WO2018137300A1 - 一种生理信号质量判断方法及装置 - Google Patents

一种生理信号质量判断方法及装置 Download PDF

Info

Publication number
WO2018137300A1
WO2018137300A1 PCT/CN2017/086393 CN2017086393W WO2018137300A1 WO 2018137300 A1 WO2018137300 A1 WO 2018137300A1 CN 2017086393 W CN2017086393 W CN 2017086393W WO 2018137300 A1 WO2018137300 A1 WO 2018137300A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
period
physiological
ith
cycle
Prior art date
Application number
PCT/CN2017/086393
Other languages
English (en)
French (fr)
Inventor
张�杰
陈文娟
董辰
朱萸
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN201780009418.0A priority Critical patent/CN108633249B/zh
Publication of WO2018137300A1 publication Critical patent/WO2018137300A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons

Definitions

  • Embodiments of the present invention relate to the field of wearable devices, and in particular, to a method and device for judging physiological signal quality.
  • wearable devices have been gradually applied to physiological monitoring of human bodies because of their non-invasive, simple and flexible characteristics.
  • Wearable devices can provide patients with low-load, non-contact, long-term continuous physiological monitoring, such as monitoring the body's electrocardiogram (ECG), pulse wave (Photoplethsmogram, PPG), breathing, blood pressure and other physiological signals.
  • ECG electrocardiogram
  • PPG pulse wave
  • the pulse wave is an abbreviation for electrical volume pulse wave tracing information.
  • the current wearable device acquires the physiological signal of the human body through the wearable sensor, and the wearable sensor is easily interfered by noise and motion artifacts, so that the acquired physiological signal and the human physiological information obtained based thereon deviate from the real situation. Therefore, before the physiological signal is obtained using the physiological signal, the signal quality of the physiological signal must be judged. Specifically, it is determined whether the physiological signal is a normal physiological signal or an abnormal physiological signal interfered by noise and motion artifacts.
  • the physiological signal quality of the human body such as electrocardiogram, pulse wave, respiration, blood pressure, etc.
  • a large number of feature values of the physiological signal are accurately acquired, that is, a plurality of feature points of the physiological signal are accurately extracted; thus, the physiological signal quality is determined according to the preset signal template and the plurality of accurate feature values.
  • the problem is that the above-mentioned preset signal template is usually obtained from a large number of offline physiological signals by using a machine learning algorithm or prior knowledge, and the offline physiological signal is deviated from the real-time acquired physiological signal, thereby The accuracy of the physiological signal quality judgment result obtained by the preset signal template needs to be improved.
  • the current wearable sensors are generally relatively simple, some features of the physiological signal, such as the beat pulse peaks, may not be extracted, that is, the above-mentioned large number of accurate feature values may not be obtained; thus, according to the above-mentioned The accuracy of the physiological signal quality judgment result obtained by the accurate eigenvalue needs to be improved, and the calculation amount in the process of judging the physiological signal quality is large.
  • the present application provides a physiological signal quality judgment method and device, which can improve the accuracy of the physiological signal quality judgment result and reduce the calculation amount in the physiological signal quality judgment process.
  • a physiological signal quality judging method comprises: collecting a physiological signal, wherein the physiological signal is a periodic signal or a periodic signal; and extracting a feature point of the physiological signal, the feature point includes a characteristic point of the physiological signal period; dividing the physiological signal according to a characteristic point of the physiological signal; determining a signal quality of the signal of the i-th period according to the similarity between the signal of the i-th period and the current set of signal templates;
  • the signal template set includes N signal templates, and the N signal templates are acquired according to a physiological signal before the signal of the ith period, where N is greater than or equal to 2, and i is greater than N.
  • each of the N signal templates in the current signal template set is a physiological signal of better quality. Therefore, if the similarity between the signal of the i-th cycle and the current set of signal templates is higher, the signal quality of the signal of the i-th cycle is better; the signal of the i-th cycle is between the current signal template set and the current signal template set. The lower the similarity, the worse the signal quality of the signal of the i-th cycle.
  • the current signal template set for judging the physiological signal quality is obtained according to the physiological signal acquired in real time, instead of using a machine learning algorithm or prior knowledge, from a large number. Obtained in the offline physiological signal; thus, the current signal template provided by the present application is more in line with the physiological signal acquired in real time, so that the accuracy of the physiological signal quality judgment result obtained according to the current signal template set is high.
  • determining the signal quality of the signal of the i-th cycle can determine whether the signal of the i-th cycle reaches the standard of the normal physiological signal, that is, whether the signal of the i-th cycle is a normal physiological signal or an abnormal physiological signal.
  • determining the signal quality of the signal of the ith period according to the similarity between the signal of the ith period and the set of signal templates may include: determining a similar result of the signal of the ith period, where the ith period is The similar result of the signal is used to indicate the similarity between the signal of the i-th cycle and the current set of signal templates; if the similar result of the signal of the i-th cycle satisfies the preset similar condition, the signal of the i-th cycle is judged to be normal.
  • the physiological signal, the preset similar condition is preset; if the similar result of the signal of the i-th cycle does not satisfy the preset similar condition, the signal of the i-th cycle is judged to be an abnormal physiological signal.
  • the similarity between the signal of the ith period and the current set of signal templates may be represented by a similarity parameter between a sample sequence of the signal of the ith period and a correlation coefficient, a mean square error, and the like of the sample sequence of the signal template.
  • the similar parameter of the signal of the i-th cycle is the correlation coefficient
  • the similarity parameter of the signal of the i-th cycle is larger, the similarity is higher, and the signal quality is better.
  • the smaller the similarity parameter of the signal of the i-th cycle the lower the similarity and the worse the signal quality.
  • the method may further include: according to the ith period
  • the signal updates the current set of signal templates. That is, if the signal quality of the signal of the i-th cycle is higher than the signal quality of at least one of the N signal templates in the current signal template set, the above method can replace the signal according to the signal of the i-th cycle.
  • the template updates the current set of signal templates.
  • the similar result of one of the N signal templates is obtained according to the physiological signal before the signal of the i-th cycle.
  • the current set of signal templates is continuously updated according to physiological signals acquired in real time.
  • the signal with relatively poor signal quality is replaced by a signal with a good signal quality period
  • the number template updates the current set of signal templates such that the signal quality of the signal templates in the current set of signal templates is increased in real time.
  • the accuracy of the physiological signal quality judgment result obtained according to the current real-time updated current signal template set is high.
  • the current signal template set may be updated according to the similar result of the signal of the ith period.
  • the updating the current signal template set according to the signal of the ith period may include: when determining that the similar result of the signal of the ith period is better than the similar result of the at least one signal template of the N signal templates: The i-cycle signal replaces the worst-performing signal template in the current set of signal templates.
  • the above “replace the signal template with the worst result of the current signal template in the current signal template set by using the signal of the ith period” may be replaced by replacing the similar result in the current signal template set with the signal of the ith period.
  • Signal template the similar result of the signal template with any similar similar results is worse than the similar result of the signal of the i-th cycle.
  • the method before determining the signal quality of the signal of the ith period according to the similarity between the signal of the ith period and the current set of signal templates, the method may further include: according to the ith period The physiological signal before the signal acquires the current set of signal templates.
  • the current signal template set may be a signal template set that has been updated.
  • the current signal template set may be a signal template set updated according to the signal of the i-1th period.
  • the current set of signal templates may be a set of signal templates that have not been updated.
  • the acquiring the current signal template set according to the physiological signal preceding the signal of the ith period may include: acquiring an initial signal template set according to the signal of the previous N+a periods; and according to the initial signal template set and The physiological signal between the signal of the N+ath cycle to the signal of the ith cycle acquires the current set of signal templates.
  • the initial signal template set is a signal template set that has not been updated.
  • the N signal templates in the initial signal template set are not necessarily normal physiological signals with good signal quality, but the physiological signal quality determining method may be performed as long as the initial signal template set includes N signal templates.
  • the method may obtain the current signal template set according to the initial signal template set and the physiological signal between the signal of the N+ath period and the signal of the ith period, and may also be based on the signal of the N+a period.
  • the similar result of the signal for each period between the signals of the i-th cycle determines the signal quality of the signal for each period.
  • the acquiring the initial signal template set according to the signal of the previous N+a periods may include: determining a similar result of the signal of each period in the signals of the previous N+a periods; a being greater than or equal to An integer of 0, N+a is less than i; wherein the similar result of the signal of one period in the signals of the first N+a periods is divided by the signal of the period and the signal of the previous N+a period except the signal of the period The similarity between the signals of other periods is composed; the signals of the first N periods with the best result of the previous N+a periods are determined as the initial signal template set.
  • the N signal templates in the initial signal template set are the signals of the first N periods.
  • the signals of the first N+a periods have a period of signals that are not the signal templates in the initial signal template set. It should be noted that the above N+a cycles are determined. After the similarity of the signals in each period of the signal, it is also possible to judge the signal quality of the signal of each of the signals of the previous N+a periods.
  • the extracting the feature point of the physiological signal may further include: acquiring the feature value of the signal of the i-th cycle according to the feature point of the physiological signal; determining the feature value of the signal of the i-th cycle is not Within the current preset threshold range, and determining that the signal of the i-th cycle is an abnormal physiological signal, the current preset threshold range is determined according to the signal of the period before the signal of the i-th cycle; the signal and signal according to the i-th cycle Before the similarity between the template sets determines the signal quality of the signal of the i-th cycle, the method may further include: determining that the feature value of the signal of the i-th cycle is within a current preset threshold range.
  • the physiological signal quality judging method provided by the present application can further improve the accuracy of the physiological signal quality judgment result.
  • the characteristic values of the signal of the i-th period include: a period value of the signal of the i-th period and/or The height value of the signal for the ith cycle.
  • the current preset threshold range may include: a current preset period range and/or a current preset height range.
  • the feature value of the signal of the ith period is not in the current preset threshold range, and the period value of the signal of the ith period is not in the current preset period range, and/or the height of the signal in the ith period.
  • the value is not within the current preset height range.
  • the eigenvalue of the signal of the ith period is in the current preset threshold range.
  • the period value of the signal of the ith period is in the current preset period range, and the height value of the signal of the ith period is in the current preset height range.
  • the method provided by the present application extracts the vertices and bottom points in the characteristic values of the physiological signals to determine the signal quality of the signals in each period of the physiological signal, and can reduce the process of judging the physiological signal quality to a certain extent. The amount of calculation in .
  • the method before the acquiring the feature value of the signal of the ith period according to the feature point of the physiological signal, the method may further include: determining, according to the signal of the period before the signal of the ith period, the current And the preset threshold range; after acquiring the feature value of the signal of the ith period according to the feature point of the physiological signal, the method further includes: updating the current preset threshold range according to the feature value of the signal of the ith period.
  • the current preset threshold range is continuously updated according to the physiological signal acquired in real time; therefore, the current preset threshold range is consistent with the physiological signal acquired in real time. Therefore, the physiological signal quality judging method provided by the present application can further improve the accuracy of the physiological signal quality judgment result.
  • the method may further include: outputting a signal quality judgment result, where the signal of the ith period is a normal physiological signal or the signal of the ith period is an abnormal physiological signal, and The signal of each cycle before the signal of the i-th cycle is a normal physiological signal or the signal of each cycle is an abnormal physiological signal.
  • the signal of the period is positive Normal physiological signal; if the similar result of the signal of one cycle before the signal of the i-th cycle does not satisfy the preset similar condition, the signal of the cycle is an abnormal physiological signal.
  • the physiological signal quality judging method can determine the signal quality of the collected physiological signals in real time and on a cycle-by-cycle basis, and accurately distinguish whether the signal of any one of the physiological signals is a normal physiological signal or Abnormal physiological signal. In this way, more accurate physiological information of the human body can be obtained according to the normal physiological signals obtained by the judgment. Moreover, the output signal quality judgment result makes the result more intuitively displayed to the user or related technical personnel to improve the user experience or meet the needs of relevant technicians.
  • a physiological signal quality judging device including: an acquisition module, an extraction module, a division module, and a determination module.
  • the acquisition module is configured to collect a physiological signal, and the physiological signal is a periodic signal or a periodic signal.
  • the extraction module is configured to extract feature points of the physiological signals collected by the collected module, and the feature points include feature points for indicating a period of the physiological signal.
  • the dividing module is configured to divide the physiological signal according to a feature point of the physiological signal extracted by the extraction module.
  • a determining module configured to determine a signal quality of the signal of the i-th period according to the similarity between the signal of the i-th cycle and the current set of signal templates; wherein the signal template set includes N signal templates, and the N signal templates are based The physiological signal before the signal of the i-th cycle acquired by the acquisition module is acquired, N is greater than or equal to 2, and i is greater than N.
  • the foregoing apparatus may further include: a determining module.
  • the determining module is configured to determine a similar result of the signal of the i th period divided by the dividing module, and the similar result of the signal of the i th period is used to indicate the similarity between the signal of the i th period and the current set of signal templates Sex.
  • the determining module is specifically configured to determine that the signal of the i-th cycle is a normal physiological signal if the similar result of the signal of the i-th cycle satisfies a preset similar condition, and the preset similar condition is preset; if the i-th cycle If the similar result of the signal does not satisfy the preset similar condition, the signal of the i-th cycle is judged to be an abnormal physiological signal.
  • the foregoing apparatus may further include: an update module.
  • the update module is configured to: when determining that the similar result of the signal of the i th period is better than the similar result of the at least one signal template of the N signal templates, update the current signal template set according to the signal of the i th period, where The similarity of one of the N signal templates is obtained based on the physiological signal before the signal of the i-th cycle.
  • the updating module is specifically configured to replace the signal template with the worst result in the current signal template set by using the signal of the ith period.
  • the foregoing apparatus may further include: an acquiring module.
  • the obtaining module is configured to: before the determining module determines the signal quality of the signal of the ith period according to the similarity between the signal of the ith period and the current set of signal templates, according to the ith period The physiological signal before the signal acquires the current set of signal templates.
  • the acquiring module is specifically configured to acquire an initial signal template set according to the signals of the first N+a periods; and according to the initial signal template set and the signal of the N+a period to the ith cycle The physiological signal between the signals acquires the current set of signal templates.
  • the foregoing determining module may also be used to determine the first N+a weeks.
  • the similarity of the signals in each period of the period signal; a is an integer greater than or equal to 0, and N+a is less than i; wherein the similar result of the signal of one period in the signals of the first N+a periods is the signal of the period It is composed of the similarity between the signals of the other periods except the signal of the period in the signals of the previous N+a periods.
  • the acquiring module is specifically configured to determine, as the initial signal template set, the signals of the first N periods with the best similar results among the signals of the previous N+a periods determined by the determining module.
  • the acquiring module may be further configured to: after the extracting module extracts the feature point of the physiological signal, acquire the feature value of the signal of the ith period according to the feature point of the physiological signal.
  • the determining module may be further configured to determine that the eigenvalue of the signal of the ith period is not within the current preset threshold, and determine that the signal of the ith period is an abnormal physiological signal, and the current preset threshold range is according to the ith period. Determining the signal of the period before the signal; determining the characteristic value of the signal of the i-th period before determining the signal quality of the signal of the i-th period based on the similarity between the signal of the i-th period and the current set of signal templates The current preset threshold range.
  • the characteristic value of the signal of the ith period includes: a period value of the signal of the ith period and/or a height value of the signal of the ith period.
  • the current preset threshold range may include: a current preset period range and/or a current preset height range.
  • the feature value of the signal of the ith period is not in the current preset threshold range, and may include: the period value of the signal of the ith period is not in the current preset period range, and/or the height value of the signal of the ith period is not at The current preset height range.
  • the eigenvalue of the signal of the ith period is in the current preset threshold range, and the period value of the signal of the ith period is in the current preset period range, and the height value of the signal of the ith period is in the current preset height range. .
  • the determining module may be further configured to: before the obtaining module acquires the feature value of the signal of the ith period according to the feature point of the physiological signal, according to the period before the signal of the ith period The signal determines the current preset threshold range.
  • the update module may be further configured to: after acquiring the feature value of the signal of the i-th cycle according to the feature point of the physiological signal, the update module updates the current preset threshold range according to the feature value of the signal of the i-th cycle.
  • the foregoing apparatus may further include: an output module.
  • the output module is configured to output a signal quality judgment result, and the signal quality judgment result comprises: the signal of the i-th cycle obtained by the judgment module is a normal physiological signal or the signal of the i-th cycle is an abnormal physiological signal, and the ith cycle The signal of each cycle before the signal is a normal physiological signal or the signal of each cycle is an abnormal physiological signal.
  • the signal of the period is judged to be a normal physiological signal; if the signal of the period of the period before the signal of the i-th period is similar If the result does not satisfy the preset similar condition, the signal of the period is judged to be an abnormal physiological signal.
  • a physiological signal quality judging device can include a processor, a memory, a display, an inputter, and a bus; the memory is configured to store the at least one instruction, the processor, the memory, the The display and the input device are coupled by the bus, and when the device is operative, the processor executes at least one instruction stored in the memory to cause the device to perform physiological signal quality determination as in the first aspect and various alternatives of the first aspect method.
  • a computer storage medium wherein at least one of the computer storage medium is stored And when the at least one instruction is run on the computer, causing the computer to perform the physiological signal quality determination method as in the first aspect and the various alternatives of the first aspect.
  • a computer program wherein at least one instruction is stored in the computing program product; and when the at least one instruction is run on a computer, causing the computer to perform the various alternatives as in the first aspect and the first aspect The physiological signal quality judgment method.
  • the processor in the third aspect of the present application may be the integration of the extraction module, the division module, the determination module, the determination module, the update module, and the acquisition module in the second aspect, and the processor may implement the The functions of the above various functional modules.
  • the processor may implement the The functions of the above various functional modules.
  • FIG. 1 is a schematic structural diagram of a wearable device according to an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of waveforms of a physiological signal according to an embodiment of the present invention
  • FIG. 3 is a schematic flowchart of a method for judging a physiological signal quality according to an embodiment of the present invention
  • FIG. 4 is a schematic diagram of waveforms of another physiological signal according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of waveforms of another physiological signal according to an embodiment of the present invention.
  • FIG. 6 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 7 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 8 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 9 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 10 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 11 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 12 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 13 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 14 is a schematic flowchart diagram of another method for judging physiological signal quality according to an embodiment of the present invention.
  • FIG. 15 is a schematic diagram of a possible composition of a physiological signal quality judging device according to an embodiment of the present invention.
  • FIG. 16 is a schematic diagram of another possible composition of a physiological signal quality judging device according to an embodiment of the present invention.
  • FIG. 17 is a schematic diagram of another possible composition of a physiological signal quality judging device according to an embodiment of the present invention.
  • FIG. 18 is a schematic diagram of another possible composition of a physiological signal quality judging device according to an embodiment of the present invention.
  • FIG. 19 is a schematic diagram of another possible composition of a physiological signal quality judging device according to an embodiment of the present invention.
  • FIG. 20 is a schematic diagram of another possible composition of a physiological signal quality judging device according to an embodiment of the present invention.
  • Embodiments of the present invention provide a method and device for judging physiological signal quality, which are applied to a process for obtaining physiological information of a human body according to physiological signals of a human body, and are specifically applied to determine the quality of the physiological signal before obtaining physiological information of the human body according to physiological signals of the human body.
  • the accuracy of the physiological signal quality judgment result can be improved, and the calculation amount in the physiological signal quality judgment process can be reduced.
  • the physiological signal quality judging method provided by the embodiment of the present invention may be a physiological signal having periodic or periodicity, such as a physiological signal having periodicity such as electrocardiogram, pulse wave, respiration, and blood pressure of the human body.
  • a physiological signal having periodicity such as electrocardiogram, pulse wave, respiration, and blood pressure of the human body.
  • the physiological signals all contain a large amount of physiological information of the human body, for example, the pulse wave signal of the human body may include physiological information such as heart rate, respiratory rate and blood oxygen of the human body.
  • the physiological signal quality determining method in addition to determining the signal quality of the physiological signal, can also determine other signal quality with periodic or periodic signals, such as in the step counting algorithm.
  • the acceleration signal is not limited in this embodiment of the present invention.
  • the physiological signal quality judging device may be a wearable device capable of acquiring a physiological signal of a human body.
  • the wearable device is a portable device that is directly worn on the user's body or integrated into the user's clothes or accessories, and most of the wearable devices have an intelligent system built in, which can connect the mobile phone and various terminals. It has one or more of the above functions such as photographing, GPS positioning, family calling, intelligent anti-lost, monitoring sleep, monitoring heart rate, running pace and so on.
  • Common wearable devices include smart wristbands supported by wrists, smart watches and other products, smart shoes, socks or other products worn on the legs supported by the feet, smart glasses, helmets and headbands supported by the head. And other products, as well as intelligent body temperature stickers, heart rate belts, smart clothing, school bags, crutches, accessories and other forms of products.
  • FIG. 1 is a schematic structural diagram of a wearable device according to an embodiment of the present invention.
  • the wearable device 10 may include one or more of the following components: a sensor component 101, a memory 102, and a processing component 103.
  • I/O input/output
  • sensor assembly 101 includes one or more sensors for providing state assessment of various aspects to wearable device 10.
  • the state change of each aspect provided by the wearable device 10 described above may be caused by an operation of a user who uses the wearable device 10 or caused by a change in physiological information of the user.
  • the sensor assembly 101 can detect the open/closed state of the wearable device 10, the relative positioning of the components.
  • the sensor assembly 101 can also detect a change in position of the wearable device 10 or one of the components, orientation of the wearable device 10 or acceleration/deceleration, and temperature changes of the wearable device 10.
  • Sensor assembly 101 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • the sensor component 101 may include a pulse sensor, such as an infrared pulse sensor, a heart rate pulse sensor, a photoelectric pulse sensor, a wrist pulse sensor, or a digital pulse sensor, for detecting a pulse wave of a user, so that a physiological rate such as a heart rate can be obtained. information.
  • the commonly used pulse sensor can be a PPG sensor.
  • the sensor assembly 101 can include a blood pressure sensor for detecting blood pressure of the human body.
  • sensor assembly 101 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • CMOS or CCD image sensor can be used to acquire a video signal of a bare portion of the skin such as a face or a hand of a human body.
  • the video signal may include multiple frames, each frame is a two-dimensional image, and the two-dimensional image is a red, green, and blue RGB image, and the RGB image may be divided into an R channel image, a G channel image, and a B channel image. Image, these three images can be used to extract the pulse wave signal of the human body.
  • the sensor assembly 101 can also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the memory 102 is configured to store various types of data to support operation at the wearable device 10. Examples of such data include instructions for any application or method operating on wearable device 10, contact data, phone book data, messages, pictures, videos, and human physiological information.
  • the memory 102 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Disk Disk or Optical Disk.
  • Processing component 103 typically controls the overall operation of wearable device 10, such as operations associated with displays, phone calls, data communications, camera operations, and recording operations, as well as processing signals or data acquired by sensors. Specifically, after the sensor component 101 detects and acquires the physiological signal, the processing component 103 can determine the quality of the physiological signal, and obtain the physiological signal as a normal physiological signal or the physiological signal is an abnormal physiological signal; thereby, obtaining the human body according to the normal physiological signal. Physiological information.
  • the processing component 103 can include one or more processors 1031 to execute the instructions.
  • processing component 103 can include one or more modules to facilitate interaction between component 103 and other components. For example, processing component 103 can include a multimedia module to facilitate interaction between multimedia component 104 and processing component 103.
  • the multimedia component 104 includes a screen that provides an output interface between the wearable device 10 and the user.
  • the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor described above may sense not only the boundary of the touch or slide action but also the duration and pressure associated with the touch or slide operation described above.
  • the multimedia component 104 includes a camera. When the wearable device 10 is in an operation mode, such as a shooting mode or a video mode, the camera can receive external multimedia data.
  • Each camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the video signal for obtaining the bare part of the skin such as the face and the hand of the human body can be transmitted by the above CMOS or CCD image sensor or the like.
  • the sensor acquisition it can also be obtained by the camera in the multimedia component 104, which is not limited by the embodiment of the present invention.
  • the audio component 105 is configured to output and/or input an audio signal.
  • the audio component 105 includes a microphone (MC) that is configured to receive an external audio signal when the wearable device 10 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal may be further stored in memory 102 or transmitted via communication component 108.
  • audio component 105 also includes a speaker for outputting an audio signal.
  • the audio component 105 can be used to output the physiological signal quality judgment result determined by the processing component 103, and output the physiological information of the human body obtained according to the physiological signal, such as the heart rate of the human body is 65 beats/min ( Beats per minute, bpm).
  • the I/O interface 106 provides an interface between the processing component 102 and the peripheral interface module, which may be a click wheel, a button, or the like. These buttons may include, but are not limited to, a home button, a start button, and a lock button. Specifically, in the implementation of the present invention, the home button in the I/O interface 106 can also be used to instruct the processing component 103 to start processing the physiological signals acquired by the sensor component 101.
  • Power component 107 provides power to various components of wearable device 10.
  • Power component 107 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for wearable device 10.
  • the communication component 108 can support wired or wireless communication between the wearable device 10 and other devices such that the wearable device 10 can access a wireless network based on a communication standard, such as WF, 2G or 3G, or a combination thereof.
  • the communication component 108 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
  • the communication component 108 described above also includes a near field communication (NFC) module to facilitate short range communication.
  • the NFC module can be implemented based on radio frequency identification (RFD) technology, infrared data association (rDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • rDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the communication component 108 can be configured to send the physiological signal quality judgment result determined by the processing component 103 to the other device, or send the physiological information of the human body obtained according to the physiological signal, for example, the heart rate of the human body is 65 bpm.
  • the wearable device may be implemented by one or more application specific integrated circuits (ASCs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), Programming gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation.
  • ASCs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA Programming gate array
  • controller microcontroller, microprocessor or other electronic component implementation.
  • non-transitory computer readable storage medium comprising instructions, such as a memory 102 comprising instructions executable by the processor 103 of the wearable device.
  • the non-transitory computer readable storage medium described above may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
  • the physiological signal judging device provided in the embodiment of the present invention may be a mobile phone, a personal computer (PC), a tablet computer, etc., which can acquire a physiological signal of a human body, in addition to the above-mentioned wearable device.
  • Terminal Equipment Terminal Equipment.
  • the embodiments of the present invention are exemplified below by using the above-mentioned physiological signal quality judging device as a wearable device as an example to describe the physiological mechanism provided by the embodiment of the present invention. Signal quality judgment method.
  • the physiological signal quality determination method provided by the embodiment of the present invention is described by taking the physiological signal as the pulse wave signal as an example.
  • FIG. 2 is a schematic diagram of a waveform of a physiological signal according to an embodiment of the present invention.
  • the waveform of the physiological signal shown in Fig. 2 is a segment of the pulse wave signal in an ideal case.
  • the signals for each cycle can have the same characteristics and feature points.
  • the signal of each period in the pulse wave signal includes the characteristics of rising branch, main peak, heavy beat wave, falling branch, and characteristic points such as vertex and bottom point.
  • variable of the abscissa t(s) in FIG. 2 is time t
  • the unit of time t is seconds (s)
  • variable of ordinate A (mv) is amplitude A
  • the unit of amplitude A is millivolts.
  • B 1 point, B 2 point, and B 3 point are three bottom points
  • C 1 point and C 2 point are two vertices.
  • the waveform between adjacent bottom points can be a one cycle signal.
  • the feature points that distinguish the period of the pulse wave signal in FIG. 2 may be other feature points such as vertices.
  • FIG 2 is a one-cycle signal (referred to as signal period 1); the period value of the signal period 1 can be recorded as T 1 .
  • the waveform between the bottom point B 2 and the bottom point B 3 is a signal of another period (referred to as signal period 2); the period value of the signal period 2 can be recorded as T 2 .
  • the periodic value of the normal pulse wave signal corresponds to a normal range of the human heart rate of 40 bpm to 180 bpm.
  • FIG 2 is a bottom waveform between point B to point F. 1 the main wave signal period 1, F 1 between the point in the end point of the waveform B 2 stroke cycle of the signal wave a weight of 1.
  • the bottom point B 1 is the starting point of the signal period 1.
  • the waveform between the bottom point B 1 and the vertex C 1 is the main wave rising branch of the signal period 1, the height value thereof can be written as H 1-1 , and the width value can be recorded as T 1-1 .
  • the waveform between the vertices C 1 to F 1 is the main wave falling branch of the signal period 1, the height value can be recorded as H 1-2 , and the width value can be recorded as T 1-2 .
  • G signal rising period of the dicrotic wave branching 1 which may be referred to as a height value H 1-3
  • width values can be written as T 1-3.
  • the peak at point G 1 is the peak of the beat wave of signal period 1.
  • B point 2 is the end point of signal period 1.
  • the period value T 1 of the signal period 1 is T 1-1 + T 1-2 + T 1-3 + T 1-4 .
  • the main wave rising branch of the signal period 1 from the bottom point B 1 to the vertex C 1 may also be referred to as a systolic wave of the signal period 1; the waveform of the vertex C 1 to the bottom point B 2 may also be referred to as a signal period 1 Diastolic wave. Therefore, the height value of the contraction wave of the signal period 1 is H 1-1 , and the height value of the diastolic wave of the signal period 1 can be written as H 1-5 .
  • the characteristics and characteristic points of the signals of other periods in the pulse wave signal are similar to those of the signal period 1, and will not be further described herein.
  • the area of the graph composed of the bottom point B 2 to E 2 of the signal period 2 and the coordinate axis t(s) can be written as S a ; the waveform between the E 2 point and the bottom point B 3 and the coordinate axis t ( s)
  • the area of the composed graph can be written as S b ; the area of the graph composed of the signal period 2 and the coordinate axis t(s) can be written as S, that is, the waveform between the bottom point B 2 and the bottom point B 3
  • the pulse wave signals acquired by the current wearable sensors often do not see features such as heavy beat waves and the peaks of the beat pulses. Feature point.
  • current wearable sensors generally have the bottom and apex of the pulse wave signal.
  • current wearable sensors can generally acquire vertices and bottom points of physiological signals other than pulse wave signals, and are not described here.
  • the physiological signal quality judging method provided by the embodiment of the present invention is described by taking the feature points of the physiological signal as the vertices and the bottom point as an example.
  • the physiological signals provided by the embodiments of the present invention are provided by the flowchart of the physiological signal quality judging method shown in FIG. 3 in conjunction with the wearable device 10 shown in FIG. The quality judgment method is described in detail.
  • the physiological signal quality determining method provided by the embodiment of the present invention may include S301-S304:
  • the wearable device collects a physiological signal, where the physiological signal is a periodic signal or a periodic signal.
  • the step 301 can be performed by the sensor component 101 in the wearable device 10 shown in FIG. 1, such as a PPG sensor.
  • the sensor component 101 can collect physiological signals at a fixed sampling frequency for a fixed duration (eg, 3 s), and the acquired physiological signals are a set of discrete samples.
  • sampling frequency does not affect the implementation of the purpose of the present application.
  • the sampling frequency is not specifically limited in the embodiment of the present invention, for example, may be 25-100 Hz.
  • the physiological signal may be preprocessed, such as filtering, to acquire a pulse wave signal, as shown in FIG. 4 , which is a preprocessed pulse wave signal.
  • the pre-processing process may be performed by a processor in the wearable device, or may be performed by a separate filtering component in the wearable device.
  • the filtering component may be a hardware-implemented filter, which is not limited by the embodiment of the present invention.
  • the wearable device extracts a feature point of the physiological signal, where the feature point includes a feature point for indicating the period of the physiological signal.
  • the feature point for indicating the period of the physiological signal may be a vertex and a bottom point of the physiological signal.
  • the feature point may also be a feature point other than a bottom point and a vertex in the physiological signal, such as a feature point where a beat wave peak of the pulse wave signal is located.
  • the waveform between adjacent bottom points may be one cycle, or the waveform between adjacent vertices may be one cycle; and the wearable device is The signal quality of the physiological signal is determined on a cycle-by-cycle basis. Therefore, the method provided by the embodiment of the present invention may further include S303:
  • the wearable device divides the physiological signal according to a feature point of the physiological signal.
  • FIG. 5 it is a waveform diagram of a physiological signal provided by an embodiment of the present invention.
  • Figure 5 shows the bottom point and apex of the wearable device extracted by the wearable sensor for the pulse wave signal shown in Figure 4. Subsequently, the wearable device can divide the waveforms between adjacent bottom points as in Fig. 5, and record the signals of each period in chronological order, that is, record the sequence of samples of the signals of each period.
  • the sample sequence x 1 of the signal of the 1st cycle may include n samples, n being a positive integer;
  • x 1_j is the jth sample in the sample sequence x 1 of the signal of the 1st cycle.
  • the wearable device acquires the signal of any period after the signal of the first period the sample sequence of the signal of the period may also be recorded, and the sample sequence of the signal of the period may also include n samples.
  • the sampling frequency provided in the embodiment of the present invention is 100 Hz
  • the time interval between two samples in the sample sequence of the signal of each period acquired by the wearable device may be 0.01 s. 3 and FIG. 5
  • the time T 1 of the signal of the first period shown in FIG. 5 may be 0.3 s
  • the waveform of the signal of the first period may include 30 points. That is, 30 samples may be included in the sample sequence of the signal of the first period.
  • the wearable device determines a signal quality of the signal of the i-th period according to the similarity between the signal of the i-th cycle and the current set of signal templates.
  • the above steps 302-304 can all be performed by the processing component 102 in the wearable device 10 shown in FIG. 1.
  • the current set of signal templates includes N signal templates, and the N signal templates can be acquired according to physiological signals preceding the signal of the i-th cycle, where N is greater than or equal to 2, and i is greater than N. That is to say, the above N signal templates may be N signals of the signals of the first period to the signals of the i-1th period, and the N signal templates are acquired by the wearable device in real time.
  • the similarity between the signal of the ith cycle and the current set of signal templates is composed of the similarity between the signal of the ith cycle and each of the N signal templates included in the current set of signal templates.
  • the similarity between the signals of every two cycles in the signal of the period acquired by the wearable device can be used to indicate the degree of similarity of the waveforms of the signals of the two periods. For example, the higher the similarity between the signals of the two periods, the higher the degree of similarity of the waveforms of the signals representing the two periods; the lower the similarity between the signals of the two periods, the signals representing the two periods The lower the similarity of the waveform.
  • the similarity between the signal and the current set of signal templates is higher.
  • each of the N signal templates in the current signal template set is a physiological signal of better quality. Therefore, if the similarity between the signal of the i-th cycle and the current set of signal templates is higher, the signal quality of the signal of the i-th cycle is better; the signal of the i-th cycle is between the current signal template set and the current signal template set. The lower the similarity, the worse the signal quality of the signal of the i-th cycle.
  • the signal of the i-th cycle may also be simply referred to as x i .
  • the sample sequence x i of the signal of the i-th cycle includes n samples
  • x i_j is the j-th sample in the sample sequence x i of the signal of the i-th cycle.
  • the wearable device may have recorded a sample sequence of signals for each of the first i-1 cycles of the signal before the wearable device acquires the signal for the ith cycle.
  • the sample sequence x i-1 of the signal of the i-1th period may also include n samples, and x i-1_j is the jth sample in the sample sequence x i-1 of the signal of the i-1th period.
  • the current signal template set for determining the physiological signal quality is obtained by the wearable device according to the physiological signal acquired in real time, instead of using a machine learning algorithm or Obtaining knowledge, obtained from a large number of offline physiological signals; thus, the current signal template provided by the embodiment of the present invention more closely matches the physiological signal acquired by the wearable device in real time, so that the physiological signal quality judgment result obtained according to the current signal template set is High accuracy.
  • the wearable device since the wearable device extracts the vertices and the bottom point in the physiological signal after obtaining the physiological signal, the wearable device can support the wearable device to determine the physiological signal quality, and does not necessarily need to extract the vertices and the bottom point in the physiological signal. There are a large number of other feature points to support the wearable device to judge the physiological signal quality; therefore, the amount of calculation in the process of determining the physiological signal quality of the wearable device can be reduced, and the accuracy of the physiological signal quality judgment result can be further improved.
  • the wearable device determines the signal quality of the signal of the ith period according to the similarity between the signal of the ith period and the current set of signal templates, and can determine the ith period. Whether the signal is a normal physiological signal or an abnormal physiological signal.
  • S304 in the physiological signal quality determining method provided by the embodiment of the present invention may include S601-S603 or S601, S602, and S604.
  • FIG. 6 it is a schematic flowchart of another physiological signal quality determining method according to an embodiment of the present invention.
  • S304 shown in FIG. 3 may include S601-S603 or S601, S602, S604:
  • the wearable device determines a similar result of the signal of the i th period, where the similarity result of the signal of the i th period is used to indicate the similarity between the signal of the i th period and the current set of signal templates.
  • the similarity between the signals of every two cycles in the periodic signal acquired by the wearable device may be represented by a similar coefficient such as a correlation coefficient or a mean square error of the sample sequence of the signals of the two cycles. That is to say, the similarity between the signal of the i-th cycle and the current set of signal templates may be similar parameters such as the correlation coefficient of the sample sequence of the signal of the i-th cycle and the sample sequence of a signal template, the mean square error, and the like. composition.
  • the similarity between the signal of the ith cycle and the current set of signal templates can be represented by similar parameters of the signal of the ith cycle.
  • the similar result of the signal of the ith cycle described above may be a similar parameter of the signal of the ith cycle.
  • the similar parameter of the signal of the ith period may be the sum of the signal of the ith period and the similar parameter of each of the current N signal templates, or the signal of the ith period and the current N signals.
  • the y t is a sample sequence of the tth signal template in the current N signal templates.
  • the sample sequence y t of the t-th signal template may also include n samples, and y t_j is the j-th sample in the sample sequence y t of the t-th signal template.
  • the wearable device can record the signal of the i-th cycle and the similar parameter of the t-th signal template of the current N signal templates as r i_t .
  • the similarity parameter r i_t of the signal of the i-th cycle can be recorded as:
  • any one of the current signal template sets y is a one-cycle signal.
  • the first signal template y 1 may be the signal x 1 of the first period.
  • a signal template and periodic signals corresponding to the signal template are respectively represented by different characters.
  • the similarity between two cycles of signals is represented by the correlation coefficients of the sample sequences of the signals of the two cycles: the signal of the ith cycle and the tth signal of the current N signal templates
  • the similarity parameter r i_t of the template is the correlation coefficient between the sample sequence x i of the signal of the i-th cycle and the sample sequence y t of the t-th signal template of the current N signal templates.
  • the similar parameter r i_t of the signal of the i th period and the t signal template of the current N signal templates may be:
  • the similar parameter r i_t of the signal of the i-th period and the t-th signal template of the current N signal templates may also be:
  • the similarity parameter r i_t is larger, the similarity between the signal of the i-th cycle and the t-th signal template of the current N signal templates is higher; and further, the i-th cycle obtained according to the similar parameter r i_t.
  • the larger the similarity parameter r i of the signal the better the similar result of the signal of the i-th cycle, and the better the signal quality of the signal of the i-th cycle.
  • the similarity parameter r i_t is smaller, the similarity between the signal of the i-th cycle and the t-th signal template of the current N signal templates is lower; and further, the signal of the i-th cycle obtained according to the similar parameter r i_t.
  • the smaller the similarity parameter r i is the worse the similar result of the signal of the i-th cycle is, and the worse the signal quality of the signal of the i-th cycle is.
  • the similarity between the signals of the two cycles is represented by the mean square error of the sample sequence of the signals of the two cycles: the signal of the ith cycle and the current N signal templates
  • the similarity parameter r i_t of the t-th signal template is the mean square error of the sample sequence x i of the signal of the i-th cycle and the sample sequence y t of the t-th signal template of the current N signal templates.
  • the mean square error mse i_t (ie, the similar parameter r i_t ) of the signal of the i-th period and the t-th signal template of the current N signal templates may be:
  • a i_j is the j-th sample of the sample sequence a i obtained by normalizing the sample sequence x i of the signal of the i-th cycle
  • the sample sequence y t of the t-th signal template obtained by b i_j is normalized The j-th sample of the sample sequence b t .
  • the difference from the correlation coefficient is that if the mean square error of the sample sequence of the signals of the two periods is smaller, the similarity between the signals of the two periods is higher; otherwise, between the signals of the two periods The lower the similarity. Therefore, in the case where the similarity parameter r i_t is the mean square error mse i_t , if the similarity parameter r i_t is smaller, the similarity between the signal of the i-th cycle and the t-th signal template of the current N signal templates is Higher; further, the smaller the similarity parameter r i of the signal of the i-th cycle obtained according to the similar parameter r i_t is, the better the similar result of the signal of the i-th cycle is, and the better the signal quality of the signal of the i-th cycle is.
  • the similarity parameter r i_t is larger, the similarity between the signal of the i-th cycle and the t-th signal template of the current N signal templates is lower; and further, the signal of the i-th cycle obtained according to the similar parameter r i_t The larger the similarity parameter r i is, the worse the similar result of the signal of the i-th cycle is, and the worse the signal quality of the signal of the i-th cycle is.
  • the similarity between the signals of the two periods is represented by the correlation coefficient of the sequence of the signal samples of the two periods, and the method for judging the physiological signal quality provided by the embodiment of the present invention is described.
  • the wearable device determines the signal quality of the signal of the ith period according to the similar result of the signal of the ith period, and specifically, the wearable device determines whether the signal of the ith period is a normal physiological signal or an abnormal physiological signal.
  • the wearable device determines whether the similar result of the signal of the i-th cycle satisfies a preset similar condition.
  • the preset similar condition may be preset by the wearable device before executing S602.
  • the preset similar condition may be used to indicate whether the signal of each period in the physiological signal acquired by the wearable device is a normal physiological signal.
  • the similar parameters of the signals of the two periods may have a value range of [0, 1].
  • the similarity parameter of the signal of two periods is greater than or equal to 0.8, it indicates that the similarity between the signals of the two periods is higher; if the similarity parameter of the signal of the two periods is less than 0.8, then The similarity between the signals of these two periods is low. If the similarity parameter of the two-cycle signal is equal to 0, then there is no similarity between the signals of the two cycles. If the similarity parameter of the two-cycle signal is equal to 1, it means that the signals of the two cycles are completely similar.
  • the similar condition satisfying the preset may be whether the similar parameter of the signal of the i-th cycle is greater than or equal to 0.8 ⁇ N. If the similarity parameter of the signal of the i-th cycle is the mean between the signal of the i-th cycle and the similarity parameter of each of the current N signal templates, is the similar result of the signal of the "i-th cycle" The similar condition satisfying the preset" may be whether the similar parameter of the signal of the i-th cycle is greater than or equal to 0.8.
  • the wearable device determines that the signal of the i-th cycle is a normal physiological signal.
  • the wearable device can mark the signal of the i-th cycle as a normal physiological signal, and obtain human physiological information according to the signal of the i-th cycle.
  • the wearable device determines that the signal of the i-th cycle is an abnormal physiological signal.
  • the wearable device can mark the signal of the i-th cycle as an abnormal physiological signal, and does not use the signal of the i-th cycle in determining the physiological information of the human body.
  • the wearable device determines that the similar result of the signal of the i-th cycle is better than the similar result of the at least one signal template of the current N signal templates, the wearable device can update the current set of signal templates.
  • the above method may further include S701 after the above S603 or S604.
  • FIG. 7 is a schematic flowchart of another physiological signal quality judging method provided by an embodiment of the present invention.
  • the above method may further include S701:
  • the wearable device updates the current signal template set according to the signal of the ith cycle.
  • the above step 701 can be performed by the processing component 102 in the wearable device 10 shown in FIG.
  • the wearable device can update the current signal according to the signal of the i-th cycle. Template collection.
  • the current set of signal templates is continuously updated by the wearable device according to the physiological signals acquired in real time.
  • the signal quality of the signal template in the current signal template set is improved in real time because the wearable device updates the current signal template set according to the signal with a relatively good signal quality and replaces the signal template with relatively poor signal quality.
  • the accuracy of the physiological signal quality judgment result obtained according to the current real-time updated current signal template set is high.
  • the signal for updating one cycle of the current signal template set is a normal physiological signal with better signal quality; of course, it may also be an abnormal physiological signal with better signal quality.
  • the update of the current signal template by the abnormal physiological signal usually occurs during several update processes after the wearable device obtains the unupdated signal template set.
  • S701 may specifically include S801-S802.
  • FIG. 8 it is a schematic flowchart of another physiological signal quality determining method according to an embodiment of the present invention.
  • S701 in FIG. 7 may specifically include S801-S802:
  • the wearable device determines that the similar result of the signal of the i-th cycle is better than the similar result of the at least one signal template of the current N signal templates.
  • the signal quality of the signal of the i-th cycle is higher than the signal quality of at least one of the current N signal templates.
  • the wearable device replaces the signal template with the worst result in the current signal template set by using the signal of the ith period.
  • the wearable device replaces the signal template with the worst result in the current signal template set by using the signal of the ith period, so that the wearable device removes the signal template with the worst result from the current signal template set, and uses similar
  • the resulting ith cycle of the signal updates the current set of signal templates as a new signal template.
  • a similar result of one of the N signal templates in the current set of signal templates can be derived from the physiological signal preceding the signal of the ith cycle.
  • the above “the wearable device replaces the worst-case signal template in the current signal template set by using the signal of the ith cycle” may be replaced by the wearable device replacing the current signal template set with the signal of the ith cycle.
  • a signal template with a similarly poor result may be replaced by the wearable device replacing the current signal template set with the signal of the ith cycle.
  • the wearable device may also acquire the current signal template before determining the signal quality of the signal of the ith period according to the similarity between the signal of the ith period and the current set of signal templates.
  • the method for judging the physiological signal quality provided by the embodiment of the present invention may further include S901 before the foregoing S304 or S601.
  • FIG. 9 is a schematic flowchart of another physiological signal quality determining method according to an embodiment of the present invention.
  • S901 may be further included:
  • the wearable device acquires a current signal template set according to a physiological signal before the signal of the i-th cycle.
  • the above step 901 can be performed by the processing component 102 in the wearable device 10 shown in FIG.
  • the current set of signal templates may be a set of signal templates that have been updated by the wearable device.
  • the current set of signal templates may be a set of signal templates that have been updated by the wearable device according to the signal of the i-1th cycle.
  • the current set of signal templates may be a set of signal templates that are not updated by the wearable device, and the current set of signal templates is a set of initial signal templates acquired by the wearable device.
  • the wearable device may further acquire an initial signal template set that has not been updated before acquiring the current signal template set according to the physiological signal before the signal of the ith period.
  • FIG. 10 it is a schematic flowchart of another physiological signal quality judging method provided by an embodiment of the present invention.
  • the method shown in FIG. 9 may further include S1001 before S901:
  • the wearable device acquires an initial signal template set according to a signal of a previous N+a period.
  • the above step 1001 can be performed by the processing component 102 in the wearable device 10 shown in FIG.
  • N+a is less than i, such as N+a is less than or equal to i-1.
  • the above a is an integer greater than or equal to zero.
  • S1001 in the foregoing method may specifically include S1101-S1102.
  • S1001 in the method shown in FIG. 10 may specifically include S1101-S1102:
  • the wearable device determines the similarity of signals in each of the signals of the previous N+a periods.
  • the similar result of the signal of one cycle of the signals of the preceding N+a periods is the similarity between the signal of the period and the signals of the period other than the signal of the previous N+a period.
  • Sexual composition The similarity between the signals of the two periods in the signals of the first N+a periods may also be represented by similar parameters of the signals of the two periods, and the similar parameters may also be samples of the signals of the two periods.
  • the correlation coefficient between the sequences Thus, a similar result of a signal of one cycle in the signals of the first N+a cycles can be represented by similar parameters of the signals of the cycle.
  • the wearable device can also record a sample sequence of signals for each of the first N+a cycles of the signal.
  • a similar result of the signal of the first period acquired by the wearable device is taken as an example to illustrate the similar result of the signal of one period in the signal of the previous N+a period: the similar result of the signal of the first period Can be represented by similar parameters of the signal of the 1st cycle.
  • the wearable device can record the similarity parameter of the signal of the first cycle as r 1 .
  • the wearable device can record the similar parameters of the signal of the first period and the signal of the second period as r 1_2 , and the similar parameter r 1_2 can be the sample sequence x 1 and the second period of the signal of the first period.
  • the wearable device can record the similar parameters of the signal of the first period and the signal of the third period as r 1_3 , and the similar parameter r 1_3 can be the sample sequence of the signal of the first period x 1 and the signal of the third period The correlation coefficient of the sample sequence x 3 .
  • the wearable device can record the similar parameters of the signal of the first period and the signal of the N+a- 1th period as r 1_N+a-1 , and the similar parameter r 1_N+a-1 can be the signal of the first period.
  • the wearable device may record the similar parameter of the signal of the first period and the signal of the N+a period as r 1_N+a , and the similar parameter r 1_N+a may be the sample sequence x 1 of the signal of the first period and Correlation coefficient of the sample sequence x N+a of the signal of the N+ath cycle.
  • the similarity parameter r 1 of the signal of the first period may be other than the signal of the first period and the signal of the first period of the signal of the first period and the first period of the previous period.
  • the sum of the similar parameters of the signals of other periods; or the similar parameters of the signals of the first period may be other than the signals of the first period and the signals of the first period of the signals of the first period and the first period of the first period.
  • the mean between similar parameters of the signals of other cycles. That is, the similar parameter of the signal of the first cycle may be
  • r 1 r 1_2 +r 1_3 +...+r 1_N +r 1_N+1 , or,
  • the similar parameter of the signal of the first period may be the period of the signal of the first period and the period of the signal of the first N+a period other than the signal of the first period.
  • the mean between similar parameters of the signal. That is, the similar parameter of the signal of the first cycle may be
  • the similar parameter r 1_2 of the signal of the first period and the signal of the second period may be
  • the similar parameter r 1_2 of the signal of the first period and the signal of the second period may also be:
  • the wearable device determines the similar result of the signal of each period in the signals of the previous N+a periods, that is, after obtaining the similar parameters of the signals of each period in the signals of the previous N+a periods, It is possible to judge the signal quality of the signal of each of the signals of the previous N+a periods. Specifically, for each of the signals in the first N+a period of the signal: if the similar result of the periodic signal satisfies the preset similar condition, the wearable device determines that the signal of the period is a normal physiological signal; The similar result of the signal does not satisfy the preset similar condition, and the wearable device judges that the signal of the cycle is an abnormal physiological signal.
  • the wearable device can obtain the initial signal template including the N signal templates from the signals of the previous N+a periods while determining the signal quality of the signal of each period in the signals of the previous N+a periods. set.
  • the foregoing method further includes S1102:
  • the wearable device determines, as the initial signal template set, a signal of a first N period of the best result of the previous N+a periods of the signal.
  • the above step 1102 can be performed by the processing component 102 in the wearable device 10 shown in FIG.
  • the N signal templates in the initial signal template set are signals of the first N cycles acquired by the wearable device.
  • the signal of the first N+a periods acquired by the wearable device has a signal of a period is not the signal template in the initial signal template set.
  • the current signal template set may also be determined when receiving the signal of each period after the signal of the N+a period.
  • the current signal template set may be an initial signal template set that has not been updated by the wearable device, or the current signal template set may be a signal template set obtained after the wearable device updates the initial signal template set.
  • S901 can be replaced by S1002:
  • the wearable device according to the initial signal template set and the signal of the N+a period to the ith
  • the physiological signal between the signals of the cycles acquires the current set of signal templates.
  • step 1002 can also be performed by the processing component 102 in the wearable device 10 shown in FIG. 1.
  • the current signal template set when the wearable device acquires the signal of the i th period is the initial signal template set that is not updated by the wearable device.
  • the current signal template set is the initial signal template set that is not updated by the wearable device; or the current signal template set is The wearable device updates the set of signal templates obtained by the initial signal template set according to the physiological signal between the signal of the N+ath period and the signal of the ith period.
  • the wearable device replaces the signal template with the worst result in the initial signal template set in the initial signal template set using the signal of the i-1th cycle. Then, when the wearable device acquires the signal of the ith period, the current signal template set is a signal template set obtained by replacing the signal template with the worst result in the initial signal template set by using the signal of the i-1th period.
  • the above “the wearable device replaces the worst-case signal template in the initial signal template set by using the signal of the i-1th period” may be replaced by the wearable device replacing the foregoing by using the signal of the i-1th period.
  • the wearable device acquires the initial set of signal templates from the signals of the first 6 cycles.
  • the similar parameter r 1 of the signal of the first period is equal to 0.7
  • the similar parameter r 2 of the signal of the second period is equal to 0.75
  • the similar parameter r 3 of the signal of the third period is equal to 0.8
  • the signal of the fourth period The similarity parameter r 4 is equal to 0.85
  • the similarity parameter r 5 of the signal of the 5th cycle is equal to 0.85
  • the similarity parameter r 6 of the signal of the 6th cycle is equal to 0.9.
  • the five signal templates in the initial signal template set acquired by the wearable device may be the signal of the second period, the signal of the third period, the signal of the fourth period, the signal of the fifth period, and the first 6 cycles of the signal.
  • the N signal templates in the initial signal template set obtained by the wearable device are not necessarily normal physiological signals with good signal quality, but the initial signal template set includes N signal templates to support the wearable device to perform the present invention.
  • the physiological signal quality judging method provided by the embodiment. As the number of cycles in the physiological signal acquired by the wearable device increases, the current set of signal templates can be continuously updated so that the signal quality of any of the current signal template sets can be improved. That is, the N signal templates in the current signal template set updated by the wearable device are generally normal physiological signals with good signal quality. Thereby, the accuracy of the physiological signal quality judgment result obtained by the wearable device according to the current signal template set is high.
  • the wearable device when the wearable device acquires the current signal template set according to the initial signal template set and the signal of the period between the signal of the N+ath period and the signal of the ith period, the N+a may also be determined. A similar result of the signal of each period between the signals of the period to the signal of the ith period.
  • the wearable device can obtain a similar parameter of the signal of each period between the signal of the N+ath period and the signal of the ith period to determine the signal of the N+ath period to the signal of the ith period. The signal quality of the signal between each cycle.
  • the wearable device determines the signal of the period It is a normal physiological signal; if the similar result of the periodic signal does not satisfy the preset similar condition, the wearable device judges that the signal of the cycle is an abnormal physiological signal.
  • the signals of each period in the physiological signals acquired by the wearable device may have the same feature points. Therefore, the wearable device can also determine the signal quality of the physiological signal according to the feature value corresponding to the feature point of the physiological signal.
  • the foregoing S303 may further include S1201, S1202, and S1203.
  • FIG. 12 it is a schematic flowchart of another physiological signal quality judging method provided by an embodiment of the present invention.
  • S1201 in FIG. 3 may further include S1201, S1202, and S1203:
  • the wearable device acquires the feature value of the signal of the i-th cycle according to the feature point of the physiological signal.
  • the wearable device can acquire the period value of the signal of each period and the height value of the signal of each period according to the vertices and the bottom point of the signal of each period in the physiological signal. Therefore, the characteristic value of the signal of the i-th period includes the period value of the signal of the i-th period and/or the height value of the signal of the ith period.
  • the height value of the signal of the ith period may include a left branch height value of the signal of the ith period and a right branch height value of the signal of the ith period.
  • the period value of the signal of each period may be a time interval between two adjacent bottom points in the signal of the period; the height value of the signal of each period may be a vertex to two bottoms of the signal of the period The magnitude of each bottom point in the point.
  • the wearable device can acquire a physiological signal every 3 s to obtain a waveform of a physiological signal.
  • the wearable device can record the period value of the signal of the ith cycle as T i .
  • the wearable device can obtain the period value of the signal of each period according to the number of points included in the signal of each period in the physiological signal and the time interval between the two points, such as the period value T i of the signal of the ith period. For example, in the case where the sampling frequency is 100 Hz, the time interval between every two discretes in the physiological signal waveform shown in FIG. 5 may be 0.01 s.
  • the waveform of the signal of the first period shown in FIG. 5 may include 30 points, and the period value T 1 of the signal of the first period may be 0.3 s.
  • the wearable device may determine the current preset threshold range according to the signal of the period before the signal of the ith period. Specifically, the wearable device may obtain an initial preset threshold range according to an average value of characteristic values of signals of all periods in a set of physiological signals acquired for the first time. Then, the wearable device may update the initial preset threshold range according to the feature values of the physiological signals of all the cycles acquired subsequently to obtain the current preset period value range. Illustrative, the mean of the current period value The current preset period value range may be
  • the average value of the current left branch height value of the physiological signal acquired by the wearable device can be recorded as The mean value of the current right branch height value can be written as
  • the current preset left height value range of the physiological signal acquired by the wearable device may be
  • the current preset left branch height value range can be
  • the preset threshold range obtained by the wearable device according to the average value of the acquired feature values of the physiological signals is not unique, and may be adjusted by the relevant technical personnel according to actual conditions.
  • the wearable device determines that the feature value of the signal of the i-th cycle is not within the current preset threshold, and determines that the signal of the i-th cycle is an abnormal physiological signal.
  • the eigenvalue of the signal of the ith period is not in the current preset threshold range, and includes: the period value of the signal of the ith period is not in the current preset period range, and/or the height of the signal of the ith period The value is not within the current preset height range.
  • the value range of the period value T i of the signal of the i-th period is not at At the time, the signal of the i-th cycle is an abnormal physiological signal.
  • the wearable device may determine the i-th of the feature value of the signal of the i-th cycle.
  • the signal of one cycle may be a normal physiological signal.
  • the foregoing method may further include S1203 before S304:
  • the wearable device determines that the feature value of the signal of the ith cycle is within a current preset threshold range.
  • the above steps 1201-1203 can all be performed by the processing component 102 in the wearable device 10 shown in FIG. 1.
  • the eigenvalue of the signal of the ith period is in the current preset threshold range
  • the period value of the signal of the ith period is in the current preset period range
  • the height value of the signal in the ith period is at the current preset. Height range.
  • the period value T i of the signal of the ith cycle is The left branch height value of the signal in the inner and the ith cycle is Inside, and the right branch height of the signal of the ith cycle is Within, the signal of the ith cycle may be a normal physiological signal.
  • the wearable device can determine each week in the physiological signal according to the period value and the height value in the characteristic value of the physiological signal.
  • the signal quality of the signal can be judged by the wearable device to extract the characteristic point of the physiological signal, and the calculation amount in the process of judging the physiological signal quality can be reduced to some extent.
  • the wearable device can determine the current preset threshold range according to the physiological signal before the signal of the i-th cycle. Specifically, the wearable device may obtain an initial preset threshold range according to an average value of characteristic values of signals of all periods in a set of physiological signals acquired for the first time. Then, the wearable device may update the initial preset threshold range according to the feature value of the signals of all the cycles in the subsequently acquired physiological signal to obtain the current preset threshold range. Therefore, in another possible implementation manner, the method provided by the embodiment of the present invention may further include S1301 and S1302 after S303. Illustratively, as shown in FIG. 13 , it is a schematic flowchart of another physiological signal quality determining method according to an embodiment of the present invention. S1301 and S1302 may also be included after S303 in FIG. 13:
  • the wearable device determines a current preset threshold range according to the physiological signal before the signal of the i-th cycle.
  • the wearable device may determine the current preset threshold range according to the signal of the period before the signal of the ith period. Specifically, the wearable device may obtain an initial preset period value range according to an average value of period values of signals of all periods in a set of physiological signals acquired for the first time. Exemplarily, the wearable device can obtain an initial preset period value range according to an average value of period values of signals of all periods in the physiological signal acquired in the first 3 seconds. Then, the wearable device may update the initial preset period value range according to the period value of the physiological signal acquired every 3 s time interval before the signal of the ith period of the ith period to obtain the current preset period value range.
  • the wearable device can obtain an initial preset left support height value range and an initial preset left support height value range according to the mean value of the height values of the signals of all the cycles in the first set of physiological signals acquired. Then, the wearable device may update the preset left support height value range and the initial preset left support height value range according to the height value of the subsequently acquired physiological signal to obtain the current preset left support height value range and the current preset left support height range. Range of values.
  • the wearable device can obtain an initial preset left-branch range and an initial right-branch height range according to the mean value of the height values of the signals of all the periods in the physiological signal acquired in the first 3 seconds. Subsequently, the wearable device may update the initial preset left-branch value range and the initial right-branch height value range according to the height values of the signals of all the periods in the physiological signals acquired every 3 s intervals before the signal of the subsequent i-th cycle.
  • the range of the preset preset value range is obtained by the current preset left branch value range and the current preset right branch height value range.
  • the wearable device may update the current preset period value range according to the period value of all periods of the physiological signals acquired every 3 s intervals after the signal of the i-th period to obtain a new current preset period. Range of values.
  • the foregoing method may further include S1302 after S1203:
  • the wearable device updates the current preset threshold range according to the feature value of the signal of the i-th cycle.
  • the above steps 1301-1302 can all be performed by the processing component 102 in the wearable device 10 shown in FIG. 1.
  • the current preset threshold range is continuously updated according to the physiological signal acquired in real time; and the current preset threshold range is a physiological signal obtained by the wearable device according to the acquired
  • the current preset threshold range is obtained according to the global variable; therefore, the current preset threshold range is consistent with the physiological signal acquired by the wearable device in real time. Therefore, the physiological signal quality judging method provided by the embodiment of the invention can further improve the accuracy of the physiological signal quality judgment result.
  • the wearable device may acquire the physiological information of the human body using the determined normal physiological signal.
  • the foregoing method may further include S1401.
  • FIG. 14 is a schematic flowchart of another physiological signal quality determining method according to an embodiment of the present invention. S1401 may also be included after S304 in FIG. 14:
  • step 1401 can be performed by the processing component 102 in the wearable device 10 shown in FIG. 1 through the multimedia component 104.
  • the signal quality judgment result includes that the signal of the i-th cycle is a normal physiological signal or an abnormal physiological signal, and the signal of each period before the signal of the i-th cycle is a normal physiological signal or an abnormal physiological signal.
  • the wearable device can perform different markings for the normal physiological signal and the abnormal physiological signal, and can also output the proportion of the normal physiological signals in the signals of all the cycles in the acquired physiological signals, which is not limited by the embodiment of the present invention. . In this way, the physiological signal quality judgment result judged by the wearable device can be displayed to the user or the related technical personnel relatively intuitively, so that the user experience is better.
  • the wearable device can judge the signal quality of the collected physiological signal in real time and on a cycle-by-cycle basis, and accurately distinguish any cycle of the physiological signal. Whether the signal is a normal physiological signal or an abnormal physiological signal. In this way, the wearable device can obtain more accurate physiological information of the human body according to the normal physiological signals obtained by the judgment.
  • the physiological signal quality judging device includes a hardware structure and/or a software module corresponding to each function in order to implement the above functions.
  • the present invention can be implemented in a combination of hardware or hardware and computer software in combination with the algorithm steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.
  • the embodiment of the present invention may divide the function module by the physiological signal quality judging device according to the above method example.
  • each function module may be divided according to each function, or two or more functions may be integrated into one processing module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of the module in the embodiment of the present invention is schematic, and is only a logical function division, and the actual implementation may have another division manner.
  • FIG. 15 is a schematic diagram showing a possible composition of the physiological signal quality judging device provided in the above embodiment.
  • the physiological signal quality judging device 15 may be configured.
  • the method includes an acquisition module 151, an extraction module 152, a division module 153, and a determination module 154.
  • the acquisition module 151 is configured to support the physiological signal quality judging device 15 to execute S301 in the above embodiment, and/or other processes for the techniques described herein.
  • the extraction module 152 is configured to support the physiological signal quality judging device 15 to perform S302 in the above embodiments, and/or other processes for the techniques described herein.
  • the dividing module 153 is configured to support the physiological signal quality judging device 15 to execute S303 in the above embodiment, and/or other processes for the techniques described herein.
  • the judging module 154 is configured to support the physiological signal quality judging device 15 to execute S304, S602, S603, S604, and S1202 in the above embodiments, and/or other processes for the techniques described herein.
  • FIG. 16 shows another possible composition diagram of the physiological signal quality judging device provided in the above embodiment.
  • the physiological signal quality judging device 15 may further include: a determining module 155.
  • the determining module 155 is configured to support the physiological signal quality judging device 15 to perform S601 and S1301 in the above embodiments, and/or other processes for the techniques described herein.
  • FIG. 17 shows another possible composition diagram of the physiological signal quality judging device provided in the above embodiment.
  • the physiological signal quality judging device 15 may further include an updating module 156.
  • the update module 156 is configured to support the physiological signal quality judging device 15 to perform S701, S801, S802, and S1302 in the above embodiments, and/or other processes for the techniques described herein.
  • FIG. 18 shows another possible composition diagram of the physiological signal quality judging device provided in the above embodiment.
  • the physiological signal quality judging device 15 may further include: an obtaining module 157.
  • the obtaining module 157 is configured to support the physiological signal quality judging device 15 to execute S901, S1001, S1002, S1102, S1102, S1201 and S1202 and S1203 in the above embodiments, and/or other processes for the techniques described herein.
  • FIG. 19 shows another possible composition diagram of the physiological signal quality judging device provided in the above embodiment.
  • the physiological signal quality judging device 15 may further include an output module 158.
  • the output module 158 is configured to support the physiological signal quality judging device 15 to perform S1401 in the above embodiment, and/or other processes for the techniques described herein.
  • the physiological signal quality judging device provided by the embodiment of the present invention is configured to perform the above physiological signal quality judging method, and thus can achieve the same effect as the above physiological signal quality judging method.
  • the above-mentioned extraction module 152, division module 153, determination module 154, determination module 155, update module 156, acquisition module 157, and the like can be integrated into one processing module.
  • the processing module may be a processor or a controller, such as a CPU, a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), and a field programmable gate array. (Field Programmable Gate Array, FPGA) or other programmable logic device, transistor logic Pieces, hardware components, or any combination thereof. It is possible to implement or carry out the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processing unit described above may also be a combination of computing functions, such as one or more microprocessor combinations, a combination of a DSP and a microprocessor, and the like.
  • the storage module can be a memory.
  • the above acquisition module 151 can be implemented by an input device.
  • the output module 158 described above can be implemented by a display.
  • the embodiment of the present invention provides a physiological signal quality determining apparatus 20 as shown in FIG.
  • the physiological signal quality judging device 20 includes a processor 201, a memory 222, a display 203, an inputter 204, and a bus 205.
  • the processor 201, the memory 202, the display 203, and the inputter 204 are connected to one another via a bus 205.
  • the bus 205 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the bus 205 can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in FIG. 20, but it does not mean that there is only one bus or one type of bus.
  • the input device 204 described above may include a camera and a wearable sensor or the like, such as the sensor assembly 101 in the wearable device 10.
  • the display 203 described above may be the multimedia component 104 or the audio component 105 in the wearable device 10.
  • each module in the physiological signal quality judging device 20 provided by the embodiment of the present invention and the technical effects of each module performing the related method steps in the foregoing embodiments may refer to the related description in the method embodiment of the present invention. , will not repeat them here.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used. Combinations can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one single unit. Yuanzhong.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a stand-alone computer program product, can be stored in a computer readable storage medium.
  • the technical solution of the present application can be implemented in whole or in part in the form of a computer program product when implemented using software.
  • the computer program product includes at least one instruction.
  • the instructions When the instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present invention are generated in whole or in part.
  • the computer can be a computer, a special purpose computer, a computer network, or other programmable device.
  • the instructions may be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer may be passed from a website site, computer, server or data center Axle cable, optical fiber, digital subscriber line (DSL) and other wired methods, or infrared, wireless, microwave, etc.
  • DSL digital subscriber line
  • the computer readable medium can be any available media that can be accessed by a computer or a data storage device such as a server, data center, or the like that includes one or more available media.
  • the usable medium may be a magnetic medium such as a floppy disk, a hard disk, or a magnetic tape, or a semiconductor medium such as a solid state disk (SSD).

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

一种生理信号质量判断方法及装置，涉及可穿戴设备领域，可以提供生理信号质量判断结果的准确性，并减小生理信号质量判断过程中的计算量。具体方案为：S301、采集生理信号，该生理信号为周期信号或类周期信号；S302、提取生理信号的特征点，该特征点包括用于指示该生理信号周期的特征点；S303、根据生理信号的特征点，对该生理信号划分周期；S304、根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量；其中，信号模板集合包括N个信号模板，N个信号模板根据第i个周期的信号之前的生理信号获取，N大于等于2，i大于等于N。该方法及装置用于根据人体的生理信号得到人体生理信息之前、判断该生理信号质量的过程中。

Description

一种生理信号质量判断方法及装置
本申请要求于2017年01月25日提交中国专利局、申请号为201710061354.0、发明名称为“极低资源消耗的实时生理信号质量判断方法和系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明实施例涉及可穿戴设备领域，尤其涉及一种生理信号质量判断方法及装置。
背景技术
近年来，可穿戴设备以其无创、简单和灵活的特点，逐渐被应用于人体的生理监测中。可穿戴设备能够为病人提供低负荷、非接触、长期连续的生理监测，如监测人体的心电(electrocardiogram，ECG)、脉搏波(Photoplethsmogram，PPG)、呼吸、血压等生理信号。其中，脉搏波为电容积脉搏波描记信息的简称。当前可穿戴设备是通过穿戴式传感器获取人体的生理信号的，而穿戴式传感器容易受到噪声及运动伪迹的干扰，使得获取的生理信号和基于此得到的人体生理信息偏离真实情况。从而，在使用生理信号得到人体生理信息之前，必须判断该生理信号的信号质量。具体为，判断上述生理信号是正常生理信号还是受到噪声及运动伪迹干扰的异常生理信号。
现有技术中，在判断获取的人体心电、脉搏波、呼吸、血压等生理信号质量之前，通常需要预先设置用于判断上述生理信号质量的信号模板；并且，在获取上述生理信号的过程中，通常需要精确获取到该生理信号的大量特征值，即精确提取该生理信号的大量特征点；从而，根据上述预先设置的信号模板和上述大量精确的特征值，判断生理信号质量。
存在问题是，上述预先设置的信号模板通常是采用机器学习算法或先验知识、从大量的离线生理信号中得到的，而离线生理信号与实时获取的生理信号是有一定偏差的，从而根据上述预先设置的信号模板得到的生理信号质量判断结果的准确性有待提高。并且，由于当前的穿戴式传感器通常较为简单，因此可能提取不到生理信号的一些特征，如重搏波波峰，即不一定能获取到上述大量精确的特征值；这样一来，使得根据上述大量精确的特征值得到的生理信号质量判断结果的准确性有待提高，且判断生理信号质量的过程中计算量较大。
发明内容
本申请提供一种生理信号质量判断方法及装置，可以提高生理信号质量判断结果的准确性，并减小生理信号质量判断过程中的计算量。
为达到上述目的，本申请采用如下技术方案：
第一方面，提供一种生理信号质量判断方法，该生理信号质量判断方法包括：采集生理信号，该生理信号为周期信号或类周期信号；提取生理信号的特征点，该特征点包括用于指示该生理信号周期的特征点；根据生理信号的特征点，对该生理信号划分周期；根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量；其中，上述信号模板集合包括N个信号模板，该N个信号模板根据第i个周期的信号之前的生理信号获取，N大于等于2，i大于N。一般而言，当前信号模板集合中N个信号模板中每个信号模板均为质量较好的生理信号。从而，若第i个周期的信号与当前信号模板集合之间的相似性越高，则说明第i个周期的信号的信号质量越好；第i个周期的信号与当前信号模板集合之间的相似性越低，则第i个周期的信号的信号质量越差。
需要说明的是，本申请提供的生理信号质量判断方法中，用于判断生理信号质量的当前信号模板集合是根据实时获取的生理信号得到的，而不是采用机器学习算法或先验知识、从大量的离线生理信号中得到的；从而，本申请提供的当前信号模板更加符合实时获取的生理信号，使得根据上述当前信号模板集合得到的生理信号质量判断结果的准确性较高。
在一种可能的实现方式中，判断第i个周期的信号的信号质量可以通过判断第i个周期的信号是否达到正常生理信号的标准，即第i个周期的信号为正常生理信号还是异常生理信号。具体的，上述根据第i个周期的信号与信号模板集合之间的相似性判断第i个周期的信号的信号质量可以包括：确定第i个周期的信号的相似结果，该第i个周期的信号的相似结果用于指示第i个周期的信号与当前信号模板集合之间的相似性；若第i个周期的信号的相似结果满足预设相似条件，则判断第i个周期的信号为正常生理信号，预设相似条件为预先设置的；若第i个周期的信号的相似结果不满足预设相似条件，则判断第i个周期的信号为异常生理信号。
其中，上述第i个周期的信号与当前信号模板集合之间的相似性，可以由第i个周期的信号的样本序列与该信号模板的样本序列的相关系数、均方误差等相似参数表示。例如，在第i个周期的信号的相似参数为相关系数的情况下，第i个周期的信号的相似参数越大、相似性就越高、信号质量越好。第i个周期的信号的相似参数越小、相似性就越低、信号质量越差。
在一种可能的实现方式中，在确定第i个周期的信号的相似结果好于N个信号模板中至少一个信号模板的相似结果的情况下，上述方法还可以包括：根据第i个周期的信号更新当前信号模板集合。也就是说，若第i个周期的信号的信号质量比当前信号模板集合中的N个信号模板中的至少一个信号模板的信号质量高，上述方法便可以根据第i个周期的信号替换该信号模板以更新上述当前信号模板集合。其中，上述N个信号模板中一个信号模板的相似结果根据第i个周期的信号之前的生理信号得到的。
需要说明的是，上述当前信号模板集合是根据实时获取的生理信号不断更新的。其中，根据信号质量较好的周期的信号替换信号质量相对较差的信 号模板以更新当前信号模板集合，使得上述当前信号模板集合中的信号模板的信号质量实时地提高。如此，根据上述实时更新的当前信号模板集合得到的生理信号质量判断结果的准确性较高。
在一种可能的实现方式中，由于上述第i个周期的信号的信号质量与第i个周期的信号的相似结果相关，因此可以根据第i个周期的信号的相似结果更新当前信号模板集合。具体的，上述根据第i个周期的信号更新当前信号模板集合可以包括：在确定第i个周期的信号的相似结果好于N个信号模板中至少一个信号模板的相似结果的情况下：使用第i个周期的信号替换当前信号模板集合中相似结果最差的信号模板。
可选的，上述“使用第i个周期的信号替换当前信号模板集合中相似结果最差的信号模板”可以替换为使用第i个周期的信号替换当前信号模板集合中任一相似结果较差的信号模板。其中，上述任一相似结果较差的信号模板的相似结果比第i个周期的信号的相似结果差。
在一种可能的实现方式中，在根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量之前，上述方法还可以包括：根据第i个周期的信号之前的生理信号获取当前信号模板集合。
其中，上述当前信号模板集合可以是已被更新过的信号模板集合，如当前信号模板集合可以是根据第i-1个周期的信号更新过的信号模板集合。或者，上述当前信号模板集合可以是未被更新过的信号模板集合。
在一种可能的实现方式中，上述根据第i个周期的信号之前的生理信号获取当前信号模板集合可以包括：根据前N+a个周期的信号获取初始信号模板集合；根据初始信号模板集合和第N+a个周期的信号到第i个周期的信号之间的生理信号获取当前信号模板集合。其中，上述初始信号模板集合为未被更新过的信号模板集合。
需要说明的是，上述初始信号模板集合中的N个信号模板不一定都为信号质量较好的正常生理信号，但只要初始信号模板集合包括N个信号模板便可以执行上述生理信号质量判断方法。其中，上述方法根据初始信号模板集合和第N+a个周期的信号到第i个周期的信号之间的生理信号获取当前信号模板集合的同时，还可以根据第N+a个周期的信号到第i个周期的信号之间的每个周期的信号的相似结果判断该每个周期的信号的信号质量。
在一种可能的实现方式中，上述根据前N+a个周期的信号获取初始信号模板集合可以包括：确定前N+a个周期的信号中每个周期的信号的相似结果；a为大于等于0的整数，N+a小于i；其中，前N+a个周期的信号中一个周期的信号的相似结果由该周期的信号与前N+a个周期的信号中除该周期的信号之外的其他周期的信号之间的相似性组成的；将前N+a个周期的信号中相似结果最好的前N个周期的信号确定为初始信号模板集合。
其中，当a等于0时，上述初始信号模板集合中的N个信号模板为前N个周期的信号。当a大于0时，前N+a个周期的信号有a个周期的信号不为初始信号模板集合中的信号模板。需要说明的是，上述确定前N+a个周期的 信号中每个周期的信号的相似性之后，还可以判断前N+a个周期的信号中每个周期的信号的信号质量。
在一种可能的实现方式中，上述提取生理信号的特征点之后还可以包括：根据生理信号的特征点，获取第i个周期的信号的特征值；确定第i个周期的信号的特征值不处于当前预设阈值范围内，并判断第i个周期的信号为异常生理信号，当前预设阈值范围根据第i个周期的信号之前的周期的信号确定；在根据第i个周期的信号与信号模板集合之间的相似性判断第i个周期的信号的信号质量之前，上述方法还可以包括：确定第i个周期的信号的特征值处于当前预设阈值范围。
需要说明的是，由于上述当前预设阈值范围是根据实时获取的生理信号中所有周期的信号得到的，即当前预设阈值范围是根据全局变量得到的；因此上述当前预设阈值范围符合实时获取的生理信号。从而，本申请提供的生理信号质量判断方法，可以进一步提高生理信号质量判断结果的准确性。
在一种可能的实现方式中，在提取的生理信号的特征点包括顶点和底点的情况下，上述第i个周期的信号的特征值包括：第i个周期的信号的周期值和/或第i个周期的信号的高度值。从而，当前预设阈值范围可以包括：当前预设周期范围和/或当前预设高度范围。具体的，第i个周期的信号的特征值不处于当前预设阈值范围可以包括：第i个周期的信号的周期值不处于当前预设周期范围，和/或第i个周期的信号的高度值不处于当前预设高度范围。第i个周期的信号的特征值处于当前预设阈值范围可以包括：第i个周期的信号的周期值处于当前预设周期范围且第i个周期的信号的高度值处于当前预设高度范围。
需要说明的是，本申请提供的方法提取到生理信号的特征值中的顶点和底点便可以判断生理信号中每个周期的信号的信号质量，可以在一定程度上减小判断生理信号质量过程中的计算量。
在一种可能的实现方式中，在上述根据生理信号的特征点，获取第i个周期的信号的特征值之前，上述方法还可以包括：根据第i个周期的信号之前的周期的信号确定当前预设阈值范围；在根据生理信号的特征点，获取第i个周期的信号的特征值之后，上述方法还包括：根据第i个周期的信号的特征值，更新当前预设阈值范围。
其中，由于上述当前预设阈值范围是根据实时获取的生理信号不断更新的；因此上述当前预设阈值范围是符合实时获取的生理信号的。从而，本申请提供的生理信号质量判断方法，可以进一步提高生理信号质量判断结果的准确性。
在一种可能的实现方式中，上述方法还可以包括：输出信号质量判断结果，该信号质量判断结果包括第i个周期的信号为正常生理信号或第i个周期的信号为异常生理信号，以及第i个周期的信号之前的每个周期的信号为正常生理信号或每个周期的信号为异常生理信号。其中，若第i个周期的信号之前的一个周期的信号的相似结果满足预设相似条件，则该周期的信号为正 常生理信号；若第i个周期的信号之前的一个周期的信号的相似结果不满足预设相似条件，则该周期的信号为异常生理信号。
需要说明的是，本申请提供的生理信号质量判断方法，可以实时地、逐周期判断采集的生理信号的信号质量，并较为准确地区分出该生理信号中任一周期的信号为正常生理信号还是异常生理信号。如此，可以根据判断得到的正常生理信号得到较为准确的人体生理信息。并且，输出信号质量判断结果使得该结果可以较为直观的展示给用户或者相关技术人员，以提高用户体验或满足相关技术人员的需求。
第二方面，提供一种生理信号质量判断装置，包括：采集模块、提取模块、划分模块和判断模块。其中，采集模块，用于采集生理信号，生理信号为周期信号或类周期信号。提取模块，用于提取所采集模块采集的生理信号的特征点，特征点包括用于指示生理信号周期的特征点。划分模块，用于根据提取模块提取的生理信号的特征点，对该生理信号划分周期。判断模块，用于根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量；其中，信号模板集合包括N个信号模板，N个信号模板为根据采集模块采集的第i个周期的信号之前的生理信号获取，N大于等于2，i大于N。
在一种可能的实现方式中，上述装置还可以包括：确定模块。其中，确定模块，用于确定划分模块划分出的第i个周期的信号的相似结果，第i个周期的信号的相似结果用于指示第i个周期的信号与当前信号模板集合之间的相似性。上述判断模块，具体用于若第i个周期的信号的相似结果满足预设相似条件，则判断第i个周期的信号为正常生理信号，预设相似条件为预先设置的；若第i个周期的信号的相似结果不满足预设相似条件，则判断第i个周期的信号为异常生理信号。
在一种可能的实现方式中，上述装置还可以包括：更新模块。其中，更新模块，用于在确定第i个周期的信号的相似结果好于N个信号模板中至少一个信号模板的相似结果的情况下，根据第i个周期的信号更新当前信号模板集合，其中，N个信号模板中一个信号模板的相似性根据第i个周期的信号之前的生理信号得到的。
在一种可能的实现方式中，上述更新模块具体用于使用第i个周期的信号替换当前信号模板集合中相似结果最差的信号模板。
在一种可能的实现方式中，上述装置还可以包括：获取模块。其中，获取模块，用于在所述判断模块根据第i个周期的信号与当前信号模板集合之间的相似性判断所述第i个周期的信号的信号质量之前，根据所述第i个周期的信号之前的生理信号获取所述当前信号模板集合。
在一种可能的实现方式中，上述获取模块，具体用于根据前N+a个周期的信号获取初始信号模板集合；根据初始信号模板集合和第N+a个周期的信号到第i个周期的信号之间的生理信号获取当前信号模板集合。
在一种可能的实现方式中，上述确定模块，还可以用于确定前N+a个周 期的信号中每个周期的信号的相似性；a为大于等于0的整数，N+a小于i；其中，前N+a个周期的信号中一个周期的信号的相似结果由该周期的信号与前N+a个周期的信号中除该周期的信号之外的其他周期的信号之间的相似性组成的。上述获取模块具体用于将上述确定模块确定出的前N+a个周期的信号中相似结果最好的前N个周期的信号确定为初始信号模板集合。
在一种可能的实现方式中，上述获取模块，还可以用于在提取模块提取生理信号的特征点之后，根据生理信号的特征点，获取第i个周期的信号的特征值。上述判断模块，还可以用于确定第i个周期的信号的特征值不处于当前预设阈值范围内，并判断第i个周期的信号为异常生理信号，当前预设阈值范围根据第i个周期的信号之前的周期的信号确定；在根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量之前，确定第i个周期的信号的特征值处于当前预设阈值范围。
在一种可能的实现方式中，上述第i个周期的信号的特征值包括：第i个周期的信号的周期值和/或第i个周期的信号的高度值。当前预设阈值范围可以包括：当前预设周期范围和/或当前预设高度范围。第i个周期的信号的特征值不处于当前预设阈值范围可以包括：第i个周期的信号的周期值不处于当前预设周期范围，和/或第i个周期的信号的高度值不处于当前预设高度范围。第i个周期的信号的特征值处于当前预设阈值范围可以包括：第i个周期的信号的周期值处于当前预设周期范围，和第i个周期的信号的高度值处于当前预设高度范围。
在一种可能的实现方式中，上述确定模块，还可以用于在上述获取模块根据生理信号的特征点，获取第i个周期的信号的特征值之前，根据第i个周期的信号之前的周期的信号确定当前预设阈值范围。上述更新模块，还可以用于在获取模块根据生理信号的特征点，获取第i个周期的信号的特征值之后，根据第i个周期的信号的特征值，更新当前预设阈值范围。
在一种可能的实现方式中，上述装置还可以包括：输出模块。其中，输出模块，用于输出信号质量判断结果，信号质量判断结果包括判断模块判断得到的第i个周期的信号为正常生理信号或第i个周期的信号为异常生理信号，以及第i个周期的信号之前的每个周期的信号为正常生理信号或该每个周期的信号为异常生理信号。其中，若第i个周期的信号之前的一个周期的信号的相似结果满足预设相似条件，则判断该周期的信号为正常生理信号；若第i个周期的信号之前的一个周期的信号的相似结果不满足预设相似条件，则判断该周期的信号为异常生理信号。
第三方面，一种生理信号质量判断装置，该生理信号质量判断装置可以包括处理器、存储器、显示器、输入器和总线；该存储器用于存储该至少一个指令，该处理器、该存储器、该显示器和该输入器通过该总线连接，当该装置运行时，处理器执行存储器存储的至少一个指令，以使装置执行如第一方面以及第一方面的各种可选方式中的生理信号质量判断方法。
第四方面，提供一种计算机存储介质，该计算机存储介质中存储有至少一 个指令；当该至少一个指令在计算机上运行时，使得计算机执行如第一方面以及第一方面的各种可选方式中的生理信号质量判断方法。
第五方面，提供一种计算机程序，该计算程序产品中存储有至少一个指令；当该至少一个指令在计算机上运行时，使得计算机执行如第一方面以及第一方面的各种可选方式中的生理信号质量判断方法。
需要说明的是，本申请的第三方面中的处理器可以为第二方面中的提取模块、划分模块、判断模块、确定模块、更新模块和获取模块等功能模块的集成，处理器可以实现第二方面上述的各个功能模块的功能。第二方面和第三方面中各个模块的详细描述以及有益效果分析可以参考上述第一方面及其各种可能的实现方式中的对应描述及技术效果，此处不再赘述。
附图说明
图1为本发明实施例提供的一种可穿戴设备的结构示意图；
图2为本发明实施例提供的一种生理信号的波形示意图；
图3为本发明实施例提供的一种生理信号质量判断方法的流程示意图；
图4为本发明实施例提供的另一种生理信号的波形示意图；
图5为本发明实施例提供的另一种生理信号的波形示意图；
图6为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图7为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图8为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图9为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图10为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图11为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图12为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图13为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图14为本发明实施例提供的另一种生理信号质量判断方法的流程示意图；
图15为本发明实施例提供的生理信号质量判断装置的一种可能的组成示意图；
图16为本发明实施例提供的生理信号质量判断装置的另一种可能的组成示意图；
图17为本发明实施例提供的生理信号质量判断装置的另一种可能的组成示意图；
图18为本发明实施例提供的生理信号质量判断装置的另一种可能的组成示意图；
图19为本发明实施例提供的生理信号质量判断装置的另一种可能的组成示意图；
图20为本发明实施例提供的生理信号质量判断装置的另一种可能的组成示意图。
具体实施方式
本发明实施例提供一种生理信号质量判断方法及装置，应用于根据人体的生理信号得到人体生理信息的过程中，具体应用于根据人体的生理信号得到人体生理信息之前、判断该生理信号质量的过程中，可以提高生理信号质量判断结果的准确性，并减少生理信号质量判断过程中的计算量。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行详细地描述。
本发明实施例提供的生理信号质量判断方法，所涉及的生理信号可以为具有周期性或类周期性的生理信号，如人体的心电、脉搏波、呼吸、血压等具有周期性的生理信号。其中，上述生理信号均包含大量人体生理信息，如人体的脉搏波信号可以包含人体的心率、呼吸率和血氧等生理信息。
需要说明的是，本发明实施例提供的生理信号质量判断方法，除了可以判断上述生理信号的信号质量之外，还可以判断其他具有周期性或类周期信号的信号质量，如计步算法中的加速度信号，本发明实施例对此不作限定。
本发明实施例提供的生理信号质量判断装置可以为能够获取人体的生理信号的可穿戴设备。其中，可穿戴设备，即直接穿在用户的身体上，或是整合到用户的衣服或配件中的一种便携式设备，且大多数可穿戴设备内置智能化系统，可连接手机及各类终端，具有拍照、GPS定位、亲情通话、智能防丢、监测睡眠、监测心率、跑步记步等以上功能中的一种或者多种。常见的可穿戴设备包括以手腕为支撑的智能手环、智能手表等产品，以脚为支撑的智能鞋、袜子或者其他腿上佩戴产品等，以头部为支撑的智能眼镜、头盔、头带等产品，以及智能体温贴、心率带、智能服装、书包、拐杖、配饰等各类形态的产品等。
示例性的，图1为本发明实施例提供的一种可穿戴设备的结构示意图，参见图1，可穿戴设备10可以包括以下一个或多个组件：传感器组件101，存储器102，处理组件103，多媒体组件104，音频组件105，输入/输出(I/O)的接口106，电源组件107，以及通信组件108。
其中，传感器组件101包括一个或多个传感器，用于为可穿戴设备10提供各个方面的状态评估。其中，上述可穿戴设备10提供的各个方面的状态变化可以是由使用该可穿戴设备10的用户的操作引起的，或者由该用户的生理信息变化引起的。
示例性的，传感器组件101可以检测到可穿戴设备10的打开/关闭状态，组件的相对定位。传感器组件101还可以检测可穿戴设备10或者其中一个组件的位置改变，可穿戴设备10方位或加速/减速和可穿戴设备10的温度变化。 传感器组件101可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。具体的，传感器组件101可以包括脉搏传感器，如红外脉搏传感器、心率脉搏传感器、光电脉搏传感器、腕部脉搏传感器或数字脉搏传感器等，用于检测用户的脉搏波，以便可以得到人体的心率等生理信息。其中，常用的脉搏传感器可以是PPG传感器。传感器组件101可以包括血压传感器，用于检测人体的血压。在一些实施例中，传感器组件101还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。例如，上述CMOS或CCD图像传感器可以用于获取人体的脸部、手部等皮肤裸露部分的视频信号。其中，上述视频信号可以包括多个帧，每一帧即一个二维图像，该二维图像为红绿蓝RGB图像，该RGB图像可以分为R路图像、G路图像和B路图像三路图像，这三路图像可以用于提取出人体的脉搏波信号。在另一些实施例中，该传感器组件101还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
存储器102被配置为存储各种类型的数据以支持在可穿戴设备10的操作。这些数据的示例包括用于在可穿戴设备10上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频，以及人体生理信息等数据。存储器102可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
处理组件103通常控制可穿戴设备10的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作，以及处理传感器获取到的信号或数据。具体的，在上述传感器组件101检测并获取生理信号之后，处理组件103可以判断该生理信号质量，得到该生理信号为正常生理信号或者该生理信号为异常生理信号；从而，根据正常生理信号得到人体生理信息。其中，处理组件103可以包括一个或多个处理器1031来执行指令。此外，处理组件103可以包括一个或多个模块，便于处理组件103和其他组件之间的交互。例如，处理组件103可以包括多媒体模块，以方便多媒体组件104和处理组件103之间的交互。
多媒体组件104包括在可穿戴设备10和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。上述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与上述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件104包括一个摄像头。当可穿戴设备10处于操作模式，如拍摄模式或视频模式时，摄像头可以接收外部的多媒体数据。每个摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。当然，上述获取人体的脸部、手部等皮肤裸露部分的视频信号除了可以由上述CMOS或CCD图像传感器等传 感器获取之外，还可以由多媒体组件104中的摄像头获取，本发明实施例对此不作限定。
音频组件105被配置为输出和/或输入音频信号。例如，音频组件105包括一个麦克风(MC)，当可穿戴设备10处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器102或经由通信组件108发送。在一些示例中，音频组件105还包括一个扬声器，用于输出音频信号。具体的，本发明实施这里，音频组件105可以用于输出上述处理组件103判断得到的生理信号质量判断结果，以及输出根据生理信号得到的人体生理细信息，如人体的心率为65次/分(beats per minute，bpm)。
I/O接口106为处理组件102和外围接口模块之间提供接口，上述外围接口模块可以是点击轮，按钮等。这些按钮可包括但不限于：主页按钮、启动按钮和锁定按钮。具体的，本发明实施这里，I/O接口106中的主页按钮还可以用于指示处理组件103开始处理上述传感器组件101获取的生理信号。
电力组件107为可穿戴设备10的各种组件提供电力。电力组件107可以包括电源管理系统，一个或多个电源，及其他与为可穿戴设备10生成、管理和分配电力相关联的组件。
通信组件108可以支持可穿戴设备10和其他设备之间有线或无线方式的通信，使得可穿戴设备10可以接入基于通信标准的无线网络，如WF，2G或3G，或它们的组合。在一个示例性实施例中，通信部件108经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，上述通信部件108还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFD)技术，红外数据协会(rDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。具体的，本发明实施例这里，通信组件108可以用于向其他设备发送上述处理组件103判断得到的生理信号质量判断结果，或者发送根据生理信号得到的人体生理信息，如人体的心率为65bpm。
在示例性实施例中，可穿戴设备可以被一个或多个应用专用集成电路(ASC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器102，上述指令可由可穿戴设备的处理器103执行。例如，上述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
需要说明的是，本发明实施例中提供的生理信号判断装置除了可以是上述可穿戴设备之外，还可以是能够获取人体的生理信号的手机、个人计算机(Personal Computer，PC)、平板电脑等终端设备。本发明实施例以下仅以上述生理信号质量判断装置为可穿戴设备为例，说明本发明实施例提供的生理 信号质量判断方法。
具体的，本发明实施例以下仅以生理信号为脉搏波信号为例，说明本发明实施例提供的生理信号质量判断方法。
如图2所示，为本发明实施例提供的一种生理信号的波形示意图。图2示出的生理信号的波形为理想情况下的一段脉搏波信号。对于理想情况下的脉搏波信号，每一个周期的信号都可以具有相同的特征及特征点。如脉搏波信号中每个周期的信号均包括上升支、主波峰、重搏波、下降支等特征，以及顶点、底点等特征点。
具体的，图2中的横坐标t(s)的变量为时间t，时间t的单位为秒(s)；纵坐标A(mv)的变量为幅值A，幅值A的单位为毫伏(mv)。B1点、B2点和B3点为三个底点，C1点和C2点为两个顶点。相邻的底点之间的波形可以为一个周期的信号。当然区分图2中的脉搏波信号的周期的特征点除了底点，还可以是其他特征点，如顶点。示例性的，图2中底点B1与底点B2之间的波形为一个周期的信号(记为信号周期1)；信号周期1的周期值可以记为T1。底点B2与底点B3之间的波形为另一个周期的信号(记为信号周期2)；信号周期2的周期值可以记为T2。一般而言，正常的脉搏波信号的周期值对应人体的心率正常范围为40bpm～180bpm。图2中底点B1到F1点之间的波形为信号周期1的主波，F1点到底点B2之间的波形为信号周期1的重搏波。
其中，底点B1为信号周期1的起点。底点B1到顶点C1之间的波形为信号周期1的主波上升支，其高度值可以记为H1-1，宽度值可以记为T1-1。顶点C1到F1点之间的波形为信号周期1的主波下降支，其高度值可以记为H1-2，宽度值可以记为T1-2。F1点至G1点之间的波形为信号周期1的重搏波上升支，其高度值可以记为H1-3，宽度值可以记为T1-3。G1点所在的波峰为信号周期1的重搏波波峰。G1点至底点B2之间的波形为信号周期1的重搏波下降支，其高度值可以记为H1-4，宽度值可以记为T1-4。底点B2点为信号周期1的终点。其中，信号周期1的周期值T1＝T1-1+T1-2+T1-3+T1-4。上述信号周期1中底点B1到顶点C1的主波上升支还可以称为信号周期1的收缩波(systolic wave)；顶点C1到底点B2的波形还可以称为信号周期1的舒张波(diastolic wave)。从而，信号周期1的收缩波的高度值为H1-1，信号周期1的舒张波的高度值可以记为H1-5。
类似的，上述脉搏波信号中的其他周期的信号(如信号周期2)的特征和特征点与信号周期1类似，本发明实施例这里不再赘述。
另外，信号周期2中底点B2到E2点的波形与坐标轴t(s)组成的图形的面积可以记为Sa；E2点到底点B3之间的波形与坐标轴t(s)组成的图形的面积可以记为Sb；信号周期2的波形与坐标轴t(s)组成的图形的面积可以记为S，即底点B2点到底点B3之间的波形与坐标轴t(s)组成的图形的面积可以记为S。其中，S＝Sa+Sb。类似的，对于脉搏波信号的信号周期1或者其他信号周期的波形与坐标轴组成的图形的面积的描述可以参照上述对信号周期2的描述，这里不再赘述。
需要说明的是，由于当前的穿戴式传感器较为简单，且大多获取的是腕部信号，因此当前的穿戴式传感器获取的脉搏波信号往往看不到重搏波等特征以及重搏波的峰值所在的特征点。但是，当前的穿戴式传感器一般都可以获取到脉搏波信号的底点和顶点。类似的，当前的穿戴式传感器一般也可以获取到除脉搏波信号之外的其他生理信号的顶点和底点，这里不再赘述。本发明实施例以下，仅以生理信号的特征点为顶点和底点为例，说明本发明实施例提供的生理信号质量判断方法。
为使本发明实施例的目的、技术方案和优点更加清楚，下面结合图1所示的可穿戴设备10，通过图3所示的生理信号质量判断方法的流程图对本发明实施例提供的生理信号质量判断方法进行详细描述。参见图3，本发明实施例这里提供的生理信号质量判断方法可以包括S301-S304：
S301、可穿戴设备采集生理信号，该生理信号为周期信号或类周期信号。
其中，步骤301可以由图1所示的可穿戴设备10中的传感器组件101，如PPG传感器来执行。
示例性的，上述传感器组件101可以以一定的采样频率按照固定时长(如3s)采集生理信号，所获取的生理信号为一组离散样本。
其中，采样频率不影响本申请目的的实现，本发明实施例对采样频率不作具体限制，例如，可以为25-100Hz。
需要说明的是，可穿戴设备获取生理信号之后，可以对该生理信号预处理，如滤波处理，获取脉搏波信号，如图4所示，为经过预处理的脉搏波信号。其中，该预处理过程可以由可穿戴设备中的处理器执行，也可以由可穿戴设备中单独的滤波组件执行，该滤波组件可以为硬件实现的滤波器，本发明实施例对此不作限定。
S302、可穿戴设备提取生理信号的特征点，该特征点包括用于指示该生理信号周期的特征点。
其中，上述用于指示该生理信号周期的特征点可以为生理信号的顶点和底点。
可选的，上述特征点还可以是生理信号中除底点和顶点外的其他特征点，如脉搏波信号的重搏波波峰所在的特征点。
由于上述可穿戴设备提取到的生理信号(如脉搏波生理信号)中、相邻底点之间的波形可以为一个周期，或者相邻顶点之间的波形可以为一个周期；而可穿戴设备是逐周期判断生理信号的信号质量的，因此本发明实施例提供的方法还可以包括S303：
S303、可穿戴设备根据生理信号的特征点，对该生理信号划分周期。
示例性的，如图5所示，为本发明实施例提供的一种生理信号的波形示意图。图5示出了可穿戴设备通过穿戴式传感器对图4所示的脉搏波信号提取出的底点和顶点。随后，可穿戴设备便可以对如图5中相邻底点之间的波形划分周期，并按照时间顺序记录每个周期的信号，即记录每个周期的信号的样本序列。
其中，可穿戴设备获取的第1个周期的信号的样本序列可以记录为x1＝{x1_1，x1_2，…x1_j，…，x1_n}，j∈{1，2，……，n}，第1个周期的信号的样本序列x1中可以包括n个样本，n为正整数；x1_j为第1个周期的信号的样本序列x1中的第j个样本。类似的，可穿戴设备获取到第1个周期的信号之后的任一周期的信号时，也可以记录该周期的信号的样本序列，该周期的信号的样本序列中也可以包括n个样本。
需要说明的是，当本发明实施例中提供的采样频率为100Hz时，可穿戴设备获取的每个周期的信号的样本序列中两个样本之间的时间间隔可以为0.01s。结合图3和图5所示的生理信号波形示意图，图5所示的第1个周期的信号的时间T1可以为0.3s，则该第1个周期的信号的波形中可以包括30个点，即该第1个周期的信号的样本序列中可以包括30个样本。
S304、可穿戴设备根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量。
其中，上述步骤302-304均可以由图1所示的可穿戴设备10中的处理组件102来执行。
上述当前信号模板集合包括N个信号模板，该N个信号模板可以根据第i个周期的信号之前的生理信号获取，N大于等于2，i大于N。也就是说，上述N个信号模板可以是第1个周期的信号到第i-1个周期的信号中的N个周期的信号，且该N个信号模板为可穿戴设备实时获取的。上述第i个周期的信号与当前信号模板集合之间的相似性，是由第i个周期的信号与当前信号模板集合包括的N个信号模板中每个信号模板之间的相似性组成的。
其中，可穿戴设备获取的周期的信号中每两个周期的信号之间具有相似性。这两个周期的信号之间的相似性可以用于指示这两个周期的信号的波形的相似程度。例如，两个周期的信号之间的相似性越高，表示这两个周期的信号的波形的相似程度越高；两个周期的信号之间的相似性越低，表示这两个周期的信号的波形的相似程度越低。也就是说，上述第i个周期的信号与任一信号模板的相似性越高，表示第i个周期的信号的波形与该信号模板的波形的相似程度越高；进而，上述第i个周期的信号与当前信号模板集合之间的相似性越高。上述第i个周期的信号与任一信号模板的相似性越低，表示第i个周期的信号的波形与该信号模板的波形的相似程度越低；进而，上述第i个周期的信号与当前信号模板集合之间的相似性越低。
一般而言，当前信号模板集合中N个信号模板中每个信号模板均为质量较好的生理信号。从而，若第i个周期的信号与当前信号模板集合之间的相似性越高，则说明第i个周期的信号的信号质量越好；第i个周期的信号与当前信号模板集合之间的相似性越低，则第i个周期的信号的信号质量越差。
其中，可穿戴设备可以在获取第i个周期的信号的同时记录第i个周期的信号的样本序列，如第i个周期的信号样本序列可以记录为xi＝{xi_1，xi_2，…xi_j，…，xi_n},j∈{1，2，……，n}。此时，第i个周期的信号也可以简称为xi。其中，第i个周期的信号的样本序列xi中包括n个样本，xi_j为第 i个周期的信号的样本序列xi中的第j个样本。当然，在可穿戴设备获取第i个周期的信号之前，可穿戴设备可以已经记录了前i-1个周期的信号中每个周期的信号的样本序列。例如，可穿戴设备可以将第i-1个周期的信号的样本序列记录为xi-1＝{xi-1_1，xi-1_2，…xi-1_j，…，xi-1_n}，第i-1个周期的信号的样本序列xi-1中也可以包括n个样本，xi-1_j为第i-1个周期的信号的样本序列xi-1中的第j个样本。
需要说明的是，本发明实施例提供的生理信号质量判断方法中，用于判断生理信号质量的当前信号模板集合是可穿戴设备根据实时获取的生理信号得到的，而不是采用机器学习算法或先验知识、从大量的离线生理信号中得到的；从而，本发明实施例提供的当前信号模板更加符合可穿戴设备实时获取的生理信号，使得根据上述当前信号模板集合得到的生理信号质量判断结果的准确性较高。并且，由于本发明实施例获取到生理信号后，可穿戴设备提取生理信号中的顶点和底点便可以支持可穿戴设备判断生理信号质量，而不一定需要提取生理信号中除了顶点和底点之外的其他大量特征点以支持可穿戴设备判断生理信号质量；因此，可以减小可穿戴设备判断生理信号质量过程中的计算量，并进一步提高生理信号质量判断结果的准确性。
具体的，在一种可能的实现方式中，可穿戴设备根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量，可以判断出第i个周期的信号为正常生理信号还是异常生理信号。本发明实施例提供的生理信号质量判断方法中的S304可以包括S601-S603或者S601、S602、S604。示例性的，如图6所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图6中，图3所示的S304可以包括S601-S603或者S601、S602、S604：
S601、可穿戴设备确定第i个周期的信号的相似结果，该第i个周期的信号的相似性结果用于指示第i个周期的信号与当前信号模板集合之间的相似性。
其中，可穿戴设备获取的周期的信号中每两个周期的信号之间的相似性，可以由这两个周期的信号的样本序列的相关系数或均方误差等相似参数表示。也就是说，上述第i个周期的信号与当前信号模板集合之间的相似性，可以由第i个周期的信号的样本序列与一个信号模板的样本序列的相关系数、均方误差等相似参数组成。从而，上述第i个周期的信号与当前信号模板集合之间的相似性，可以由第i个周期的信号的相似参数表示。如此，上述第i个周期的信号的相似结果可以为第i个周期的信号的相似参数。其中，第i个周期的信号的相似参数，可以为第i个周期的信号与当前N个信号模板中每个信号模板的相似参数之和，或者为第i个周期的信号与当前N个信号模板中每个信号模板的相似参数之间的均值。
其中，可穿戴设备可以将当前信号模板集合记录为y＝{y1，y2，…yt，…，yN-1，yN}，t∈{1，2，……，N}，该yt为当前N个信号模板中的第t个信号模板的样本序列。同时，可穿戴设备可以将第t个信号模板的样本 序列yt记录为yt＝{yt_1，yt_2，…yt_j，…，yt_n},j∈{1，2，……，n}。第t个信号模板的样本序列yt中也可以包括n个样本，yt_j为第t个信号模板的样本序列yt中的第j个样本。随后，可穿戴设备可以将第i个周期的信号与当前N个信号模板中第t个信号模板的相似参数记录为ri_t。从而，第i个周期的信号的相似参数ri_t可以记录为：
Figure PCTCN2017086393-appb-000001
或者，
Figure PCTCN2017086393-appb-000002
需要说明的是，上述当前信号模板集合y中的任一信号模板为一个周期的信号，例如第1个信号模板y1可以为第1个周期的信号x1。本发明实施例为了方便描述，将一个信号模板和该信号模板对应的周期的信号分别用不同的字符表示。
示例性的，在两个周期的信号之间的相似性由这两个周期的信号的样本序列的相关系数表示的情况下：第i个周期的信号与当前N个信号模板中第t个信号模板的相似参数ri_t为第i个周期的信号的样本序列xi与当前N个信号模板中第t个信号模板的样本序列yt的相关系数。
具体的，第i个周期的信号与当前N个信号模板中第t个信号模板的相似参数ri_t可以为：
Figure PCTCN2017086393-appb-000003
其中，
Figure PCTCN2017086393-appb-000004
为第i个周期的信号的样本序列xi中n个样本的均值，且
Figure PCTCN2017086393-appb-000005
为第t个信号模板的样本序列yt中n个样本的均值，且
Figure PCTCN2017086393-appb-000006
进一步的，将
Figure PCTCN2017086393-appb-000007
带入(1)式中，第i个周期的信号与当前N个信号模板中第t个信号模板的相似参数ri_t还可以为：
Figure PCTCN2017086393-appb-000008
需要说明的是，若两个周期的信号的样本序列的相关系数越大，则这两个周期的信号之间的相似性越高；反之，这两个周期的信号之间的相似性越 低。从而，若相似参数ri_t越大，则第i个周期的信号与当前N个信号模板中第t个信号模板之间的相似性越高；进而，根据相似参数ri_t得到的第i个周期的信号的相似参数ri越大，第i个周期的信号的相似结果也就越好，第i个周期的信号的信号质量越好。若相似参数ri_t越小，则第i个周期的信号与当前N个信号模板中第t个信号模板之间的相似性越低；进而，根据相似参数ri_t得到的第i个周期的信号的相似参数ri越小，第i个周期的信号的相似结果也就越差，第i个周期的信号的信号质量越差。
在另一种示例中，在两个周期的信号之间的相似性由这两个周期的信号的样本序列的均方误差表示的情况下：第i个周期的信号与当前N个信号模板中第t个信号模板的相似参数ri_t为第i个周期的信号的样本序列xi与当前N个信号模板中第t个信号模板的样本序列yt的均方误差。
具体的，第i个周期的信号与当前N个信号模板中第t个信号模板的均方误差msei_t(即相似参数ri_t)可以为：
Figure PCTCN2017086393-appb-000009
其中，ai_j为第i个周期的信号的样本序列xi经过归一化得到的样本序列ai的第j个样本，bi_j为第t个信号模板的样本序列yt经过归一化得到的样本序列bt的第j个样本。
其中，与相关系数不同的是，若两个周期的信号的样本序列的均方误差越小，则这两个周期的信号之间的相似性越高；反之，这两个周期的信号之间的相似性越低。从而，在相似参数ri_t为均方误差msei_t的情况下，若相似参数ri_t越小，则第i个周期的信号与当前N个信号模板中第t个信号模板之间的相似性越高；进而，根据相似参数ri_t得到的第i个周期的信号的相似参数ri越小，第i个周期的信号的相似结果也就越好，第i个周期的信号的信号质量越好。若相似参数ri_t越大，则第i个周期的信号与当前N个信号模板中第t个信号模板之间的相似性越低；进而，根据相似参数ri_t得到的第i个周期的信号的相似参数ri越大，第i个周期的信号的相似结果也就越差，第i个周期的信号的信号质量越差。
需要说明的是，本发明实施例以下，仅以两个周期的信号之间的相似性由这两个周期的信号样本序列的相关系数表示，说明本发明实施例提供的生理信号质量判断方法。
进一步的，上述可穿戴设备根据第i个周期的信号的相似结果判断第i个周期的信号的信号质量，具体可以为可穿戴设备判断第i个周期的信号为正常生理信号还是异常生理信号。
S602、可穿戴设备判断第i个周期的信号的相似结果是否满足预设相似条件。
其中，上述预设相似条件可以为可穿戴设备在执行S602之前预先设置的， 该预设的相似条件可以用于指示可穿戴设备获取的生理信号中每个周期的信号是否为正常生理信号。
需要说明的是，在两个周期的信号之间的相似性由这两个周期的信号的样本序列的相关系数表示时，这两个周期的信号的相似参数的取值范围可以为[0，1]。一般而言，若两个周期的信号的相似参数大于或等于0.8时，则说明这两个周期的信号之间的相似性较高；若两个周期的信号的相似参数小于0.8时，则说明这两个周期的信号之间的相似性较低。若两个周期的信号的相似参数等于0时，则说明这两个周期的信号之间没有相似性。若两个周期的信号的相似参数等于1时，则说明这两个周期的信号之间完全相似。
其中，若上述第i个周期的信号的相似参数为第i个周期的信号与当前N个信号模板中每个信号模板的相似参数之和，则上述“第i个周期的信号的相结果是否满足预设的相似条件”可以为第i个周期的信号的相似参数是否大于等于0.8×N。若上述第i个周期的信号的相似参数为第i个周期的信号与当前N个信号模板中每个信号模板的相似参数之间的均值，则上述“第i个周期的信号的相似结果是否满足预设的相似条件”可以为第i个周期的信号的相似参数是否大于等于0.8。
S603、若第i个周期的信号的相似结果满足预设相似条件，可穿戴设备则判断第i个周期的信号为正常生理信号。
其中，上述若第i个周期的信号的相似结果满足预设相似条件时，说明第i个周期的信号的信号质量达到正常生理信号的标准，即第i个周期的信号为正常生理信号。随后，可穿戴设备可以标记第i个周期的信号为正常生理信号，并根据第i个周期的信号得到人体生理信息。
S604、若第i个周期的信号的相似结果不满足预设相似条件，可穿戴设备则判断第i个周期的信号为异常生理信号。
其中，上述若第i个周期的信号的相似结果不满足预设相似条件时，说明第i个周期的信号的信号质量没有达到正常生理信号的标准，即第i个周期的信号为异常生理信号。随后，可穿戴设备可以标记第i个周期的信号为异常生理信号，并在确定人体生理信息的过程中不使用第i个周期的信号。
进一步的，在可穿戴设备确定第i个周期的信号的相似结果好于当前N个信号模板中至少一个信号模板的相似结果的情况下，可穿戴设备便可以更新当前信号模板集合。如在上述S603或S604之后，上述方法还可以包括S701。示例性的，如图7所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图7中，在图6所示的S603之后，上述方法还可以包括S701：
S701、可穿戴设备根据第i个周期的信号更新当前信号模板集合。
上述步骤701可以由图1所示的可穿戴设备10中的处理组件102来执行。
其中，若第i个周期的信号的信号质量比当前信号模板集合中的N个信号模板中的至少一个信号模板的信号质量高，可穿戴设备便可以根据第i个周期的信号更新上述当前信号模板集合。
需要说明的是，上述当前信号模板集合是可穿戴设备根据实时获取的生理信号不断更新的。其中，由于可穿戴设备根据信号质量较好的周期的信号替换信号质量相对较差的信号模板更新当前信号模板集合，因此上述当前信号模板集合中的信号模板的信号质量实时地提高。如此，根据上述实时更新的当前信号模板集合得到的生理信号质量判断结果的准确性较高。
一般而言，用于更新当前信号模板集合的一个周期的信号为信号质量较好的正常生理信号；当然，也可以为信号质量较好的异常生理信号。其中，由异常生理信号更新当前信号模板的情况通常发生在可穿戴设备得到未更新的信号模板集合之后的几次更新过程中。
由于本发明实施例中第i个周期的信号的信号质量与第i个周期的信号的相似结果是相关的，因此可穿戴设备可以根据第i个周期的信号的相似结果更新当前信号模板集合。在另一种可能的实现方式中，本发明实施例提供的生理信号质量判断方法中，上述S701具体可以包括S801-S802。示例性的，如图8所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图8中，图7中的S701具体可以包括S801-S802：
S801、可穿戴设备确定第i个周期的信号的相似结果好于当前N个信号模板中至少一个信号模板的相似结果。
此时，第i个周期的信号的信号质量高于当前N个信号模板中至少一个信号模板的信号质量。
S802、可穿戴设备使用第i个周期的信号替换当前信号模板集合中相似结果最差的信号模板。
其中，可穿戴设备使用第i个周期的信号替换当前信号模板集合中相似结果最差的信号模板，即可穿戴设备将该相似结果最差的信号模板从当前信号模板集合中删除，并使用相似结果较好的第i个周期的信号作为新的信号模板更新当前信号模板集合。当前信号模板集合中的N个信号模板中一个信号模板的相似结果可以根据第i个周期的信号之前的生理信号得到。
可选的，上述“可穿戴设备使用第i个周期的信号替换当前信号模板集合中相似结果最差的信号模板”可以替换为可穿戴设备使用第i个周期的信号替换当前信号模板集合中任一相似结果较差的信号模板。其中，上述任一相似结果较差的信号模板的相似结果比第i个周期的信号的相似结果差。
需要说明的是，可穿戴设备在根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量之前，还可以获取该当前信号模板。具体的，在另一种可能的实现方式中，本发明实施例提供的生理信号质量判断方法，在上述S304或者S601之前还可以包括S901。示例性的，如图9所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图9中，图8所示的S601之前还可以包括S901：
S901、可穿戴设备根据第i个周期的信号之前的生理信号获取当前信号模板集合。
上述步骤901可以由图1所示的可穿戴设备10中的处理组件102来执行。
其中，上述当前信号模板集合可以是已被可穿戴设备更新过的信号模板集合，如当前信号模板集合可以是已被可穿戴设备根据第i-1个周期的信号更新过的信号模板集合。或者，上述当前信号模板集合可以是未被可穿戴设备更新过的信号模板集合，此时当前信号模板集合为可穿戴设备获取的初始信号模板集合。
具体的，在另一种可能的实现方式中，可穿戴设备在根据第i个周期的信号之前的生理信号获取当前信号模板集合之前，还可以获取未被更新过的初始信号模板集合。示例性的，如图10所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图10中，图9所示的方法在S901之前还可以包括S1001：
S1001、可穿戴设备根据前N+a个周期的信号获取初始信号模板集合。
上述步骤1001可以由图1所示的可穿戴设备10中的处理组件102来执行。
其中，上述N+a小于i，如N+a小于或等于i-1。上述a为大于等于0的整数。
具体的，可穿戴设备根据前N+a个周期的信号获取初始信号模板集合，可以是根据前N+a个周期的信号中每个周期的信号的相似性获取的。从而，在另一种可能的实现方式中，上述方法中的S1001具体可以包括S1101-S1102。示例性的，如图11所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图11中，图10中所示方法中的S1001具体可以包括S1101-S1102：
S1101、可穿戴设备确定前N+a个周期的信号中每个周期的信号的相似性。
其中，上述前N+a个周期的信号中一个周期的信号的相似结果为该周期的信号与前N+a个周期的信号中除该周期的信号之外的其他周期的信号之间的相似性组成的。其中，前N+a个周期的信号中的两个周期的信号之间的相似性也可以由这两个周期的信号的相似参数表示，该相似参数也可以为这两个周期的信号的样本序列之间的相关系数。从而，前N+a个周期的信号中一个周期的信号的相似结果，可以由该周期的信号的相似参数表示。
参考上述实施例中，可穿戴设备还可以记录前N+a个周期的信号中每个周期的信号的样本序列。例如，可穿戴设备可以将第2个周期的信号记录为x2＝{x2_1，x2_2，…x2_j，…，x2_n}，j∈{1，2，……，n}；将第3个周期的信号记录为x3＝{x3_1，x3_2，…x3_j，…，x3_n}；将第N+a-1个周期的信号记录为xN+a-1＝{xN+a-1_1，xN+a-1_2，…xN+a-1_j，…，xN+a-1_n}；将第N+a个周期的信号记录为xN+a＝{xN+a_1，xN+a_2，…xN+a_j，…，xN+a_n}。
示例性的，以可穿戴设备获取的第1个周期的信号的相似结果为例，说明上述前N+a个周期的信号中一个周期的信号的相似结果：第1个周期的信号的相似结果，可以由第1个周期的信号的相似参数表示。可穿戴设备可以将第1个周期的信号的相似参数记录为r1。
同时，可穿戴设备可以将第1个周期的信号与第2个周期的信号的相似参数记录为r1_2，相似参数r1_2可以为第1个周期的信号的样本序列x1与第2个周期的信号的样本序列x2的相关系数。可穿戴设备可以将第1个周期的信号与第3个周期的信号的相似参数记录为r1_3，相似参数r1_3可以为第1个周期的信号的样本序列x1与第3个周期的信号的样本序列x3的相关系数。可穿戴设备可以将第1个周期的信号与第N+a-1个周期的信号的相似参数记录为r1_N+a-1，相似参数r1_N+a-1可以为第1个周期的信号的样本序列x1与第N+a-1个周期的信号的样本序列xN+a-1的相关系数。可穿戴设备可以将第1个周期的信号与第N+a个周期的信号的相似参数记录为r1_N+a，相似参数r1_N+a可以为第1个周期的信号的样本序列x1与第N+a个周期的信号的样本序列xN+a的相关系数。
从而，在a等于1的情况下：第1个周期的信号的相似参数r1，可以为第1个周期的信号与前N+1个周期的信号中除第1个周期的信号之外的其他周期的信号的相似参数之和；或者，第1个周期的信号的相似参数，还可以为第1个周期的信号与前N+1个周期的信号中除第1个周期的信号之外的其他周期的信号的相似参数之间的均值。即第1个周期的信号的相似参数可以为
r1＝r1_2+r1_3+......+r1_N+r1_N+1，或者，
Figure PCTCN2017086393-appb-000010
在a不等于1的情况下：第1个周期的信号的相似参数，可以为第1个周期的信号与前N+a个周期的信号中除第1个周期的信号之外的其他周期的信号的相似参数之间的均值。即第1个周期的信号的相似参数可以为
Figure PCTCN2017086393-appb-000011
示例性的，第1个周期的信号与第2个周期的信号的相似参数r1_2可以为
Figure PCTCN2017086393-appb-000012
其中，
Figure PCTCN2017086393-appb-000013
为第1个周期的信号的样本序列x1中n个样本的均值，且
Figure PCTCN2017086393-appb-000014
为第2个周期的信号的样本序列x2中n个样本的均值，且
Figure PCTCN2017086393-appb-000015
进一步的，将
Figure PCTCN2017086393-appb-000016
带入(3)式中，第1个周期的信号与第2个周期的信号的相似参数r1_2还可以为：
Figure PCTCN2017086393-appb-000017
类似的，对第1个周期的信号的相似参数r1_3、相似参数r1_N+a-1、相似参数r1_N+a以及其他相似参数的具体描述可以参考对相似参数r1_2的详细描述，本发明实施例不再赘述。
需要说明的是，可穿戴设备确定前N+a个周期的信号中每个周期的信号的相似结果之后，即得到前N+a个周期的信号中每个周期的信号的相似参数之后，便可以判断前N+a个周期的信号中每个周期的信号的信号质量。具体的，对于前N+a个周期的信号中每个周期的信号：若周期的信号的相似结果满足预设的相似条件，可穿戴设备则判断该周期的信号为正常生理信号；若周期的信号的相似结果不满足预设的相似条件，可穿戴设备则判断该周期的信号为异常生理信号。
进一步的，可穿戴设备在判断得到前N+a个周期的信号中每个周期的信号的信号质量的同时，还可以从前N+a个周期的信号中获取包括N个信号模板的初始信号模板集合。具体的，在另一种可能的实现方式中，上述方法在S1101之后，还包括S1102:
S1102、可穿戴设备将前N+a个周期的信号中相似结果最好的前N个周期的信号确定为初始信号模板集合。
上述步骤1102可以由图1所示的可穿戴设备10中的处理组件102来执行。
其中，当a等于0时，上述初始信号模板集合中的N个信号模板为可穿戴设备获取的前N个周期的信号。当a大于0时，可穿戴设备获取的前N+a个周期的信号有a个周期的信号不为初始信号模板集合中的信号模板。
需要说明的是，可穿戴设备根据前N+a个周期的信号获取初始信号模板集合之后，在接收第N+a个周期的信号之后的每个周期的信号时，还可以确定当前信号模板集合。其中，当前信号模板集合可以为未被可穿戴设备更新过的初始信号模板集合，或者当前信号模板集合可以为可穿戴设备更新初始信号模板集合后得到的信号模板集合。
相应的，在另一种可能的实现方式中，图10或图11所示的方法中，S901可以替换为S1002：
S1002、可穿戴设备根据初始信号模板集合和第N+a个周期的信号到第i 个周期的信号之间的生理信号获取当前信号模板集合。
相应的，上述步骤1002也可以由图1所示的可穿戴设备10中的处理组件102来执行。
具体的，在N+a等于i-1的情况下，可穿戴设备获取第i个周期的信号时的当前信号模板集合为上述未被可穿戴设备更新过的初始信号模板集合。
在N+a小于i-1的情况下，可穿戴设备获取第i个周期的信号时，当前信号模板集合为上述未被可穿戴设备更新过的初始信号模板集合；或者，当前信号模板集合为可穿戴设备根据第N+a个周期的信号到第i个周期的信号之间的生理信号更新上述初始信号模板集合得到的信号模板集合。
示例性的，在N+a小于i-1的情况下，若i-1等于N+a+1，并且第i-1个周期的信号的相似结果好于上述初始信号模板集合包括的N个信号模板中至少一个信号模板的相似结果，可穿戴设备则使用第i-1个周期的信号替换上述初始信号模板集合中相似结果最差的信号模板。随后，可穿戴设备获取第i个周期的信号时，当前信号模板集合为使用第i-1个周期的信号替换初始信号模板集合中相似结果最差的信号模板后得到的信号模板集合。
可选的，上述“可穿戴设备使用第i-1个周期的信号替换上述初始信号模板集合中相似结果最差的信号模板”可以替换为可穿戴设备使用第i-1个周期的信号替换上述初始信号模板集合中任一相似结果较差的信号模板。其中，上述任一相似结果较差的信号模板的相似结果比第i-1个周期的信号的相似结果差。
例如，在N等于5，a等于1，i-1等于7，i等于8的情况下，可穿戴设备从前6个周期的信号中获取初始信号模板集合。假设第1个周期的信号的相似参数r1等于0.7，第2个周期的信号的相似参数r2等于0.75，第3个周期的信号的相似参数r3等于0.8，第4个周期的信号的相似参数r4等于0.85，第5个周期的信号的相似参数r5等于0.85，第6个周期的信号的相似参数r6等于0.9。此时，可穿戴设备获取到的初始信号模板集合中的5个信号模板可以为第2个周期的信号、第3个周期的信号、第4个周期的信号、第5个周期的信号和第6个周期的信号。可穿戴设备可以将初始信号模板集合可以记录为y＝{x2，x3，x4，x5，x6}。
随后，若第7个周期的信号的相似参数r7等于0.6，可穿戴设备则不会更新上述初始信号模板集合。从而，可穿戴设备获取第8个周期的信号时，当前信号模板集合为上述初始信号模板集合。也就是说，当前信号模板集合中包括的5个信号模板仍为第2-6个周期的信号；可穿戴设备可以将当前信号模板集合可以记录为y＝{x2，x3，x4，x5，x6}。
若第7个周期的信号的相似参数r7等于0.95，可穿戴设备则使用第7个周期的信号替换上述初始信号模板集合中相似结果最差的第2个周期的信号。从而，可穿戴设备获取第8个周期的信号时，当前信号模板集合为更新上述初始信号模板集合得到的信号模板集合。也就是说，当前信号模板集合中包括的5个信号模板为第2-7个周期的信号；可穿戴设备可以将当前信号模板 集合可以记录为y＝{x7，x3，x4，x5，x6}。
其中，可穿戴设备获取的初始信号模板集合中的N个信号模板不一定都为信号质量较好的正常生理信号，但只要初始信号模板集合包括N个信号模板便可以支持可穿戴设备执行本发明实施例提供的生理信号质量判断方法。随着可穿戴设备获取的生理信号中周期数的增多，当前信号模板集合可以被不断更新，使得当前信号模板集合中任一信号模板的信号质量可以被提高。即经过可穿戴设备更新过的当前信号模板集合中的N个信号模板通常均为信号质量较好的正常生理信号。从而，使得可穿戴设备根据上述当前信号模板集合得到的生理信号质量判断结果的准确性较高。
需要说明的是，可穿戴设备根据初始信号模板集合和第N+a个周期的信号到第i个周期的信号之间的周期的信号获取当前信号模板集合的同时，还可以确定第N+a个周期的信号到第i个周期的信号之间的每个周期的信号的相似结果。即可穿戴设备可以得到第N+a个周期的信号到第i个周期的信号之间的每个周期的信号的相似参数，以判断第N+a个周期的信号到第i个周期的信号之间的每个周期的信号的信号质量。具体的，第N+a个周期的信号到第i个周期的信号之间的每个周期的信号：若周期的信号的相似结果满足预设的相似条件，可穿戴设备则判断该周期的信号为正常生理信号；若周期的信号的相似结果不满足预设的相似条件，可穿戴设备则判断该周期的信号为异常生理信号。
进一步的，由于可穿戴设备获取的生理信号中每个周期的信号都可以具有相同特征点。因此可穿戴设备还可以根据生理信号的特征点对应的特征值判断生理信号的信号质量。具体的，在另一种可能的实现方式中，本发明实施例提供的生理信号质量判断方法中，上述S303之后还可以包括S1201、S1202和S1203。示例性的，如图12所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图12中，图3中的S303之后还可以包括S1201、S1202和S1203：
S1201、可穿戴设备根据生理信号的特征点，获取第i个周期的信号的特征值。
其中，可穿戴设备可以根据生理信号中每个周期的信号的顶点和底点，获取上述每个周期的信号的周期值以及该每个周期的信号的高度值。从而，上述第i个周期的信号的特征值包括：第i个周期的信号的周期值和/或第i个周期的信号的高度值。其中，第i个周期的信号的高度值的可以包括第i个周期的信号的左支高度值和第i个周期的信号的右支高度值。具体的，每个周期的信号的周期值可以为该周期的信号中两个相邻底点之间的时间间隔；每个周期的信号的高度值可以为该周期的信号中顶点到两个底点中每个底点的幅值。
具体的，可穿戴设备可以每隔3s获取一次生理信号，得到一段生理信号的波形。可穿戴设备可以将第i个周期的信号的周期值记录为Ti。可穿戴设备可以根据生理信号中每个周期的信号包括的点数和两个点之间的时间间隔， 得到每个周期的信号的周期值，如得到第i个周期的信号的周期值Ti。例如，在采样频率为100Hz的情况下，图5所示的生理信号波形中每两个离散的之间的时间间隔可以为0.01s。此时，图5所示的第1个周期的信号的波形中可以包括30个点，则第1个周期的信号的周期值T1可以是0.3s。
其中，可穿戴设备可以根据第i个周期的信号之前的周期的信号确定当前预设阈值范围。具体的，可穿戴设备可以根据第一次获取的一组生理信号中所有周期的信号的特征值的均值得到初始预设阈值范围。随后，可穿戴设备可以根据后续获取的所有周期的生理信号的特征值更新初始预设阈值范围，以得到当前预设周期值范围。示例性的，当前的周期值的均值为
Figure PCTCN2017086393-appb-000018
则当前预设周期值范围可以为
Figure PCTCN2017086393-appb-000019
类似的，可穿戴设备获取的生理信号的当前的左支高度值的均值可以记为
Figure PCTCN2017086393-appb-000020
当前的右支高度值的均值可以记为
Figure PCTCN2017086393-appb-000021
可穿戴设备获取的生理信号的当前预设左支高度值范围可以为
Figure PCTCN2017086393-appb-000022
当前预设左支高度值范围可以为
Figure PCTCN2017086393-appb-000023
需要说明的是，本发明实施例中可穿戴设备根据获取的生理信号的特征值的均值得到的预设阈值范围不是唯一的，可以由相关技术人员根据实际情况调整。
S1202、可穿戴设备确定第i个周期的信号的特征值不处于当前预设阈值范围内，并判断第i个周期的信号为异常生理信号。
具体的，第i个周期的信号的特征值不处于当前预设阈值范围，包括：第i个周期的信号的周期值不处于当前预设周期范围，和/或第i个周期的信号的高度值不处于当前预设高度范围。例如，第i个周期的信号的周期值Ti的取值范围不处于
Figure PCTCN2017086393-appb-000024
时，第i个周期的信号为异常生理信号。
相应的，可穿戴设备在根据第i个周期的信号与当前信号模板集合之间的相似性判断第i个周期的信号的信号质量之前，还可以第i个周期的信号的特征值判断第i个周期的信号有可能为正常生理信号。具体的，上述方法在S304之前，还可以包括S1203：
S1203、可穿戴设备确定第i个周期的信号的特征值处于当前预设阈值范围。
其中，上述步骤1201-1203均可以由图1所示的可穿戴设备10中的处理组件102来执行。
具体的，第i个周期的信号的特征值处于当前预设阈值范围，包括：第i个周期的信号的周期值处于当前预设周期范围和第i个周期的信号的高度值处于当前预设高度范围。例如，第i个周期的信号的周期值Ti在
Figure PCTCN2017086393-appb-000025
Figure PCTCN2017086393-appb-000026
内、第i个周期的信号的左支高度值在
Figure PCTCN2017086393-appb-000027
内，且第i个周期的信号的右支高度值在
Figure PCTCN2017086393-appb-000028
内，则第i个周期的信号可能为正常生理信号。
需要说明的是，本发明实施例提供的生理信号质量判断方法中，可穿戴设备可以根据生理信号的特征值中的周期值和高度值判断生理信号中每个周 期的信号的信号质量。即可穿戴设备提取到生理信号的特征点便可以判断生理信号中每个周期的信号的信号质量，可以在一定程度上减小判断生理信号质量过程中的计算量。
进一步的，可穿戴设备可以根据第i个周期的信号之前的生理信号确定当前预设阈值范围。具体的，可穿戴设备可以根据第一次获取的一组生理信号中所有周期的信号的特征值的均值得到初始预设阈值范围。随后，可穿戴设备可以根据后续获取的生理信号中所有周期的信号的特征值更新初始预设阈值范围，以得到当前预设阈值范围。从而，在另一种可能的实现方式中，本发明实施例提供的方法，在S303之后，还可以包括S1301和S1302。示例性的，如图13所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图13中的S303之后还可以包括S1301和S1302：
S1301、可穿戴设备根据第i个周期的信号之前的生理信号确定当前预设阈值范围。
其中，可穿戴设备可以根据第i个周期的信号之前的周期的信号确定当前预设阈值范围。具体的，可穿戴设备可以根据第一次获取的一组生理信号中所有周期的信号的周期值的均值得到初始预设周期值范围。示例性的，可穿戴设备可以根据前3s内获取的生理信号中所有周期的信号的周期值的均值得到初始预设周期值范围。随后，可穿戴设备可以根据后续的、第i个周期的信号之前每隔3s时间间隔获取的生理信号的周期值更新初始预设周期值范围，以得到当前预设周期值范围。
类似的，可穿戴设备可以根据第一次获取的一组生理信号中所有周期的信号的高度值的均值得到初始预设左支高度值范围和初始预设左支高度值范围。随后，可穿戴设备可以根据后续获取的生理信号的高度值更新预设左支高度值范围和初始预设左支高度值范围，以得到当前预设左支高度值范围和当前预设左支高度值范围。
示例性的，可穿戴设备可以根据前3s内获取的生理信号中所有周期的信号的高度值的均值得到初始预设左支值范围和初始右支高度值范围。随后，可穿戴设备可以根据后续的、第i个周期的信号之前每隔3s时间间隔获取的生理信号中所有周期的信号的高度值更新初始预设左支值范围和初始右支高度值范围，以得到当前预设左支值范围和当前预设右支高度值范围预设周期值范围。
需要说明的是，可穿戴设备可以根据第i个周期的信号之后每隔3s时间间隔获取的生理信号中所有周期的信号的周期值更新当前预设周期值范围，以得到新的当前预设周期值范围。相应的，上述方法在S1203之后还可以包括S1302：
S1302、可穿戴设备根据第i个周期的信号的特征值，更新当前预设阈值范围。
其中，上述步骤1301-1302均可以由图1所示的可穿戴设备10中的处理组件102来执行。
需要说明的是，本发明实施例提供的生理信号质量判断方法中，上述当前预设阈值范围是根据实时获取的生理信号不断更新的；并且当前预设阈值范围是可穿戴设备根据获取的生理信号中的所有周期的信号获取的，即当前预设阈值范围是根据全局变量得到的；因此，上述当前预设阈值范围是符合可穿戴设备实时获取的生理信号的。从而，本发明实施例提供的生理信号质量判断方法，可以进一步提高生理信号质量判断结果的准确性。
进一步的，可穿戴设备在判断得到生理信号中每个周期的信号的信号质量之后，可以使用判断的到的正常生理信号获取人体生理信息。具体的，在另一种可能的实现方式中，上述S304或者S603或者S604之后，上述方法还可以包括S1401。示例性的，如图14所示，为本发明实施例提供的另一种生理信号质量判断方法的流程示意图。图14中的S304之后还可以包括S1401：
S1401、可穿戴设备输出信号质量判断结果。
上述步骤1401可以由图1所示的可穿戴设备10中的处理组件102通过多媒体组件104来执行。
其中，上述信号质量判断结果包括第i个周期的信号为正常生理信号或异常生理信号，以及第i个周期的信号之前的每个周期的信号为正常生理信号或异常生理信号。具体的，可穿戴设备可以为正常生理信号和异常生理信号作不同的标记，还可以输出获取的生理信号中的所有周期的信号中正常生理信号所占的比例，本发明实施例对此不作限定。这样一来，可穿戴设备判断得到的生理信号质量判断结果可以较为直观的展示给用户或者相关技术人员，使得用户体验较好。
需要说明的是，本发明实施例提供的生理信号质量判断方法，可穿戴设备可以实时地、逐周期判断采集到的生理信号的信号质量，并较为准确地区分出该生理信号中任一周期的信号为正常生理信号还是异常生理信号。如此，可穿戴设备可以根据判断得到的正常生理信号得到较为准确的人体生理信息。
上述主要从生理信号质量判断装置中可穿戴设备的角度对本发明实施例提供的方案进行了介绍。可以理解的是，生理信号质量判断装置为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的算法步骤，本发明能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
本发明实施例可以根据上述方法示例对生理信号质量判断装置进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本发明实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用对应各个功能划分各个功能模块的情况下，图15示出了上述实施例中提供的生理信号质量判断装置的一种可能的组成示意图，如图15所示，生理信号质量判断装置15可以包括：采集模块151、提取模块152、划分模块153和判断模块154。其中，采集模块151，用于支持生理信号质量判断装置15执行上述实施例中的S301，和/或用于本文所描述的技术的其它过程。提取模块152，用于支持生理信号质量判断装置15执行上述实施例中的S302，和/或用于本文所描述的技术的其它过程。划分模块153，用于支持生理信号质量判断装置15执行上述实施例中的S303，和/或用于本文所描述的技术的其它过程。判断模块154，用于支持生理信号质量判断装置15执行上述实施例中的S304、S602、S603、S604和S1202，和/或用于本文所描述的技术的其它过程。
进一步的，图16示出了上述实施例中提供的生理信号质量判断装置的另一种可能的组成示意图，如图16所示，生理信号质量判断装置15还可以包括：确定模块155。确定模块155，用于支持生理信号质量判断装置15执行上述实施例中的S601和S1301，和/或用于本文所描述的技术的其它过程。
进一步的，图17示出了上述实施例中提供的生理信号质量判断装置的另一种可能的组成示意图，如图17所示，生理信号质量判断装置15还可以包括：更新模块156。更新模块156，用于支持生理信号质量判断装置15执行上述实施例中的S701、S801、S802和S1302，和/或用于本文所描述的技术的其它过程。
进一步的，图18示出了上述实施例中提供的生理信号质量判断装置的另一种可能的组成示意图，如图18所示，生理信号质量判断装置15还可以包括：获取模块157。获取模块157，用于支持生理信号质量判断装置15执行上述实施例中的S901、S1001、S1002、S1102、S1102、S1201和S1202和S1203，和/或用于本文所描述的技术的其它过程。
进一步的，图19示出了上述实施例中提供的生理信号质量判断装置的另一种可能的组成示意图，如图19所示，生理信号质量判断装置15还可以包括：输出模块158。输出模块158，用于支持生理信号质量判断装置15执行上述实施例中的S1401，和/或用于本文所描述的技术的其它过程。
需要说明的是，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
本发明实施例提供的生理信号质量判断装置，用于执行上述生理信号质量判断方法，因此可以达到与上述生理信号质量判断方法相同的效果。
在采用集成的单元的情况下，上述提取模块152、划分模块153、判断模块154、确定模块155、更新模块156和获取模块157等可以集成在一个处理模块中实现。上述处理模块可以是处理器或控制器，例如可以是CPU，通用处理器，数字信号处理器(Digital Signal Processor，DSP)，专用集成电路(Application-Specific Integrated Circuit，ASIC)，现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、晶体管逻辑器 件、硬件部件或者其任意组合。其可以实现或执行结合本发明公开内容所描述的各种举例说明逻辑方框，模块和电路。上述处理单元也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。存储模块可以是存储器。上述采集模块151可以由输入器实现。上述输出模块158可以由显示器实现。
当上述处理模块为处理器，存储模块为存储器时，本发明实施例提供一种如图20所示的生理信号质量判断装置20。如图20所示，生理信号质量判断装置20包括：处理器201、存储器222、显示器203、输入器204以及总线205。其中，处理器201、存储器202、显示器203和输入器204通过总线205相互连接。其中，上述总线205可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。上述总线205可以分为地址总线、数据总线、控制总线等。为便于表示，图20中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
示例性的，上述输入器204可以包括摄像头和穿戴式传感器等，如穿戴设备10中的传感器组件101。上述显示器203可以为可穿戴设备10中的多媒体组件104或音频组件105。
其中，本发明实施例提供的生理信号质量判断装置20中各个模块的详细描述以及各个模块执行上述实施例中的相关方法步骤后所带来的技术效果可以参考本发明方法实施例中的相关描述，此处不再赘述。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单 元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。所述集成的单元如果以软件功能单元的形式实现并作为独立的计算机程序产品销售或使用时，可以存储在一个计算机可读取存储介质中。
本申请的技术方案在使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括至少一个指令。在计算机上加载和执行所述指令时，全部或部分地产生按照本发明实施例所述的流程或功能。所述计算机可以是通过计算机、专用计算机、计算机网络、或者其他可编程装置。所述指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机可以从一个网站站点、计算机、服务器或数据中心通过同轴电缆、光纤、数字用户线(DSL)等有线方式，或红外、无线、微波等无线方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是软盘、硬盘、磁带等磁性介质，或者固态硬盘(Solid State Disk，SSD)等半导体介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何在本申请揭露的技术范围内的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (25)

  1. 一种生理信号质量判断方法，其特征在于，包括：
    采集生理信号，所述生理信号为周期信号或类周期信号；
    提取所述生理信号的特征点，所述特征点包括用于指示所述生理信号周期的特征点；
    根据所述生理信号的特征点，对所述生理信号划分周期；
    根据第i个周期的信号与当前信号模板集合之间的相似性判断所述第i个周期的信号的信号质量；其中，所述信号模板集合包括N个信号模板，所述N个信号模板根据所述第i个周期的信号之前的生理信号获取，所述N大于等于2，所述i大于所述N。
  2. 根据权利要求1所述的方法，其特征在于，所述根据第i个周期的信号与信号模板集合之间的相似性判断所述第i个周期的信号的信号质量，包括：
    确定所述第i个周期的信号的相似结果，所述第i个周期的信号的相似结果用于指示所述第i个周期的信号与所述当前信号模板集合之间相似性；
    若所述第i个周期的信号的相似结果满足预设相似条件，则判断所述第i个周期的信号为正常生理信号，所述预设相似条件为预先设置的；
    若所述第i个周期的信号的相似结果不满足所述预设相似条件，则判断所述第i个周期的信号为异常生理信号。
  3. 根据权利要求2所述的方法，其特征在于，在确定所述第i个周期的信号的相似结果好于所述N个信号模板中至少一个信号模板的相似结果的情况下，所述方法还包括：根据所述第i个周期的信号更新所述当前信号模板集合，其中，所述N个信号模板中一个信号模板的相似结果根据第i个周期的信号之前的生理信号得到的。
  4. 根据权利要求3所述的方法，其特征在于，所述根据所述第i个周期的信号更新所述当前信号模板集合，包括：
    使用所述第i个周期的信号替换所述当前信号模板集合中相似结果最差的信号模板。
  5. 根据权利要求1-4中任一项所述的方法，其特征在于，在所述根据第i个周期的信号与当前信号模板集合之间的相似性判断所述第i个周期的信号的信号质量之前，所述方法还包括：根据所述第i个周期的信号之前的生理信号获取所述当前信号模板集合。
  6. 根据权利要求4所述的方法，其特征在于，所述根据所述第i个周期的信号之前的生理信号获取所述当前信号模板集合，包括：
    根据前N+a个周期的信号获取初始信号模板集合；
    根据所述初始信号模板集合和第N+a个周期的信号到所述第i个周期的信号之间的生理信号获取所述当前信号模板集合。
  7. 根据权利要求6所述的方法，其特征在于，所述根据前N+a个周期的信号获取初始信号模板集合，包括：
    确定前N+a个周期的信号中每个周期的信号的相似结果；所述a为大于等 于0的整数，所述N+a小于所述i；其中，所述前N+a个周期的信号中一个周期的信号的相似结果由所述周期的信号与所述前N+a个周期的信号中除所述周期的信号之外的其他周期的信号之间的相似性组成的；
    将所述前N+a个周期的信号中相似结果最好的前N个周期的信号确定为所述初始信号模板集合。
  8. 根据权利要求7所述的方法，其特征在于，在所述提取所述生理信号的特征点之后，还包括：
    根据所述生理信号的特征点，获取所述第i个周期的信号的特征值；
    确定所述第i个周期的信号的特征值不处于当前预设阈值范围内，并判断所述第i个周期的信号为异常生理信号，所述当前预设阈值范围根据所述第i个周期的信号之前的生理信号确定；
    在所述根据第i个周期的信号与信号模板集合之间的相似性判断所述第i个周期的信号的信号质量之前，所述方法还包括：确定所述第i个周期的信号的特征值处于所述当前预设阈值范围。
  9. 根据权利8所述的方法，其特征在于，所述第i个周期的信号的特征值包括：所述第i个周期的信号的周期值和/或所述第i个周期的信号的高度值；
    所述当前预设阈值范围包括：当前预设周期范围和/或当前预设高度范围；所述第i个周期的信号的特征值不处于所述当前预设阈值范围，包括：所述第i个周期的信号的周期值不处于所述当前预设周期范围，和/或所述第i个周期的信号的高度值不处于所述当前预设高度范围；
    所述第i个周期的信号的特征值处于所述当前预设阈值范围，包括：所述第i个周期的信号的周期值处于所述当前预设周期范围，和所述第i个周期的信号的高度值处于所述当前预设高度范围。
  10. 根据权利9所述的方法，其特征在于，在所述根据所述生理信号的特征点，获取所述第i个周期的信号的特征值之前，还包括：
    根据所述第i个周期的信号之前的周期的信号确定所述当前预设阈值范围；
    在所述根据所述生理信号的特征点，获取所述第i个周期的信号的特征值之后，所述方法还包括：
    根据所述第i个周期的信号的特征值，更新所述当前预设阈值范围。
  11. 根据权利要求1-10中任一项所述的方法，其特征在于，还包括：
    输出信号质量判断结果，所述信号质量判断结果包括所述第i个周期的信号为正常生理信号或所述第i个周期的信号为异常生理信号，以及所述第i个周期的信号之前的每个周期的信号为正常生理信号或所述每个周期的信号为异常生理信号；
    其中，若所述第i个周期的信号之前的一个周期的信号的相似结果满足所述预设相似条件，则所述周期的信号为正常生理信号；若所述第i个周期的信号之前的一个周期的信号的相似结果不满足所述预设相似条件，则所述周期的信号为异常生理信号。
  12. 一种生理信号质量判断装置，其特征在于，包括：
    采集模块，用于采集生理信号，所述生理信号为周期信号或类周期信号；
    提取模块，用于提取所采集模块采集的所述生理信号的特征点，所述特征点包括用于指示所述生理信号周期的特征点；
    划分模块，用于根据所述提取模块提取的所述生理信号的特征点，对所述生理信号划分周期；
    判断模块，用于根据第i个周期的信号与当前信号模板集合之间的相似性判断所述第i个周期的信号的信号质量；其中，所述信号模板集合包括N个信号模板，所述N个信号模板为根据所述采集模块采集的所述第i个周期的信号之前的生理信号获取，所述N大于等于2，所述i大于所述N。
  13. 根据权利要求12所述的装置，其特征在于，还包括：
    确定模块，用于确定所述划分模块划分出的第i个周期的信号的相似结果，所述第i个周期的信号的相似结果用于指示所述第i个周期的信号与所述当前信号模板集合之间的相似性；
    所述判断模块，具体用于若所述第i个周期的信号的相似结果满足预设相似条件，则判断所述第i个周期的信号为正常生理信号，所述预设相似条件为预先设置的；若所述第i个周期的信号的相似结果不满足所述预设相似条件，则判断所述第i个周期的信号为异常生理信号。
  14. 根据权利要求13所述的装置，其特征在于，还包括：更新模块，用于在确定所述第i个周期的信号的相似结果好于所述N个信号模板中至少一个信号模板的相似结果的情况下，根据所述第i个周期的信号更新所述当前信号模板集合，其中，所述N个信号模板中一个信号模板的相似性根据第i个周期的信号之前的生理信号得到的。
  15. 根据权利要求14所述的装置，其特征在于，所述更新模块具体用于使用所述第i个周期的信号替换所述当前信号模板集合中相似性最低的信号模板。
  16. 根据权利要求12-15中任一项所述的装置，其特征在于，还包括：
    获取模块，用于在所述判断模块根据第i个周期的信号与当前信号模板集合之间的相似性判断所述第i个周期的信号的信号质量之前，根据所述第i个周期的信号之前的生理信号获取所述当前信号模板集合。
  17. 根据权利要求16所述的装置，其特征在于，所述获取模块，具体用于根据前N+a个周期的信号获取初始信号模板集合；根据所述初始信号模板集合和第N+a个周期的信号到所述第i个周期的信号之间的生理信号获取所述当前信号模板集合。
  18. 根据权利要求17所述的装置，其特征在于，所述确定模块，还用于确定前N+a个周期的信号中每个周期的信号的相似结果；所述a为大于等于0的整数，所述N+a小于所述i；其中，所述前N+a个周期的信号中一个周期的信号的相似结果为所述周期的信号与所述前N+a个周期的信号中除所述周期的信号之外的其他周期的信号之间的相似性组成的；
    所述获取模块具体用于将所述确定模块确定出的所述前N+a个周期的信 号中相似结果最好的前N个周期的信号确定为所述初始信号模板集合。
  19. 根据权利要求18所述的装置，其特征在于，所述获取模块，还用于在所述提取模块提取所述生理信号的特征点之后，根据所述生理信号的特征点，获取所述第i个周期的信号的特征值；
    所述判断模块，还用于确定所述第i个周期的信号的特征值不处于当前预设阈值范围内，并判断所述第i个周期的信号为异常生理信号，所述当前预设阈值范围根据所述第i个周期的信号之前的周期的信号确定；在所述根据第i个周期的信号与信号模板集合之间的相似性判断所述第i个周期的信号的信号质量之前，确定所述第i个周期的信号的特征值处于所述当前预设阈值范围。
  20. 根据权利要求19所述的装置，其特征在于，所述第i个周期的信号的特征值包括：所述第i个周期的信号的周期值和/或所述第i个周期的信号的高度值；所述当前预设阈值范围包括：当前预设周期范围和/或当前预设高度范围；
    所述第i个周期的信号的特征值不处于所述当前预设阈值范围，包括：所述第i个周期的信号的周期值不处于所述当前预设周期范围，和/或所述第i个周期的信号的高度值不处于所述当前预设高度范围；
    所述第i个周期的信号的特征值处于所述当前预设阈值范围，包括：所述第i个周期的信号的周期值处于所述当前预设周期范围，和所述第i个周期的信号的高度值处于所述当前预设高度范围。
  21. 根据权利要求20所述的装置，其特征在于，所述确定模块，还用于在所述获取模块根据所述生理信号的特征点，获取所述第i个周期的信号的特征值之前，根据所述第i个周期的信号之前的生理信号确定所述当前预设阈值范围；
    所述更新模块，还用于在所述获取模块根据所述生理信号的特征点，获取所述第i个周期的信号的特征值之后，根据所述第i个周期的信号的特征值，更新所述当前预设阈值范围。
  22. 根据权利要求12-21中任一项所述的装置，其特征在于，还包括：
    输出模块，用于输出信号质量判断结果，所述信号质量判断结果包括所述判断模块判断得到的所述第i个周期的信号为正常生理信号或所述第i个周期的信号为异常生理信号，以及所述第i个周期的信号之前的每个周期的信号为正常生理信号或所述每个周期的信号为异常生理信号；
    其中，若所述第i个周期的信号之前的一个周期的信号的相似结果满足所述预设相似条件，则判断所述周期的信号为正常生理信号；若所述第i个周期的信号之前的一个周期的信号的相似结果不满足所述预设相似条件，则判断所述周期的信号为异常生理信号。
  23. 一种生理信号质量判断装置，其特征在于，包括：处理器、存储器、显示器、输入器和总线；
    所述存储器用于存储至少一个指令，所述处理器、所述存储器、所述显示器和所述输入器通过所述总线连接，当所述装置运行时，所述处理器执行所述 存储器存储的所述至少一个指令，以使所述装置执行如权利要求1-11中任一项所述的生理信号质量判断方法。
  24. 一种计算机存储介质，其特征在于，包括：至少一个指令；
    当所述至少一个指令在计算机上运行时，使得所述计算机执行如权利要求1-11中任一项所述的生理信号质量判断方法。
  25. 一种计算机程序产品，其特征在于，包括：至少一个指令；
    当所述至少一个指令在计算机上运行时，使得所述计算机执行如权利要求1-11中任一项所述的生理信号质量判断方法。
PCT/CN2017/086393 2017-01-25 2017-05-27 一种生理信号质量判断方法及装置 WO2018137300A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201780009418.0A CN108633249B (zh) 2017-01-25 2017-05-27 一种生理信号质量判断方法及装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710061354 2017-01-25
CN201710061354.0 2017-01-25

Publications (1)

Publication Number Publication Date
WO2018137300A1 true WO2018137300A1 (zh) 2018-08-02

Family

ID=62978863

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/086393 WO2018137300A1 (zh) 2017-01-25 2017-05-27 一种生理信号质量判断方法及装置

Country Status (2)

Country Link
CN (1) CN108633249B (zh)
WO (1) WO2018137300A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3492003A1 (en) * 2017-12-01 2019-06-05 Samsung Electronics Co., Ltd. Bio-signal quality assessment apparatus and bio-signal quality assessment method
EP3991640A3 (en) * 2020-09-10 2022-06-01 Samsung Electronics Co., Ltd. Method of determining regularity of bio-signal, apparatus and method for estimating bio-information
US11457872B2 (en) 2017-12-01 2022-10-04 Samsung Electronics Co., Ltd. Bio-signal quality assessment apparatus and bio-signal quality assessment method
EP4166070A1 (en) * 2021-10-14 2023-04-19 Samsung Electronics Co., Ltd. Method of evaluating quality of bio-signal and apparatus for estimating bio-information
WO2023108331A1 (zh) * 2021-12-13 2023-06-22 中国科学院深圳先进技术研究院 自适应实时心电信号质量评估方法
WO2024066962A1 (zh) * 2022-09-28 2024-04-04 华为技术有限公司 呼吸健康检测方法及可穿戴电子设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112836546A (zh) * 2019-11-22 2021-05-25 深圳市理邦精密仪器股份有限公司 检测生理信号质量的方法、装置及电子设备
CN113040771B (zh) * 2021-03-01 2022-12-23 青岛歌尔智能传感器有限公司 情绪识别方法、系统、可穿戴设备及存储介质
CN115670397B (zh) * 2022-11-17 2023-06-02 北京中科心研科技有限公司 一种ppg伪迹识别方法、装置、存储介质及电子设备

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060224074A1 (en) * 2005-03-29 2006-10-05 Kabushiki Kaisha Toshiba Heartbeat measuring apparatus
US20100280402A1 (en) * 2009-04-30 2010-11-04 Texas Instruments Incorporated Method and Apparatus for Heart Rate Monitoring
US20110213559A1 (en) * 2010-02-05 2011-09-01 Prima-Temp Inc. Multi-sensor patch and system
CN102270264A (zh) * 2010-06-04 2011-12-07 中国科学院深圳先进技术研究院 生理信号质量评估系统及方法
CN102316792A (zh) * 2009-02-17 2012-01-11 皇家飞利浦电子股份有限公司 用于自动获取和存档临床上有意义的体征的系统和方法
CN103020472A (zh) * 2012-12-27 2013-04-03 中国科学院深圳先进技术研究院 基于约束估计的生理信号质量评估方法和系统
CN104321107A (zh) * 2012-03-27 2015-01-28 心脏起搏器股份公司 膈神经刺激阈值的确定
CN105138823A (zh) * 2015-07-28 2015-12-09 中国科学院电子学研究所 一种基于自相关函数的生理信号质量检测方法
WO2015190994A1 (en) * 2014-06-13 2015-12-17 Nitto Denko Corporation Device and method for removing artifacts in physiological measurements
CN105578960A (zh) * 2013-09-27 2016-05-11 皇家飞利浦有限公司 用于处理生理信号的处理装置、处理方法和系统
CA2930745A1 (en) * 2015-05-26 2016-11-26 Reticle Ventures Canada Incorporated System and method for asset authentication and management
US20160360984A1 (en) * 2015-06-15 2016-12-15 Microsoft Technology Licensing, Llc Optical Photoplethysmogram Signal Shape Feature Biological Monitor

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100527132C (zh) * 2007-06-22 2009-08-12 腾讯科技（深圳）有限公司 分类样本集的优化方法和内容相关广告服务器
EP2688468B1 (en) * 2011-03-24 2020-12-23 Drägerwerk AG & Co. KGaA Apparatus and method for measuring physiological signal quality
CN102592093B (zh) * 2012-01-16 2014-12-10 河南科技大学 一种基于生物免疫机制的主机入侵检测方法
CN103800003B (zh) * 2014-01-21 2016-10-05 杭州电子科技大学 一种心电检测方法及检测仪
CN105938552B (zh) * 2016-06-29 2020-04-24 北京旷视科技有限公司 底图自动更新的人脸识别方法及装置

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060224074A1 (en) * 2005-03-29 2006-10-05 Kabushiki Kaisha Toshiba Heartbeat measuring apparatus
CN102316792A (zh) * 2009-02-17 2012-01-11 皇家飞利浦电子股份有限公司 用于自动获取和存档临床上有意义的体征的系统和方法
US20100280402A1 (en) * 2009-04-30 2010-11-04 Texas Instruments Incorporated Method and Apparatus for Heart Rate Monitoring
US20110213559A1 (en) * 2010-02-05 2011-09-01 Prima-Temp Inc. Multi-sensor patch and system
CN102270264A (zh) * 2010-06-04 2011-12-07 中国科学院深圳先进技术研究院 生理信号质量评估系统及方法
CN104321107A (zh) * 2012-03-27 2015-01-28 心脏起搏器股份公司 膈神经刺激阈值的确定
CN103020472A (zh) * 2012-12-27 2013-04-03 中国科学院深圳先进技术研究院 基于约束估计的生理信号质量评估方法和系统
CN105578960A (zh) * 2013-09-27 2016-05-11 皇家飞利浦有限公司 用于处理生理信号的处理装置、处理方法和系统
WO2015190994A1 (en) * 2014-06-13 2015-12-17 Nitto Denko Corporation Device and method for removing artifacts in physiological measurements
CA2930745A1 (en) * 2015-05-26 2016-11-26 Reticle Ventures Canada Incorporated System and method for asset authentication and management
US20160360984A1 (en) * 2015-06-15 2016-12-15 Microsoft Technology Licensing, Llc Optical Photoplethysmogram Signal Shape Feature Biological Monitor
CN105138823A (zh) * 2015-07-28 2015-12-09 中国科学院电子学研究所 一种基于自相关函数的生理信号质量检测方法

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3492003A1 (en) * 2017-12-01 2019-06-05 Samsung Electronics Co., Ltd. Bio-signal quality assessment apparatus and bio-signal quality assessment method
US11457872B2 (en) 2017-12-01 2022-10-04 Samsung Electronics Co., Ltd. Bio-signal quality assessment apparatus and bio-signal quality assessment method
US11911184B2 (en) 2017-12-01 2024-02-27 Samsung Electronics Co., Ltd. Bio-signal quality assessment apparatus and bio-signal quality assessment method
EP3991640A3 (en) * 2020-09-10 2022-06-01 Samsung Electronics Co., Ltd. Method of determining regularity of bio-signal, apparatus and method for estimating bio-information
EP4166070A1 (en) * 2021-10-14 2023-04-19 Samsung Electronics Co., Ltd. Method of evaluating quality of bio-signal and apparatus for estimating bio-information
WO2023108331A1 (zh) * 2021-12-13 2023-06-22 中国科学院深圳先进技术研究院 自适应实时心电信号质量评估方法
WO2024066962A1 (zh) * 2022-09-28 2024-04-04 华为技术有限公司 呼吸健康检测方法及可穿戴电子设备

Also Published As

Publication number Publication date
CN108633249A (zh) 2018-10-09
CN108633249B (zh) 2021-03-23

Similar Documents

Publication Publication Date Title
WO2018137300A1 (zh) 一种生理信号质量判断方法及装置
US20200260956A1 (en) Open api-based medical information providing method and system
US10341554B2 (en) Method for control of camera module based on physiological signal
KR101777738B1 (ko) 동영상을 이용하여 혈압을 추정하는 방법
Hernandez et al. Biophone: Physiology monitoring from peripheral smartphone motions
JPWO2014136310A1 (ja) 脈波伝播速度の測定方法、その測定方法を用いた測定システムの作動方法及び脈波伝播速度の測定システム並びに撮像装置
Alnaggar et al. Video-based real-time monitoring for heart rate and respiration rate
Tang et al. Mmpd: multi-domain mobile video physiology dataset
Wang et al. VitaSi: A real-time contactless vital signs estimation system
CN113996046B (zh) 热身判断方法、装置及电子设备
WO2021036562A1 (zh) 用于健身训练的提示方法和电子设备
KR20190117100A (ko) 전자 장치에서 생체 정보 측정 방법 및 장치
US20220240865A1 (en) Video based detection of pulse waveform
WO2022111704A1 (zh) 心率检测方法及电子设备
WO2021254091A1 (zh) 运动次数的确定方法和终端
CN114649096A (zh) 体型数据确定方法、装置、设备、存储介质及产品
CN113693556A (zh) 运动后肌肉疲劳度的检测方法及装置、电子设备
KR20220003887A (ko) 혈압을 추정하는 방법 및 장치
Lyu et al. Video-based heart rate measurement via the anti-shake remote photoplethysmography (rPPG) pulse extraction
US20240161498A1 (en) Non-contrastive unsupervised learning of physiological signals from video
CN117711565B (zh) 一种运动恢复时间确定方法及电子设备
CN118078234B (zh) Ppg信号处理方法、设备及存储介质
WO2023160158A9 (zh) 心率检测方法及装置、计算机可读存储介质和电子设备
WO2022206641A1 (zh) 高血压风险检测方法及相关装置
Ngodjou Doukaga et al. Fine-Grained Human Activity Recognition in Smart Homes Through Photoplethysmography-Based Hand Gesture Detection

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17893844

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17893844

Country of ref document: EP

Kind code of ref document: A1