Contactless heart rate measurement method and device based on confidence coefficient and gradient change

Abstract

The invention relates to the technical field of information processing, and discloses a non-contact heart rate measurement method and device based on confidence and gradient variation, and the method comprises the steps: obtaining a sensed first measured heart rate signal of a current frame and a first actual heart rate signal of a previous adjacent frame of the current frame; calculating a first confidence value of the first measured heart rate signal of the current frame; according to the first confidence value and the first actual heart rate signal, matching a heart rate signal correction condition satisfying generation of a second actual heart rate signal of the current frame; generating a second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal and the first actual heart rate signal; and determining the second actual heart rate signal of the current frame as the first actual heart rate signal of the previous adjacent frame of the new current frame. Therefore, the accuracy of non-contact heart rate measurement can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and particularly to a non-contact heart rate measurement method and device based on confidence and gradient change. Background Art

[0002] With the intensification of the global population aging trend, the demand for health monitoring of the elderly is becoming increasingly urgent; traditional contact monitoring means (such as electrocardiogram, oximeter) rely on physical contact, and have problems such as inconvenient use and inability to continuously monitor; millimeter wave radar technology has become a research hotspot in the field of health monitoring due to its non-contact and high-sensitivity characteristics; it emits millimeter wave signals and receives the reflected signals of human body micro-motions (such as chest fluctuations caused by heartbeat and breathing), and extracts physiological parameters from them to provide all-weather and non-invasive monitoring services for the elderly.

[0003] However, it is found in practice that during the continuous heart rate measurement process of millimeter wave radar, due to interference such as random body movements, involuntary jitters, and respiratory harmonics of the target itself, as well as interference from the surrounding environment, the periodicity of the target heart rate signal will be destroyed, contaminating the perceived target heart rate signal, resulting in a drift problem in the calculated target heart rate signal, and the accuracy of heart rate measurement is relatively low, affecting subsequent practical applications.

[0004] Therefore, how to improve the accuracy of non-contact heart rate measurement is particularly important. Summary of the Invention

[0005] The present invention provides a non-contact heart rate measurement method and device based on confidence and gradient change, which can improve the accuracy of heart rate measurement.

[0006] To solve the above technical problems, in the first aspect of the present invention, a non-contact heart rate measurement method based on confidence and gradient change is disclosed, and the method includes:

[0007] Obtain the first measured heart rate signal of the current frame and the first actual heart rate signal of the previous adjacent frame of the current frame;

[0008] Calculate the first confidence value of the first measured heart rate signal of the current frame;

[0009] Match the heart rate signal correction condition that satisfies generating the second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal;

[0010] Generate the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal;

[0011] Determine the second actual heart rate signal of the current frame as the first actual heart rate signal of the adjacent frame before the new current frame.

[0012] As an alternative implementation manner, in the first aspect of the present invention, the matching of the heart rate signal correction condition for generating the second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal includes:

[0013] Judge whether the first confidence value is greater than or equal to a preset first confidence threshold to obtain a first judgment result;

[0014] According to the first judgment result, match the first weight value of the first actual heart rate signal and the second weight value of the first measured heart rate signal;

[0015] According to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, match the heart rate signal correction condition for generating the second actual heart rate signal of the current frame.

[0016] As an alternative implementation manner, in the first aspect of the present invention, the generating of the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal and the first actual heart rate signal includes:

[0017] Calculate a first target value according to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, and the first target value is used to represent the distance degree between the first actual heart rate signal and the first measured heart rate signal;

[0018] According to the first target value, judge whether the first measured heart rate signal meets a preset first gradient correction condition to obtain a second judgment result; the preset first gradient correction condition is used to represent that the first target value is greater than a preset first target threshold or the first target value is less than a preset second target threshold;

[0019] According to the second judgment result, determine the second measured heart rate signal of the current frame;

[0020] Generate the second actual heart rate signal of the current frame according to the second measured heart rate signal of the current frame;

[0021] And, the determining of the second measured heart rate signal of the current frame according to the second judgment result includes:

[0022] When the second judgment result is that the first measured heart rate signal meets the preset first gradient correction condition, the first measured heart rate signal is corrected according to the first actual heart rate signal to obtain the second measured heart rate signal of the current frame;

[0023] When the second judgment result is that the first measured heart rate signal does not meet the preset first gradient correction condition, the first measured heart rate signal is determined as the second measured heart rate signal of the current frame.

[0024] As an optional implementation manner, in the first aspect of the present invention, the method further includes:

[0025] When it is determined that the first target value is greater than the preset first target threshold, the measured respiratory rate signal of the current frame is obtained, and both the measured respiratory rate signal and the first measured heart rate signal are obtained by processing the perceived cardiopulmonary detection signal of the current frame;

[0026] Calculate the multi-dimensional target harmonic signal of the measured respiratory rate signal;

[0027] Calculate a second target value between the multi-dimensional target harmonic signal and the first measured heart rate signal, where the second target value is used to represent the distance degree between the multi-dimensional target harmonic signal and the first measured heart rate signal;

[0028] Judge whether the second target value is less than or equal to a preset third target threshold. When it is determined that the second target value is less than or equal to the preset third target threshold, it is determined that the first measured heart rate signal meets the preset first gradient correction condition;

[0029] When it is determined that the second target value is greater than the preset third target threshold, it is determined that the first measured heart rate signal does not meet the preset first gradient correction condition.

[0030] As an optional implementation manner, in the first aspect of the present invention, the generating the second actual heart rate signal of the current frame according to the second measured heart rate signal of the current frame includes:

[0031] Calculate the second confidence value of the second measured heart rate signal of the current frame;

[0032] According to the second confidence value, judge whether the second measured heart rate signal meets a preset second gradient correction condition to obtain a third judgment result; the preset second gradient correction condition is used to represent that the second confidence value is greater than or equal to a preset second confidence threshold;

[0033] According to the third judgment result, match the preset third gradient correction condition of the second measured heart rate signal;

[0034] Generate the second actual heart rate signal of the current frame according to the preset third gradient correction condition.

[0035] As an optional implementation manner, in the first aspect of the present invention, the generating the second actual heart rate signal of the current frame according to the preset third gradient correction condition includes:

[0036] Obtain the historical high-confidence continuous count value corresponding to the previous historical frame of the current frame, where the previous historical frame includes the previous adjacent frame;

[0037] When the third judgment result is that the second measured heart rate signal does not meet the preset second gradient correction condition, update the historical high-confidence continuous count value according to the first count value to obtain a second count value; calculate a third target value according to the second measured heart rate signal and the first actual heart rate signal, where the third target value is used to represent the distance degree between the second measured heart rate signal and the first actual heart rate signal; judge whether the third target distance value is less than a preset fourth target threshold to obtain a fourth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result;

[0038] When the third judgment result is that the second measured heart rate signal meets the preset second gradient correction condition, update the historical high-confidence continuous count value according to the third count value to obtain a fourth count value, where the fourth count value is greater than the second count value; obtain the heart rate continuous increase count value and the heart rate continuous decrease count value corresponding to the previous historical frame of the current frame; judge whether the second measured heart rate signal is within a preset limit gradient threshold range to obtain a fifth judgment result; update the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value.

[0039] As an optional implementation manner, in the first aspect of the present invention, the determining the second actual heart rate signal of the current frame according to the fourth judgment result includes:

[0040] When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold, determine the second measured heart rate signal as the second actual heart rate signal of the current frame;

[0041] When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold, the first actual heart rate signal is determined as the second actual heart rate signal of the current frame;

[0042] Moreover, the preset limit gradient threshold interval range is the complementary set of the interval between the preset first gradient threshold and the preset second gradient threshold, and the preset first gradient threshold is less than the preset second gradient threshold; the updating of the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result includes:

[0043] When the fifth judgment result indicates that the second measured heart rate signal is less than the preset second gradient threshold, the heart rate continuous increase count value is updated according to the fifth count value, and the updated heart rate continuous increase count value is less than the heart rate continuous increase count value before the update;

[0044] When the fifth judgment result indicates that the second measured heart rate signal is greater than the preset first gradient threshold, the heart rate continuous decrease count value is updated according to the sixth count value, and the updated heart rate continuous decrease count value is less than the heart rate continuous decrease count value before the update;

[0045] Moreover, the determining of the second actual heart rate signal of the current frame according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value includes:

[0046] When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value is greater than or equal to the corresponding preset count threshold, the second measured heart rate signal is determined as the second actual heart rate signal;

[0047] When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value is less than the corresponding preset count threshold, the first actual heart rate signal is determined as the second actual heart rate signal of the current frame.

[0048] The second aspect of the present invention discloses a non-contact heart rate measurement device based on confidence and gradient change, and the device includes:

[0049] An acquisition module, configured to acquire the first measured heart rate signal of the currently sensed current frame and the first actual heart rate signal of the previous adjacent frame of the current frame;

[0050] A calculation module, configured to calculate a first confidence value of the first measured heart rate signal of the current frame;

[0051] A matching module, configured to match a heart rate signal correction condition that satisfies generating a second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal;

[0052] A generating module, configured to generate the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal;

[0053] A closed-loop module, configured to determine the second actual heart rate signal of the current frame as the first actual heart rate signal of the previous adjacent frame of the new current frame.

[0054] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the matching module matches a heart rate signal correction condition that satisfies generating a second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal includes:

[0055] Judge whether the first confidence value is greater than or equal to a preset first confidence threshold to obtain a first judgment result;

[0056] According to the first judgment result, match a first weight value of the first actual heart rate signal and a second weight value of the first measured heart rate signal;

[0057] According to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, match a heart rate signal correction condition that satisfies generating a second actual heart rate signal of the current frame.

[0058] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the generating module generates the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal includes:

[0059] Calculate a first target value according to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, where the first target value is used to represent the distance degree between the first actual heart rate signal and the first measured heart rate signal;

[0060] According to the first target value, judge whether the first measured heart rate signal satisfies a preset first gradient correction condition to obtain a second judgment result; the preset first gradient correction condition is used to represent that the first target value is greater than a preset first target threshold or the first target value is less than a preset second target threshold;

[0061] Based on the second judgment result, determine the second measured heart rate signal of the current frame;

[0062] Generate the second actual heart rate signal of the current frame according to the second measured heart rate signal of the current frame;

[0063] Moreover, the specific manner in which the generating module determines the second measured heart rate signal of the current frame according to the second judgment result includes:

[0064] When the second judgment result is that the first measured heart rate signal satisfies the preset first gradient correction condition, then correct the first measured heart rate signal according to the first actual heart rate signal to obtain the second measured heart rate signal of the current frame;

[0065] When the second judgment result is that the first measured heart rate signal does not satisfy the preset first gradient correction condition, then determine the first measured heart rate signal as the second measured heart rate signal of the current frame.

[0066] As an optional implementation manner, in the second aspect of the present invention, the obtaining module is further configured to, when the generating module determines that the first target value is greater than the preset first target threshold, obtain the measured respiratory rate signal of the current frame, where the measured respiratory rate signal and the first measured heart rate signal are both obtained by processing the perceived cardiorespiratory detection signal of the current frame;

[0067] The calculating module is further configured to calculate the multi-dimensional target harmonic signal of the measured respiratory rate signal;

[0068] The calculating module is further configured to calculate a second target value between the multi-dimensional target harmonic signal and the first measured heart rate signal, where the second target value is used to represent the distance degree between the multi-dimensional target harmonic signal and the first measured heart rate signal;

[0069] Moreover, the device further includes:

[0070] A judgment module, configured to judge whether the second target value is less than or equal to a preset third target threshold;

[0071] A determination module, configured to, when the judgment module determines that the second target value is less than or equal to the preset third target threshold, determine that the first measured heart rate signal satisfies the preset first gradient correction condition;

[0072] The determination module is further configured to, when the judgment module determines that the second target value is greater than the preset third target threshold, determine that the first measured heart rate signal does not satisfy the preset first gradient correction condition.

[0073] As an alternative implementation manner, in the second aspect of the present invention, the specific manner in which the generating module generates the second actual heart rate signal of the current frame according to the second measured heart rate signal of the current frame includes:

[0074] Calculate a second confidence value of the second measured heart rate signal of the current frame;

[0075] According to the second confidence value, determine whether the second measured heart rate signal meets a preset second gradient correction condition to obtain a third judgment result; the preset second gradient correction condition is used to indicate that the second confidence value is greater than or equal to a preset second confidence threshold;

[0076] According to the third judgment result, match a preset third gradient correction condition of the second measured heart rate signal;

[0077] Generate the second actual heart rate signal of the current frame according to the preset third gradient correction condition.

[0078] As an alternative implementation manner, in the second aspect of the present invention, the specific manner in which the generating module generates the second actual heart rate signal of the current frame according to the preset third gradient correction condition includes:

[0079] Obtain a historical high-confidence continuous count value corresponding to a previous historical frame of the current frame, where the previous historical frame includes the previous adjacent frame;

[0080] When the third judgment result is that the second measured heart rate signal does not meet the preset second gradient correction condition, update the historical high-confidence continuous count value according to a first count value to obtain a second count value; calculate a third target value according to the second measured heart rate signal and the first actual heart rate signal, where the third target value is used to represent the distance degree between the second measured heart rate signal and the first actual heart rate signal; determine whether the third target distance value is less than a preset fourth target threshold to obtain a fourth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result;

[0081] When the third judgment result is that the second measured heart rate signal satisfies the preset second gradient correction condition, update the historical high-confidence continuous count value according to the third count value to obtain a fourth count value, and the fourth count value is greater than the second count value; obtain the heart rate continuous increase count value and the heart rate continuous decrease count value corresponding to the previous historical frame of the current frame; determine whether the second measured heart rate signal is within the preset limit gradient threshold range to obtain a fifth judgment result; update the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value.

[0082] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the generation module determines the second actual heart rate signal of the current frame according to the fourth judgment result includes:

[0083] When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold, determine the second measured heart rate signal as the second actual heart rate signal of the current frame;

[0084] When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold, determine the first actual heart rate signal as the second actual heart rate signal of the current frame;

[0085] Moreover, the preset limit gradient threshold range is the complementary set of the interval between the preset first gradient threshold and the preset second gradient threshold, and the preset first gradient threshold is less than the preset second gradient threshold; the specific manner in which the generation module updates the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result includes:

[0086] When the fifth judgment result indicates that the second measured heart rate signal is less than the preset second gradient threshold, update the heart rate continuous increase count value according to the fifth count value, and the updated heart rate continuous increase count value is less than the heart rate continuous increase count value before update;

[0087] When the fifth judgment result indicates that the second measured heart rate signal is greater than the preset first gradient threshold, update the heart rate continuous decrease count value according to the sixth count value, and the updated heart rate continuous decrease count value is less than the heart rate continuous decrease count value before update;

[0088] Moreover, the specific manner in which the generation module determines the second actual heart rate signal of the current frame according to the fourth determination result, the updated continuously increasing heart rate count value, the continuously decreasing heart rate count value, and the fourth count value includes:

[0089] When the fourth determination result is that the third target distance value is less than the preset fourth target threshold and / or any one of the continuously increasing heart rate count value, the continuously decreasing heart rate count value, and the fourth count value is greater than or equal to the corresponding preset count threshold, then the second measured heart rate signal is determined as the second actual heart rate signal;

[0090] When the fourth determination result is that the third target distance value is greater than or equal to the preset fourth target threshold and / or any one of the continuously increasing heart rate count value, the continuously decreasing heart rate count value, and the fourth count value is less than the corresponding preset count threshold, then the first actual heart rate signal is determined as the second actual heart rate signal of the current frame.

[0091] A third aspect of the present invention discloses another non-contact heart rate measurement device based on confidence and gradient change, and the device includes:

[0092] A memory storing executable program code;

[0093] A processor coupled to the memory;

[0094] The processor calls the executable program code stored in the memory and executes the non-contact heart rate measurement method based on confidence and gradient change disclosed in the first aspect of the present invention.

[0095] A fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which are used to execute the non-contact heart rate measurement method based on confidence and gradient change disclosed in the first aspect of the present invention when the computer instructions are called.

[0096] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0097] In an embodiment of the present invention, a first measured heart rate signal of a currently sensed frame and a first actual heart rate signal of a previous adjacent frame of the currently sensed frame are obtained; a first confidence value of the first measured heart rate signal of the currently sensed frame is calculated; a heart rate signal correction condition for generating a second actual heart rate signal of the currently sensed frame is matched according to the first confidence value and the first actual heart rate signal; a second actual heart rate signal of the currently sensed frame is generated according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal; and the second actual heart rate signal of the currently sensed frame is determined as the first actual heart rate signal of the previous adjacent frame of the new currently sensed frame. It can be seen that implementing the present invention can, for the first measured heart rate signal of the currently sensed frame, match a heart rate signal correction condition for generating a second actual heart rate signal of the currently sensed frame based on the calculated first confidence value of the first measured heart rate signal and the first actual heart rate signal of the previous adjacent frame of the currently sensed frame, implement gradient filtering of the heart rate signal between the currently sensed frame and the previous adjacent frame, and thus generate a second actual heart rate signal of the currently sensed frame based on the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal, improve the accuracy of the sensed measurement of the second actual heart rate signal, reduce interference such as random body movements, involuntary jitters, and respiratory harmonics of the target itself during continuous measurement, as well as interference from the surrounding environment. At the same time, by determining the second actual heart rate signal of the currently sensed frame as the first actual heart rate signal of the previous adjacent frame of the new currently sensed frame, continuous closed-loop measurement of the heart rate signal is realized, and the stability of contactless heart rate measurement is improved. At the same time, compared with traditional algorithms that use methods such as precise heart positioning, differential enhancement, EMD, and VMD to enhance the heartbeat signal to reduce the influence of interference and respiratory harmonics on the heartbeat, the present invention can reduce the complexity of algorithm implementation, reduce the amount of data processing, and do not require high computing power and storage resource requirements. By matching the heart rate signal correction condition for generating a second actual heart rate signal of the currently sensed frame and closed-loop measurement, it is possible to further reduce the consumption of computing resources on the basis of improving computing efficiency, which is conducive to realizing portable extended applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] 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 description in the embodiments. Obviously, the following drawings 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.

[0099] Figure 1 FIG. is a schematic diagram of a contactless heart rate measurement scenario based on confidence and gradient change disclosed in an embodiment of the present invention;

[0100] Figure 2 FIG. is a flowchart of a contactless heart rate measurement method based on confidence and gradient change disclosed in an embodiment of the present invention;

[0101] Figure 3 It is a comparison graph of measured heart rate results disclosed in an embodiment of the present invention;

[0102] Figure 4 It is a schematic structural diagram of a non-contact heart rate measurement device based on confidence and gradient change disclosed in an embodiment of the present invention;

[0103] Figure 5 It is a schematic structural diagram of another non-contact heart rate measurement device based on confidence and gradient change disclosed in an embodiment of the present invention;

[0104] Figure 6 It is a schematic structural diagram of yet another non-contact heart rate measurement device based on confidence and gradient change disclosed in an embodiment of the present invention. Detailed implementation manners

[0105] 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 with reference to 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 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.

[0106] 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 that includes 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.

[0107] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection 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 will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0108] The present invention discloses a non-contact heart rate measurement method and device based on confidence and gradient change. For the first measured heart rate signal of the current frame sensed, based on the calculated first confidence value of the first measured heart rate signal and the first actual heart rate signal of the previous adjacent frame of the current frame, the heart rate signal correction condition for generating the second actual heart rate signal of the current frame is matched, so as to realize the heart rate signal gradient filtering between the current frame and the previous adjacent frame. Thus, based on the heart rate signal correction condition, the first measured heart rate signal and the first actual heart rate signal, the second actual heart rate signal of the current frame is generated, improving the sensing measurement accuracy of the second actual heart rate signal, reducing the interference of random body movements, involuntary jitters, respiratory harmonics, etc. existing in the target itself during continuous measurement, as well as the interference of the surrounding environment. At the same time, by determining the second actual heart rate signal of the current frame as the first actual heart rate signal of the new current frame's previous adjacent frame, the continuous closed-loop measurement of the heart rate signal is realized, improving the stability of non-contact heart rate measurement. At the same time, compared with the traditional algorithms that enhance the heartbeat signal by precise heart positioning, differential enhancement, EMD, VMD, etc. to reduce the influence of interference and respiratory harmonics on the heartbeat, the present invention can reduce the algorithm implementation complexity, reduce the data processing volume, and does not require high computing power and storage resource requirements. By matching the heart rate signal correction condition for generating the second actual heart rate signal of the current frame and closed-loop measurement, it can further reduce the consumption of computing resources on the basis of improving the computing efficiency, which is beneficial to realizing portable extended applications. The following will be described in detail respectively.

[0109] To better understand a non-contact heart rate measurement method and device based on confidence and gradient change described in the present invention, first, the applicable scenario of a non-contact heart rate measurement method based on confidence and gradient change is described. Specifically, the schematic diagram of this scenario can be as Figure 1 shown. This scenario includes a target space (such as a house) divided into three regions, an intelligent air conditioner, and a user / target. Among them, the target space includes the first space (region B) of the user and the second space (region A, region C) associated with the first space. Optionally, the above-mentioned first space and second space can respectively represent different target scenarios. The user / target can perform different activities in the above-mentioned first space and second space to present different target scenarios. The target scenarios can include at least one of the scenarios of the user reading, the user sleeping, the user cooking, the user exercising, and the user washing up. Optionally, as Figure 1As shown in the figure, the intelligent air conditioner obtains the first measured heart rate signal of the currently sensed current frame and the first actual heart rate signal of the previous adjacent frame of the current frame; calculates the first confidence value of the first measured heart rate signal of the current frame; matches the heart rate signal correction condition for generating the second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal; generates the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal and the first actual heart rate signal; and determines the second actual heart rate signal of the current frame as the first actual heart rate signal of the new previous adjacent frame of the current frame. In practical applications, the above-mentioned intelligent air conditioner can be in the second space where the user is located or in the first space. It should be noted that Figure 1 The schematic diagram of the scene shown is only for representing the scene applicable to a non-contact heart rate measurement method based on confidence and gradient change. The target space (such as a house), intelligent air conditioner, user / target, etc. involved are also only shown schematically, Figure 1 and the schematic diagram of the scene shown does not limit this. A non-contact heart rate measurement method and device based on confidence and gradient change will be described in detail below.

[0110] Embodiment 1

[0111] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of a non-contact heart rate measurement method based on confidence and gradient change disclosed in an embodiment of the present invention. Among them, Figure 2 The described non-contact heart rate measurement method based on confidence and gradient change can be applied to radar devices, and can also be applied to smart home devices, such as intelligent air conditioners, and can also be applied to smart devices related to the above-mentioned radar devices and smart home devices. The smart device includes, but is not limited to, one or more of battery devices, cloud devices, edge computing devices, relay devices, base station devices, urban management devices, and intelligent connected devices. Embodiments of the present invention do not limit this. As Figure 2 shown, the non-contact heart rate measurement method based on confidence and gradient change can include the following operations:

[0112] 101. Obtain the first measured heart rate signal of the currently sensed current frame and the first actual heart rate signal of the previous adjacent frame of the current frame;

[0113] In an embodiment of the present invention, optionally, the above-mentioned first measured heart rate signal and the subsequent mentioned measured respiratory rate signal can both be obtained by processing the cardiopulmonary detection signal of the currently sensed current frame. The specific processing method includes separating and filtering the respiratory and heartbeat signals through a filter (band-pass, low-pass, high-pass, etc., selected according to actual application needs), and then through frequency domain analysis, the measured respiratory rate signal and the first measured heart rate signal can be obtained;

[0114] Further optionally, for different application scenarios, the processing accuracies of the corresponding first measured heart rate signal and the measured respiratory rate signal can be different.

[0115] In the embodiments of the present invention, during the actual development process, developers can conduct actual measurement experiments using millimeter-wave radars with various accuracies, such as conducting actual measurement experiments using the TI 60GHz millimeter-wave radar chip IWR6843AOPEVM; the radar can be placed on an office desk, and the test person sits about 60 cm away from the radar, and a pulse oximeter is used to record the true heart rate value as the basis for judging the result accuracy.

[0116] Among them, taking BRData to represent the respiratory rate and HRData to represent the heart rate as an example, when using the radar for target heart rate monitoring, a total of two targets are tested. The heart rate values of target 1 and target 2 have a large degree of differentiation. The monitoring duration of target 1 is about 5 minutes. Then, without shutting down the radar, target 1 leaves, and target 2 is switched for monitoring. The monitoring duration of target 2 is about 8 minutes. The final measured results are plotted as Figure 3 shown in Figure 3 a comparison chart of actual measured heartbeat results disclosed in the embodiments of the present invention;

[0117] As Figure 3 shown, the HRData plotted by the thin line is the heart rate value directly calculated by traditional signal processing, and the HRCur plotted by the thick black line is the processing result of the algorithm of the present invention. The true heart rate value of target 1 is in the range of 70 - 85 beats / min, and the true heart rate value of target 2 is in the range of 98 - 106 beats / min. It can be seen from the comparison that for the heart rate values directly calculated for target 1 and target 2 by the traditional signal processing method, there are problems of relatively large heart rate drift errors and instability during the monitoring process. However, the heart rate results measured by the algorithm of the present invention always remain within the true value range. This algorithm can accurately locate the time periods when the traditional algorithm makes calculation errors and reasonably correct them to avoid the occurrence of heart rate drift phenomena. The calculation results have great advantages in terms of accuracy and stability.

[0118] 102. Calculate the first confidence value of the first measured heart rate signal of the current frame;

[0119] In the embodiments of the present invention, optionally, the calculation method of the above-mentioned first confidence value is the same as that of the second confidence value mentioned later. For different objects, taking the first confidence value as an example, the calculation method is the energy ratio of the heart rate frequency point (i.e., the maximum frequency point) in the frequency domain within the entire heart rate frequency band detection range;

[0120] 103. According to the first confidence value and the first actual heart rate signal, match the heart rate signal correction conditions that satisfy the generation of the second actual heart rate signal of the current frame;

[0121] In an embodiment of the present invention, as an alternative implementation, matching the heart rate signal correction condition for generating the second actual heart rate signal of the current frame based on the first confidence value and the first actual heart rate signal includes:

[0122] Determine whether the first confidence value is greater than or equal to a preset first confidence threshold to obtain a first judgment result;

[0123] According to the first judgment result, match the first weight value of the first actual heart rate signal and the second weight value of the first measured heart rate signal;

[0124] According to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, match the heart rate signal correction condition for generating the second actual heart rate signal of the current frame.

[0125] It can be seen that implementing this alternative embodiment can, based on the first judgment result of whether the first confidence value is greater than or equal to the preset first confidence threshold, match the first weight value of the first actual heart rate signal and the second weight value of the first measured heart rate signal, and then, based on the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, match the heart rate signal correction condition for generating the second actual heart rate signal of the current frame, thereby further improving the matching accuracy, scientificity, and convenience of the heart rate signal correction condition for generating the second actual heart rate signal of the current frame, which is conducive to further improving the perception measurement accuracy, convenience, scientificity, and stability of the contactless heart rate signal.

[0126] 104. Generate the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal;

[0127] In this alternative embodiment, as an alternative implementation, generating the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal includes:

[0128] Calculate a first target value according to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, and the first target value is used to represent the distance degree between the first actual heart rate signal and the first measured heart rate signal;

[0129] According to the first target value, determine whether the first measured heart rate signal meets a preset first gradient correction condition to obtain a second judgment result; the preset first gradient correction condition is used to represent that the first target value is greater than a preset first target threshold or the first target value is less than a preset second target threshold;

[0130] According to the second judgment result, determine the second measured heart rate signal of the current frame;

[0131] Generate a second actual heart rate signal for the current frame based on the second measured heart rate signal of the current frame;

[0132] In an embodiment of the present invention, optionally, the above heart rate signal correction conditions may include: abs(DataOut_last / a - HRdata / b) < Diff_Thresh; and abs(DataOut_last / c - HRdata / d) > BRGrad_thresh;

[0133] Wherein, abs() is used to represent taking the absolute value, DataOut_last is used to represent the first actual heart rate signal, HRdata is used to represent the first measured heart rate signal, and 1 / a and 1 / c above are the above first weight values, 1 / b and 1 / d above are the above second weight values, Diff_Thresh is a preset second target threshold, and BRGrad_thresh is a preset first target threshold;

[0134] Optionally, when the first judgment result is that the first confidence value is greater than or equal to the preset first confidence threshold, the abs(DataOut_last / a - HRdata / b) < Diff_Thresh judgment logic is triggered. When the first judgment result is that the first confidence value is less than the preset first confidence threshold, the abs(DataOut_last / c - HRdata / d) > BRGrad_thresh judgment logic is triggered;

[0135] Optionally, the above-mentioned determining the second measured heart rate signal of the current frame according to the second judgment result includes:

[0136] When the second judgment result is that the first measured heart rate signal meets the preset first gradient correction condition, the first measured heart rate signal is corrected according to the first actual heart rate signal to obtain the second measured heart rate signal of the current frame;

[0137] When the second judgment result is that the first measured heart rate signal does not meet the preset first gradient correction condition, the first measured heart rate signal is determined as the second measured heart rate signal of the current frame.

[0138] It can be seen that implementing this optional embodiment can execute different gradient correction logics based on gradient changes and confidence levels, thereby improving the generation accuracy of the second measured heart rate signal, and further improving the non-contact measurement accuracy of the second actual heart rate signal.

[0139] In this optional embodiment, as another optional implementation manner, the method further includes:

[0140] When it is determined that the first target value is greater than the preset first target threshold, obtain the measured respiratory rate signal of the current frame. Both the measured respiratory rate signal and the first measured heart rate signal are obtained by processing the perceived cardiorespiratory detection signal of the current frame.

[0141] Calculate the multi-dimensional target harmonic signal of the measured respiratory rate signal.

[0142] Calculate the second target value between the multi-dimensional target harmonic signal and the first measured heart rate signal. The second target value is used to represent the distance degree between the multi-dimensional target harmonic signal and the first measured heart rate signal.

[0143] Determine whether the second target value is less than or equal to the preset third target threshold. When it is determined that the second target value is less than or equal to the preset third target threshold, it is determined that the first measured heart rate signal meets the preset first gradient correction condition.

[0144] When it is determined that the second target value is greater than the preset third target threshold, it is determined that the first measured heart rate signal does not meet the preset first gradient correction condition.

[0145] In an embodiment of the present invention, optionally, the above multi-dimensional target harmonic signal may be a second-order, third-order, or nth-order harmonic signal.

[0146] It can be seen that implementing this optional embodiment can, when it is determined that the first target value is greater than the preset first target threshold, perform further gradient filtering by combining the measured respiratory rate signal, improving the generation accuracy of the second measured heart rate signal, and facilitating further improvement of the non-contact measurement accuracy of the second actual heart rate signal.

[0147] In this optional embodiment, as another optional implementation manner, generating the second actual heart rate signal of the current frame according to the second measured heart rate signal of the current frame includes:

[0148] Calculate the second confidence value of the second measured heart rate signal of the current frame.

[0149] According to the second confidence value, determine whether the second measured heart rate signal meets the preset second gradient correction condition to obtain a third judgment result. The preset second gradient correction condition is used to indicate that the second confidence value is greater than or equal to the preset second confidence threshold.

[0150] According to the third judgment result, match the preset third gradient correction condition of the second measured heart rate signal.

[0151] Generate the second actual heart rate signal of the current frame according to the preset third gradient correction condition.

[0152] It should be noted that the second confidence value may be the same as or different from the first confidence value.

[0153] It can be seen that implementing this optional embodiment can, after obtaining the second measured heart rate signal of the current frame, calculate the second confidence value of the second measured heart rate signal of the current frame, and based on the second confidence value, determine whether the second measured heart rate signal meets the preset second gradient correction condition to obtain a third judgment result. Furthermore, based on the third judgment result, match the preset third gradient correction condition of the second measured heart rate signal to generate the second actual heart rate signal of the current frame, realizing further segmented filtering based on confidence and gradient changes, and further improving the non-contact measurement accuracy of the second actual heart rate signal.

[0154] In this optional embodiment, as another optional implementation manner, generating the second actual heart rate signal of the current frame according to the preset third gradient correction condition includes:

[0155] Obtain the historical high-confidence continuous count value corresponding to the previous historical frame of the current frame, where the previous historical frame includes the previous adjacent frames;

[0156] When the third judgment result is that the second measured heart rate signal does not meet the preset second gradient correction condition, update the historical high-confidence continuous count value according to the first count value to obtain the second count value; calculate the third target value according to the second measured heart rate signal and the first actual heart rate signal, where the third target value is used to represent the distance degree between the second measured heart rate signal and the first actual heart rate signal; determine whether the third target distance value is less than the preset fourth target threshold to obtain a fourth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result.

[0157] When the third judgment result is that the second measured heart rate signal meets the preset second gradient correction condition, update the historical high-confidence continuous count value according to the third count value to obtain the fourth count value, where the fourth count value is greater than the second count value; obtain the heart rate continuous increase count value and the heart rate continuous decrease count value corresponding to the previous historical frame of the current frame; determine whether the second measured heart rate signal is within the preset limit gradient threshold range to obtain a fifth judgment result; update the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value.

[0158] It can be seen that implementing this optional embodiment can also further improve the granularity of segmented filtering, control extreme data processing situations during the data processing process, and further improve the non-contact perception measurement accuracy and scientificity of the second actual heart rate signal, and is beneficial to improving the credibility of heart rate data by further adding branch logic for segmented filtering, adding historical high-confidence continuous count values, and limit gradient threshold ranges, heart rate continuous increase count values, and heart rate continuous decrease count values.

[0159] In an optional embodiment, determining the second actual heart rate signal of the current frame according to the fourth judgment result includes:

[0160] When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold, the second measured heart rate signal is determined as the second actual heart rate signal of the current frame;

[0161] When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold, the first actual heart rate signal is determined as the second actual heart rate signal of the current frame;

[0162] Optionally, the preset limit gradient threshold range is the complementary set of the interval between the preset first gradient threshold and the preset second gradient threshold, and the preset first gradient threshold is less than the preset second gradient threshold; updating the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result includes:

[0163] When the fifth judgment result indicates that the second measured heart rate signal is less than the preset second gradient threshold, the heart rate continuous increase count value is updated according to the fifth count value, and the updated heart rate continuous increase count value is less than the heart rate continuous increase count value before update;

[0164] When the fifth judgment result indicates that the second measured heart rate signal is greater than the preset first gradient threshold, the heart rate continuous decrease count value is updated according to the sixth count value, and the updated heart rate continuous decrease count value is less than the heart rate continuous decrease count value before update;

[0165] Optionally, determining the second actual heart rate signal of the current frame according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value includes:

[0166] When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value is greater than or equal to the corresponding preset count threshold, the second measured heart rate signal is determined as the second actual heart rate signal;

[0167] When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value is less than the corresponding preset count threshold, the first actual heart rate signal is determined as the second actual heart rate signal of the current frame.

[0168] It can be seen that implementing this optional embodiment discloses the specific generation logic of the second actual heart rate signal, responding to the above-mentioned multi-dimensional gradient change correction logic, thereby realizing the closed-loop measurement of the contactless heart rate signal and improving the stability, feasibility, and accuracy of contactless heart rate measurement.

[0169] 105. Determine the second actual heart rate signal of the current frame as the first actual heart rate signal of the adjacent frame before the new current frame.

[0170] In an embodiment of the present invention, optionally, after the execution of step 105 is triggered and completed, the specific operations of the above steps 101 - 104 can be further triggered to implement closed-loop measurement and processing.

[0171] It can be seen that implementing the embodiments of the present invention can, for the first measured heart rate signal of the sensed current frame, based on the calculated first confidence value of the first measured heart rate signal and the first actual heart rate signal of the adjacent frame before the current frame, match and satisfy the heart rate signal correction condition for generating the second actual heart rate signal of the current frame, implement gradient filtering of the heart rate signal between the current frame and the adjacent frame before it, and thus generate the second actual heart rate signal of the current frame based on the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal, improving the sensing measurement accuracy of the second actual heart rate signal, reducing interference such as random body movements, involuntary jitters, and respiratory harmonics of the target itself during continuous measurement, as well as interference from the surrounding environment. At the same time, by determining the second actual heart rate signal of the current frame as the first actual heart rate signal of the adjacent frame before the new current frame, continuous closed-loop measurement of the heart rate signal is achieved, improving the stability of contactless heart rate measurement. Also, compared with traditional algorithms that use methods such as precise heart positioning, differential enhancement, EMD, and VMD to enhance the heartbeat signal to reduce the impact of interference and respiratory harmonics on the heartbeat, the present invention can reduce the algorithm implementation complexity, reduce the data processing volume, and has no high requirements for computing power and storage resources. By matching and satisfying the heart rate signal correction condition for generating the second actual heart rate signal of the current frame and closed-loop measurement, it can further reduce the consumption of computing resources on the basis of improving the computing efficiency, which is beneficial to realizing portable extended applications.

[0172] Embodiment 2

[0173] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of a contactless heart rate measurement device based on confidence and gradient change disclosed in an embodiment of the present invention. Among them, the contactless heart rate measurement device based on confidence and gradient change can be applied to radar devices, and can also be applied to smart home devices such as smart air conditioners, and can also be applied to smart devices related to the above-mentioned radar devices and smart home devices. The smart device includes, but is not limited to, one or more of battery devices, cloud devices, edge computing devices, relay devices, base station devices, urban management devices, and intelligent networked devices. The embodiments of the present invention do not make limitations. As Figure 4 shown, the contactless heart rate measurement device based on confidence and gradient change may include:

[0174] An acquisition module 301, configured to acquire a first measured heart rate signal of a currently sensed current frame and a first actual heart rate signal of a previous adjacent frame of the current frame;

[0175] A calculation module 302, configured to calculate a first confidence value of the first measured heart rate signal of the current frame;

[0176] A matching module 303, configured to match a heart rate signal correction condition that satisfies generating a second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal;

[0177] A generation module 304, configured to generate a second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal;

[0178] A closed-loop module 305, configured to determine the second actual heart rate signal of the current frame as the first actual heart rate signal of the previous adjacent frame of the new current frame.

[0179] It can be seen that implementing the embodiments of the present invention can, for the first measured heart rate signal of the currently sensed current frame, based on the calculated first confidence value of the first measured heart rate signal and the first actual heart rate signal of the previous adjacent frame of the current frame, match the heart rate signal correction condition that satisfies generating the second actual heart rate signal of the current frame, implement gradient filtering of the heart rate signal between the current frame and the previous adjacent frame, and thus generate the second actual heart rate signal of the current frame based on the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal, improve the perceptual measurement accuracy of the second actual heart rate signal, reduce the interference of random body movements, involuntary jitters, respiratory harmonics, etc. existing in the target itself during continuous measurement, as well as the interference of the surrounding environment. At the same time, by determining the second actual heart rate signal of the current frame as the first actual heart rate signal of the previous adjacent frame of the new current frame, continuous closed-loop measurement of the heart rate signal is realized, and the stability of contactless heart rate measurement is improved. At the same time, compared with the traditional algorithms that enhance the heartbeat signal through precise cardiac positioning, differential enhancement, EMD, VMD, etc. to reduce the influence of interference and respiratory harmonics on the heartbeat, the present invention can reduce the algorithm implementation complexity, reduce the data processing volume, and do not require high computing power and storage resource requirements. By matching the heart rate signal correction condition that satisfies generating the second actual heart rate signal of the current frame and closed-loop measurement, it can further reduce the consumption of computing resources on the basis of improving the computing efficiency, which is beneficial to realizing portable extended applications.

[0180] In this optional embodiment, as an optional implementation manner, the specific manner in which the above-mentioned matching module 303 matches the heart rate signal correction condition that satisfies generating the second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal includes:

[0181] Determine whether the first confidence value is greater than or equal to a preset first confidence threshold to obtain a first determination result;

[0182] According to the first determination result, match the first weight value of the first actual heart rate signal and the second weight value of the first measured heart rate signal;

[0183] According to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, match the heart rate signal correction conditions for generating the second actual heart rate signal of the current frame.

[0184] It can be seen that implementing this optional embodiment can, based on the first determination result of whether the determined first confidence value is greater than or equal to the preset first confidence threshold, match the first weight value of the first actual heart rate signal and the second weight value of the first measured heart rate signal, and then, based on the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, match the heart rate signal correction conditions for generating the second actual heart rate signal of the current frame, thereby further improving the matching accuracy, scientificity, and convenience of the heart rate signal correction conditions for generating the second actual heart rate signal of the current frame, which is beneficial to further improving the sensing measurement accuracy, convenience, scientificity, and stability of the contactless heart rate signal.

[0185] In this optional embodiment, as another optional implementation manner, the specific manner in which the above-mentioned generation module 304 generates the second actual heart rate signal of the current frame according to the heart rate signal correction conditions, the first measured heart rate signal, and the first actual heart rate signal includes:

[0186] According to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, calculate a first target value, where the first target value is used to represent the distance degree between the first actual heart rate signal and the first measured heart rate signal;

[0187] According to the first target value, determine whether the first measured heart rate signal meets the preset first gradient correction condition to obtain a second determination result; the preset first gradient correction condition is used to represent that the first target value is greater than a preset first target threshold or the first target value is less than a preset second target threshold;

[0188] According to the second determination result, determine the second measured heart rate signal of the current frame;

[0189] According to the second measured heart rate signal of the current frame, generate the second actual heart rate signal of the current frame;

[0190] Optionally, the specific manner in which the generation module 304 determines the second measured heart rate signal of the current frame according to the second determination result includes:

[0191] When the second judgment result is that the first measured heart rate signal meets the preset first gradient correction condition, the first measured heart rate signal is corrected according to the first actual heart rate signal to obtain the second measured heart rate signal of the current frame;

[0192] When the second judgment result is that the first measured heart rate signal does not meet the preset first gradient correction condition, the first measured heart rate signal is determined as the second measured heart rate signal of the current frame.

[0193] It can be seen that implementing this optional embodiment can execute different gradient correction logics based on gradient changes and confidence levels, thereby improving the generation accuracy of the second measured heart rate signal, and further improving the non-contact measurement accuracy of the second actual heart rate signal.

[0194] In this optional embodiment, as another optional implementation manner, the above-mentioned acquisition module 301 is further configured to obtain the measured respiratory rate signal of the current frame when the generation module 304 determines that the first target value is greater than the preset first target threshold. The measured respiratory rate signal and the first measured heart rate signal are both obtained by processing the perceived cardiopulmonary detection signal of the current frame;

[0195] The calculation module 302 is further configured to calculate the multi-dimensional target harmonic signal of the measured respiratory rate signal;

[0196] The calculation module 302 is further configured to calculate the second target value between the multi-dimensional target harmonic signal and the first measured heart rate signal, and the second target value is used to represent the distance degree between the multi-dimensional target harmonic signal and the first measured heart rate signal;

[0197] Optionally, as Figure 5 shown, the device further includes:

[0198] The judgment module 306 is configured to judge whether the second target value is less than or equal to the preset third target threshold;

[0199] The determination module 307 is configured to determine that the first measured heart rate signal meets the preset first gradient correction condition when the judgment module 306 determines that the second target value is less than or equal to the preset third target threshold;

[0200] The determination module 307 is further configured to determine that the first measured heart rate signal does not meet the preset first gradient correction condition when the judgment module 306 determines that the second target value is greater than the preset third target threshold.

[0201] It can be seen that implementing this optional embodiment can, when it is determined that the first target value is greater than the preset first target threshold, perform further gradient filtering by combining the measured respiratory rate signal, improve the generation accuracy of the second measured heart rate signal, and is beneficial to further improving the non-contact measurement accuracy of the second actual heart rate signal.

[0202] In this alternative embodiment, as another alternative implementation, the specific manner in which the above-mentioned generation module 304 generates the second actual heart rate signal of the current frame based on the second measured heart rate signal of the current frame includes:

[0203] Calculate the second confidence value of the second measured heart rate signal of the current frame;

[0204] Based on the second confidence value, determine whether the second measured heart rate signal meets the preset second gradient correction condition to obtain a third judgment result; the preset second gradient correction condition is used to indicate that the second confidence value is greater than or equal to the preset second confidence threshold;

[0205] Based on the third judgment result, match the preset third gradient correction condition of the second measured heart rate signal;

[0206] Based on the preset third gradient correction condition, generate the second actual heart rate signal of the current frame.

[0207] It can be seen that implementing this alternative embodiment can, after obtaining the second measured heart rate signal of the current frame, calculate the second confidence value of the second measured heart rate signal of the current frame, based on the second confidence value, determine whether the second measured heart rate signal meets the preset second gradient correction condition to obtain a third judgment result, and then, based on the third judgment result, match the preset third gradient correction condition of the second measured heart rate signal to generate the second actual heart rate signal of the current frame, thereby realizing further piecewise filtering based on confidence and gradient changes, and further improving the non-contact measurement accuracy of the second actual heart rate signal.

[0208] In an alternative embodiment, the specific manner in which the above-mentioned generation module 304 generates the second actual heart rate signal of the current frame based on the preset third gradient correction condition includes:

[0209] Obtain the historical high-confidence continuous count value corresponding to the previous historical frame of the current frame, where the previous historical frame includes the previous adjacent frames;

[0210] When the third judgment result is that the second measured heart rate signal does not meet the preset second gradient correction condition, then update the historical high-confidence continuous count value according to the first count value to obtain a second count value; calculate a third target value based on the second measured heart rate signal and the first actual heart rate signal, where the third target value is used to represent the degree of distance between the second measured heart rate signal and the first actual heart rate signal; determine whether the third target distance value is less than the preset fourth target threshold to obtain a fourth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result;

[0211] When the third judgment result indicates that the second measured heart rate signal meets the preset second gradient correction condition, the historical high-confidence continuous count value is updated according to the third count value to obtain a fourth count value, and the fourth count value is greater than the second count value; the heart rate continuous increase count value and the heart rate continuous decrease count value corresponding to the previous historical frame of the current frame are obtained; it is judged whether the second measured heart rate signal is within the preset limit gradient threshold range to obtain a fifth judgment result; according to the fifth judgment result, the heart rate continuous increase count value and the heart rate continuous decrease count value are updated; according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value and the fourth count value, the second actual heart rate signal of the current frame is determined.

[0212] It can be seen that implementing this optional embodiment also further improves the granularity of the segmented filtering by further adding the branch logic of the segmented filtering, adding the historical high-confidence continuous count value, and the limit gradient threshold range, and the heart rate continuous increase count value and the heart rate continuous decrease count value can further control the extreme data processing situation in the data processing process, so as to further improve the non-contact perception measurement accuracy and scientificity of the second actual heart rate signal, which is beneficial to improving the credibility of the heart rate data.

[0213] In this optional embodiment, as an optional implementation manner, the specific manner in which the above-mentioned generating module 304 determines the second actual heart rate signal of the current frame according to the fourth judgment result includes:

[0214] When the fourth judgment result indicates that the third target distance value is less than the preset fourth target threshold, the second measured heart rate signal is determined as the second actual heart rate signal of the current frame;

[0215] When the fourth judgment result indicates that the third target distance value is greater than or equal to the preset fourth target threshold, the first actual heart rate signal is determined as the second actual heart rate signal of the current frame;

[0216] Optionally, the preset limit gradient threshold range is the interval complement between the preset first gradient threshold and the preset second gradient threshold, and the preset first gradient threshold is less than the preset second gradient threshold; the specific manner in which the generating module 304 updates the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result includes:

[0217] When the fifth judgment result indicates that the second measured heart rate signal is less than the preset second gradient threshold, the heart rate continuous increase count value is updated according to the fifth count value, and the updated heart rate continuous increase count value is less than the heart rate continuous increase count value before the update;

[0218] When the fifth judgment result indicates that the second measured heart rate signal is greater than the preset first gradient threshold, update the heart rate continuous decline count value according to the sixth count value, and the updated heart rate continuous decline count value is less than the heart rate continuous decline count value before the update;

[0219] Optionally, the specific manner in which the generating module 304 determines the second actual heart rate signal of the current frame according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decline count value, and the fourth count value includes:

[0220] When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decline count value, and the fourth count value is greater than or equal to the corresponding preset count threshold, then determine the second measured heart rate signal as the second actual heart rate signal;

[0221] When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decline count value, and the fourth count value is less than the corresponding preset count threshold, then determine the first actual heart rate signal as the second actual heart rate signal of the current frame.

[0222] It can be seen that implementing this optional embodiment discloses the specific generation logic of the second actual heart rate signal, responding to the above-mentioned multi-dimensional gradient change correction logic, thereby realizing the closed-loop measurement of the contactless heart rate signal and improving the stability, feasibility, and accuracy of contactless heart rate measurement.

[0223] Embodiment III

[0224] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of another contactless heart rate measurement device based on confidence and gradient change disclosed in the embodiments of the present invention. Among them, this contactless heart rate measurement device based on confidence and gradient change can be applied to radar devices, and can also be applied to smart home devices, such as smart air conditioners, and can also be applied to smart devices related to the above-mentioned radar devices and smart home devices. The smart device includes one or more of, but is not limited to, battery devices, cloud devices, edge computing devices, relay devices, base station devices, urban management devices, and intelligent network-connected devices. The embodiments of the present invention do not make limitations. As Figure 6 shown, this contactless heart rate measurement device based on confidence and gradient change may include:

[0225] A memory 401 storing executable program code.

[0226] A processor 402 coupled to the memory 401.

[0227] The processor 402 calls the executable program code stored in the memory 401 and executes the steps in the non-contact heart rate measurement method based on confidence and gradient change described in the first embodiment of the present invention.

[0228] Embodiment 4

[0229] The embodiment of the present invention discloses a computer storage medium. The computer storage medium stores computer instructions, which are used to execute the steps in the non-contact heart rate measurement method based on confidence and gradient change described in the first embodiment of the present invention when the computer instructions are called.

[0230] Embodiment 5

[0231] The embodiment of the present invention discloses a computer program product. The computer program product includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the non-contact heart rate measurement method based on confidence and gradient change described in the first embodiment.

[0232] The device embodiments described above are merely 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. Those of ordinary skill in the art can understand and implement it without creative labor.

[0233] 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 above technical solutions, in essence, or the parts that contribute 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 medium that can be used to carry or store data and is computer-readable.

[0234] Finally, it should be noted that: The non-contact heart rate measurement method and device based on confidence and gradient change disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention. It is only used to illustrate the technical solutions 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. A non-contact heart rate measurement method based on confidence and gradient change, characterized in that, The method includes: Obtaining a first measured heart rate signal of a currently sensed current frame and a first actual heart rate signal of a previous adjacent frame of the current frame; Calculating a first confidence value of the first measured heart rate signal of the current frame; Matching, according to the first confidence value and the first actual heart rate signal, a heart rate signal correction condition that satisfies generating a second actual heart rate signal of the current frame; Generating the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal; Determining the second actual heart rate signal of the current frame as the first actual heart rate signal of a previous adjacent frame of a new current frame.

2. The non-contact heart rate measurement method based on confidence and gradient change according to claim 1, wherein, The matching, according to the first confidence value and the first actual heart rate signal, a heart rate signal correction condition that satisfies generating a second actual heart rate signal of the current frame includes: Judging whether the first confidence value is greater than or equal to a preset first confidence threshold to obtain a first judgment result; Matching, according to the first judgment result, a first weight value of the first actual heart rate signal and a second weight value of the first measured heart rate signal; Matching, according to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, a heart rate signal correction condition that satisfies generating a second actual heart rate signal of the current frame.

3. The non-contact heart rate measurement method based on confidence and gradient change according to claim 2, wherein The generating the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal includes: Calculating a first target value according to the first actual heart rate signal and its first weight value, the first measured heart rate signal and its second weight value, where the first target value is used to represent the distance degree between the first actual heart rate signal and the first measured heart rate signal; Judging whether the first measured heart rate signal satisfies a preset first gradient correction condition according to the first target value to obtain a second judgment result; the preset first gradient correction condition is used to represent that the first target value is greater than a preset first target threshold or the first target value is less than a preset second target threshold; Determining a second measured heart rate signal of the current frame according to the second judgment result; Generating the second actual heart rate signal of the current frame according to the second measured heart rate signal of the current frame; And, the determining the second measured heart rate signal of the current frame according to the second judgment result includes: When the second judgment result is that the first measured heart rate signal satisfies the preset first gradient correction condition, correcting the first measured heart rate signal according to the first actual heart rate signal to obtain the second measured heart rate signal of the current frame; When the second judgment result is that the first measured heart rate signal does not satisfy the preset first gradient correction condition, determining the first measured heart rate signal as the second measured heart rate signal of the current frame.

4. The non-contact heart rate measurement method based on confidence and gradient change according to claim 3, characterized in that The method further includes: When it is determined that the first target value is greater than the preset first target threshold, obtain the measured respiratory rate signal of the current frame, where both the measured respiratory rate signal and the first measured heart rate signal are obtained by processing the perceived cardiopulmonary detection signal of the current frame; Calculate the multi-dimensional target harmonic signal of the measured respiratory rate signal; Calculate a second target value between the multi-dimensional target harmonic signal and the first measured heart rate signal, where the second target value is used to represent the degree of distance between the multi-dimensional target harmonic signal and the first measured heart rate signal; Determine whether the second target value is less than or equal to a preset third target threshold. When it is determined that the second target value is less than or equal to the preset third target threshold, it is determined that the first measured heart rate signal meets the preset first gradient correction condition; When it is determined that the second target value is greater than the preset third target threshold, it is determined that the first measured heart rate signal does not meet the preset first gradient correction condition.

5. The non-contact heart rate measurement method based on confidence level and gradient change according to claim 3, characterized in that The generating the second actual heart rate signal of the current frame according to the second measured heart rate signal of the current frame includes: Calculate a second confidence value of the second measured heart rate signal of the current frame; According to the second confidence value, determine whether the second measured heart rate signal meets a preset second gradient correction condition to obtain a third judgment result; the preset second gradient correction condition is used to indicate that the second confidence value is greater than or equal to a preset second confidence threshold; According to the third judgment result, match a preset third gradient correction condition of the second measured heart rate signal; According to the preset third gradient correction condition, generate the second actual heart rate signal of the current frame.

6. The non-contact heart rate measurement method based on confidence and gradient change according to claim 5, characterized in that, The generating the second actual heart rate signal of the current frame according to the preset third gradient correction condition includes: Obtain the historical high-confidence continuous count value corresponding to the previous historical frame of the current frame, where the previous historical frame includes the previous adjacent frame; When the third judgment result is that the second measured heart rate signal does not meet the preset second gradient correction condition, update the historical high-confidence continuous count value according to a first count value to obtain a second count value; calculate a third target value according to the second measured heart rate signal and the first actual heart rate signal, where the third target value is used to represent the degree of distance between the second measured heart rate signal and the first actual heart rate signal; determine whether the third target distance value is less than a preset fourth target threshold to obtain a fourth judgment result; determine the second actual heart rate signal of the current frame according to the fourth judgment result; When the third judgment result is that the second measured heart rate signal satisfies the preset second gradient correction condition, the historical high-confidence continuous count value is updated according to the third count value to obtain a fourth count value, and the fourth count value is greater than the second count value; the heart rate continuous increase count value and the heart rate continuous decrease count value corresponding to the previous historical frame of the current frame are obtained; it is judged whether the second measured heart rate signal is within the preset limit gradient threshold range to obtain a fifth judgment result; the heart rate continuous increase count value and the heart rate continuous decrease count value are updated according to the fifth judgment result; the second actual heart rate signal of the current frame is determined according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value.

7. The non-contact heart rate measurement method based on confidence and gradient change according to claim 6, characterized in that, The determining the second actual heart rate signal of the current frame according to the fourth judgment result includes: When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold, the second measured heart rate signal is determined as the second actual heart rate signal of the current frame; When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold, the first actual heart rate signal is determined as the second actual heart rate signal of the current frame; Moreover, the preset limit gradient threshold range is the complementary set of the interval between the preset first gradient threshold and the preset second gradient threshold, and the preset first gradient threshold is less than the preset second gradient threshold; the updating the heart rate continuous increase count value and the heart rate continuous decrease count value according to the fifth judgment result includes: When the fifth judgment result indicates that the second measured heart rate signal is less than the preset second gradient threshold, the heart rate continuous increase count value is updated according to the fifth count value, and the updated heart rate continuous increase count value is less than the heart rate continuous increase count value before update; When the fifth judgment result indicates that the second measured heart rate signal is greater than the preset first gradient threshold, the heart rate continuous decrease count value is updated according to the sixth count value, and the updated heart rate continuous decrease count value is less than the heart rate continuous decrease count value before update; Moreover, the determining the second actual heart rate signal of the current frame according to the fourth judgment result, the updated heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value includes: When the fourth judgment result is that the third target distance value is less than the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value is greater than or equal to the corresponding preset count threshold, the second measured heart rate signal is determined as the second actual heart rate signal; When the fourth judgment result is that the third target distance value is greater than or equal to the preset fourth target threshold and / or any one of the heart rate continuous increase count value, the heart rate continuous decrease count value, and the fourth count value is less than the corresponding preset count threshold, the first actual heart rate signal is determined as the second actual heart rate signal of the current frame.

8. A non-contact heart rate measurement device based on confidence and gradient change, characterized in that, The device includes: An acquisition module, configured to acquire the first measured heart rate signal of the currently sensed current frame and the first actual heart rate signal of the immediately preceding adjacent frame of the current frame; A calculation module, configured to calculate a first confidence value of the first measured heart rate signal of the current frame; A matching module, configured to match a heart rate signal correction condition that satisfies generating the second actual heart rate signal of the current frame according to the first confidence value and the first actual heart rate signal; A generation module, configured to generate the second actual heart rate signal of the current frame according to the heart rate signal correction condition, the first measured heart rate signal, and the first actual heart rate signal; A closed-loop module, configured to determine the second actual heart rate signal of the current frame as the first actual heart rate signal of the immediately preceding adjacent frame of the new current frame.

9. A non-contact heart rate measurement device based on confidence and gradient change, 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 and executes the contactless heart rate measurement method based on confidence and gradient change according to any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which are used to execute the contactless heart rate measurement method based on confidence and gradient change according to any one of claims 1-7 when the computer instructions are called.

Images