Intelligent Analysis Method and Device for Signal Acquisition Quality

Abstract

The present invention discloses an intelligent analysis method and device for signal acquisition quality. The method includes: obtaining a PPG signal collected by a certain acquisition sensor, where the acquisition sensor is any acquisition sensor on the acquisition device worn by the user; performing time-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and performing frequency-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal; calculating the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal. It can be seen that the present invention can realize the intelligent analysis of PPG signal acquisition quality, improve the analysis accuracy and analysis efficiency of signal quality, is beneficial to improving the accuracy of the determined signal acquisition position, and further beneficial to improving the signal acquisition accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of signal analysis, and in particular, to an intelligent analysis method and device for signal acquisition quality. Background Art

[0002] In practical applications, relevant personnel's PPG signals of fingers are usually collected by corresponding collection devices (such as finger clip collection devices, wristband collection devices, or patch collection devices, etc.). Taking the finger clip collection device as an example, one side of the finger clip collection device is a light emission device, and the other side is a light reception device. The corresponding PPG signal collection principle is as follows: When light passes through tissues such as the skin, muscle, and capillaries of the human finger from the light emission device and enters the light reception device, due to the heartbeat, the volume of capillaries in the human finger tissue will change, thereby affecting the light passing rate, and further causing the received light intensity to change periodically corresponding to the heartbeat cycle. The change in the volume of blood vessels in the human finger tissue is indirectly traced through the change in the intensity of the light received by the light reception device, and then the PPG signal is obtained.

[0003] However, it is found in practice that due to the differences in the physiological structures of different people, such as the distribution and roughness of the hand skin, muscle, and blood vessels of each person being different, the quality of the PPG signals collected at different collection positions is different. Therefore, how to intelligently analyze the PPG signal acquisition quality and then provide an accurate reference basis for determining a suitable collection position is particularly important. Summary of the Invention

[0004] The present invention provides an intelligent analysis method and device for signal acquisition quality, which can realize the intelligent analysis of PPG signal acquisition quality and improve the analysis accuracy and efficiency of signal quality.

[0005] To solve the above technical problems, in the first aspect of the present invention, an intelligent analysis method for signal acquisition quality is disclosed, and the method includes:

[0006] Obtain a PPG signal collected by a certain collection sensor, where the collection sensor is any collection sensor on the collection device worn by the user;

[0007] Perform a time-domain analysis operation on the PPG signal collected by the collection sensor to obtain a time-domain analysis result of the PPG signal, and perform a frequency-domain analysis operation on the PPG signal collected by the collection sensor to obtain a frequency-domain analysis result of the PPG signal;

[0008] Calculate the signal acquisition quality of the collection sensor at the corresponding collection position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal.

[0009] The second aspect of the present invention discloses an intelligent analysis device for signal acquisition quality, and the device includes:

[0010] An acquisition module, configured to acquire a PPG signal collected by a certain acquisition sensor, where the acquisition sensor is any acquisition sensor on an acquisition device worn by a user;

[0011] A time-domain analysis module, configured to perform time-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain a time-domain analysis result of the PPG signal;

[0012] A frequency-domain analysis module, configured to perform frequency-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain a frequency-domain analysis result of the PPG signal;

[0013] A quality analysis module, configured to calculate the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal.

[0014] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the time-domain analysis module performs time-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain a time-domain analysis result of the PPG signal includes:

[0015] Filter and cut the PPG signal collected by the acquisition sensor to obtain N PPG waveform segments with a heartbeat as a period, extract the morphological features of the N PPG waveform segments, perform screening operations on all the PPG waveform segments according to the morphological features of each PPG waveform segment and a preset screening condition to obtain all valid PPG waveform segments among all the PPG waveform segments, and determine the time-domain analysis result of the PPG signal corresponding to the acquisition sensor according to the ratio of all the valid PPG waveform segments to all the PPG waveform segments.

[0016] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the frequency-domain analysis module performs frequency-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain a frequency-domain analysis result of the PPG signal includes:

[0017] Segment the waveform of the PPG signal collected by the acquisition sensor with a preset segmentation duration to obtain multiple waveform segments with the preset segmentation duration as a unit;

[0018] Perform band-pass filtering on all the waveform segments to obtain a target waveform signal within a preset frequency range; calculate multiple frequency-domain features of the target waveform signal to obtain a calculation result, and compare the calculation result with a preset threshold to obtain a spectrum offset degree;

[0019] Calculate the frequency-domain analysis result of the PPG signal corresponding to the acquisition sensor according to the degree of spectrum offset.

[0020] As an optional implementation manner, in the second aspect of the present invention, the time-domain analysis result of the PPG signal is the time-domain waveform morphological score corresponding to the PPG signal collected by the acquisition sensor, and the frequency-domain analysis result of the PPG signal is the frequency-domain waveform morphological score corresponding to the PPG signal collected by the acquisition sensor;

[0021] Wherein, the specific manner in which the quality analysis module calculates the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal includes:

[0022] Calculate the mean value of the time-domain waveform morphological score and the frequency-domain waveform morphological score as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position; or,

[0023] Determine the time-domain influence degree value and the frequency-domain influence degree value respectively corresponding to the PPG signal collected by the acquisition sensor;

[0024] Calculate the first product of the time-domain influence degree value and the time-domain waveform morphological score and calculate the second product of the frequency-domain influence degree value and the frequency-domain waveform morphological score, and calculate the sum value of the first product and the second product as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position.

[0025] As an optional implementation manner, in the second aspect of the present invention, the device further includes:

[0026] A judgment module, configured to determine the waveform parameters of the PPG signal after the acquisition module acquires the PPG signal collected by a certain acquisition sensor; and judge whether the waveform parameters of the PPG signal meet the preset waveform parameter conditions, and when the judgment result is yes, trigger the time-domain analysis module to perform the time-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and, trigger the frequency-domain analysis module to perform the frequency-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0027] As an optional implementation manner, in the second aspect of the present invention, the judgment module is further configured to determine the user's corresponding user physiological state information, user health state information, user motion state information, and user posture information when the user wears the acquisition device after determining that the waveform parameters of the PPG signal meet the preset waveform parameter conditions;

[0028] Calculate the influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located according to the user physiological state information, the user health state information, the user posture information, and the user motion state information; determine whether the influence degree is a negative influence degree. When it is determined that it is not the negative influence degree, trigger the time domain analysis module to perform the time domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the time domain analysis result of the PPG signal, and trigger the frequency domain analysis module to perform the frequency domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the frequency domain analysis result of the PPG signal.

[0029] As an optional implementation manner, in the second aspect of the present invention, the judgment module is further configured to, after determining that the influence degree is the negative influence degree, determine whether the absolute value of the negative influence degree is greater than or equal to a preset influence degree threshold. When it is determined that the absolute value of the negative influence degree is greater than or equal to the preset influence degree threshold, trigger the time domain analysis module to perform the time domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the time domain analysis result of the PPG signal, and trigger the frequency domain analysis module to perform the frequency domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the frequency domain analysis result of the PPG signal;

[0030] Moreover, the specific manner in which the judgment module calculates the influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located according to the user physiological state information, the user health state information, the user posture information, and the user motion state information includes:

[0031] Input the user physiological state information and the user health state information into a pre-trained state-influence degree determination model to obtain a first sub-influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located;

[0032] Input the user posture information and the user motion state information into a pre-trained posture-influence degree determination model to obtain a second sub-influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located;

[0033] Calculate the influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located according to the first sub-influence degree and the second sub-influence degree.

[0034] The third aspect of the present invention discloses another intelligent analysis device for signal acquisition quality, and the device includes:

[0035] A memory storing executable program code;

[0036] A processor coupled to the memory;

[0037] The processor calls the executable program code stored in the memory and executes the intelligent analysis method for signal acquisition quality disclosed in the first aspect of the present invention.

[0038] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which are used to execute the intelligent analysis method for signal acquisition quality disclosed in the first aspect of the present invention when called.

[0039] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0040] In the embodiments of the present invention, for any acquisition sensor that acquires a PPG signal, time-domain analysis operations and frequency-domain analysis operations are respectively performed on the acquired PPG signal to obtain the corresponding time-domain analysis result and frequency-domain analysis result of the PPG signal, and then the signal acquisition quality of the acquisition sensor is calculated according to the time-domain analysis result and frequency-domain analysis result of the PPG signal. It can be seen that implementing the present invention can analyze the signal acquisition quality of the acquisition sensor from two dimensions of time domain and frequency domain, which is beneficial to improving the analysis accuracy of signal acquisition quality. In addition, it can also provide an accurate reference basis for determining the optimal PPG signal, which is beneficial to improving the determination efficiency and determination accuracy of the optimal PPG signal. Further, in the scenario where the PPG signal is used for user state monitoring, it can also be beneficial to improve the monitoring efficiency and monitoring accuracy of the user state. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0042] Figure 1 is a schematic flowchart of an intelligent analysis method for signal acquisition quality disclosed in an embodiment of the present invention;

[0043] Figure 2 is a schematic flowchart of another intelligent analysis method for signal acquisition quality disclosed in an embodiment of the present invention;

[0044] Figure 3 is a schematic structural diagram of an intelligent analysis device for signal acquisition quality disclosed in an embodiment of the present invention;

[0045] Figure 4It is a schematic structural diagram of another intelligent analysis device for signal acquisition quality disclosed in an embodiment of the present invention;

[0046] Figure 5 It is a schematic structural diagram of another intelligent analysis device for signal acquisition quality disclosed in an embodiment of the present invention. Specific embodiments

[0047] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or terminal comprising a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or terminals.

[0049] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0050] The present invention discloses an intelligent analysis method and device for signal acquisition quality, which can analyze the signal acquisition quality of a collection sensor from two dimensions of time domain and frequency domain, is beneficial to improving the analysis accuracy of signal acquisition quality. In addition, it can also provide an accurate reference basis for determining the optimal PPG signal, which is beneficial to improving the determination efficiency and determination accuracy of the optimal PPG signal. Further, in the scenario where the PPG signal is used for user state monitoring, it can also be beneficial to improving the monitoring efficiency and monitoring accuracy of the user state. The following will be described in detail respectively.

[0051] Embodiment 1

[0052] Please refer to Figure 1 , Figure 1It is a schematic flow chart of an intelligent analysis method for signal acquisition quality disclosed in an embodiment of the present invention. Among them, Figure 1 The described method can be applied to an analysis device for signal acquisition quality. The analysis device is used to realize the signal acquisition quality of the acquisition sensors on the acquisition device, and the analysis device can be integrated on the acquisition device and exist as a part of the acquisition device, or can be integrated in the control server or control device corresponding to the acquisition device. The embodiments of the present invention do not make limitations. As Figure 1 shown, the intelligent analysis method for signal acquisition quality can include the following operations:

[0053] 101. Obtain the PPG signal collected by a certain acquisition sensor, and the acquisition sensor is any acquisition sensor on the acquisition device worn by the user.

[0054] 102. Perform time-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and perform frequency-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0055] 103. Calculate the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal.

[0056] It can be seen that implementing the method described in the embodiments of the present invention can analyze the signal acquisition quality of the acquisition sensor from two dimensions of time domain and frequency domain, which is beneficial to improving the accuracy of signal acquisition quality analysis. In addition, it can also provide an accurate reference basis for determining the optimal PPG signal, which is beneficial to improving the determination efficiency and determination accuracy of the optimal PPG signal. Further, in the scenario where the PPG signal is used for user status monitoring, it can also be beneficial to improve the monitoring efficiency and monitoring accuracy of the user status.

[0057] In an optional embodiment, the above-mentioned performing time-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal may include:

[0058] Perform filtering and cutting on the PPG signal collected by the acquisition sensor to obtain N PPG waveform segments with the heartbeat as the period (that is, with the heartbeat interval as the period), extract the morphological features of the N PPG waveform segments, perform screening operations on all PPG waveform segments according to the morphological features of each PPG waveform segment and the preset screening conditions to obtain all valid PPG waveform segments among all PPG waveform segments, and determine the time-domain analysis result of the PPG signal corresponding to the acquisition sensor according to the ratio of all valid PPG waveform segments to all PPG waveform segments.

[0059] Optionally, the above PPG signal time-domain analysis result is the time-domain waveform morphological score corresponding to the PPG signal collected by the acquisition sensor, and specifically equals the ratio of the number of all effective PPG waveform segments to the number of all PPG waveform segments multiplied by 100.

[0060] It can be seen that this optional embodiment provides an intelligent implementation method for time-domain analysis of PPG signals. It filters and cuts the PPG waveform segments of the PPG signal, then screens them, and further determines the PPG signal time-domain analysis result corresponding to the acquisition sensor according to the ratio of the number of all effective PPG waveform segments selected to the total number of PPG waveform segments. The determination method is simple and fast, which is beneficial to improving the determination efficiency of the PPG signal time-domain analysis result, and further beneficial to improving the calculation efficiency of the signal acquisition quality.

[0061] In another optional embodiment, the above operation of performing frequency-domain analysis on the PPG signal collected by the acquisition sensor to obtain the PPG signal frequency-domain analysis result may include:

[0062] Segment the waveform of the PPG signal collected by the acquisition sensor with a preset segmentation duration (such as 5 seconds) to obtain multiple waveform segments in units of the preset segmentation duration;

[0063] Perform band-pass filtering on all waveform segments to obtain a target waveform signal within a preset frequency domain range (that is, retain the signal within the 0.5 - 5 hz frequency domain); calculate multiple frequency-domain features of the target waveform signal to obtain a calculation result, and compare the calculation result with a preset threshold to obtain the degree of spectral shift; optionally, the multiple frequency-domain features of the target waveform signal may include waveform power spectral density, main frequency position, and the power ratio of the main frequency to the second and third harmonics, etc.;

[0064] Calculate the PPG signal frequency-domain analysis result corresponding to the acquisition sensor according to the degree of spectral shift.

[0065] Optionally, the above PPG signal frequency-domain analysis result is the frequency-domain waveform morphological score corresponding to the PPG signal collected by the acquisition sensor. Further, the degree of spectral shift is the percentage p, and the frequency-domain waveform morphological score equals (1 - p) * 100.

[0066] It can be seen that this optional embodiment provides an intelligent implementation method for frequency-domain analysis of PPG signals. It can determine the PPG signal frequency-domain analysis result corresponding to the acquisition sensor based on the degree of spectral shift, and the degree of spectral shift is obtained by calculating the frequency-domain features of the target waveform signal obtained after band-pass filtering of the waveform segments and comparing the calculation result with a preset threshold, which is beneficial to improving the accuracy of the PPG signal frequency-domain analysis result, and further beneficial to improving the accuracy of the calculated signal acquisition quality.

[0067] In yet another alternative embodiment, as an alternative implementation manner, calculating the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal includes:

[0068] Calculating the mean value of the time-domain waveform morphology score and the frequency-domain waveform morphology score as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position.

[0069] It can be seen that this alternative implementation manner can determine the signal acquisition quality of the acquisition sensor at the corresponding acquisition position based on the mean value of the time-domain waveform morphology score and the frequency-domain waveform morphology score, which is beneficial to improving the determination efficiency of the signal acquisition quality.

[0070] In this alternative embodiment, as another alternative implementation manner, calculating the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal includes:

[0071] Determining the time-domain influence degree value and the frequency-domain influence degree value corresponding to the PPG signal collected by the acquisition sensor respectively;

[0072] Calculating the first product of the time-domain influence degree value and the time-domain waveform morphology score and calculating the second product of the frequency-domain influence degree value and the frequency-domain waveform morphology score, and calculating the sum value of the first product and the second product as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position.

[0073] It can be seen that this alternative embodiment can calculate the signal acquisition quality of the acquisition sensor at the corresponding acquisition position based on the time-domain waveform morphology score, the frequency-domain waveform morphology score, and the influence degree values corresponding to the two, which is beneficial to improving the accuracy and reliability of the calculated signal acquisition quality of the acquisition sensor at the corresponding acquisition position.

[0074] Embodiment 2

[0075] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of another intelligent analysis method for signal acquisition quality disclosed in the embodiments of the present invention. Among them, Figure 2 the described method can be applied to an analysis device for signal acquisition quality. The analysis device is used to implement the signal acquisition quality of the acquisition sensor on the acquisition device, and the analysis device can be integrated on the acquisition device and exist as a part of the acquisition device, or can be integrated in the control server or control device corresponding to the acquisition device. The embodiments of the present invention do not make limitations. As Figure 2 shown, the intelligent analysis method for signal acquisition quality can include the following operations:

[0076] 201. Obtain the PPG signal collected by a certain acquisition sensor, where the acquisition sensor is any acquisition sensor on the acquisition device worn by the user.

[0077] 202. Determine the waveform parameters of the above PPG signal.

[0078] 203. Determine whether the waveform parameters of the above PPG signal meet the preset waveform parameter conditions. When the judgment result of step 203 is yes, trigger the execution of step 204. When the judgment result of step 203 is no, this process can be ended, that is, no analysis operation on the signal acquisition quality of the above acquisition sensor is performed.

[0079] 204. When it is determined that the waveform parameters of the above PPG signal meet the preset waveform parameter conditions, perform a time-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and perform a frequency-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0080] 205. Calculate the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal.

[0081] It can be seen that implementing the method described in the embodiments of the present invention can analyze the signal acquisition quality of the acquisition sensor from two dimensions of time domain and frequency domain, which is beneficial to improving the analysis accuracy of the signal acquisition quality. In addition, it can also provide an accurate reference basis for determining the optimal PPG signal, which is beneficial to improving the determination efficiency and determination accuracy of the optimal PPG signal. Further, in the scenario where the PPG signal is used for user state monitoring, it can also be beneficial to improving the monitoring efficiency and monitoring accuracy of the user state. In addition, before performing the time-domain analysis and frequency-domain analysis on the PPG signal, it can also be determined whether the PPG signal meets the preset waveform parameter conditions based on the waveform parameters of the PPG signal. If it meets, then subsequent analysis operations are performed, which can reduce unnecessary analysis operations and improve the reliability of the time-domain analysis operation and frequency-domain analysis operation on the PPG signal.

[0082] In an optional embodiment, after it is determined that the waveform parameters of the PPG signal meet the preset waveform parameter conditions, the method may further include:

[0083] Determine the user's corresponding physiological state information, health state information, exercise state information, and user posture information when the user wears the acquisition device;

[0084] Calculate the degree of influence on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located according to the user's physiological state information, user health state information, user posture information, and user motion state information;

[0085] Determine whether the degree of influence is a negative degree of influence. When it is determined that it is not a negative degree of influence, trigger the steps of performing a time-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and performing a frequency-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0086] It can be seen that after determining that the waveform parameters of the PPG signal meet the preset waveform parameter conditions, this optional embodiment can also calculate the degree of influence on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located based on the user's relevant state information and relevant posture information. If it is not a negative degree of influence, then further perform a time-domain analysis operation and a frequency-domain analysis operation on the PPG signal. In this way, when analyzing the signal quality of the PPG signal, in addition to considering the waveform parameters of the PPG signal itself, the degree of influence of the acquisition sensor on the user at the current acquisition position is also considered, which is beneficial to further reducing unnecessary analysis operations and further improving the reliability of performing a time-domain analysis operation and a frequency-domain analysis operation on the PPG signal. In addition, when calculating the degree of influence of the acquisition sensor on the user at the current acquisition position, considering from two dimensions of the user state and the user posture (motion posture, wearing posture of the acquisition device) is beneficial to improving the accuracy of the calculated degree of influence.

[0087] In this optional embodiment, further optionally, after determining that the degree of influence is a negative degree of influence, the method may further include:

[0088] Determine whether the absolute value of the negative degree of influence is greater than or equal to a preset degree of influence threshold. When it is determined that the absolute value of the negative degree of influence is greater than or equal to the preset degree of influence threshold, trigger the steps of performing a time-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and performing a frequency-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0089] It can be seen that this optional embodiment can further consider the specific situation of the negative degree of influence, reduce the occurrence of missed analysis of the acquisition sensor, and is beneficial to improving the reliability and accuracy of the signal acquisition quality analysis of the acquisition sensor, and further beneficial to improving the comprehensiveness and accuracy of the signal acquisition quality of all acquisition sensors that need to be analyzed on the acquisition device.

[0090] In another alternative embodiment, calculating the impact degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user based on the user's physiological state information, user health state information, user posture information, and user motion state information may include:

[0091] Input the user's physiological state information and user health state information into a pre-trained state-impact degree determination model to obtain the first sub-impact degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user;

[0092] Input the user's posture information and user motion state information into a pre-trained posture-impact degree determination model to obtain the second sub-impact degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user;

[0093] Calculate the impact degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user according to the first sub-impact degree and the second sub-impact degree.

[0094] It can be seen that this alternative embodiment provides an intelligent calculation method for the impact degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located. By selecting a matching impact degree determination model for different types of user-related information, it realizes personalized and accurate calculation of the impact degree, which is beneficial to improving the accuracy and reliability of the finally calculated impact degree.

[0095] It should be noted that for other descriptions in Embodiment 2, please refer to the relevant descriptions in Embodiment 1, and the embodiments of the present invention will not be elaborated herein.

[0096] Embodiment 3

[0097] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of an intelligent analysis device for signal acquisition quality disclosed in an embodiment of the present invention. Among them, Figure 3 the described device is used to implement the signal acquisition quality of the acquisition sensor on the acquisition device, and Figure 3 the described device can be integrated on the acquisition device and exist as a part of the acquisition device, or can be integrated in the control server or control device corresponding to the acquisition device. The embodiments of the present invention do not make any limitations. As Figure 3 shown, the intelligent analysis device for signal acquisition quality may include:

[0098] An acquisition module 301, configured to acquire the PPG signal acquired by a certain acquisition sensor, where the acquisition sensor is any acquisition sensor on the acquisition device worn by the user;

[0099] The time-domain analysis module 302 is used to perform time-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal;

[0100] The frequency-domain analysis module 303 is used to perform frequency-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal;

[0101] The quality analysis module 304 is used to calculate the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal.

[0102] It can be seen that implementing Figure 3 the described device can analyze the signal acquisition quality of the acquisition sensor from two dimensions of time domain and frequency domain, which is beneficial to improving the analysis accuracy of signal acquisition quality. In addition, it can also provide an accurate reference basis for determining the optimal PPG signal, which is beneficial to improving the determination efficiency and determination accuracy of the optimal PPG signal. Further, in the scenario where the PPG signal is used for user state monitoring, it can also be beneficial to improving the monitoring efficiency and monitoring accuracy of the user state.

[0103] In an alternative embodiment, the specific manner in which the frequency-domain analysis module 303 performs frequency-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal may include:

[0104] Filter and cut the PPG signal collected by the acquisition sensor to obtain N PPG waveform segments with a heartbeat period, extract the morphological features of the N PPG waveform segments, perform a screening operation on all PPG waveform segments according to the morphological features of each PPG waveform segment and the preset screening conditions to obtain all valid PPG waveform segments among all PPG waveform segments, and determine the time-domain analysis result of the PPG signal corresponding to the acquisition sensor according to the ratio of all valid PPG waveform segments to all PPG waveform segments.

[0105] It can be seen that this alternative embodiment provides an intelligent implementation method for time-domain analysis of the PPG signal. The PPG waveform segments after filtering and cutting the PPG signal are screened, and then the time-domain analysis result of the PPG signal corresponding to the acquisition sensor is determined according to the ratio of the number of all valid PPG waveform segments selected to the total number of PPG waveform segments. The determination method is simple and fast, which is beneficial to improving the determination efficiency of the time-domain analysis result of the PPG signal, and further beneficial to improving the calculation efficiency of signal acquisition quality.

[0106] In another alternative embodiment, the specific manner in which the frequency-domain analysis module 303 performs frequency-domain analysis operations on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal may include:

[0107] Segment the waveform of the PPG signal collected by the acquisition sensor at a preset segmentation duration to obtain multiple waveform segments with the preset segmentation duration as the unit;

[0108] Perform band-pass filtering on all waveform segments to obtain a target waveform signal within a preset frequency domain range; calculate multiple frequency domain features of the target waveform signal to obtain a calculation result, and compare the calculation result with a preset threshold to obtain the degree of spectral offset;

[0109] Calculate the frequency domain analysis result of the PPG signal corresponding to the acquisition sensor according to the degree of spectral offset.

[0110] It can be seen that this optional embodiment provides an intelligent implementation method for frequency domain analysis of PPG signals, which can determine the frequency domain analysis result of the PPG signal corresponding to the acquisition sensor based on the degree of spectral offset, and the degree of spectral offset is calculated based on the frequency domain features of the target waveform signal obtained after band-pass filtering of the waveform segments and the calculation result is compared with a preset threshold, which is beneficial to improving the accuracy of the frequency domain analysis result of the PPG signal, and further beneficial to improving the accuracy of the calculated signal acquisition quality.

[0111] In another optional embodiment, the time domain analysis result of the PPG signal is the time domain waveform morphology score corresponding to the PPG signal collected by the acquisition sensor, and the frequency domain analysis result of the PPG signal is the frequency domain waveform morphology score corresponding to the PPG signal collected by the acquisition sensor.

[0112] Among them, the specific manner in which the quality analysis module 304 calculates the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time domain analysis result of the PPG signal and the frequency domain analysis result of the PPG signal may include:

[0113] Calculate the mean value of the time domain waveform morphology score and the frequency domain waveform morphology score as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position; or,

[0114] Determine the time domain influence degree value and the frequency domain influence degree value corresponding to the PPG signal collected by the acquisition sensor respectively;

[0115] Calculate the first product of the time domain influence degree value and the time domain waveform morphology score and the second product of the frequency domain influence degree value and the frequency domain waveform morphology score, and calculate the sum value of the first product and the second product as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position.

[0116] It can be seen that this optional embodiment can also determine the signal acquisition quality of the acquisition sensor at the corresponding acquisition position based on the mean value of the time-domain waveform morphology score and the frequency-domain waveform morphology score, which is beneficial to improving the determination efficiency of the signal acquisition quality. Or, the signal acquisition quality of the acquisition sensor at the corresponding acquisition position can also be calculated based on the time-domain waveform morphology score, the frequency-domain waveform morphology score, and the corresponding influence degree values of the two, which is beneficial to improving the accuracy and reliability of the calculated signal acquisition quality of the acquisition sensor at the corresponding acquisition position.

[0117] In yet another optional embodiment, as Figure 4 shown, the device may further include:

[0118] A judgment module 305, configured to, after the acquisition module 301 acquires the PPG signal acquired by a certain acquisition sensor, determine the waveform parameters of the PPG signal; and judge whether the waveform parameters of the PPG signal meet the preset waveform parameter conditions. When the judgment result is yes, trigger the time-domain analysis module 302 to perform the above-mentioned time-domain analysis operation on the PPG signal acquired by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and trigger the frequency-domain analysis module 303 to perform the above-mentioned frequency-domain analysis operation on the PPG signal acquired by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0119] It can be seen that this optional embodiment can also judge whether the PPG signal meets the preset waveform parameter conditions based on the waveform parameters of the PPG signal before performing the time-domain analysis and frequency-domain analysis on the PPG signal. If it meets, then perform the subsequent analysis operations, which can reduce unnecessary analysis operations and improve the reliability of the time-domain analysis operation and frequency-domain analysis operation on the PPG signal.

[0120] In this optional embodiment, further optionally, the judgment module 305 is further configured to, after judging that the waveform parameters of the PPG signal meet the preset waveform parameter conditions, determine the user's corresponding physiological state information, health state information, exercise state information, and user posture information when the user wears the acquisition device; calculate the influence degree of performing the signal acquisition operation on the user at the acquisition position where the acquisition sensor is located according to the user's physiological state information, health state information, posture information, and exercise state information; judge whether the influence degree is a negative influence degree. When it is judged that it is not a negative influence degree, trigger the time-domain analysis module 302 to perform the above-mentioned time-domain analysis operation on the PPG signal acquired by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and trigger the frequency-domain analysis module 303 to perform the above-mentioned frequency-domain analysis operation on the PPG signal acquired by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0121] It can be seen that this alternative embodiment can further calculate the degree of influence on the user when performing the signal acquisition operation at the acquisition position where the acquisition sensor is located based on the relevant status information and relevant posture information of the user after determining that the waveform parameters of the PPG signal meet the preset waveform parameter conditions. If the degree of influence is not a negative influence, then further perform time-domain analysis and frequency-domain analysis operations on the PPG signal. In this way, when analyzing the signal quality of the PPG signal, in addition to considering the waveform parameters of the PPG signal itself, the degree of influence of the acquisition sensor at the current acquisition position on the user is also considered, which helps to further reduce unnecessary analysis operations and further improve the reliability of performing time-domain analysis and frequency-domain analysis operations on the PPG signal. In addition, when calculating the degree of influence of the acquisition sensor at the current acquisition position on the user, considering from two dimensions of the user status and the user posture (motion posture, wearing posture of the acquisition device) helps to improve the accuracy of the calculated degree of influence.

[0122] In this alternative embodiment, further optionally, the determination module 305 is further configured to, after determining that the degree of influence is a negative degree of influence, determine whether the absolute value of the negative degree of influence is greater than or equal to a preset influence degree threshold. When it is determined that the absolute value of the negative degree of influence is greater than or equal to the preset influence degree threshold, trigger the time-domain analysis module 302 to perform the above-mentioned time-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the time-domain analysis result of the PPG signal, and trigger the frequency-domain analysis module 303 to perform the above-mentioned frequency-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain the frequency-domain analysis result of the PPG signal.

[0123] It can be seen that this alternative embodiment can further consider the specific situation of the negative degree of influence, reduce the occurrence of missed analysis of the acquisition sensor, and is beneficial to improving the reliability and accuracy of the signal acquisition quality analysis of the acquisition sensor, and further beneficial to improving the comprehensiveness and accuracy of the signal acquisition quality of all acquisition sensors that need to be analyzed on the acquisition device.

[0124] In another alternative embodiment, the specific manner in which the determination module 305 calculates the degree of influence on the user when performing the signal acquisition operation at the acquisition position where the acquisition sensor is located based on the user's physiological status information, user's health status information, user's posture information, and user's motion status information includes:

[0125] Input the user's physiological status information and user's health status information into a pre-trained status-influence degree determination model to obtain the first sub-degree of influence on the user when performing the signal acquisition operation at the acquisition position where the acquisition sensor is located;

[0126] Input the user posture information and the user motion state information into a pre-trained posture - influence degree determination model to obtain the second sub - influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located;

[0127] Calculate the influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located according to the first sub - influence degree and the second sub - influence degree.

[0128] It can be seen that this optional embodiment provides an intelligent calculation method for the influence degree on the user when performing a signal acquisition operation at the acquisition position where the acquisition sensor is located. By selecting a matching influence degree determination model for different types of user - related information, the personalized and accurate calculation of the influence degree is realized, which is beneficial to improving the accuracy and reliability of the finally calculated influence degree.

[0129] It should be noted that for other relevant descriptions of any device described in Embodiment 3, please refer to the relevant descriptions in Embodiment 1 and / or Embodiment 2, and the embodiments of the present invention will not be elaborated herein.

[0130] Embodiment 4

[0131] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of another intelligent analysis device for signal acquisition quality disclosed in the embodiments of the present invention. Among them, Figure 5 the described device is used to realize the signal acquisition quality of the acquisition sensor on the acquisition device, and Figure 5 the described device can be integrated on the acquisition device and exist as a part of the acquisition device, or can be integrated in the control server or control device corresponding to the acquisition device. The embodiments of the present invention do not make any limitations. As Figure 5 shown, this intelligent analysis device for signal acquisition quality may include:

[0132] A memory 401 storing executable program code;

[0133] A processor 402 coupled to the memory 401;

[0134] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the intelligent analysis method for signal acquisition quality described in Embodiment 1 or Embodiment 2 of the present invention.

[0135] Embodiment 5

[0136] The embodiments of the present invention disclose a computer storage medium. When the computer instructions stored in the computer storage medium are called, they are used to execute the steps in the intelligent analysis method for signal acquisition quality described in Embodiment 1 or Embodiment 2 of the present invention.

[0137] Example Six

[0138] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the intelligent analysis of signal acquisition quality described in Embodiment One or Embodiment Two.

[0139] Example Seven

[0140] An embodiment of the present invention discloses a collection device, which can be used to execute the steps in the intelligent analysis of signal acquisition quality described in Embodiment One or Embodiment Two, or the collection device can include any one of the intelligent devices for signal acquisition quality described in Embodiment Three, which is not limited in the embodiments of the present invention. Optionally, the collection device can be a wearable collection device.

[0141] The device embodiments described above are only illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0142] Through the specific descriptions of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, and the storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium that can be used to carry or store data.

[0143] Finally, it should be noted that: what is disclosed in an intelligent analysis method and device for signal acquisition quality according to an embodiment of the present invention is only a preferred embodiment of the present invention, and is only used to illustrate the technical solution of the present invention, rather than limiting it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent analysis method for signal acquisition quality, characterized in that The method includes: Obtaining a PPG signal collected by a certain acquisition sensor, where the acquisition sensor is any acquisition sensor on an acquisition device worn by a user; Determining waveform parameters of the PPG signal; judging whether the waveform parameters of the PPG signal meet preset waveform parameter conditions. When the judgment result is yes, determining user physiological state information, user health state information, user motion state information, and user posture information of the user when wearing the acquisition device for the user; according to the user physiological state information, the user health state information, the user posture information, and the user motion state information, calculating the influence degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user; judging whether the influence degree is a negative influence degree. When it is judged that it is not the negative influence degree, performing a time-domain analysis operation on the PPG signal to obtain a PPG signal time-domain analysis result, and performing a frequency-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain a PPG signal frequency-domain analysis result; Calculating the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the PPG signal time-domain analysis result and the PPG signal frequency-domain analysis result, and using the signal acquisition quality as a reference basis for determining the optimal PPG signal; Among them, the calculating the influence degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user according to the user physiological state information, the user health state information, the user posture information, and the user motion state information includes: Inputting the user physiological state information and the user health state information into a pre-trained state-influence degree determination model to obtain a first sub-influence degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user; Inputting the user posture information and the user motion state information into a pre-trained posture-influence degree determination model to obtain a second sub-influence degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user; Calculating the influence degree of performing a signal acquisition operation at the acquisition position where the acquisition sensor is located on the user according to the first sub-influence degree and the second sub-influence degree.

2. The intelligent analysis method for signal acquisition quality according to claim 1, wherein The performing a time-domain analysis operation on the PPG signal collected by the acquisition sensor to obtain a PPG signal time-domain analysis result includes: Filtering and cutting the PPG signal collected by the acquisition sensor to obtain N PPG waveform segments with a heartbeat period, extracting morphological features of the N PPG waveform segments, performing a screening operation on all the PPG waveform segments according to the morphological features of each PPG waveform segment and preset screening conditions to obtain all valid PPG waveform segments among all the PPG waveform segments, and determining the PPG signal time-domain analysis result corresponding to the acquisition sensor according to the ratio of all the valid PPG waveform segments to all the PPG waveform segments.

3. The intelligent analysis method for signal acquisition quality according to claim 1, wherein Performing frequency-domain analysis on the PPG signal collected by the acquisition sensor to obtain the PPG signal frequency-domain analysis result includes: Segmenting the waveform of the PPG signal collected by the acquisition sensor at a preset segmentation duration to obtain a plurality of waveform segments in units of the preset segmentation duration; Performing band-pass filtering on all the waveform segments to obtain a target waveform signal within a preset frequency domain range; calculating a plurality of frequency-domain features of the target waveform signal to obtain a calculation result, and comparing the calculation result with a preset threshold to obtain the degree of spectral shift; Calculating the PPG signal frequency-domain analysis result corresponding to the acquisition sensor according to the degree of spectral shift.

4. The intelligent analysis method for signal acquisition quality according to any one of claims 1-3, characterized in that, The PPG signal time-domain analysis result is the time-domain waveform morphological score corresponding to the PPG signal collected by the acquisition sensor, and the PPG signal frequency-domain analysis result is the frequency-domain waveform morphological score corresponding to the PPG signal collected by the acquisition sensor; Among them, calculating the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the PPG signal time-domain analysis result and the PPG signal frequency-domain analysis result includes: Calculating the average value of the time-domain waveform morphological score and the frequency-domain waveform morphological score as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position; or, Determining the time-domain influence degree value and the frequency-domain influence degree value respectively corresponding to the PPG signal collected by the acquisition sensor; Calculating a first product of the time-domain influence degree value and the time-domain waveform morphological score and a second product of the frequency-domain influence degree value and the frequency-domain waveform morphological score, and calculating the sum value of the first product and the second product as the signal acquisition quality of the acquisition sensor at the corresponding acquisition position.

5. The intelligent analysis method for signal acquisition quality according to claim 1, wherein After it is determined that the influence degree is the negative influence degree, the method further includes: Judging whether the absolute value of the negative influence degree is greater than or equal to a preset influence degree threshold. When it is judged that the absolute value of the negative influence degree is greater than or equal to the preset influence degree threshold, triggering the steps of performing time-domain analysis on the PPG signal collected by the acquisition sensor to obtain the PPG signal time-domain analysis result, and performing frequency-domain analysis on the PPG signal collected by the acquisition sensor to obtain the PPG signal frequency-domain analysis result.

6. An intelligent analysis device for signal acquisition quality, characterized in that, The device is used to execute the intelligent analysis method for signal acquisition quality according to any one of claims 1-5, and the device includes: An acquisition module, configured to acquire the PPG signal collected by a certain acquisition sensor, and the acquisition sensor is any acquisition sensor on the acquisition device worn by the user; A time-domain analysis module, configured to perform time-domain analysis on the PPG signal collected by the acquisition sensor to obtain the PPG signal time-domain analysis result; A frequency-domain analysis module, configured to perform frequency-domain analysis on the PPG signal collected by the acquisition sensor to obtain the PPG signal frequency-domain analysis result; A quality analysis module, configured to calculate the signal acquisition quality of the acquisition sensor at the corresponding acquisition position according to the time-domain analysis result of the PPG signal and the frequency-domain analysis result of the PPG signal.

7. An intelligent analysis device for signal acquisition quality, characterized in that The device includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent analysis method for signal acquisition quality according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to execute the intelligent analysis method for signal acquisition quality according to any one of claims 1-5 when the computer instructions are called.

Images