its embodiment.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following Claim is pointed out.

It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.

The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all essences in the disclosure Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of disclosure protection.

Claims

1. a kind of rhythm of the heart monitoring method characterized by comprising

Obtain prosodic feature in short-term；The prosodic feature in short-term is the rhythm and pace of moving things number of heart rate signal of the measurand within the first period According to；

If it is determined that the prosodic feature in short-term contains target rhythm of the heart feature, prosodic feature when obtaining long；The rhythm and pace of moving things is special when described long Sign is the rhythm and pace of moving things data of heart rate signal of the measurand within the second period；When second period is longer than described first Section；

If it is determined that prosodic feature contains the target rhythm of the heart feature when described long, output measurand has the prison of target rhythm of the heart feature Control result.

2. the method according to claim 1, wherein obtaining prosodic feature in short-term, comprising:

For multiple continuous first periods, the measurand is obtained respectively in the wherein heart rate signal of each first period Rhythm and pace of moving things data obtain the prosodic feature in short-term of each first period；

The method also includes following steps:

If in the prosodic feature in short-term of the first period of continuous predetermined number, containing target rhythm of the heart feature respectively, output is tested Object has the monitored results of target rhythm of the heart feature.

3. the method according to claim 1, wherein heart rate letter of the measurand within first period Number are as follows: the ECG signal of real-time detection in first period；

Heart rate signal of the measurand within second period are as follows: the PPG signal of real-time detection in second period.

4. according to the method described in claim 3, it is characterized in that, described obtain prosodic feature in short-term, comprising:

Obtain the spacing at each pair of adjacent R peak in the ECG signal；

5. according to the method described in claim 4, it is characterized in that, the method also includes:

According to the calculated result that the model exports, show whether the prosodic feature in short-term has determining for target rhythm of the heart feature to tie Fruit.

6. according to the method described in claim 5, it is characterized in that, the model is convolutional neural networks CNN model or 31 layers AlexNet network model.

7. according to the method described in claim 3, it is characterized in that, it is described obtain it is long when prosodic feature, comprising:

Obtain the spacing at each pair of adjacent pulse peak in the PPG signal；

Calculated sample is marked in a manner of scatter plot；

Scatter plot is divided into the sub-district of predetermined number；

8. the method according to the description of claim 7 is characterized in that the method also includes:

According to the calculated result that the model exports, the rhythm and pace of moving things is characterized in the no determining knot for having the target rhythm of the heart feature when obtaining described long Fruit.

9. according to the method described in claim 8, it is characterized in that, the model is ANN model.

10. the method according to claim 1, wherein the target rhythm of the heart feature includes uneven rhythm of the heart feature.

11. method according to any one of claim 1 to 10, which is characterized in that the described method includes:

Before obtaining prosodic feature in short-term, disturbed from baseline drift is eliminated in first period in the heart rate signal of measurand With high-frequency noise；

When obtaining long before prosodic feature, disturbed from baseline drift is eliminated in second period in the heart rate signal of measurand With high-frequency noise.

12. a kind of rhythm of the heart monitoring device characterized by comprising

Short feature obtains module, is configured as: obtaining prosodic feature in short-term；The prosodic feature in short-term is measurand first The rhythm and pace of moving things data of heart rate signal in period；

Long feature obtains module, is configured as: when prosodic feature contains target rhythm of the heart feature in short-term described in determining, obtaining the long time Restrain feature；Prosodic feature is the rhythm and pace of moving things data of heart rate signal of the measurand within the second period when described long；Described Two periods were longer than first period；

As a result output module is configured as: when prosodic feature contains the target rhythm of the heart feature when determining described long, exporting measurand Monitored results with target rhythm of the heart feature.

13. device according to claim 12, which is characterized in that the short feature obtains module, comprising:

Short feature acquisition submodule, is configured as: being directed to multiple continuous first periods, obtains the measurand respectively at it In each first period heart rate signal rhythm and pace of moving things data, obtain the prosodic feature in short-term of each first period；

In the prosodic feature in short-term of the first period of continuous predetermined number, when containing target rhythm of the heart feature respectively, output is tested Object has the monitored results of target rhythm of the heart feature.

14. device according to claim 12, which is characterized in that heart rate of the measurand within first period Signal are as follows: the ECG signal of real-time detection in first period；

15. device according to claim 14, which is characterized in that the short feature obtains module, comprising:

Statistics with histogram module, is configured as: counting the interval at each pair of adjacent R peak, the first differential and described respectively The histogram distribution of second-order differential.

16. device according to claim 15, which is characterized in that described device further includes short feature judgment module, is matched It is set to:

17. device according to claim 16, which is characterized in that the model is convolutional neural networks CNN model or 31 The AlexNet network model of layer.

18. device according to claim 14, which is characterized in that the long feature obtains module, comprising:

Long characteristic determination module, is configured as: number of samples of the accumulation in each sub-district, the characteristic vector for obtaining predetermined dimension are Prosodic feature when described long.

19. device according to claim 18, which is characterized in that described device further includes long feature judgment module, is matched It is set to:

20. device according to claim 19, which is characterized in that the model is ANN model.

21. device according to claim 12, which is characterized in that the target rhythm of the heart feature includes that the uneven rhythm of the heart is special Sign.

22. device described in any one of 2 to 21 according to claim 1, which is characterized in that described device includes:

First signal enhancing module, is configured as: before obtaining prosodic feature in short-term, the measurand out of described first period Baseline drift disturbance and high-frequency noise are eliminated in heart rate signal；

Second signal enhances module, is configured as: when obtaining long before prosodic feature, the measurand out of described second period Baseline drift disturbance and high-frequency noise are eliminated in heart rate signal.

23. a kind of electronic equipment characterized by comprising

Processor；

Memory for storage processor executable instruction；

Wherein, the processor is configured to executing such as the operation in claim 1 to 11 in any the method.

24. a kind of computer readable storage medium, which is characterized in that computer program is stored thereon with, when by one or more When processor executes, so that processor is executed such as the operation in any one of claims 1 to 11 the method.